Massive pullreq but almost all of that is RTH's SVE refactoring patchset. The other interesting thing here is the fix for compiling on aarch64 macos. thanks -- PMM The following changes since commit f7a1ea403e0282a7f57edd4298c4f65f24165da5: Merge tag 'misc-pull-request' of gitlab.com:marcandre.lureau/qemu into staging (2022-05-29 16:34:56 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220530 for you to fetch changes up to b1071174d2a2ab371082b7d4b5f19e98edc61ac6: target/arm: Remove aa64_sve check from before disas_sve (2022-05-30 17:05:12 +0100) ---------------------------------------------------------------- target-arm queue: * docs/system/arm: Add FEAT_HCX to list of emulated features * target/arm/hvf: Include missing "cpregs.h" * hw/sd/allwinner-sdhost: report FIFO water level as 1 when data ready * SVE: refactor to use TRANS/TRANS_FEAT macros and push SVE feature check down to individual insn level ---------------------------------------------------------------- Icenowy Zheng (1): hw/sd/allwinner-sdhost: report FIFO water level as 1 when data ready Peter Maydell (1): docs/system/arm: Add FEAT_HCX to list of emulated features Philippe Mathieu-Daudé (1): target/arm/hvf: Include missing "cpregs.h" Richard Henderson (114): target/arm: Introduce TRANS, TRANS_FEAT target/arm: Move null function and sve check into gen_gvec_ool_zz target/arm: Use TRANS_FEAT for gen_gvec_ool_zz target/arm: Move null function and sve check into gen_gvec_ool_zzz target/arm: Introduce gen_gvec_ool_arg_zzz target/arm: Use TRANS_FEAT for gen_gvec_ool_arg_zzz target/arm: Use TRANS_FEAT for do_sve2_zzz_ool target/arm: Move null function and sve check into gen_gvec_ool_zzzz target/arm: Use TRANS_FEAT for gen_gvec_ool_zzzz target/arm: Introduce gen_gvec_ool_arg_zzzz target/arm: Use TRANS_FEAT for do_sve2_zzzz_ool target/arm: Use TRANS_FEAT for gen_gvec_ool_arg_zzzz target/arm: Rename do_zzxz_ool to gen_gvec_ool_arg_zzxz target/arm: Use TRANS_FEAT for gen_gvec_ool_arg_zzxz target/arm: Use TRANS_FEAT for do_sve2_zzz_data target/arm: Use TRANS_FEAT for do_sve2_zzzz_data target/arm: Use TRANS_FEAT for do_sve2_zzw_data target/arm: Use TRANS_FEAT for USDOT_zzzz target/arm: Move null function and sve check into gen_gvec_ool_zzp target/arm: Introduce gen_gvec_ool_arg_zpz target/arm: Use TRANS_FEAT for gen_gvec_ool_arg_zpz target/arm: Use TRANS_FEAT for do_sve2_zpz_data target/arm: Rename do_zpzi_ool to gen_gvec_ool_arg_zpzi target/arm: Use TRANS_FEAT for gen_gvec_ool_arg_zpzi target/arm: Move null function and sve check into gen_gvec_ool_zzzp target/arm: Introduce gen_gvec_ool_arg_zpzz target/arm: Use TRANS_FEAT for gen_gvec_ool_arg_zpzz target/arm: Use TRANS_FEAT for do_sve2_zpzz_ool target/arm: Merge gen_gvec_fn_zz into do_mov_z target/arm: Move null function and sve check into gen_gvec_fn_zzz target/arm: Rename do_zzz_fn to gen_gvec_fn_arg_zzz target/arm: More use of gen_gvec_fn_arg_zzz target/arm: Use TRANS_FEAT for gen_gvec_fn_arg_zzz target/arm: Use TRANS_FEAT for do_sve2_fn_zzz target/arm: Use TRANS_FEAT for RAX1 target/arm: Introduce gen_gvec_fn_arg_zzzz target/arm: Use TRANS_FEAT for do_sve2_zzzz_fn target/arm: Introduce gen_gvec_fn_zzi target/arm: Use TRANS_FEAT for do_zz_dbm target/arm: Hoist sve access check through do_sel_z target/arm: Introduce gen_gvec_fn_arg_zzi target/arm: Use TRANS_FEAT for do_sve2_fn2i target/arm: Use TRANS_FEAT for do_vpz_ool target/arm: Use TRANS_FEAT for do_shift_imm target/arm: Introduce do_shift_zpzi target/arm: Use TRANS_FEAT for do_shift_zpzi target/arm: Use TRANS_FEAT for do_zpzzz_ool target/arm: Move sve check into do_index target/arm: Use TRANS_FEAT for do_index target/arm: Use TRANS_FEAT for do_adr target/arm: Use TRANS_FEAT for do_predset target/arm: Use TRANS_FEAT for RDFFR, WRFFR target/arm: Use TRANS_FEAT for do_pfirst_pnext target/arm: Use TRANS_FEAT for do_EXT target/arm: Use TRANS_FEAT for do_perm_pred3 target/arm: Use TRANS_FEAT for do_perm_pred2 target/arm: Move sve zip high_ofs into simd_data target/arm: Use gen_gvec_ool_arg_zzz for do_zip, do_zip_q target/arm: Use TRANS_FEAT for do_zip, do_zip_q target/arm: Use TRANS_FEAT for do_clast_vector target/arm: Use TRANS_FEAT for do_clast_fp target/arm: Use TRANS_FEAT for do_clast_general target/arm: Use TRANS_FEAT for do_last_fp target/arm: Use TRANS_FEAT for do_last_general target/arm: Use TRANS_FEAT for SPLICE target/arm: Use TRANS_FEAT for do_ppzz_flags target/arm: Use TRANS_FEAT for do_sve2_ppzz_flags target/arm: Use TRANS_FEAT for do_ppzi_flags target/arm: Use TRANS_FEAT for do_brk2, do_brk3 target/arm: Use TRANS_FEAT for MUL_zzi target/arm: Reject dup_i w/ shifted byte early target/arm: Reject add/sub w/ shifted byte early target/arm: Reject copy w/ shifted byte early target/arm: Use TRANS_FEAT for ADD_zzi target/arm: Use TRANS_FEAT for do_zzi_sat target/arm: Use TRANS_FEAT for do_zzi_ool target/arm: Introduce gen_gvec_{ptr,fpst}_zzzz target/arm: Use TRANS_FEAT for FMMLA target/arm: Move sve check into gen_gvec_fn_ppp target/arm: Implement NOT (prediates) alias target/arm: Use TRANS_FEAT for SEL_zpzz target/arm: Use TRANS_FEAT for MOVPRFX target/arm: Use TRANS_FEAT for FMLA target/arm: Use TRANS_FEAT for BFMLA target/arm: Rename do_zzz_fp to gen_gvec_ool_fpst_arg_zzz target/arm: Use TRANS_FEAT for DO_FP3 target/arm: Use TRANS_FEAT for FMUL_zzx target/arm: Use TRANS_FEAT for FTMAD target/arm: Move null function and sve check into do_reduce target/arm: Use TRANS_FEAT for do_reduce target/arm: Use TRANS_FEAT for FRECPE, FRSQRTE target/arm: Expand frint_fns for MO_8 target/arm: Rename do_zpz_ptr to gen_gvec_ool_fpst_arg_zpz target/arm: Move null function and sve check into do_frint_mode target/arm: Use TRANS_FEAT for do_frint_mode target/arm: Use TRANS_FEAT for FLOGB target/arm: Use TRANS_FEAT for do_ppz_fp target/arm: Rename do_zpzz_ptr to gen_gvec_fpst_arg_zpzz target/arm: Use TRANS_FEAT for gen_gvec_fpst_arg_zpzz target/arm: Use TRANS_FEAT for FCADD target/arm: Introduce gen_gvec_fpst_zzzzp target/arm: Use TRANS_FEAT for gen_gvec_fpst_zzzzp target/arm: Move null function and sve check into do_fp_imm target/arm: Use TRANS_FEAT for DO_FP_IMM target/arm: Use TRANS_FEAT for DO_FPCMP target/arm: Remove assert in trans_FCMLA_zzxz target/arm: Use TRANS_FEAT for FCMLA_zzxz target/arm: Use TRANS_FEAT for do_narrow_extract target/arm: Use TRANS_FEAT for do_shll_tb target/arm: Use TRANS_FEAT for do_shr_narrow target/arm: Use TRANS_FEAT for do_FMLAL_zzzw target/arm: Use TRANS_FEAT for do_FMLAL_zzxw target/arm: Add sve feature check for remaining trans_* functions target/arm: Remove aa64_sve check from before disas_sve docs/system/arm/emulation.rst | 1 + target/arm/translate.h | 11 + target/arm/sve.decode | 57 +- hw/sd/allwinner-sdhost.c | 7 + target/arm/hvf/hvf.c | 1 + target/arm/sve_helper.c | 6 +- target/arm/translate-a64.c | 2 +- target/arm/translate-sve.c | 5367 +++++++++++++++-------------------------- 8 files changed, 2067 insertions(+), 3385 deletions(-) In commit 5814d587fe861fe9 we added support for emulating FEAT_HCX (Support for the HCRX_EL2 register). However we forgot to add it to the list in emulated.rst. Correct the omission. Fixes: 5814d587fe861fe9 ("target/arm: Enable FEAT_HCX for -cpu max") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220520084320.424166-1-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_FRINTTS (Floating-point to integer instructions) - FEAT_FlagM (Flag manipulation instructions v2) - FEAT_FlagM2 (Enhancements to flag manipulation instructions) +- FEAT_HCX (Support for the HCRX_EL2 register) - FEAT_HPDS (Hierarchical permission disables) - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) - FEAT_IDST (ID space trap handling) -- 2.25.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Fix when building HVF on macOS Aarch64: target/arm/hvf/hvf.c:586:15: error: unknown type name 'ARMCPRegInfo'; did you mean 'ARMCPUInfo'? const ARMCPRegInfo *ri; ^~~~~~~~~~~~ ARMCPUInfo target/arm/cpu-qom.h:38:3: note: 'ARMCPUInfo' declared here } ARMCPUInfo; ^ target/arm/hvf/hvf.c:589:14: error: implicit declaration of function 'get_arm_cp_reginfo' is invalid in C99 [-Werror,-Wimplicit-function-declaration] ri = get_arm_cp_reginfo(arm_cpu->cp_regs, key); ^ target/arm/hvf/hvf.c:589:12: warning: incompatible integer to pointer conversion assigning to 'const ARMCPUInfo *' (aka 'const struct ARMCPUInfo *') from 'int' [-Wint-conversion] ri = get_arm_cp_reginfo(arm_cpu->cp_regs, key); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ target/arm/hvf/hvf.c:591:26: error: no member named 'type' in 'struct ARMCPUInfo' assert(!(ri->type & ARM_CP_NO_RAW)); ~~ ^ /Library/Developer/CommandLineTools/SDKs/MacOSX.sdk/usr/include/assert.h:99:25: note: expanded from macro 'assert' (__builtin_expect(!(e), 0) ? __assert_rtn(__func__, __ASSERT_FILE_NAME, __LINE__, #e) : (void)0) ^ target/arm/hvf/hvf.c:591:33: error: use of undeclared identifier 'ARM_CP_NO_RAW' assert(!(ri->type & ARM_CP_NO_RAW)); ^ 1 warning and 4 errors generated. Fixes: cf7c6d1004 ("target/arm: Split out cpregs.h") Reported-by: Duncan Bayne <duncan@bayne.id.au> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220525161926.34233-1-philmd@fungible.com Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1029 Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/hvf/hvf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/hvf_int.h" #include "sysemu/hw_accel.h" #include "hvf_arm.h" +#include "cpregs.h" #include <mach/mach_time.h> -- 2.25.1 From: Icenowy Zheng <uwu@icenowy.me> U-Boot queries the FIFO water level to reduce checking status register when doing PIO SD card operation. Report a FIFO water level of 1 when data is ready, to prevent the code from trying to read 0 words from the FIFO each time. Signed-off-by: Icenowy Zheng <uwu@icenowy.me> Message-id: 20220520124200.2112699-1-uwu@icenowy.me Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/allwinner-sdhost.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/sd/allwinner-sdhost.c b/hw/sd/allwinner-sdhost.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/allwinner-sdhost.c +++ b/hw/sd/allwinner-sdhost.c @@ -XXX,XX +XXX,XX @@ enum { }; enum { + SD_STAR_FIFO_EMPTY = (1 << 2), SD_STAR_CARD_PRESENT = (1 << 8), + SD_STAR_FIFO_LEVEL_1 = (1 << 17), }; enum { @@ -XXX,XX +XXX,XX @@ static uint64_t allwinner_sdhost_read(void *opaque, hwaddr offset, break; case REG_SD_STAR: /* Status */ res = s->status; + if (sdbus_data_ready(&s->sdbus)) { + res |= SD_STAR_FIFO_LEVEL_1; + } else { + res |= SD_STAR_FIFO_EMPTY; + } break; case REG_SD_FWLR: /* FIFO Water Level */ res = s->fifo_wlevel; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Steal the idea for these leaf function expanders from PowerPC. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) */ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op); +/* + * Helpers for implementing sets of trans_* functions. + * Defer the implementation of NAME to FUNC, with optional extra arguments. + */ +#define TRANS(NAME, FUNC, ...) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { return FUNC(s, __VA_ARGS__); } +#define TRANS_FEAT(NAME, FEAT, FUNC, ...) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { return dc_isar_feature(FEAT, s) && FUNC(s, __VA_ARGS__); } + #endif /* TARGET_ARM_TRANSLATE_H */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 36 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 21 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static int pred_gvec_reg_size(DisasContext *s) } /* Invoke an out-of-line helper on 2 Zregs. */ -static void gen_gvec_ool_zz(DisasContext *s, gen_helper_gvec_2 *fn, +static bool gen_gvec_ool_zz(DisasContext *s, gen_helper_gvec_2 *fn, int rd, int rn, int data) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_2_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vsz, vsz, data, fn); + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vsz, vsz, data, fn); + } + return true; } /* Invoke an out-of-line helper on 3 Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool trans_FEXPA(DisasContext *s, arg_rr_esz *a) gen_helper_sve_fexpa_s, gen_helper_sve_fexpa_d, }; - if (a->esz == 0) { - return false; - } - if (sve_access_check(s)) { - gen_gvec_ool_zz(s, fns[a->esz], a->rd, a->rn, 0); - } - return true; + return gen_gvec_ool_zz(s, fns[a->esz], a->rd, a->rn, 0); } static bool trans_FTSSEL(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_REV_v(DisasContext *s, arg_rr_esz *a) gen_helper_sve_rev_b, gen_helper_sve_rev_h, gen_helper_sve_rev_s, gen_helper_sve_rev_d }; - - if (sve_access_check(s)) { - gen_gvec_ool_zz(s, fns[a->esz], a->rd, a->rn, 0); - } - return true; + return gen_gvec_ool_zz(s, fns[a->esz], a->rd, a->rn, 0); } static bool trans_TBL(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_AESMC(DisasContext *s, arg_AESMC *a) if (!dc_isar_feature(aa64_sve2_aes, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zz(s, gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt); - } - return true; + return gen_gvec_ool_zz(s, gen_helper_crypto_aesmc, + a->rd, a->rd, a->decrypt); } static bool do_aese(DisasContext *s, arg_rrr_esz *a, bool decrypt) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using gen_gvec_ool_zz to TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 39 +++++++++++++------------------------- 1 file changed, 13 insertions(+), 26 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_ADR_u32(DisasContext *s, arg_rrri *a) *** SVE Integer Misc - Unpredicated Group */ -static bool trans_FEXPA(DisasContext *s, arg_rr_esz *a) -{ - static gen_helper_gvec_2 * const fns[4] = { - NULL, - gen_helper_sve_fexpa_h, - gen_helper_sve_fexpa_s, - gen_helper_sve_fexpa_d, - }; - return gen_gvec_ool_zz(s, fns[a->esz], a->rd, a->rn, 0); -} +static gen_helper_gvec_2 * const fexpa_fns[4] = { + NULL, gen_helper_sve_fexpa_h, + gen_helper_sve_fexpa_s, gen_helper_sve_fexpa_d, +}; +TRANS_FEAT(FEXPA, aa64_sve, gen_gvec_ool_zz, + fexpa_fns[a->esz], a->rd, a->rn, 0) static bool trans_FTSSEL(DisasContext *s, arg_rrr_esz *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_INSR_r(DisasContext *s, arg_rrr_esz *a) return true; } -static bool trans_REV_v(DisasContext *s, arg_rr_esz *a) -{ - static gen_helper_gvec_2 * const fns[4] = { - gen_helper_sve_rev_b, gen_helper_sve_rev_h, - gen_helper_sve_rev_s, gen_helper_sve_rev_d - }; - return gen_gvec_ool_zz(s, fns[a->esz], a->rd, a->rn, 0); -} +static gen_helper_gvec_2 * const rev_fns[4] = { + gen_helper_sve_rev_b, gen_helper_sve_rev_h, + gen_helper_sve_rev_s, gen_helper_sve_rev_d +}; +TRANS_FEAT(REV_v, aa64_sve, gen_gvec_ool_zz, rev_fns[a->esz], a->rd, a->rn, 0) static bool trans_TBL(DisasContext *s, arg_rrr_esz *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) return true; } -static bool trans_AESMC(DisasContext *s, arg_AESMC *a) -{ - if (!dc_isar_feature(aa64_sve2_aes, s)) { - return false; - } - return gen_gvec_ool_zz(s, gen_helper_crypto_aesmc, - a->rd, a->rd, a->decrypt); -} +TRANS_FEAT(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, + gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) static bool do_aese(DisasContext *s, arg_rrr_esz *a, bool decrypt) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 74 ++++++++++++-------------------------- 1 file changed, 23 insertions(+), 51 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_zz(DisasContext *s, gen_helper_gvec_2 *fn, } /* Invoke an out-of-line helper on 3 Zregs. */ -static void gen_gvec_ool_zzz(DisasContext *s, gen_helper_gvec_3 *fn, +static bool gen_gvec_ool_zzz(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int rm, int data) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vsz, vsz, data, fn); + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vsz, vsz, data, fn); + } + return true; } /* Invoke an out-of-line helper on 4 Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool trans_LSL_zzi(DisasContext *s, arg_rri_esz *a) static bool do_zzw_ool(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) { - if (fn == NULL) { - return false; - } - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); - } - return true; + return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); } #define DO_ZZW(NAME, name) \ @@ -XXX,XX +XXX,XX @@ static bool trans_RDVL(DisasContext *s, arg_RDVL *a) static bool do_adr(DisasContext *s, arg_rrri *a, gen_helper_gvec_3 *fn) { - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, a->imm); - } - return true; + return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, a->imm); } static bool trans_ADR_p32(DisasContext *s, arg_rrri *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FTSSEL(DisasContext *s, arg_rrr_esz *a) gen_helper_sve_ftssel_s, gen_helper_sve_ftssel_d, }; - if (a->esz == 0) { - return false; - } - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); - } - return true; + return gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); } /* @@ -XXX,XX +XXX,XX @@ static bool trans_TBL(DisasContext *s, arg_rrr_esz *a) gen_helper_sve_tbl_b, gen_helper_sve_tbl_h, gen_helper_sve_tbl_s, gen_helper_sve_tbl_d }; - - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); - } - return true; + return gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); } static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_TBX(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); - } - return true; + return gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); } static bool trans_UNPK(DisasContext *s, arg_UNPK *a) @@ -XXX,XX +XXX,XX @@ static bool do_zip(DisasContext *s, arg_rrr_esz *a, bool high) static bool do_zzz_data_ool(DisasContext *s, arg_rrr_esz *a, int data, gen_helper_gvec_3 *fn) { - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, data); - } - return true; + return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, data); } static bool trans_ZIP1_z(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a) static bool do_sve2_zzz_ool(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) { - if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); - } - return true; + return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); } static bool trans_SMULH_zzz(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_aese(DisasContext *s, arg_rrr_esz *a, bool decrypt) if (!dc_isar_feature(aa64_sve2_aes, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, gen_helper_crypto_aese, - a->rd, a->rn, a->rm, decrypt); - } - return true; + return gen_gvec_ool_zzz(s, gen_helper_crypto_aese, + a->rd, a->rn, a->rm, decrypt); } static bool trans_AESE(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_sm4(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) if (!dc_isar_feature(aa64_sve2_sm4, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); - } - return true; + return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); } static bool trans_SM4E(DisasContext *s, arg_rrr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use gen_gvec_ool_arg_zzz instead of gen_gvec_ool_zzz when the arguments come from arg_rrr_esz. Replaces do_zzw_ool and do_zzz_data_ool. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 48 +++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 27 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_zzz(DisasContext *s, gen_helper_gvec_3 *fn, return true; } +static bool gen_gvec_ool_arg_zzz(DisasContext *s, gen_helper_gvec_3 *fn, + arg_rrr_esz *a, int data) +{ + return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, data); +} + /* Invoke an out-of-line helper on 4 Zregs. */ static void gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, int rd, int rn, int rm, int ra, int data) @@ -XXX,XX +XXX,XX @@ static bool trans_LSL_zzi(DisasContext *s, arg_rri_esz *a) return do_shift_imm(s, a, false, tcg_gen_gvec_shli); } -static bool do_zzw_ool(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) -{ - return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); -} - #define DO_ZZW(NAME, name) \ static bool trans_##NAME##_zzw(DisasContext *s, arg_rrr_esz *a) \ { \ @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME##_zzw(DisasContext *s, arg_rrr_esz *a) \ gen_helper_sve_##name##_zzw_b, gen_helper_sve_##name##_zzw_h, \ gen_helper_sve_##name##_zzw_s, NULL \ }; \ - return do_zzw_ool(s, a, fns[a->esz]); \ + return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); \ } DO_ZZW(ASR, asr) @@ -XXX,XX +XXX,XX @@ static bool trans_FTSSEL(DisasContext *s, arg_rrr_esz *a) gen_helper_sve_ftssel_s, gen_helper_sve_ftssel_d, }; - return gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); + return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); } /* @@ -XXX,XX +XXX,XX @@ static bool trans_TBL(DisasContext *s, arg_rrr_esz *a) gen_helper_sve_tbl_b, gen_helper_sve_tbl_h, gen_helper_sve_tbl_s, gen_helper_sve_tbl_d }; - return gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); + return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); } static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_TBX(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); + return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); } static bool trans_UNPK(DisasContext *s, arg_UNPK *a) @@ -XXX,XX +XXX,XX @@ static bool do_zip(DisasContext *s, arg_rrr_esz *a, bool high) return true; } -static bool do_zzz_data_ool(DisasContext *s, arg_rrr_esz *a, int data, - gen_helper_gvec_3 *fn) -{ - return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, data); -} - static bool trans_ZIP1_z(DisasContext *s, arg_rrr_esz *a) { return do_zip(s, a, false); @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const uzp_fns[4] = { static bool trans_UZP1_z(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_data_ool(s, a, 0, uzp_fns[a->esz]); + return gen_gvec_ool_arg_zzz(s, uzp_fns[a->esz], a, 0); } static bool trans_UZP2_z(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_data_ool(s, a, 1 << a->esz, uzp_fns[a->esz]); + return gen_gvec_ool_arg_zzz(s, uzp_fns[a->esz], a, 1 << a->esz); } static bool trans_UZP1_q(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_UZP1_q(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } - return do_zzz_data_ool(s, a, 0, gen_helper_sve2_uzp_q); + return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_uzp_q, a, 0); } static bool trans_UZP2_q(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_UZP2_q(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } - return do_zzz_data_ool(s, a, 16, gen_helper_sve2_uzp_q); + return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_uzp_q, a, 16); } static gen_helper_gvec_3 * const trn_fns[4] = { @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const trn_fns[4] = { static bool trans_TRN1_z(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_data_ool(s, a, 0, trn_fns[a->esz]); + return gen_gvec_ool_arg_zzz(s, trn_fns[a->esz], a, 0); } static bool trans_TRN2_z(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_data_ool(s, a, 1 << a->esz, trn_fns[a->esz]); + return gen_gvec_ool_arg_zzz(s, trn_fns[a->esz], a, 1 << a->esz); } static bool trans_TRN1_q(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_TRN1_q(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } - return do_zzz_data_ool(s, a, 0, gen_helper_sve2_trn_q); + return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_trn_q, a, 0); } static bool trans_TRN2_q(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_TRN2_q(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } - return do_zzz_data_ool(s, a, 16, gen_helper_sve2_trn_q); + return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_trn_q, a, 16); } /* @@ -XXX,XX +XXX,XX @@ static bool do_sve2_zzz_ool(DisasContext *s, arg_rrr_esz *a, if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); + return gen_gvec_ool_arg_zzz(s, fn, a, 0); } static bool trans_SMULH_zzz(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_aese(DisasContext *s, arg_rrr_esz *a, bool decrypt) if (!dc_isar_feature(aa64_sve2_aes, s)) { return false; } - return gen_gvec_ool_zzz(s, gen_helper_crypto_aese, - a->rd, a->rn, a->rm, decrypt); + return gen_gvec_ool_arg_zzz(s, gen_helper_crypto_aese, a, decrypt); } static bool trans_AESE(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_sm4(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) if (!dc_isar_feature(aa64_sve2_sm4, s)) { return false; } - return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); + return gen_gvec_ool_arg_zzz(s, fn, a, 0); } static bool trans_SM4E(DisasContext *s, arg_rrr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using gen_gvec_ool_arg_zzz to TRANS_FEAT. Remove trivial wrappers do_aese, do_sm4. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 165 ++++++++++--------------------------- 1 file changed, 45 insertions(+), 120 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LSL_zzi(DisasContext *s, arg_rri_esz *a) } #define DO_ZZW(NAME, name) \ -static bool trans_##NAME##_zzw(DisasContext *s, arg_rrr_esz *a) \ -{ \ - static gen_helper_gvec_3 * const fns[4] = { \ + static gen_helper_gvec_3 * const name##_zzw_fns[4] = { \ gen_helper_sve_##name##_zzw_b, gen_helper_sve_##name##_zzw_h, \ gen_helper_sve_##name##_zzw_s, NULL \ }; \ - return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); \ -} + TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_arg_zzz, \ + name##_zzw_fns[a->esz], a, 0) -DO_ZZW(ASR, asr) -DO_ZZW(LSR, lsr) -DO_ZZW(LSL, lsl) +DO_ZZW(ASR_zzw, asr) +DO_ZZW(LSR_zzw, lsr) +DO_ZZW(LSL_zzw, lsl) #undef DO_ZZW @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_2 * const fexpa_fns[4] = { TRANS_FEAT(FEXPA, aa64_sve, gen_gvec_ool_zz, fexpa_fns[a->esz], a->rd, a->rn, 0) -static bool trans_FTSSEL(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, - gen_helper_sve_ftssel_h, - gen_helper_sve_ftssel_s, - gen_helper_sve_ftssel_d, - }; - return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const ftssel_fns[4] = { + NULL, gen_helper_sve_ftssel_h, + gen_helper_sve_ftssel_s, gen_helper_sve_ftssel_d, +}; +TRANS_FEAT(FTSSEL, aa64_sve, gen_gvec_ool_arg_zzz, ftssel_fns[a->esz], a, 0) /* *** SVE Predicate Logical Operations Group @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_2 * const rev_fns[4] = { }; TRANS_FEAT(REV_v, aa64_sve, gen_gvec_ool_zz, rev_fns[a->esz], a->rd, a->rn, 0) -static bool trans_TBL(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve_tbl_b, gen_helper_sve_tbl_h, - gen_helper_sve_tbl_s, gen_helper_sve_tbl_d - }; - return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const sve_tbl_fns[4] = { + gen_helper_sve_tbl_b, gen_helper_sve_tbl_h, + gen_helper_sve_tbl_s, gen_helper_sve_tbl_d +}; +TRANS_FEAT(TBL, aa64_sve, gen_gvec_ool_arg_zzz, sve_tbl_fns[a->esz], a, 0) static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) return true; } -static bool trans_TBX(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h, - gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d - }; - - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const tbx_fns[4] = { + gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h, + gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d +}; +TRANS_FEAT(TBX, aa64_sve2, gen_gvec_ool_arg_zzz, tbx_fns[a->esz], a, 0) static bool trans_UNPK(DisasContext *s, arg_UNPK *a) { @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const uzp_fns[4] = { gen_helper_sve_uzp_s, gen_helper_sve_uzp_d, }; -static bool trans_UZP1_z(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_ool_arg_zzz(s, uzp_fns[a->esz], a, 0); -} +TRANS_FEAT(UZP1_z, aa64_sve, gen_gvec_ool_arg_zzz, + uzp_fns[a->esz], a, 0) +TRANS_FEAT(UZP2_z, aa64_sve, gen_gvec_ool_arg_zzz, + uzp_fns[a->esz], a, 1 << a->esz) -static bool trans_UZP2_z(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_ool_arg_zzz(s, uzp_fns[a->esz], a, 1 << a->esz); -} - -static bool trans_UZP1_q(DisasContext *s, arg_rrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_f64mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_uzp_q, a, 0); -} - -static bool trans_UZP2_q(DisasContext *s, arg_rrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_f64mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_uzp_q, a, 16); -} +TRANS_FEAT(UZP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, + gen_helper_sve2_uzp_q, a, 0) +TRANS_FEAT(UZP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, + gen_helper_sve2_uzp_q, a, 16) static gen_helper_gvec_3 * const trn_fns[4] = { gen_helper_sve_trn_b, gen_helper_sve_trn_h, gen_helper_sve_trn_s, gen_helper_sve_trn_d, }; -static bool trans_TRN1_z(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_ool_arg_zzz(s, trn_fns[a->esz], a, 0); -} +TRANS_FEAT(TRN1_z, aa64_sve, gen_gvec_ool_arg_zzz, + trn_fns[a->esz], a, 0) +TRANS_FEAT(TRN2_z, aa64_sve, gen_gvec_ool_arg_zzz, + trn_fns[a->esz], a, 1 << a->esz) -static bool trans_TRN2_z(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_ool_arg_zzz(s, trn_fns[a->esz], a, 1 << a->esz); -} - -static bool trans_TRN1_q(DisasContext *s, arg_rrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_f64mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_trn_q, a, 0); -} - -static bool trans_TRN2_q(DisasContext *s, arg_rrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_f64mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_trn_q, a, 16); -} +TRANS_FEAT(TRN1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, + gen_helper_sve2_trn_q, a, 0) +TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, + gen_helper_sve2_trn_q, a, 16) /* *** SVE Permute Vector - Predicated Group @@ -XXX,XX +XXX,XX @@ static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) TRANS_FEAT(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) -static bool do_aese(DisasContext *s, arg_rrr_esz *a, bool decrypt) -{ - if (!dc_isar_feature(aa64_sve2_aes, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, gen_helper_crypto_aese, a, decrypt); -} +TRANS_FEAT(AESE, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, false) +TRANS_FEAT(AESD, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, true) -static bool trans_AESE(DisasContext *s, arg_rrr_esz *a) -{ - return do_aese(s, a, false); -} - -static bool trans_AESD(DisasContext *s, arg_rrr_esz *a) -{ - return do_aese(s, a, true); -} - -static bool do_sm4(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) -{ - if (!dc_isar_feature(aa64_sve2_sm4, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, fn, a, 0); -} - -static bool trans_SM4E(DisasContext *s, arg_rrr_esz *a) -{ - return do_sm4(s, a, gen_helper_crypto_sm4e); -} - -static bool trans_SM4EKEY(DisasContext *s, arg_rrr_esz *a) -{ - return do_sm4(s, a, gen_helper_crypto_sm4ekey); -} +TRANS_FEAT(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4e, a, 0) +TRANS_FEAT(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4ekey, a, 0) static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zzz_ool to use TRANS_FEAT and gen_gvec_ool_arg_zzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 88 ++++++++++++++------------------------ 1 file changed, 31 insertions(+), 57 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a) return true; } -static bool do_sve2_zzz_ool(DisasContext *s, arg_rrr_esz *a, - gen_helper_gvec_3 *fn) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, fn, a, 0); -} +static gen_helper_gvec_3 * const smulh_zzz_fns[4] = { + gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h, + gen_helper_gvec_smulh_s, gen_helper_gvec_smulh_d, +}; +TRANS_FEAT(SMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + smulh_zzz_fns[a->esz], a, 0) -static bool trans_SMULH_zzz(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h, - gen_helper_gvec_smulh_s, gen_helper_gvec_smulh_d, - }; - return do_sve2_zzz_ool(s, a, fns[a->esz]); -} +static gen_helper_gvec_3 * const umulh_zzz_fns[4] = { + gen_helper_gvec_umulh_b, gen_helper_gvec_umulh_h, + gen_helper_gvec_umulh_s, gen_helper_gvec_umulh_d, +}; +TRANS_FEAT(UMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + umulh_zzz_fns[a->esz], a, 0) -static bool trans_UMULH_zzz(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_gvec_umulh_b, gen_helper_gvec_umulh_h, - gen_helper_gvec_umulh_s, gen_helper_gvec_umulh_d, - }; - return do_sve2_zzz_ool(s, a, fns[a->esz]); -} +TRANS_FEAT(PMUL_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + gen_helper_gvec_pmul_b, a, 0) -static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b); -} +static gen_helper_gvec_3 * const sqdmulh_zzz_fns[4] = { + gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, + gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, +}; +TRANS_FEAT(SQDMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + sqdmulh_zzz_fns[a->esz], a, 0) -static bool trans_SQDMULH_zzz(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, - gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, - }; - return do_sve2_zzz_ool(s, a, fns[a->esz]); -} - -static bool trans_SQRDMULH_zzz(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h, - gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d, - }; - return do_sve2_zzz_ool(s, a, fns[a->esz]); -} +static gen_helper_gvec_3 * const sqrdmulh_zzz_fns[4] = { + gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h, + gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d, +}; +TRANS_FEAT(SQRDMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + sqrdmulh_zzz_fns[a->esz], a, 0) /* * SVE2 Integer - Predicated @@ -XXX,XX +XXX,XX @@ static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a) } #define DO_SVE2_ZZZ_NARROW(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ -{ \ - static gen_helper_gvec_3 * const fns[4] = { \ + static gen_helper_gvec_3 * const name##_fns[4] = { \ NULL, gen_helper_sve2_##name##_h, \ gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ }; \ - return do_sve2_zzz_ool(s, a, fns[a->esz]); \ -} + TRANS_FEAT(NAME, aa64_sve2, gen_gvec_ool_arg_zzz, \ + name##_fns[a->esz], a, 0) DO_SVE2_ZZZ_NARROW(ADDHNB, addhnb) DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt) @@ -XXX,XX +XXX,XX @@ static bool trans_HISTCNT(DisasContext *s, arg_rprr_esz *a) return do_sve2_zpzz_ool(s, a, fns[a->esz - 2]); } -static bool trans_HISTSEG(DisasContext *s, arg_rrr_esz *a) -{ - if (a->esz != 0) { - return false; - } - return do_sve2_zzz_ool(s, a, gen_helper_sve2_histseg); -} +TRANS_FEAT(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, + a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4_ptr *fn) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 102 ++++++++++++++----------------------- 1 file changed, 38 insertions(+), 64 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zzz(DisasContext *s, gen_helper_gvec_3 *fn, } /* Invoke an out-of-line helper on 4 Zregs. */ -static void gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, +static bool gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, int rd, int rn, int rm, int ra, int data) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vec_full_reg_offset(s, ra), - vsz, vsz, data, fn); + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + vsz, vsz, data, fn); + } + return true; } /* Invoke an out-of-line helper on 2 Zregs and a predicate. */ @@ -XXX,XX +XXX,XX @@ static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, - (a->rn + 1) % 32, a->rm, 0); - } - return true; + return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, + (a->rn + 1) % 32, a->rm, 0); } static gen_helper_gvec_3 * const tbx_fns[4] = { @@ -XXX,XX +XXX,XX @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } }; - - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0); - } - return true; + return gen_gvec_ool_zzzz(s, fns[a->u][a->sz], + a->rd, a->rn, a->rm, a->ra, 0); } /* @@ -XXX,XX +XXX,XX @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a, gen_helper_gvec_4 *fn) { - if (fn == NULL) { - return false; - } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index); - } - return true; + return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index); } #define DO_RRXR(NAME, FUNC) \ @@ -XXX,XX +XXX,XX @@ static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a) static bool do_sve2_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, gen_helper_gvec_4 *fn, int data) { - if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); - } - return true; + return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); } static bool do_abal(DisasContext *s, arg_rrrr_esz *a, bool uns, bool sel) @@ -XXX,XX +XXX,XX @@ static bool trans_CMLA_zzzz(DisasContext *s, arg_CMLA_zzzz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot); - } - return true; + return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, + a->rm, a->ra, a->rot); } static bool trans_CDOT_zzzz(DisasContext *s, arg_CMLA_zzzz *a) { - if (!dc_isar_feature(aa64_sve2, s) || a->esz < MO_32) { + static gen_helper_gvec_4 * const fns[] = { + NULL, NULL, gen_helper_sve2_cdot_zzzz_s, gen_helper_sve2_cdot_zzzz_d + }; + + if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_helper_gvec_4 *fn = (a->esz == MO_32 - ? gen_helper_sve2_cdot_zzzz_s - : gen_helper_sve2_cdot_zzzz_d); - gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->rot); - } - return true; + return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, + a->rm, a->ra, a->rot); } static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot); - } - return true; + return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, + a->rm, a->ra, a->rot); } static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) @@ -XXX,XX +XXX,XX @@ static bool do_i8mm_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, if (!dc_isar_feature(aa64_sve_i8mm, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); - } - return true; + return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); } static bool trans_SMMLA(DisasContext *s, arg_rrrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_BFDOT_zzzz(DisasContext *s, arg_rrrr_esz *a) if (!dc_isar_feature(aa64_sve_bf16, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot, - a->rd, a->rn, a->rm, a->ra, 0); - } - return true; + return gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot, + a->rd, a->rn, a->rm, a->ra, 0); } static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a) if (!dc_isar_feature(aa64_sve_bf16, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot_idx, - a->rd, a->rn, a->rm, a->ra, a->index); - } - return true; + return gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot_idx, + a->rd, a->rn, a->rm, a->ra, a->index); } static bool trans_BFMMLA(DisasContext *s, arg_rrrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_BFMMLA(DisasContext *s, arg_rrrr_esz *a) if (!dc_isar_feature(aa64_sve_bf16, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, gen_helper_gvec_bfmmla, - a->rd, a->rn, a->rm, a->ra, 0); - } - return true; + return gen_gvec_ool_zzzz(s, gen_helper_gvec_bfmmla, + a->rd, a->rn, a->rm, a->ra, 0); } static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions directly using gen_gvec_ool_zzzz to TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-10-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 89 +++++++++++++------------------------- 1 file changed, 29 insertions(+), 60 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const sve_tbl_fns[4] = { }; TRANS_FEAT(TBL, aa64_sve, gen_gvec_ool_arg_zzz, sve_tbl_fns[a->esz], a, 0) -static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_4 * const fns[4] = { - gen_helper_sve2_tbl_b, gen_helper_sve2_tbl_h, - gen_helper_sve2_tbl_s, gen_helper_sve2_tbl_d - }; - - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, - (a->rn + 1) % 32, a->rm, 0); -} +static gen_helper_gvec_4 * const sve2_tbl_fns[4] = { + gen_helper_sve2_tbl_b, gen_helper_sve2_tbl_h, + gen_helper_sve2_tbl_s, gen_helper_sve2_tbl_d +}; +TRANS_FEAT(TBL_sve2, aa64_sve2, gen_gvec_ool_zzzz, sve2_tbl_fns[a->esz], + a->rd, a->rn, (a->rn + 1) % 32, a->rm, 0) static gen_helper_gvec_3 * const tbx_fns[4] = { gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h, @@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin) #undef DO_ZZI -static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) -{ - static gen_helper_gvec_4 * const fns[2][2] = { - { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, - { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } - }; - return gen_gvec_ool_zzzz(s, fns[a->u][a->sz], - a->rd, a->rn, a->rm, a->ra, 0); -} +static gen_helper_gvec_4 * const dot_fns[2][2] = { + { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, + { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } +}; +TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, + dot_fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0) /* * SVE Multiply - Indexed @@ -XXX,XX +XXX,XX @@ static bool trans_UMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) return do_umlsl_zzzw(s, a, true); } -static bool trans_CMLA_zzzz(DisasContext *s, arg_CMLA_zzzz *a) -{ - static gen_helper_gvec_4 * const fns[] = { - gen_helper_sve2_cmla_zzzz_b, gen_helper_sve2_cmla_zzzz_h, - gen_helper_sve2_cmla_zzzz_s, gen_helper_sve2_cmla_zzzz_d, - }; +static gen_helper_gvec_4 * const cmla_fns[] = { + gen_helper_sve2_cmla_zzzz_b, gen_helper_sve2_cmla_zzzz_h, + gen_helper_sve2_cmla_zzzz_s, gen_helper_sve2_cmla_zzzz_d, +}; +TRANS_FEAT(CMLA_zzzz, aa64_sve2, gen_gvec_ool_zzzz, + cmla_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, - a->rm, a->ra, a->rot); -} +static gen_helper_gvec_4 * const cdot_fns[] = { + NULL, NULL, gen_helper_sve2_cdot_zzzz_s, gen_helper_sve2_cdot_zzzz_d +}; +TRANS_FEAT(CDOT_zzzz, aa64_sve2, gen_gvec_ool_zzzz, + cdot_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) -static bool trans_CDOT_zzzz(DisasContext *s, arg_CMLA_zzzz *a) -{ - static gen_helper_gvec_4 * const fns[] = { - NULL, NULL, gen_helper_sve2_cdot_zzzz_s, gen_helper_sve2_cdot_zzzz_d - }; - - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, - a->rm, a->ra, a->rot); -} - -static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a) -{ - static gen_helper_gvec_4 * const fns[] = { - gen_helper_sve2_sqrdcmlah_zzzz_b, gen_helper_sve2_sqrdcmlah_zzzz_h, - gen_helper_sve2_sqrdcmlah_zzzz_s, gen_helper_sve2_sqrdcmlah_zzzz_d, - }; - - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, - a->rm, a->ra, a->rot); -} +static gen_helper_gvec_4 * const sqrdcmlah_fns[] = { + gen_helper_sve2_sqrdcmlah_zzzz_b, gen_helper_sve2_sqrdcmlah_zzzz_h, + gen_helper_sve2_sqrdcmlah_zzzz_s, gen_helper_sve2_sqrdcmlah_zzzz_d, +}; +TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, + sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use gen_gvec_ool_arg_zzzz instead of gen_gvec_ool_zzzz when the arguments come from arg_rrrr_esz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-11-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, return true; } +static bool gen_gvec_ool_arg_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, + arg_rrrr_esz *a, int data) +{ + return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); +} + /* Invoke an out-of-line helper on 2 Zregs and a predicate. */ static void gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int pg, int data) @@ -XXX,XX +XXX,XX @@ static bool do_sve2_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); + return gen_gvec_ool_arg_zzzz(s, fn, a, data); } static bool do_abal(DisasContext *s, arg_rrrr_esz *a, bool uns, bool sel) @@ -XXX,XX +XXX,XX @@ static bool do_i8mm_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, if (!dc_isar_feature(aa64_sve_i8mm, s)) { return false; } - return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); + return gen_gvec_ool_arg_zzzz(s, fn, a, data); } static bool trans_SMMLA(DisasContext *s, arg_rrrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_BFDOT_zzzz(DisasContext *s, arg_rrrr_esz *a) if (!dc_isar_feature(aa64_sve_bf16, s)) { return false; } - return gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot, - a->rd, a->rn, a->rm, a->ra, 0); + return gen_gvec_ool_arg_zzzz(s, gen_helper_gvec_bfdot, a, 0); } static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_BFMMLA(DisasContext *s, arg_rrrr_esz *a) if (!dc_isar_feature(aa64_sve_bf16, s)) { return false; } - return gen_gvec_ool_zzzz(s, gen_helper_gvec_bfmmla, - a->rd, a->rn, a->rm, a->ra, 0); + return gen_gvec_ool_arg_zzzz(s, gen_helper_gvec_bfmmla, a, 0); } static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zzzz_ool to use TRANS_FEAT and gen_gvec_ool_arg_zzzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-12-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 263 +++++++++++-------------------------- 1 file changed, 79 insertions(+), 184 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a) return do_cadd(s, a, true, true); } -static bool do_sve2_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, - gen_helper_gvec_4 *fn, int data) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zzzz(s, fn, a, data); -} +static gen_helper_gvec_4 * const sabal_fns[4] = { + NULL, gen_helper_sve2_sabal_h, + gen_helper_sve2_sabal_s, gen_helper_sve2_sabal_d, +}; +TRANS_FEAT(SABALB, aa64_sve2, gen_gvec_ool_arg_zzzz, sabal_fns[a->esz], a, 0) +TRANS_FEAT(SABALT, aa64_sve2, gen_gvec_ool_arg_zzzz, sabal_fns[a->esz], a, 1) -static bool do_abal(DisasContext *s, arg_rrrr_esz *a, bool uns, bool sel) -{ - static gen_helper_gvec_4 * const fns[2][4] = { - { NULL, gen_helper_sve2_sabal_h, - gen_helper_sve2_sabal_s, gen_helper_sve2_sabal_d }, - { NULL, gen_helper_sve2_uabal_h, - gen_helper_sve2_uabal_s, gen_helper_sve2_uabal_d }, - }; - return do_sve2_zzzz_ool(s, a, fns[uns][a->esz], sel); -} - -static bool trans_SABALB(DisasContext *s, arg_rrrr_esz *a) -{ - return do_abal(s, a, false, false); -} - -static bool trans_SABALT(DisasContext *s, arg_rrrr_esz *a) -{ - return do_abal(s, a, false, true); -} - -static bool trans_UABALB(DisasContext *s, arg_rrrr_esz *a) -{ - return do_abal(s, a, true, false); -} - -static bool trans_UABALT(DisasContext *s, arg_rrrr_esz *a) -{ - return do_abal(s, a, true, true); -} +static gen_helper_gvec_4 * const uabal_fns[4] = { + NULL, gen_helper_sve2_uabal_h, + gen_helper_sve2_uabal_s, gen_helper_sve2_uabal_d, +}; +TRANS_FEAT(UABALB, aa64_sve2, gen_gvec_ool_arg_zzzz, uabal_fns[a->esz], a, 0) +TRANS_FEAT(UABALT, aa64_sve2, gen_gvec_ool_arg_zzzz, uabal_fns[a->esz], a, 1) static bool do_adcl(DisasContext *s, arg_rrrr_esz *a, bool sel) { @@ -XXX,XX +XXX,XX @@ static bool do_adcl(DisasContext *s, arg_rrrr_esz *a, bool sel) * Note that in this case the ESZ field encodes both size and sign. * Split out 'subtract' into bit 1 of the data field for the helper. */ - return do_sve2_zzzz_ool(s, a, fns[a->esz & 1], (a->esz & 2) | sel); + return gen_gvec_ool_arg_zzzz(s, fns[a->esz & 1], a, (a->esz & 2) | sel); } -static bool trans_ADCLB(DisasContext *s, arg_rrrr_esz *a) -{ - return do_adcl(s, a, false); -} - -static bool trans_ADCLT(DisasContext *s, arg_rrrr_esz *a) -{ - return do_adcl(s, a, true); -} +TRANS_FEAT(ADCLB, aa64_sve2, do_adcl, a, false) +TRANS_FEAT(ADCLT, aa64_sve2, do_adcl, a, true) static bool do_sve2_fn2i(DisasContext *s, arg_rri_esz *a, GVecGen2iFn *fn) { @@ -XXX,XX +XXX,XX @@ static bool trans_FMMLA(DisasContext *s, arg_rrrr_esz *a) return true; } -static bool do_sqdmlal_zzzw(DisasContext *s, arg_rrrr_esz *a, - bool sel1, bool sel2) -{ - static gen_helper_gvec_4 * const fns[] = { - NULL, gen_helper_sve2_sqdmlal_zzzw_h, - gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1); -} +static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { + NULL, gen_helper_sve2_sqdmlal_zzzw_h, + gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d, +}; +TRANS_FEAT(SQDMLALB_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqdmlal_zzzw_fns[a->esz], a, 0) +TRANS_FEAT(SQDMLALT_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqdmlal_zzzw_fns[a->esz], a, 3) +TRANS_FEAT(SQDMLALBT, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqdmlal_zzzw_fns[a->esz], a, 2) -static bool do_sqdmlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, - bool sel1, bool sel2) -{ - static gen_helper_gvec_4 * const fns[] = { - NULL, gen_helper_sve2_sqdmlsl_zzzw_h, - gen_helper_sve2_sqdmlsl_zzzw_s, gen_helper_sve2_sqdmlsl_zzzw_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1); -} +static gen_helper_gvec_4 * const sqdmlsl_zzzw_fns[] = { + NULL, gen_helper_sve2_sqdmlsl_zzzw_h, + gen_helper_sve2_sqdmlsl_zzzw_s, gen_helper_sve2_sqdmlsl_zzzw_d, +}; +TRANS_FEAT(SQDMLSLB_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqdmlsl_zzzw_fns[a->esz], a, 0) +TRANS_FEAT(SQDMLSLT_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqdmlsl_zzzw_fns[a->esz], a, 3) +TRANS_FEAT(SQDMLSLBT, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqdmlsl_zzzw_fns[a->esz], a, 2) -static bool trans_SQDMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sqdmlal_zzzw(s, a, false, false); -} +static gen_helper_gvec_4 * const sqrdmlah_fns[] = { + gen_helper_sve2_sqrdmlah_b, gen_helper_sve2_sqrdmlah_h, + gen_helper_sve2_sqrdmlah_s, gen_helper_sve2_sqrdmlah_d, +}; +TRANS_FEAT(SQRDMLAH_zzzz, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqrdmlah_fns[a->esz], a, 0) -static bool trans_SQDMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sqdmlal_zzzw(s, a, true, true); -} +static gen_helper_gvec_4 * const sqrdmlsh_fns[] = { + gen_helper_sve2_sqrdmlsh_b, gen_helper_sve2_sqrdmlsh_h, + gen_helper_sve2_sqrdmlsh_s, gen_helper_sve2_sqrdmlsh_d, +}; +TRANS_FEAT(SQRDMLSH_zzzz, aa64_sve2, gen_gvec_ool_arg_zzzz, + sqrdmlsh_fns[a->esz], a, 0) -static bool trans_SQDMLALBT(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sqdmlal_zzzw(s, a, false, true); -} +static gen_helper_gvec_4 * const smlal_zzzw_fns[] = { + NULL, gen_helper_sve2_smlal_zzzw_h, + gen_helper_sve2_smlal_zzzw_s, gen_helper_sve2_smlal_zzzw_d, +}; +TRANS_FEAT(SMLALB_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + smlal_zzzw_fns[a->esz], a, 0) +TRANS_FEAT(SMLALT_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + smlal_zzzw_fns[a->esz], a, 1) -static bool trans_SQDMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sqdmlsl_zzzw(s, a, false, false); -} +static gen_helper_gvec_4 * const umlal_zzzw_fns[] = { + NULL, gen_helper_sve2_umlal_zzzw_h, + gen_helper_sve2_umlal_zzzw_s, gen_helper_sve2_umlal_zzzw_d, +}; +TRANS_FEAT(UMLALB_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + umlal_zzzw_fns[a->esz], a, 0) +TRANS_FEAT(UMLALT_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + umlal_zzzw_fns[a->esz], a, 1) -static bool trans_SQDMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sqdmlsl_zzzw(s, a, true, true); -} +static gen_helper_gvec_4 * const smlsl_zzzw_fns[] = { + NULL, gen_helper_sve2_smlsl_zzzw_h, + gen_helper_sve2_smlsl_zzzw_s, gen_helper_sve2_smlsl_zzzw_d, +}; +TRANS_FEAT(SMLSLB_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + smlsl_zzzw_fns[a->esz], a, 0) +TRANS_FEAT(SMLSLT_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + smlsl_zzzw_fns[a->esz], a, 1) -static bool trans_SQDMLSLBT(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sqdmlsl_zzzw(s, a, false, true); -} - -static bool trans_SQRDMLAH_zzzz(DisasContext *s, arg_rrrr_esz *a) -{ - static gen_helper_gvec_4 * const fns[] = { - gen_helper_sve2_sqrdmlah_b, gen_helper_sve2_sqrdmlah_h, - gen_helper_sve2_sqrdmlah_s, gen_helper_sve2_sqrdmlah_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], 0); -} - -static bool trans_SQRDMLSH_zzzz(DisasContext *s, arg_rrrr_esz *a) -{ - static gen_helper_gvec_4 * const fns[] = { - gen_helper_sve2_sqrdmlsh_b, gen_helper_sve2_sqrdmlsh_h, - gen_helper_sve2_sqrdmlsh_s, gen_helper_sve2_sqrdmlsh_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], 0); -} - -static bool do_smlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) -{ - static gen_helper_gvec_4 * const fns[] = { - NULL, gen_helper_sve2_smlal_zzzw_h, - gen_helper_sve2_smlal_zzzw_s, gen_helper_sve2_smlal_zzzw_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); -} - -static bool trans_SMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_smlal_zzzw(s, a, false); -} - -static bool trans_SMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_smlal_zzzw(s, a, true); -} - -static bool do_umlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) -{ - static gen_helper_gvec_4 * const fns[] = { - NULL, gen_helper_sve2_umlal_zzzw_h, - gen_helper_sve2_umlal_zzzw_s, gen_helper_sve2_umlal_zzzw_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); -} - -static bool trans_UMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_umlal_zzzw(s, a, false); -} - -static bool trans_UMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_umlal_zzzw(s, a, true); -} - -static bool do_smlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) -{ - static gen_helper_gvec_4 * const fns[] = { - NULL, gen_helper_sve2_smlsl_zzzw_h, - gen_helper_sve2_smlsl_zzzw_s, gen_helper_sve2_smlsl_zzzw_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); -} - -static bool trans_SMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_smlsl_zzzw(s, a, false); -} - -static bool trans_SMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_smlsl_zzzw(s, a, true); -} - -static bool do_umlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) -{ - static gen_helper_gvec_4 * const fns[] = { - NULL, gen_helper_sve2_umlsl_zzzw_h, - gen_helper_sve2_umlsl_zzzw_s, gen_helper_sve2_umlsl_zzzw_d, - }; - return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); -} - -static bool trans_UMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_umlsl_zzzw(s, a, false); -} - -static bool trans_UMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_umlsl_zzzw(s, a, true); -} +static gen_helper_gvec_4 * const umlsl_zzzw_fns[] = { + NULL, gen_helper_sve2_umlsl_zzzw_h, + gen_helper_sve2_umlsl_zzzw_s, gen_helper_sve2_umlsl_zzzw_d, +}; +TRANS_FEAT(UMLSLB_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + umlsl_zzzw_fns[a->esz], a, 0) +TRANS_FEAT(UMLSLT_zzzw, aa64_sve2, gen_gvec_ool_arg_zzzz, + umlsl_zzzw_fns[a->esz], a, 1) static gen_helper_gvec_4 * const cmla_fns[] = { gen_helper_sve2_cmla_zzzz_b, gen_helper_sve2_cmla_zzzz_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions directly using gen_gvec_ool_arg_zzzz to TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-13-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 47 ++++++++------------------------------ 1 file changed, 10 insertions(+), 37 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FMLSLT_zzxw(DisasContext *s, arg_rrxr_esz *a) return do_FMLAL_zzxw(s, a, true, true); } -static bool do_i8mm_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, - gen_helper_gvec_4 *fn, int data) -{ - if (!dc_isar_feature(aa64_sve_i8mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzzz(s, fn, a, data); -} +TRANS_FEAT(SMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_smmla_b, a, 0) +TRANS_FEAT(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_usmmla_b, a, 0) +TRANS_FEAT(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_ummla_b, a, 0) -static bool trans_SMMLA(DisasContext *s, arg_rrrr_esz *a) -{ - return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_smmla_b, 0); -} - -static bool trans_USMMLA(DisasContext *s, arg_rrrr_esz *a) -{ - return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_usmmla_b, 0); -} - -static bool trans_UMMLA(DisasContext *s, arg_rrrr_esz *a) -{ - return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_ummla_b, 0); -} - -static bool trans_BFDOT_zzzz(DisasContext *s, arg_rrrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_bf16, s)) { - return false; - } - return gen_gvec_ool_arg_zzzz(s, gen_helper_gvec_bfdot, a, 0); -} +TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_bfdot, a, 0) static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a) a->rd, a->rn, a->rm, a->ra, a->index); } -static bool trans_BFMMLA(DisasContext *s, arg_rrrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_bf16, s)) { - return false; - } - return gen_gvec_ool_arg_zzzz(s, gen_helper_gvec_bfmmla, a, 0); -} +TRANS_FEAT(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_bfmmla, a, 0) static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Rename the function to match gen_gvec_ool_arg_zzzz, and move to be adjacent. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-14-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); } +static bool gen_gvec_ool_arg_zzxz(DisasContext *s, gen_helper_gvec_4 *fn, + arg_rrxr_esz *a) +{ + return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index); +} + /* Invoke an out-of-line helper on 2 Zregs and a predicate. */ static void gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int pg, int data) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, * SVE Multiply - Indexed */ -static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a, - gen_helper_gvec_4 *fn) -{ - return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index); -} - #define DO_RRXR(NAME, FUNC) \ static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ - { return do_zzxz_ool(s, a, FUNC); } + { return gen_gvec_ool_arg_zzxz(s, FUNC, a); } DO_RRXR(trans_SDOT_zzxw_s, gen_helper_gvec_sdot_idx_b) DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h) @@ -XXX,XX +XXX,XX @@ static bool trans_SUDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) if (!dc_isar_feature(aa64_sve_i8mm, s)) { return false; } - return do_zzxz_ool(s, a, gen_helper_gvec_sudot_idx_b); + return gen_gvec_ool_arg_zzxz(s, gen_helper_gvec_sudot_idx_b, a); } static bool trans_USDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_USDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) if (!dc_isar_feature(aa64_sve_i8mm, s)) { return false; } - return do_zzxz_ool(s, a, gen_helper_gvec_usdot_idx_b); + return gen_gvec_ool_arg_zzxz(s, gen_helper_gvec_usdot_idx_b, a); } #undef DO_RRXR -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions directly using gen_gvec_ool_arg_zzxz to TRANS_FEAT. Also include BFDOT_zzxz, which was using gen_gvec_ool_zzzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-15-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 48 +++++++++++--------------------------- 1 file changed, 14 insertions(+), 34 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, * SVE Multiply - Indexed */ -#define DO_RRXR(NAME, FUNC) \ - static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ - { return gen_gvec_ool_arg_zzxz(s, FUNC, a); } +TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sdot_idx_b, a) +TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sdot_idx_h, a) +TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_udot_idx_b, a) +TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_udot_idx_h, a) -DO_RRXR(trans_SDOT_zzxw_s, gen_helper_gvec_sdot_idx_b) -DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h) -DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b) -DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h) - -static bool trans_SUDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_i8mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzxz(s, gen_helper_gvec_sudot_idx_b, a); -} - -static bool trans_USDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_i8mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzxz(s, gen_helper_gvec_usdot_idx_b, a); -} - -#undef DO_RRXR +TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sudot_idx_b, a) +TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_usdot_idx_b, a) static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data, gen_helper_gvec_3 *fn) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, gen_helper_gvec_bfdot, a, 0) - -static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_bf16, s)) { - return false; - } - return gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot_idx, - a->rd, a->rn, a->rm, a->ra, a->index); -} +TRANS_FEAT(BFDOT_zzxz, aa64_sve_bf16, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_bfdot_idx, a) TRANS_FEAT(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, gen_helper_gvec_bfmmla, a, 0) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zzz_data to use TRANS_FEAT and gen_gvec_ool_zzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-16-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 69 ++++++++++++++------------------------ 1 file changed, 25 insertions(+), 44 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, gen_helper_gvec_usdot_idx_b, a) -static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data, - gen_helper_gvec_3 *fn) -{ - if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vsz, vsz, data, fn); - } - return true; -} - #define DO_SVE2_RRX(NAME, FUNC) \ - static bool NAME(DisasContext *s, arg_rrx_esz *a) \ - { return do_sve2_zzz_data(s, a->rd, a->rn, a->rm, a->index, FUNC); } + TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \ + a->rd, a->rn, a->rm, a->index) -DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h) -DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s) -DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d) +DO_SVE2_RRX(MUL_zzx_h, gen_helper_gvec_mul_idx_h) +DO_SVE2_RRX(MUL_zzx_s, gen_helper_gvec_mul_idx_s) +DO_SVE2_RRX(MUL_zzx_d, gen_helper_gvec_mul_idx_d) -DO_SVE2_RRX(trans_SQDMULH_zzx_h, gen_helper_sve2_sqdmulh_idx_h) -DO_SVE2_RRX(trans_SQDMULH_zzx_s, gen_helper_sve2_sqdmulh_idx_s) -DO_SVE2_RRX(trans_SQDMULH_zzx_d, gen_helper_sve2_sqdmulh_idx_d) +DO_SVE2_RRX(SQDMULH_zzx_h, gen_helper_sve2_sqdmulh_idx_h) +DO_SVE2_RRX(SQDMULH_zzx_s, gen_helper_sve2_sqdmulh_idx_s) +DO_SVE2_RRX(SQDMULH_zzx_d, gen_helper_sve2_sqdmulh_idx_d) -DO_SVE2_RRX(trans_SQRDMULH_zzx_h, gen_helper_sve2_sqrdmulh_idx_h) -DO_SVE2_RRX(trans_SQRDMULH_zzx_s, gen_helper_sve2_sqrdmulh_idx_s) -DO_SVE2_RRX(trans_SQRDMULH_zzx_d, gen_helper_sve2_sqrdmulh_idx_d) +DO_SVE2_RRX(SQRDMULH_zzx_h, gen_helper_sve2_sqrdmulh_idx_h) +DO_SVE2_RRX(SQRDMULH_zzx_s, gen_helper_sve2_sqrdmulh_idx_s) +DO_SVE2_RRX(SQRDMULH_zzx_d, gen_helper_sve2_sqrdmulh_idx_d) #undef DO_SVE2_RRX #define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \ - static bool NAME(DisasContext *s, arg_rrx_esz *a) \ - { \ - return do_sve2_zzz_data(s, a->rd, a->rn, a->rm, \ - (a->index << 1) | TOP, FUNC); \ - } + TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \ + a->rd, a->rn, a->rm, (a->index << 1) | TOP) -DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_s, gen_helper_sve2_sqdmull_idx_s, false) -DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_d, gen_helper_sve2_sqdmull_idx_d, false) -DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_s, gen_helper_sve2_sqdmull_idx_s, true) -DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_d, gen_helper_sve2_sqdmull_idx_d, true) +DO_SVE2_RRX_TB(SQDMULLB_zzx_s, gen_helper_sve2_sqdmull_idx_s, false) +DO_SVE2_RRX_TB(SQDMULLB_zzx_d, gen_helper_sve2_sqdmull_idx_d, false) +DO_SVE2_RRX_TB(SQDMULLT_zzx_s, gen_helper_sve2_sqdmull_idx_s, true) +DO_SVE2_RRX_TB(SQDMULLT_zzx_d, gen_helper_sve2_sqdmull_idx_d, true) -DO_SVE2_RRX_TB(trans_SMULLB_zzx_s, gen_helper_sve2_smull_idx_s, false) -DO_SVE2_RRX_TB(trans_SMULLB_zzx_d, gen_helper_sve2_smull_idx_d, false) -DO_SVE2_RRX_TB(trans_SMULLT_zzx_s, gen_helper_sve2_smull_idx_s, true) -DO_SVE2_RRX_TB(trans_SMULLT_zzx_d, gen_helper_sve2_smull_idx_d, true) +DO_SVE2_RRX_TB(SMULLB_zzx_s, gen_helper_sve2_smull_idx_s, false) +DO_SVE2_RRX_TB(SMULLB_zzx_d, gen_helper_sve2_smull_idx_d, false) +DO_SVE2_RRX_TB(SMULLT_zzx_s, gen_helper_sve2_smull_idx_s, true) +DO_SVE2_RRX_TB(SMULLT_zzx_d, gen_helper_sve2_smull_idx_d, true) -DO_SVE2_RRX_TB(trans_UMULLB_zzx_s, gen_helper_sve2_umull_idx_s, false) -DO_SVE2_RRX_TB(trans_UMULLB_zzx_d, gen_helper_sve2_umull_idx_d, false) -DO_SVE2_RRX_TB(trans_UMULLT_zzx_s, gen_helper_sve2_umull_idx_s, true) -DO_SVE2_RRX_TB(trans_UMULLT_zzx_d, gen_helper_sve2_umull_idx_d, true) +DO_SVE2_RRX_TB(UMULLB_zzx_s, gen_helper_sve2_umull_idx_s, false) +DO_SVE2_RRX_TB(UMULLB_zzx_d, gen_helper_sve2_umull_idx_d, false) +DO_SVE2_RRX_TB(UMULLT_zzx_s, gen_helper_sve2_umull_idx_s, true) +DO_SVE2_RRX_TB(UMULLT_zzx_d, gen_helper_sve2_umull_idx_d, true) #undef DO_SVE2_RRX_TB -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zzzz_data to use TRANS_FEAT and gen_gvec_ool_{zzzz,zzxz}. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-17-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 106 ++++++++++++++----------------------- 1 file changed, 41 insertions(+), 65 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRX_TB(UMULLT_zzx_d, gen_helper_sve2_umull_idx_d, true) #undef DO_SVE2_RRX_TB -static bool do_sve2_zzzz_data(DisasContext *s, int rd, int rn, int rm, int ra, - int data, gen_helper_gvec_4 *fn) -{ - if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vec_full_reg_offset(s, ra), - vsz, vsz, data, fn); - } - return true; -} - #define DO_SVE2_RRXR(NAME, FUNC) \ - static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ - { return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra, a->index, FUNC); } + TRANS_FEAT(NAME, aa64_sve2, gen_gvec_ool_arg_zzxz, FUNC, a) -DO_SVE2_RRXR(trans_MLA_zzxz_h, gen_helper_gvec_mla_idx_h) -DO_SVE2_RRXR(trans_MLA_zzxz_s, gen_helper_gvec_mla_idx_s) -DO_SVE2_RRXR(trans_MLA_zzxz_d, gen_helper_gvec_mla_idx_d) +DO_SVE2_RRXR(MLA_zzxz_h, gen_helper_gvec_mla_idx_h) +DO_SVE2_RRXR(MLA_zzxz_s, gen_helper_gvec_mla_idx_s) +DO_SVE2_RRXR(MLA_zzxz_d, gen_helper_gvec_mla_idx_d) -DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h) -DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s) -DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d) +DO_SVE2_RRXR(MLS_zzxz_h, gen_helper_gvec_mls_idx_h) +DO_SVE2_RRXR(MLS_zzxz_s, gen_helper_gvec_mls_idx_s) +DO_SVE2_RRXR(MLS_zzxz_d, gen_helper_gvec_mls_idx_d) -DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_h, gen_helper_sve2_sqrdmlah_idx_h) -DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_s, gen_helper_sve2_sqrdmlah_idx_s) -DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_d, gen_helper_sve2_sqrdmlah_idx_d) +DO_SVE2_RRXR(SQRDMLAH_zzxz_h, gen_helper_sve2_sqrdmlah_idx_h) +DO_SVE2_RRXR(SQRDMLAH_zzxz_s, gen_helper_sve2_sqrdmlah_idx_s) +DO_SVE2_RRXR(SQRDMLAH_zzxz_d, gen_helper_sve2_sqrdmlah_idx_d) -DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_h, gen_helper_sve2_sqrdmlsh_idx_h) -DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_s, gen_helper_sve2_sqrdmlsh_idx_s) -DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d) +DO_SVE2_RRXR(SQRDMLSH_zzxz_h, gen_helper_sve2_sqrdmlsh_idx_h) +DO_SVE2_RRXR(SQRDMLSH_zzxz_s, gen_helper_sve2_sqrdmlsh_idx_s) +DO_SVE2_RRXR(SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d) #undef DO_SVE2_RRXR #define DO_SVE2_RRXR_TB(NAME, FUNC, TOP) \ - static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ - { \ - return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->rd, \ - (a->index << 1) | TOP, FUNC); \ - } + TRANS_FEAT(NAME, aa64_sve2, gen_gvec_ool_zzzz, FUNC, \ + a->rd, a->rn, a->rm, a->ra, (a->index << 1) | TOP) -DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, false) -DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, false) -DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, true) -DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, true) +DO_SVE2_RRXR_TB(SQDMLALB_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, false) +DO_SVE2_RRXR_TB(SQDMLALB_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, false) +DO_SVE2_RRXR_TB(SQDMLALT_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, true) +DO_SVE2_RRXR_TB(SQDMLALT_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, true) -DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, false) -DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, false) -DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, true) -DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, true) +DO_SVE2_RRXR_TB(SQDMLSLB_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, false) +DO_SVE2_RRXR_TB(SQDMLSLB_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, false) +DO_SVE2_RRXR_TB(SQDMLSLT_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, true) +DO_SVE2_RRXR_TB(SQDMLSLT_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, true) -DO_SVE2_RRXR_TB(trans_SMLALB_zzxw_s, gen_helper_sve2_smlal_idx_s, false) -DO_SVE2_RRXR_TB(trans_SMLALB_zzxw_d, gen_helper_sve2_smlal_idx_d, false) -DO_SVE2_RRXR_TB(trans_SMLALT_zzxw_s, gen_helper_sve2_smlal_idx_s, true) -DO_SVE2_RRXR_TB(trans_SMLALT_zzxw_d, gen_helper_sve2_smlal_idx_d, true) +DO_SVE2_RRXR_TB(SMLALB_zzxw_s, gen_helper_sve2_smlal_idx_s, false) +DO_SVE2_RRXR_TB(SMLALB_zzxw_d, gen_helper_sve2_smlal_idx_d, false) +DO_SVE2_RRXR_TB(SMLALT_zzxw_s, gen_helper_sve2_smlal_idx_s, true) +DO_SVE2_RRXR_TB(SMLALT_zzxw_d, gen_helper_sve2_smlal_idx_d, true) -DO_SVE2_RRXR_TB(trans_UMLALB_zzxw_s, gen_helper_sve2_umlal_idx_s, false) -DO_SVE2_RRXR_TB(trans_UMLALB_zzxw_d, gen_helper_sve2_umlal_idx_d, false) -DO_SVE2_RRXR_TB(trans_UMLALT_zzxw_s, gen_helper_sve2_umlal_idx_s, true) -DO_SVE2_RRXR_TB(trans_UMLALT_zzxw_d, gen_helper_sve2_umlal_idx_d, true) +DO_SVE2_RRXR_TB(UMLALB_zzxw_s, gen_helper_sve2_umlal_idx_s, false) +DO_SVE2_RRXR_TB(UMLALB_zzxw_d, gen_helper_sve2_umlal_idx_d, false) +DO_SVE2_RRXR_TB(UMLALT_zzxw_s, gen_helper_sve2_umlal_idx_s, true) +DO_SVE2_RRXR_TB(UMLALT_zzxw_d, gen_helper_sve2_umlal_idx_d, true) -DO_SVE2_RRXR_TB(trans_SMLSLB_zzxw_s, gen_helper_sve2_smlsl_idx_s, false) -DO_SVE2_RRXR_TB(trans_SMLSLB_zzxw_d, gen_helper_sve2_smlsl_idx_d, false) -DO_SVE2_RRXR_TB(trans_SMLSLT_zzxw_s, gen_helper_sve2_smlsl_idx_s, true) -DO_SVE2_RRXR_TB(trans_SMLSLT_zzxw_d, gen_helper_sve2_smlsl_idx_d, true) +DO_SVE2_RRXR_TB(SMLSLB_zzxw_s, gen_helper_sve2_smlsl_idx_s, false) +DO_SVE2_RRXR_TB(SMLSLB_zzxw_d, gen_helper_sve2_smlsl_idx_d, false) +DO_SVE2_RRXR_TB(SMLSLT_zzxw_s, gen_helper_sve2_smlsl_idx_s, true) +DO_SVE2_RRXR_TB(SMLSLT_zzxw_d, gen_helper_sve2_smlsl_idx_d, true) -DO_SVE2_RRXR_TB(trans_UMLSLB_zzxw_s, gen_helper_sve2_umlsl_idx_s, false) -DO_SVE2_RRXR_TB(trans_UMLSLB_zzxw_d, gen_helper_sve2_umlsl_idx_d, false) -DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_s, gen_helper_sve2_umlsl_idx_s, true) -DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_d, gen_helper_sve2_umlsl_idx_d, true) +DO_SVE2_RRXR_TB(UMLSLB_zzxw_s, gen_helper_sve2_umlsl_idx_s, false) +DO_SVE2_RRXR_TB(UMLSLB_zzxw_d, gen_helper_sve2_umlsl_idx_d, false) +DO_SVE2_RRXR_TB(UMLSLT_zzxw_s, gen_helper_sve2_umlsl_idx_s, true) +DO_SVE2_RRXR_TB(UMLSLT_zzxw_d, gen_helper_sve2_umlsl_idx_d, true) #undef DO_SVE2_RRXR_TB #define DO_SVE2_RRXR_ROT(NAME, FUNC) \ - static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ - { \ - return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra, \ - (a->index << 2) | a->rot, FUNC); \ - } + TRANS_FEAT(NAME, aa64_sve2, gen_gvec_ool_zzzz, FUNC, \ + a->rd, a->rn, a->rm, a->ra, (a->index << 2) | a->rot) DO_SVE2_RRXR_ROT(CMLA_zzxz_h, gen_helper_sve2_cmla_idx_h) DO_SVE2_RRXR_ROT(CMLA_zzxz_s, gen_helper_sve2_cmla_idx_s) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zzw_data to use TRANS_FEAT and gen_gvec_ool_arg_zzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-18-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 297 ++++++++++++++++++------------------- 1 file changed, 145 insertions(+), 152 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ(USQADD, usqadd) * SVE2 Widening Integer Arithmetic */ -static bool do_sve2_zzw_ool(DisasContext *s, arg_rrr_esz *a, - gen_helper_gvec_3 *fn, int data) -{ - if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vsz, vsz, data, fn); - } - return true; -} +static gen_helper_gvec_3 * const saddl_fns[4] = { + NULL, gen_helper_sve2_saddl_h, + gen_helper_sve2_saddl_s, gen_helper_sve2_saddl_d, +}; +TRANS_FEAT(SADDLB, aa64_sve2, gen_gvec_ool_arg_zzz, + saddl_fns[a->esz], a, 0) +TRANS_FEAT(SADDLT, aa64_sve2, gen_gvec_ool_arg_zzz, + saddl_fns[a->esz], a, 3) +TRANS_FEAT(SADDLBT, aa64_sve2, gen_gvec_ool_arg_zzz, + saddl_fns[a->esz], a, 2) -#define DO_SVE2_ZZZ_TB(NAME, name, SEL1, SEL2) \ -static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ -{ \ - static gen_helper_gvec_3 * const fns[4] = { \ - NULL, gen_helper_sve2_##name##_h, \ - gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ - }; \ - return do_sve2_zzw_ool(s, a, fns[a->esz], (SEL2 << 1) | SEL1); \ -} +static gen_helper_gvec_3 * const ssubl_fns[4] = { + NULL, gen_helper_sve2_ssubl_h, + gen_helper_sve2_ssubl_s, gen_helper_sve2_ssubl_d, +}; +TRANS_FEAT(SSUBLB, aa64_sve2, gen_gvec_ool_arg_zzz, + ssubl_fns[a->esz], a, 0) +TRANS_FEAT(SSUBLT, aa64_sve2, gen_gvec_ool_arg_zzz, + ssubl_fns[a->esz], a, 3) +TRANS_FEAT(SSUBLBT, aa64_sve2, gen_gvec_ool_arg_zzz, + ssubl_fns[a->esz], a, 2) +TRANS_FEAT(SSUBLTB, aa64_sve2, gen_gvec_ool_arg_zzz, + ssubl_fns[a->esz], a, 1) -DO_SVE2_ZZZ_TB(SADDLB, saddl, false, false) -DO_SVE2_ZZZ_TB(SSUBLB, ssubl, false, false) -DO_SVE2_ZZZ_TB(SABDLB, sabdl, false, false) +static gen_helper_gvec_3 * const sabdl_fns[4] = { + NULL, gen_helper_sve2_sabdl_h, + gen_helper_sve2_sabdl_s, gen_helper_sve2_sabdl_d, +}; +TRANS_FEAT(SABDLB, aa64_sve2, gen_gvec_ool_arg_zzz, + sabdl_fns[a->esz], a, 0) +TRANS_FEAT(SABDLT, aa64_sve2, gen_gvec_ool_arg_zzz, + sabdl_fns[a->esz], a, 3) -DO_SVE2_ZZZ_TB(UADDLB, uaddl, false, false) -DO_SVE2_ZZZ_TB(USUBLB, usubl, false, false) -DO_SVE2_ZZZ_TB(UABDLB, uabdl, false, false) +static gen_helper_gvec_3 * const uaddl_fns[4] = { + NULL, gen_helper_sve2_uaddl_h, + gen_helper_sve2_uaddl_s, gen_helper_sve2_uaddl_d, +}; +TRANS_FEAT(UADDLB, aa64_sve2, gen_gvec_ool_arg_zzz, + uaddl_fns[a->esz], a, 0) +TRANS_FEAT(UADDLT, aa64_sve2, gen_gvec_ool_arg_zzz, + uaddl_fns[a->esz], a, 3) -DO_SVE2_ZZZ_TB(SADDLT, saddl, true, true) -DO_SVE2_ZZZ_TB(SSUBLT, ssubl, true, true) -DO_SVE2_ZZZ_TB(SABDLT, sabdl, true, true) +static gen_helper_gvec_3 * const usubl_fns[4] = { + NULL, gen_helper_sve2_usubl_h, + gen_helper_sve2_usubl_s, gen_helper_sve2_usubl_d, +}; +TRANS_FEAT(USUBLB, aa64_sve2, gen_gvec_ool_arg_zzz, + usubl_fns[a->esz], a, 0) +TRANS_FEAT(USUBLT, aa64_sve2, gen_gvec_ool_arg_zzz, + usubl_fns[a->esz], a, 3) -DO_SVE2_ZZZ_TB(UADDLT, uaddl, true, true) -DO_SVE2_ZZZ_TB(USUBLT, usubl, true, true) -DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true) +static gen_helper_gvec_3 * const uabdl_fns[4] = { + NULL, gen_helper_sve2_uabdl_h, + gen_helper_sve2_uabdl_s, gen_helper_sve2_uabdl_d, +}; +TRANS_FEAT(UABDLB, aa64_sve2, gen_gvec_ool_arg_zzz, + uabdl_fns[a->esz], a, 0) +TRANS_FEAT(UABDLT, aa64_sve2, gen_gvec_ool_arg_zzz, + uabdl_fns[a->esz], a, 3) -DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true) -DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true) -DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false) +static gen_helper_gvec_3 * const sqdmull_fns[4] = { + NULL, gen_helper_sve2_sqdmull_zzz_h, + gen_helper_sve2_sqdmull_zzz_s, gen_helper_sve2_sqdmull_zzz_d, +}; +TRANS_FEAT(SQDMULLB_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + sqdmull_fns[a->esz], a, 0) +TRANS_FEAT(SQDMULLT_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + sqdmull_fns[a->esz], a, 3) -DO_SVE2_ZZZ_TB(SQDMULLB_zzz, sqdmull_zzz, false, false) -DO_SVE2_ZZZ_TB(SQDMULLT_zzz, sqdmull_zzz, true, true) +static gen_helper_gvec_3 * const smull_fns[4] = { + NULL, gen_helper_sve2_smull_zzz_h, + gen_helper_sve2_smull_zzz_s, gen_helper_sve2_smull_zzz_d, +}; +TRANS_FEAT(SMULLB_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + smull_fns[a->esz], a, 0) +TRANS_FEAT(SMULLT_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + smull_fns[a->esz], a, 3) -DO_SVE2_ZZZ_TB(SMULLB_zzz, smull_zzz, false, false) -DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true) +static gen_helper_gvec_3 * const umull_fns[4] = { + NULL, gen_helper_sve2_umull_zzz_h, + gen_helper_sve2_umull_zzz_s, gen_helper_sve2_umull_zzz_d, +}; +TRANS_FEAT(UMULLB_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + umull_fns[a->esz], a, 0) +TRANS_FEAT(UMULLT_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, + umull_fns[a->esz], a, 3) -DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false) -DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true) - -static bool do_eor_tb(DisasContext *s, arg_rrr_esz *a, bool sel1) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_eoril_b, gen_helper_sve2_eoril_h, - gen_helper_sve2_eoril_s, gen_helper_sve2_eoril_d, - }; - return do_sve2_zzw_ool(s, a, fns[a->esz], (!sel1 << 1) | sel1); -} - -static bool trans_EORBT(DisasContext *s, arg_rrr_esz *a) -{ - return do_eor_tb(s, a, false); -} - -static bool trans_EORTB(DisasContext *s, arg_rrr_esz *a) -{ - return do_eor_tb(s, a, true); -} +static gen_helper_gvec_3 * const eoril_fns[4] = { + gen_helper_sve2_eoril_b, gen_helper_sve2_eoril_h, + gen_helper_sve2_eoril_s, gen_helper_sve2_eoril_d, +}; +TRANS_FEAT(EORBT, aa64_sve2, gen_gvec_ool_arg_zzz, eoril_fns[a->esz], a, 2) +TRANS_FEAT(EORTB, aa64_sve2, gen_gvec_ool_arg_zzz, eoril_fns[a->esz], a, 1) static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) { @@ -XXX,XX +XXX,XX @@ static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) if (a->esz == 0 && !dc_isar_feature(aa64_sve2_pmull128, s)) { return false; } - return do_sve2_zzw_ool(s, a, fns[a->esz], sel); + return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, sel); } -static bool trans_PMULLB(DisasContext *s, arg_rrr_esz *a) -{ - return do_trans_pmull(s, a, false); -} +TRANS_FEAT(PMULLB, aa64_sve2, do_trans_pmull, a, false) +TRANS_FEAT(PMULLT, aa64_sve2, do_trans_pmull, a, true) -static bool trans_PMULLT(DisasContext *s, arg_rrr_esz *a) -{ - return do_trans_pmull(s, a, true); -} +static gen_helper_gvec_3 * const saddw_fns[4] = { + NULL, gen_helper_sve2_saddw_h, + gen_helper_sve2_saddw_s, gen_helper_sve2_saddw_d, +}; +TRANS_FEAT(SADDWB, aa64_sve2, gen_gvec_ool_arg_zzz, saddw_fns[a->esz], a, 0) +TRANS_FEAT(SADDWT, aa64_sve2, gen_gvec_ool_arg_zzz, saddw_fns[a->esz], a, 1) -#define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \ -static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ -{ \ - static gen_helper_gvec_3 * const fns[4] = { \ - NULL, gen_helper_sve2_##name##_h, \ - gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ - }; \ - return do_sve2_zzw_ool(s, a, fns[a->esz], SEL2); \ -} +static gen_helper_gvec_3 * const ssubw_fns[4] = { + NULL, gen_helper_sve2_ssubw_h, + gen_helper_sve2_ssubw_s, gen_helper_sve2_ssubw_d, +}; +TRANS_FEAT(SSUBWB, aa64_sve2, gen_gvec_ool_arg_zzz, ssubw_fns[a->esz], a, 0) +TRANS_FEAT(SSUBWT, aa64_sve2, gen_gvec_ool_arg_zzz, ssubw_fns[a->esz], a, 1) -DO_SVE2_ZZZ_WTB(SADDWB, saddw, false) -DO_SVE2_ZZZ_WTB(SADDWT, saddw, true) -DO_SVE2_ZZZ_WTB(SSUBWB, ssubw, false) -DO_SVE2_ZZZ_WTB(SSUBWT, ssubw, true) +static gen_helper_gvec_3 * const uaddw_fns[4] = { + NULL, gen_helper_sve2_uaddw_h, + gen_helper_sve2_uaddw_s, gen_helper_sve2_uaddw_d, +}; +TRANS_FEAT(UADDWB, aa64_sve2, gen_gvec_ool_arg_zzz, uaddw_fns[a->esz], a, 0) +TRANS_FEAT(UADDWT, aa64_sve2, gen_gvec_ool_arg_zzz, uaddw_fns[a->esz], a, 1) -DO_SVE2_ZZZ_WTB(UADDWB, uaddw, false) -DO_SVE2_ZZZ_WTB(UADDWT, uaddw, true) -DO_SVE2_ZZZ_WTB(USUBWB, usubw, false) -DO_SVE2_ZZZ_WTB(USUBWT, usubw, true) +static gen_helper_gvec_3 * const usubw_fns[4] = { + NULL, gen_helper_sve2_usubw_h, + gen_helper_sve2_usubw_s, gen_helper_sve2_usubw_d, +}; +TRANS_FEAT(USUBWB, aa64_sve2, gen_gvec_ool_arg_zzz, usubw_fns[a->esz], a, 0) +TRANS_FEAT(USUBWT, aa64_sve2, gen_gvec_ool_arg_zzz, usubw_fns[a->esz], a, 1) static void gen_sshll_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t imm) { @@ -XXX,XX +XXX,XX @@ static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a) return do_sve2_shll_tb(s, a, true, true); } -static bool trans_BEXT(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_bext_b, gen_helper_sve2_bext_h, - gen_helper_sve2_bext_s, gen_helper_sve2_bext_d, - }; - if (!dc_isar_feature(aa64_sve2_bitperm, s)) { - return false; - } - return do_sve2_zzw_ool(s, a, fns[a->esz], 0); -} +static gen_helper_gvec_3 * const bext_fns[4] = { + gen_helper_sve2_bext_b, gen_helper_sve2_bext_h, + gen_helper_sve2_bext_s, gen_helper_sve2_bext_d, +}; +TRANS_FEAT(BEXT, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bext_fns[a->esz], a, 0) -static bool trans_BDEP(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h, - gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d, - }; - if (!dc_isar_feature(aa64_sve2_bitperm, s)) { - return false; - } - return do_sve2_zzw_ool(s, a, fns[a->esz], 0); -} +static gen_helper_gvec_3 * const bdep_fns[4] = { + gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h, + gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d, +}; +TRANS_FEAT(BDEP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bdep_fns[a->esz], a, 0) -static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h, - gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d, - }; - if (!dc_isar_feature(aa64_sve2_bitperm, s)) { - return false; - } - return do_sve2_zzw_ool(s, a, fns[a->esz], 0); -} +static gen_helper_gvec_3 * const bgrp_fns[4] = { + gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h, + gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d, +}; +TRANS_FEAT(BGRP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bgrp_fns[a->esz], a, 0) -static bool do_cadd(DisasContext *s, arg_rrr_esz *a, bool sq, bool rot) -{ - static gen_helper_gvec_3 * const fns[2][4] = { - { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h, - gen_helper_sve2_cadd_s, gen_helper_sve2_cadd_d }, - { gen_helper_sve2_sqcadd_b, gen_helper_sve2_sqcadd_h, - gen_helper_sve2_sqcadd_s, gen_helper_sve2_sqcadd_d }, - }; - return do_sve2_zzw_ool(s, a, fns[sq][a->esz], rot); -} +static gen_helper_gvec_3 * const cadd_fns[4] = { + gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h, + gen_helper_sve2_cadd_s, gen_helper_sve2_cadd_d, +}; +TRANS_FEAT(CADD_rot90, aa64_sve2, gen_gvec_ool_arg_zzz, + cadd_fns[a->esz], a, 0) +TRANS_FEAT(CADD_rot270, aa64_sve2, gen_gvec_ool_arg_zzz, + cadd_fns[a->esz], a, 1) -static bool trans_CADD_rot90(DisasContext *s, arg_rrr_esz *a) -{ - return do_cadd(s, a, false, false); -} - -static bool trans_CADD_rot270(DisasContext *s, arg_rrr_esz *a) -{ - return do_cadd(s, a, false, true); -} - -static bool trans_SQCADD_rot90(DisasContext *s, arg_rrr_esz *a) -{ - return do_cadd(s, a, true, false); -} - -static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a) -{ - return do_cadd(s, a, true, true); -} +static gen_helper_gvec_3 * const sqcadd_fns[4] = { + gen_helper_sve2_sqcadd_b, gen_helper_sve2_sqcadd_h, + gen_helper_sve2_sqcadd_s, gen_helper_sve2_sqcadd_d, +}; +TRANS_FEAT(SQCADD_rot90, aa64_sve2, gen_gvec_ool_arg_zzz, + sqcadd_fns[a->esz], a, 0) +TRANS_FEAT(SQCADD_rot270, aa64_sve2, gen_gvec_ool_arg_zzz, + sqcadd_fns[a->esz], a, 1) static gen_helper_gvec_4 * const sabal_fns[4] = { NULL, gen_helper_sve2_sabal_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is the last direct user of tcg_gen_gvec_4_ool. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-19-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_4 * const sqrdcmlah_fns[] = { TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) -static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) -{ - if (a->esz != 2 || !dc_isar_feature(aa64_sve_i8mm, s)) { - return false; - } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - vsz, vsz, 0, gen_helper_gvec_usdot_b); - } - return true; -} +TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0) TRANS_FEAT(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-20-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 37 +++++++++++++++---------------------- 1 file changed, 15 insertions(+), 22 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zzxz(DisasContext *s, gen_helper_gvec_4 *fn, } /* Invoke an out-of-line helper on 2 Zregs and a predicate. */ -static void gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, +static bool gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int pg, int data) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - pred_full_reg_offset(s, pg), - vsz, vsz, data, fn); + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + pred_full_reg_offset(s, pg), + vsz, vsz, data, fn); + } + return true; } /* Invoke an out-of-line helper on 3 Zregs and a predicate. */ @@ -XXX,XX +XXX,XX @@ static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) static bool do_zpz_ool(DisasContext *s, arg_rpr_esz *a, gen_helper_gvec_3 *fn) { - if (fn == NULL) { - return false; - } - if (sve_access_check(s)) { - gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, 0); - } - return true; + return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, 0); } #define DO_ZPZ(NAME, name) \ @@ -XXX,XX +XXX,XX @@ static bool do_movz_zpz(DisasContext *s, int rd, int rn, int pg, gen_helper_sve_movz_b, gen_helper_sve_movz_h, gen_helper_sve_movz_s, gen_helper_sve_movz_d, }; - - if (sve_access_check(s)) { - gen_gvec_ool_zzp(s, fns[esz], rd, rn, pg, invert); - } - return true; + return gen_gvec_ool_zzp(s, fns[esz], rd, rn, pg, invert); } static bool do_zpzi_ool(DisasContext *s, arg_rpri_esz *a, gen_helper_gvec_3 *fn) { - if (sve_access_check(s)) { - gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, a->imm); - } - return true; + return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, a->imm); } static bool trans_ASR_zpzi(DisasContext *s, arg_rpri_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use gen_gvec_ool_arg_zpz instead of gen_gvec_ool_zzp when the arguments come from arg_rpr_esz. Replaces do_zpz_ool. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-21-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 45 +++++++++++++++++++++----------------- 1 file changed, 25 insertions(+), 20 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, return true; } +static bool gen_gvec_ool_arg_zpz(DisasContext *s, gen_helper_gvec_3 *fn, + arg_rpr_esz *a, int data) +{ + return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, data); +} + + /* Invoke an out-of-line helper on 3 Zregs and a predicate. */ static void gen_gvec_ool_zzzp(DisasContext *s, gen_helper_gvec_4 *fn, int rd, int rn, int rm, int pg, int data) @@ -XXX,XX +XXX,XX @@ static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) *** SVE Integer Arithmetic - Unary Predicated Group */ -static bool do_zpz_ool(DisasContext *s, arg_rpr_esz *a, gen_helper_gvec_3 *fn) -{ - return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, 0); -} - #define DO_ZPZ(NAME, name) \ static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a) \ { \ @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a) \ gen_helper_sve_##name##_b, gen_helper_sve_##name##_h, \ gen_helper_sve_##name##_s, gen_helper_sve_##name##_d, \ }; \ - return do_zpz_ool(s, a, fns[a->esz]); \ + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); \ } DO_ZPZ(CLS, cls) @@ -XXX,XX +XXX,XX @@ static bool trans_FABS(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_fabs_s, gen_helper_sve_fabs_d }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_FNEG(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FNEG(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_fneg_s, gen_helper_sve_fneg_d }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_SXTB(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_SXTB(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_sxtb_s, gen_helper_sve_sxtb_d }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_UXTB(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_UXTB(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_uxtb_s, gen_helper_sve_uxtb_d }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_SXTH(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_SXTH(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_sxth_s, gen_helper_sve_sxth_d }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_UXTH(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_UXTH(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_uxth_s, gen_helper_sve_uxth_d }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_SXTW(DisasContext *s, arg_rpr_esz *a) { - return do_zpz_ool(s, a, a->esz == 3 ? gen_helper_sve_sxtw_d : NULL); + return gen_gvec_ool_arg_zpz(s, a->esz == 3 ? gen_helper_sve_sxtw_d + : NULL, a, 0); } static bool trans_UXTW(DisasContext *s, arg_rpr_esz *a) { - return do_zpz_ool(s, a, a->esz == 3 ? gen_helper_sve_uxtw_d : NULL); + return gen_gvec_ool_arg_zpz(s, a->esz == 3 ? gen_helper_sve_uxtw_d + : NULL, a, 0); } #undef DO_ZPZ @@ -XXX,XX +XXX,XX @@ static bool trans_COMPACT(DisasContext *s, arg_rpr_esz *a) static gen_helper_gvec_3 * const fns[4] = { NULL, NULL, gen_helper_sve_compact_s, gen_helper_sve_compact_d }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } /* Call the helper that computes the ARM LastActiveElement pseudocode @@ -XXX,XX +XXX,XX @@ static bool trans_REVB(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_revb_s, gen_helper_sve_revb_d, }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_REVH(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_REVH(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_revh_s, gen_helper_sve_revh_d, }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_REVW(DisasContext *s, arg_rpr_esz *a) { - return do_zpz_ool(s, a, a->esz == 3 ? gen_helper_sve_revw_d : NULL); + return gen_gvec_ool_arg_zpz(s, a->esz == 3 ? gen_helper_sve_revw_d + : NULL, a, 0); } static bool trans_RBIT(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_RBIT(DisasContext *s, arg_rpr_esz *a) gen_helper_sve_rbit_s, gen_helper_sve_rbit_d, }; - return do_zpz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); } static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_sve2_zpz_ool(DisasContext *s, arg_rpr_esz *a, if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return do_zpz_ool(s, a, fn); + return gen_gvec_ool_arg_zpz(s, fn, a, 0); } static bool trans_URECPE(DisasContext *s, arg_rpr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions directly using gen_gvec_ool_arg_zpz to TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-22-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 189 ++++++++++++------------------------- 1 file changed, 60 insertions(+), 129 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) *** SVE Integer Arithmetic - Unary Predicated Group */ -#define DO_ZPZ(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a) \ -{ \ - static gen_helper_gvec_3 * const fns[4] = { \ - gen_helper_sve_##name##_b, gen_helper_sve_##name##_h, \ - gen_helper_sve_##name##_s, gen_helper_sve_##name##_d, \ +#define DO_ZPZ(NAME, FEAT, name) \ + static gen_helper_gvec_3 * const name##_fns[4] = { \ + gen_helper_##name##_b, gen_helper_##name##_h, \ + gen_helper_##name##_s, gen_helper_##name##_d, \ }; \ - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); \ -} + TRANS_FEAT(NAME, FEAT, gen_gvec_ool_arg_zpz, name##_fns[a->esz], a, 0) -DO_ZPZ(CLS, cls) -DO_ZPZ(CLZ, clz) -DO_ZPZ(CNT_zpz, cnt_zpz) -DO_ZPZ(CNOT, cnot) -DO_ZPZ(NOT_zpz, not_zpz) -DO_ZPZ(ABS, abs) -DO_ZPZ(NEG, neg) +DO_ZPZ(CLS, aa64_sve, sve_cls) +DO_ZPZ(CLZ, aa64_sve, sve_clz) +DO_ZPZ(CNT_zpz, aa64_sve, sve_cnt_zpz) +DO_ZPZ(CNOT, aa64_sve, sve_cnot) +DO_ZPZ(NOT_zpz, aa64_sve, sve_not_zpz) +DO_ZPZ(ABS, aa64_sve, sve_abs) +DO_ZPZ(NEG, aa64_sve, sve_neg) +DO_ZPZ(RBIT, aa64_sve, sve_rbit) -static bool trans_FABS(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, - gen_helper_sve_fabs_h, - gen_helper_sve_fabs_s, - gen_helper_sve_fabs_d - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const fabs_fns[4] = { + NULL, gen_helper_sve_fabs_h, + gen_helper_sve_fabs_s, gen_helper_sve_fabs_d, +}; +TRANS_FEAT(FABS, aa64_sve, gen_gvec_ool_arg_zpz, fabs_fns[a->esz], a, 0) -static bool trans_FNEG(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, - gen_helper_sve_fneg_h, - gen_helper_sve_fneg_s, - gen_helper_sve_fneg_d - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const fneg_fns[4] = { + NULL, gen_helper_sve_fneg_h, + gen_helper_sve_fneg_s, gen_helper_sve_fneg_d, +}; +TRANS_FEAT(FNEG, aa64_sve, gen_gvec_ool_arg_zpz, fneg_fns[a->esz], a, 0) -static bool trans_SXTB(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, - gen_helper_sve_sxtb_h, - gen_helper_sve_sxtb_s, - gen_helper_sve_sxtb_d - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const sxtb_fns[4] = { + NULL, gen_helper_sve_sxtb_h, + gen_helper_sve_sxtb_s, gen_helper_sve_sxtb_d, +}; +TRANS_FEAT(SXTB, aa64_sve, gen_gvec_ool_arg_zpz, sxtb_fns[a->esz], a, 0) -static bool trans_UXTB(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, - gen_helper_sve_uxtb_h, - gen_helper_sve_uxtb_s, - gen_helper_sve_uxtb_d - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const uxtb_fns[4] = { + NULL, gen_helper_sve_uxtb_h, + gen_helper_sve_uxtb_s, gen_helper_sve_uxtb_d, +}; +TRANS_FEAT(UXTB, aa64_sve, gen_gvec_ool_arg_zpz, uxtb_fns[a->esz], a, 0) -static bool trans_SXTH(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, NULL, - gen_helper_sve_sxth_s, - gen_helper_sve_sxth_d - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const sxth_fns[4] = { + NULL, NULL, gen_helper_sve_sxth_s, gen_helper_sve_sxth_d +}; +TRANS_FEAT(SXTH, aa64_sve, gen_gvec_ool_arg_zpz, sxth_fns[a->esz], a, 0) -static bool trans_UXTH(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, NULL, - gen_helper_sve_uxth_s, - gen_helper_sve_uxth_d - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const uxth_fns[4] = { + NULL, NULL, gen_helper_sve_uxth_s, gen_helper_sve_uxth_d +}; +TRANS_FEAT(UXTH, aa64_sve, gen_gvec_ool_arg_zpz, uxth_fns[a->esz], a, 0) -static bool trans_SXTW(DisasContext *s, arg_rpr_esz *a) -{ - return gen_gvec_ool_arg_zpz(s, a->esz == 3 ? gen_helper_sve_sxtw_d - : NULL, a, 0); -} - -static bool trans_UXTW(DisasContext *s, arg_rpr_esz *a) -{ - return gen_gvec_ool_arg_zpz(s, a->esz == 3 ? gen_helper_sve_uxtw_d - : NULL, a, 0); -} - -#undef DO_ZPZ +TRANS_FEAT(SXTW, aa64_sve, gen_gvec_ool_arg_zpz, + a->esz == 3 ? gen_helper_sve_sxtw_d : NULL, a, 0) +TRANS_FEAT(UXTW, aa64_sve, gen_gvec_ool_arg_zpz, + a->esz == 3 ? gen_helper_sve_uxtw_d : NULL, a, 0) /* *** SVE Integer Reduction Group @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, *** SVE Permute Vector - Predicated Group */ -static bool trans_COMPACT(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, NULL, gen_helper_sve_compact_s, gen_helper_sve_compact_d - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const compact_fns[4] = { + NULL, NULL, gen_helper_sve_compact_s, gen_helper_sve_compact_d +}; +TRANS_FEAT(COMPACT, aa64_sve, gen_gvec_ool_arg_zpz, compact_fns[a->esz], a, 0) /* Call the helper that computes the ARM LastActiveElement pseudocode * function, scaled by the element size. This includes the not found @@ -XXX,XX +XXX,XX @@ static bool trans_CPY_m_v(DisasContext *s, arg_rpr_esz *a) return true; } -static bool trans_REVB(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, - gen_helper_sve_revb_h, - gen_helper_sve_revb_s, - gen_helper_sve_revb_d, - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const revb_fns[4] = { + NULL, gen_helper_sve_revb_h, + gen_helper_sve_revb_s, gen_helper_sve_revb_d, +}; +TRANS_FEAT(REVB, aa64_sve, gen_gvec_ool_arg_zpz, revb_fns[a->esz], a, 0) -static bool trans_REVH(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - NULL, - NULL, - gen_helper_sve_revh_s, - gen_helper_sve_revh_d, - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_3 * const revh_fns[4] = { + NULL, NULL, gen_helper_sve_revh_s, gen_helper_sve_revh_d, +}; +TRANS_FEAT(REVH, aa64_sve, gen_gvec_ool_arg_zpz, revh_fns[a->esz], a, 0) -static bool trans_REVW(DisasContext *s, arg_rpr_esz *a) -{ - return gen_gvec_ool_arg_zpz(s, a->esz == 3 ? gen_helper_sve_revw_d - : NULL, a, 0); -} - -static bool trans_RBIT(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve_rbit_b, - gen_helper_sve_rbit_h, - gen_helper_sve_rbit_s, - gen_helper_sve_rbit_d, - }; - return gen_gvec_ool_arg_zpz(s, fns[a->esz], a, 0); -} +TRANS_FEAT(REVW, aa64_sve, gen_gvec_ool_arg_zpz, + a->esz == 3 ? gen_helper_sve_revw_d : NULL, a, 0) static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zpz_data to use TRANS_FEAT and gen_gvec_ool_arg_zpz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-23-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 53 ++++++++++---------------------------- 1 file changed, 14 insertions(+), 39 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UADALP_zpzz(DisasContext *s, arg_rprr_esz *a) * SVE2 integer unary operations (predicated) */ -static bool do_sve2_zpz_ool(DisasContext *s, arg_rpr_esz *a, - gen_helper_gvec_3 *fn) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zpz(s, fn, a, 0); -} +TRANS_FEAT(URECPE, aa64_sve2, gen_gvec_ool_arg_zpz, + a->esz == 2 ? gen_helper_sve2_urecpe_s : NULL, a, 0) -static bool trans_URECPE(DisasContext *s, arg_rpr_esz *a) -{ - if (a->esz != 2) { - return false; - } - return do_sve2_zpz_ool(s, a, gen_helper_sve2_urecpe_s); -} +TRANS_FEAT(URSQRTE, aa64_sve2, gen_gvec_ool_arg_zpz, + a->esz == 2 ? gen_helper_sve2_ursqrte_s : NULL, a, 0) -static bool trans_URSQRTE(DisasContext *s, arg_rpr_esz *a) -{ - if (a->esz != 2) { - return false; - } - return do_sve2_zpz_ool(s, a, gen_helper_sve2_ursqrte_s); -} +static gen_helper_gvec_3 * const sqabs_fns[4] = { + gen_helper_sve2_sqabs_b, gen_helper_sve2_sqabs_h, + gen_helper_sve2_sqabs_s, gen_helper_sve2_sqabs_d, +}; +TRANS_FEAT(SQABS, aa64_sve2, gen_gvec_ool_arg_zpz, sqabs_fns[a->esz], a, 0) -static bool trans_SQABS(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_sqabs_b, gen_helper_sve2_sqabs_h, - gen_helper_sve2_sqabs_s, gen_helper_sve2_sqabs_d, - }; - return do_sve2_zpz_ool(s, a, fns[a->esz]); -} - -static bool trans_SQNEG(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_sqneg_b, gen_helper_sve2_sqneg_h, - gen_helper_sve2_sqneg_s, gen_helper_sve2_sqneg_d, - }; - return do_sve2_zpz_ool(s, a, fns[a->esz]); -} +static gen_helper_gvec_3 * const sqneg_fns[4] = { + gen_helper_sve2_sqneg_b, gen_helper_sve2_sqneg_h, + gen_helper_sve2_sqneg_s, gen_helper_sve2_sqneg_d, +}; +TRANS_FEAT(SQNEG, aa64_sve2, gen_gvec_ool_arg_zpz, sqneg_fns[a->esz], a, 0) #define DO_SVE2_ZPZZ(NAME, name) \ static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Rename the function to match gen_gvec_ool_arg_zpz, and move to be adjacent. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-24-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zpz(DisasContext *s, gen_helper_gvec_3 *fn, return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, data); } +static bool gen_gvec_ool_arg_zpzi(DisasContext *s, gen_helper_gvec_3 *fn, + arg_rpri_esz *a) +{ + return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, a->imm); +} /* Invoke an out-of-line helper on 3 Zregs and a predicate. */ static void gen_gvec_ool_zzzp(DisasContext *s, gen_helper_gvec_4 *fn, @@ -XXX,XX +XXX,XX @@ static bool do_movz_zpz(DisasContext *s, int rd, int rn, int pg, return gen_gvec_ool_zzp(s, fns[esz], rd, rn, pg, invert); } -static bool do_zpzi_ool(DisasContext *s, arg_rpri_esz *a, - gen_helper_gvec_3 *fn) -{ - return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, a->imm); -} - static bool trans_ASR_zpzi(DisasContext *s, arg_rpri_esz *a) { static gen_helper_gvec_3 * const fns[4] = { @@ -XXX,XX +XXX,XX @@ static bool trans_ASR_zpzi(DisasContext *s, arg_rpri_esz *a) /* Shift by element size is architecturally valid. For arithmetic right-shift, it's the same as by one less. */ a->imm = MIN(a->imm, (8 << a->esz) - 1); - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } static bool trans_LSR_zpzi(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_LSR_zpzi(DisasContext *s, arg_rpri_esz *a) if (a->imm >= (8 << a->esz)) { return do_movz_zpz(s, a->rd, a->rd, a->pg, a->esz, true); } else { - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } } @@ -XXX,XX +XXX,XX @@ static bool trans_LSL_zpzi(DisasContext *s, arg_rpri_esz *a) if (a->imm >= (8 << a->esz)) { return do_movz_zpz(s, a->rd, a->rd, a->pg, a->esz, true); } else { - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } } @@ -XXX,XX +XXX,XX @@ static bool trans_ASRD(DisasContext *s, arg_rpri_esz *a) if (a->imm >= (8 << a->esz)) { return do_movz_zpz(s, a->rd, a->rd, a->pg, a->esz, true); } else { - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } } @@ -XXX,XX +XXX,XX @@ static bool trans_SQSHL_zpzi(DisasContext *s, arg_rpri_esz *a) if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { return false; } - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } static bool trans_UQSHL_zpzi(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_zpzi(DisasContext *s, arg_rpri_esz *a) if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { return false; } - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } static bool trans_SRSHR(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_SRSHR(DisasContext *s, arg_rpri_esz *a) if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { return false; } - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } static bool trans_URSHR(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_URSHR(DisasContext *s, arg_rpri_esz *a) if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { return false; } - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } static bool trans_SQSHLU(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_SQSHLU(DisasContext *s, arg_rpri_esz *a) if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { return false; } - return do_zpzi_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert some SVE translation functions using gen_gvec_ool_arg_zpzi to TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-25-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 85 ++++++++++++++------------------------ 1 file changed, 30 insertions(+), 55 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_ASRD(DisasContext *s, arg_rpri_esz *a) } } -static bool trans_SQSHL_zpzi(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_sqshl_zpzi_b, gen_helper_sve2_sqshl_zpzi_h, - gen_helper_sve2_sqshl_zpzi_s, gen_helper_sve2_sqshl_zpzi_d, - }; - if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); -} +static gen_helper_gvec_3 * const sqshl_zpzi_fns[4] = { + gen_helper_sve2_sqshl_zpzi_b, gen_helper_sve2_sqshl_zpzi_h, + gen_helper_sve2_sqshl_zpzi_s, gen_helper_sve2_sqshl_zpzi_d, +}; +TRANS_FEAT(SQSHL_zpzi, aa64_sve2, gen_gvec_ool_arg_zpzi, + a->esz < 0 ? NULL : sqshl_zpzi_fns[a->esz], a) -static bool trans_UQSHL_zpzi(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_uqshl_zpzi_b, gen_helper_sve2_uqshl_zpzi_h, - gen_helper_sve2_uqshl_zpzi_s, gen_helper_sve2_uqshl_zpzi_d, - }; - if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); -} +static gen_helper_gvec_3 * const uqshl_zpzi_fns[4] = { + gen_helper_sve2_uqshl_zpzi_b, gen_helper_sve2_uqshl_zpzi_h, + gen_helper_sve2_uqshl_zpzi_s, gen_helper_sve2_uqshl_zpzi_d, +}; +TRANS_FEAT(UQSHL_zpzi, aa64_sve2, gen_gvec_ool_arg_zpzi, + a->esz < 0 ? NULL : uqshl_zpzi_fns[a->esz], a) -static bool trans_SRSHR(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_srshr_b, gen_helper_sve2_srshr_h, - gen_helper_sve2_srshr_s, gen_helper_sve2_srshr_d, - }; - if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); -} +static gen_helper_gvec_3 * const srshr_fns[4] = { + gen_helper_sve2_srshr_b, gen_helper_sve2_srshr_h, + gen_helper_sve2_srshr_s, gen_helper_sve2_srshr_d, +}; +TRANS_FEAT(SRSHR, aa64_sve2, gen_gvec_ool_arg_zpzi, + a->esz < 0 ? NULL : srshr_fns[a->esz], a) -static bool trans_URSHR(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_urshr_b, gen_helper_sve2_urshr_h, - gen_helper_sve2_urshr_s, gen_helper_sve2_urshr_d, - }; - if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); -} +static gen_helper_gvec_3 * const urshr_fns[4] = { + gen_helper_sve2_urshr_b, gen_helper_sve2_urshr_h, + gen_helper_sve2_urshr_s, gen_helper_sve2_urshr_d, +}; +TRANS_FEAT(URSHR, aa64_sve2, gen_gvec_ool_arg_zpzi, + a->esz < 0 ? NULL : urshr_fns[a->esz], a) -static bool trans_SQSHLU(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve2_sqshlu_b, gen_helper_sve2_sqshlu_h, - gen_helper_sve2_sqshlu_s, gen_helper_sve2_sqshlu_d, - }; - if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); -} +static gen_helper_gvec_3 * const sqshlu_fns[4] = { + gen_helper_sve2_sqshlu_b, gen_helper_sve2_sqshlu_h, + gen_helper_sve2_sqshlu_s, gen_helper_sve2_sqshlu_d, +}; +TRANS_FEAT(SQSHLU, aa64_sve2, gen_gvec_ool_arg_zpzi, + a->esz < 0 ? NULL : sqshlu_fns[a->esz], a) /* *** SVE Bitwise Shift - Predicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-26-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 42 ++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 24 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zpzi(DisasContext *s, gen_helper_gvec_3 *fn, } /* Invoke an out-of-line helper on 3 Zregs and a predicate. */ -static void gen_gvec_ool_zzzp(DisasContext *s, gen_helper_gvec_4 *fn, +static bool gen_gvec_ool_zzzp(DisasContext *s, gen_helper_gvec_4 *fn, int rd, int rn, int rm, int pg, int data) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - pred_full_reg_offset(s, pg), - vsz, vsz, data, fn); + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + pred_full_reg_offset(s, pg), + vsz, vsz, data, fn); + } + return true; } /* Invoke a vector expander on two Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool trans_UQSUB_zzz(DisasContext *s, arg_rrr_esz *a) static bool do_zpzz_ool(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4 *fn) { - if (fn == NULL) { - return false; - } - if (sve_access_check(s)) { - gen_gvec_ool_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, 0); - } - return true; + return gen_gvec_ool_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, 0); } /* Select active elememnts from Zn and inactive elements from Zm, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(REVW, aa64_sve, gen_gvec_ool_arg_zpz, static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a) { - if (sve_access_check(s)) { - gen_gvec_ool_zzzp(s, gen_helper_sve_splice, - a->rd, a->rn, a->rm, a->pg, a->esz); - } - return true; + return gen_gvec_ool_zzzp(s, gen_helper_sve_splice, + a->rd, a->rn, a->rm, a->pg, a->esz); } static bool trans_SPLICE_sve2(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_SPLICE_sve2(DisasContext *s, arg_rpr_esz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_ool_zzzp(s, gen_helper_sve_splice, - a->rd, a->rn, (a->rn + 1) % 32, a->pg, a->esz); - } - return true; + return gen_gvec_ool_zzzp(s, gen_helper_sve_splice, + a->rd, a->rn, (a->rn + 1) % 32, a->pg, a->esz); } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use gen_gvec_ool_arg_zpzz instead of gen_gvec_ool_zzzp when the arguments come from arg_rprr_esz. Replaces do_zpzz_ool. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-27-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_zzzp(DisasContext *s, gen_helper_gvec_4 *fn, return true; } +static bool gen_gvec_ool_arg_zpzz(DisasContext *s, gen_helper_gvec_4 *fn, + arg_rprr_esz *a, int data) +{ + return gen_gvec_ool_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, data); +} + /* Invoke a vector expander on two Zregs. */ static void gen_gvec_fn_zz(DisasContext *s, GVecGen2Fn *gvec_fn, int esz, int rd, int rn) @@ -XXX,XX +XXX,XX @@ static bool trans_UQSUB_zzz(DisasContext *s, arg_rrr_esz *a) *** SVE Integer Arithmetic - Binary Predicated Group */ -static bool do_zpzz_ool(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4 *fn) -{ - return gen_gvec_ool_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, 0); -} - /* Select active elememnts from Zn and inactive elements from Zm, * storing the result in Zd. */ @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME##_zpzz(DisasContext *s, arg_rprr_esz *a) \ gen_helper_sve_##name##_zpzz_b, gen_helper_sve_##name##_zpzz_h, \ gen_helper_sve_##name##_zpzz_s, gen_helper_sve_##name##_zpzz_d, \ }; \ - return do_zpzz_ool(s, a, fns[a->esz]); \ + return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); \ } DO_ZPZZ(AND, and) @@ -XXX,XX +XXX,XX @@ static bool trans_SDIV_zpzz(DisasContext *s, arg_rprr_esz *a) static gen_helper_gvec_4 * const fns[4] = { NULL, NULL, gen_helper_sve_sdiv_zpzz_s, gen_helper_sve_sdiv_zpzz_d }; - return do_zpzz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); } static bool trans_UDIV_zpzz(DisasContext *s, arg_rprr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_UDIV_zpzz(DisasContext *s, arg_rprr_esz *a) static gen_helper_gvec_4 * const fns[4] = { NULL, NULL, gen_helper_sve_udiv_zpzz_s, gen_helper_sve_udiv_zpzz_d }; - return do_zpzz_ool(s, a, fns[a->esz]); + return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); } static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME##_zpzw(DisasContext *s, arg_rprr_esz *a) \ if (a->esz < 0 || a->esz >= 3) { \ return false; \ } \ - return do_zpzz_ool(s, a, fns[a->esz]); \ + return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); \ } DO_ZPZW(ASR, asr) @@ -XXX,XX +XXX,XX @@ static bool do_sve2_zpzz_ool(DisasContext *s, arg_rprr_esz *a, if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return do_zpzz_ool(s, a, fn); + return gen_gvec_ool_arg_zpzz(s, fn, a, 0); } static bool trans_SADALP_zpzz(DisasContext *s, arg_rprr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions directly using gen_gvec_ool_arg_zpzz to TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-28-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 85 ++++++++++++++++---------------------- 1 file changed, 36 insertions(+), 49 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_sel_z(DisasContext *s, int rd, int rn, int rm, int pg, int esz) gen_gvec_ool_zzzp(s, fns[esz], rd, rn, rm, pg, 0); } -#define DO_ZPZZ(NAME, name) \ -static bool trans_##NAME##_zpzz(DisasContext *s, arg_rprr_esz *a) \ -{ \ - static gen_helper_gvec_4 * const fns[4] = { \ - gen_helper_sve_##name##_zpzz_b, gen_helper_sve_##name##_zpzz_h, \ - gen_helper_sve_##name##_zpzz_s, gen_helper_sve_##name##_zpzz_d, \ +#define DO_ZPZZ(NAME, FEAT, name) \ + static gen_helper_gvec_4 * const name##_zpzz_fns[4] = { \ + gen_helper_##name##_zpzz_b, gen_helper_##name##_zpzz_h, \ + gen_helper_##name##_zpzz_s, gen_helper_##name##_zpzz_d, \ }; \ - return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); \ -} + TRANS_FEAT(NAME, FEAT, gen_gvec_ool_arg_zpzz, \ + name##_zpzz_fns[a->esz], a, 0) -DO_ZPZZ(AND, and) -DO_ZPZZ(EOR, eor) -DO_ZPZZ(ORR, orr) -DO_ZPZZ(BIC, bic) +DO_ZPZZ(AND_zpzz, aa64_sve, sve_and) +DO_ZPZZ(EOR_zpzz, aa64_sve, sve_eor) +DO_ZPZZ(ORR_zpzz, aa64_sve, sve_orr) +DO_ZPZZ(BIC_zpzz, aa64_sve, sve_bic) -DO_ZPZZ(ADD, add) -DO_ZPZZ(SUB, sub) +DO_ZPZZ(ADD_zpzz, aa64_sve, sve_add) +DO_ZPZZ(SUB_zpzz, aa64_sve, sve_sub) -DO_ZPZZ(SMAX, smax) -DO_ZPZZ(UMAX, umax) -DO_ZPZZ(SMIN, smin) -DO_ZPZZ(UMIN, umin) -DO_ZPZZ(SABD, sabd) -DO_ZPZZ(UABD, uabd) +DO_ZPZZ(SMAX_zpzz, aa64_sve, sve_smax) +DO_ZPZZ(UMAX_zpzz, aa64_sve, sve_umax) +DO_ZPZZ(SMIN_zpzz, aa64_sve, sve_smin) +DO_ZPZZ(UMIN_zpzz, aa64_sve, sve_umin) +DO_ZPZZ(SABD_zpzz, aa64_sve, sve_sabd) +DO_ZPZZ(UABD_zpzz, aa64_sve, sve_uabd) -DO_ZPZZ(MUL, mul) -DO_ZPZZ(SMULH, smulh) -DO_ZPZZ(UMULH, umulh) +DO_ZPZZ(MUL_zpzz, aa64_sve, sve_mul) +DO_ZPZZ(SMULH_zpzz, aa64_sve, sve_smulh) +DO_ZPZZ(UMULH_zpzz, aa64_sve, sve_umulh) -DO_ZPZZ(ASR, asr) -DO_ZPZZ(LSR, lsr) -DO_ZPZZ(LSL, lsl) +DO_ZPZZ(ASR_zpzz, aa64_sve, sve_asr) +DO_ZPZZ(LSR_zpzz, aa64_sve, sve_lsr) +DO_ZPZZ(LSL_zpzz, aa64_sve, sve_lsl) -static bool trans_SDIV_zpzz(DisasContext *s, arg_rprr_esz *a) -{ - static gen_helper_gvec_4 * const fns[4] = { - NULL, NULL, gen_helper_sve_sdiv_zpzz_s, gen_helper_sve_sdiv_zpzz_d - }; - return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_4 * const sdiv_fns[4] = { + NULL, NULL, gen_helper_sve_sdiv_zpzz_s, gen_helper_sve_sdiv_zpzz_d +}; +TRANS_FEAT(SDIV_zpzz, aa64_sve, gen_gvec_ool_arg_zpzz, sdiv_fns[a->esz], a, 0) -static bool trans_UDIV_zpzz(DisasContext *s, arg_rprr_esz *a) -{ - static gen_helper_gvec_4 * const fns[4] = { - NULL, NULL, gen_helper_sve_udiv_zpzz_s, gen_helper_sve_udiv_zpzz_d - }; - return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); -} +static gen_helper_gvec_4 * const udiv_fns[4] = { + NULL, NULL, gen_helper_sve_udiv_zpzz_s, gen_helper_sve_udiv_zpzz_d +}; +TRANS_FEAT(UDIV_zpzz, aa64_sve, gen_gvec_ool_arg_zpzz, udiv_fns[a->esz], a, 0) static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) { @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQSHLU, aa64_sve2, gen_gvec_ool_arg_zpzi, */ #define DO_ZPZW(NAME, name) \ -static bool trans_##NAME##_zpzw(DisasContext *s, arg_rprr_esz *a) \ -{ \ - static gen_helper_gvec_4 * const fns[3] = { \ + static gen_helper_gvec_4 * const name##_zpzw_fns[4] = { \ gen_helper_sve_##name##_zpzw_b, gen_helper_sve_##name##_zpzw_h, \ - gen_helper_sve_##name##_zpzw_s, \ + gen_helper_sve_##name##_zpzw_s, NULL \ }; \ - if (a->esz < 0 || a->esz >= 3) { \ - return false; \ - } \ - return gen_gvec_ool_arg_zpzz(s, fns[a->esz], a, 0); \ -} + TRANS_FEAT(NAME##_zpzw, aa64_sve, gen_gvec_ool_arg_zpzz, \ + a->esz < 0 ? NULL : name##_zpzw_fns[a->esz], a, 0) DO_ZPZW(ASR, asr) DO_ZPZW(LSR, lsr) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zpzz_ool to use TRANS_FEAT and gen_gvec_ool_arg_zpzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-29-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 118 +++++++++++++------------------------ 1 file changed, 40 insertions(+), 78 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) return true; } -#undef DO_ZPZZ - /* *** SVE Integer Arithmetic - Unary Predicated Group */ @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, * SVE2 Integer - Predicated */ -static bool do_sve2_zpzz_ool(DisasContext *s, arg_rprr_esz *a, - gen_helper_gvec_4 *fn) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_arg_zpzz(s, fn, a, 0); -} +static gen_helper_gvec_4 * const sadlp_fns[4] = { + NULL, gen_helper_sve2_sadalp_zpzz_h, + gen_helper_sve2_sadalp_zpzz_s, gen_helper_sve2_sadalp_zpzz_d, +}; +TRANS_FEAT(SADALP_zpzz, aa64_sve2, gen_gvec_ool_arg_zpzz, + sadlp_fns[a->esz], a, 0) -static bool trans_SADALP_zpzz(DisasContext *s, arg_rprr_esz *a) -{ - static gen_helper_gvec_4 * const fns[3] = { - gen_helper_sve2_sadalp_zpzz_h, - gen_helper_sve2_sadalp_zpzz_s, - gen_helper_sve2_sadalp_zpzz_d, - }; - if (a->esz == 0) { - return false; - } - return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]); -} - -static bool trans_UADALP_zpzz(DisasContext *s, arg_rprr_esz *a) -{ - static gen_helper_gvec_4 * const fns[3] = { - gen_helper_sve2_uadalp_zpzz_h, - gen_helper_sve2_uadalp_zpzz_s, - gen_helper_sve2_uadalp_zpzz_d, - }; - if (a->esz == 0) { - return false; - } - return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]); -} +static gen_helper_gvec_4 * const uadlp_fns[4] = { + NULL, gen_helper_sve2_uadalp_zpzz_h, + gen_helper_sve2_uadalp_zpzz_s, gen_helper_sve2_uadalp_zpzz_d, +}; +TRANS_FEAT(UADALP_zpzz, aa64_sve2, gen_gvec_ool_arg_zpzz, + uadlp_fns[a->esz], a, 0) /* * SVE2 integer unary operations (predicated) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const sqneg_fns[4] = { }; TRANS_FEAT(SQNEG, aa64_sve2, gen_gvec_ool_arg_zpz, sqneg_fns[a->esz], a, 0) -#define DO_SVE2_ZPZZ(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ -{ \ - static gen_helper_gvec_4 * const fns[4] = { \ - gen_helper_sve2_##name##_zpzz_b, gen_helper_sve2_##name##_zpzz_h, \ - gen_helper_sve2_##name##_zpzz_s, gen_helper_sve2_##name##_zpzz_d, \ - }; \ - return do_sve2_zpzz_ool(s, a, fns[a->esz]); \ -} +DO_ZPZZ(SQSHL, aa64_sve2, sve2_sqshl) +DO_ZPZZ(SQRSHL, aa64_sve2, sve2_sqrshl) +DO_ZPZZ(SRSHL, aa64_sve2, sve2_srshl) -DO_SVE2_ZPZZ(SQSHL, sqshl) -DO_SVE2_ZPZZ(SQRSHL, sqrshl) -DO_SVE2_ZPZZ(SRSHL, srshl) +DO_ZPZZ(UQSHL, aa64_sve2, sve2_uqshl) +DO_ZPZZ(UQRSHL, aa64_sve2, sve2_uqrshl) +DO_ZPZZ(URSHL, aa64_sve2, sve2_urshl) -DO_SVE2_ZPZZ(UQSHL, uqshl) -DO_SVE2_ZPZZ(UQRSHL, uqrshl) -DO_SVE2_ZPZZ(URSHL, urshl) +DO_ZPZZ(SHADD, aa64_sve2, sve2_shadd) +DO_ZPZZ(SRHADD, aa64_sve2, sve2_srhadd) +DO_ZPZZ(SHSUB, aa64_sve2, sve2_shsub) -DO_SVE2_ZPZZ(SHADD, shadd) -DO_SVE2_ZPZZ(SRHADD, srhadd) -DO_SVE2_ZPZZ(SHSUB, shsub) +DO_ZPZZ(UHADD, aa64_sve2, sve2_uhadd) +DO_ZPZZ(URHADD, aa64_sve2, sve2_urhadd) +DO_ZPZZ(UHSUB, aa64_sve2, sve2_uhsub) -DO_SVE2_ZPZZ(UHADD, uhadd) -DO_SVE2_ZPZZ(URHADD, urhadd) -DO_SVE2_ZPZZ(UHSUB, uhsub) +DO_ZPZZ(ADDP, aa64_sve2, sve2_addp) +DO_ZPZZ(SMAXP, aa64_sve2, sve2_smaxp) +DO_ZPZZ(UMAXP, aa64_sve2, sve2_umaxp) +DO_ZPZZ(SMINP, aa64_sve2, sve2_sminp) +DO_ZPZZ(UMINP, aa64_sve2, sve2_uminp) -DO_SVE2_ZPZZ(ADDP, addp) -DO_SVE2_ZPZZ(SMAXP, smaxp) -DO_SVE2_ZPZZ(UMAXP, umaxp) -DO_SVE2_ZPZZ(SMINP, sminp) -DO_SVE2_ZPZZ(UMINP, uminp) - -DO_SVE2_ZPZZ(SQADD_zpzz, sqadd) -DO_SVE2_ZPZZ(UQADD_zpzz, uqadd) -DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub) -DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub) -DO_SVE2_ZPZZ(SUQADD, suqadd) -DO_SVE2_ZPZZ(USQADD, usqadd) +DO_ZPZZ(SQADD_zpzz, aa64_sve2, sve2_sqadd) +DO_ZPZZ(UQADD_zpzz, aa64_sve2, sve2_uqadd) +DO_ZPZZ(SQSUB_zpzz, aa64_sve2, sve2_sqsub) +DO_ZPZZ(UQSUB_zpzz, aa64_sve2, sve2_uqsub) +DO_ZPZZ(SUQADD, aa64_sve2, sve2_suqadd) +DO_ZPZZ(USQADD, aa64_sve2, sve2_usqadd) /* * SVE2 Widening Integer Arithmetic @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ DO_SVE2_PPZZ_MATCH(MATCH, match) DO_SVE2_PPZZ_MATCH(NMATCH, nmatch) -static bool trans_HISTCNT(DisasContext *s, arg_rprr_esz *a) -{ - static gen_helper_gvec_4 * const fns[2] = { - gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d - }; - if (a->esz < 2) { - return false; - } - return do_sve2_zpzz_ool(s, a, fns[a->esz - 2]); -} +static gen_helper_gvec_4 * const histcnt_fns[4] = { + NULL, NULL, gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d +}; +TRANS_FEAT(HISTCNT, aa64_sve2, gen_gvec_ool_arg_zpzz, + histcnt_fns[a->esz], a, 0) TRANS_FEAT(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> There is only one caller for gen_gvec_fn_zz; inline it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-30-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zpzz(DisasContext *s, gen_helper_gvec_4 *fn, return gen_gvec_ool_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, data); } -/* Invoke a vector expander on two Zregs. */ -static void gen_gvec_fn_zz(DisasContext *s, GVecGen2Fn *gvec_fn, - int esz, int rd, int rn) -{ - unsigned vsz = vec_full_reg_size(s); - gvec_fn(esz, vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), vsz, vsz); -} - /* Invoke a vector expander on three Zregs. */ static void gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, int esz, int rd, int rn, int rm) @@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn_zzzz(DisasContext *s, GVecGen4Fn *gvec_fn, static bool do_mov_z(DisasContext *s, int rd, int rn) { if (sve_access_check(s)) { - gen_gvec_fn_zz(s, tcg_gen_gvec_mov, MO_8, rd, rn); + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_mov(MO_8, vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), vsz, vsz); } return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-31-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 36 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 21 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zpzz(DisasContext *s, gen_helper_gvec_4 *fn, } /* Invoke a vector expander on three Zregs. */ -static void gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, +static bool gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, int esz, int rd, int rn, int rm) { - unsigned vsz = vec_full_reg_size(s); - gvec_fn(esz, vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), vsz, vsz); + if (gvec_fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + gvec_fn(esz, vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), vsz, vsz); + } + return true; } /* Invoke a vector expander on four Zregs. */ @@ -XXX,XX +XXX,XX @@ const uint64_t pred_esz_masks[4] = { static bool do_zzz_fn(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *gvec_fn) { - if (sve_access_check(s)) { - gen_gvec_fn_zzz(s, gvec_fn, a->esz, a->rd, a->rn, a->rm); - } - return true; + return gen_gvec_fn_zzz(s, gvec_fn, a->esz, a->rd, a->rn, a->rm); } static bool trans_AND_zzz(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_fn_zzz(s, tcg_gen_gvec_mul, a->esz, a->rd, a->rn, a->rm); - } - return true; + return gen_gvec_fn_zzz(s, tcg_gen_gvec_mul, a->esz, a->rd, a->rn, a->rm); } static gen_helper_gvec_3 * const smulh_zzz_fns[4] = { @@ -XXX,XX +XXX,XX @@ static bool do_sve2_fn_zzz(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *fn) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_fn_zzz(s, fn, a->esz, a->rd, a->rn, a->rm); - } - return true; + return gen_gvec_fn_zzz(s, fn, a->esz, a->rd, a->rn, a->rm); } static bool trans_SABA(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve2_sha3, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_fn_zzz(s, gen_gvec_rax1, MO_64, a->rd, a->rn, a->rm); - } - return true; + return gen_gvec_fn_zzz(s, gen_gvec_rax1, MO_64, a->rd, a->rn, a->rm); } static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Rename the function to match gen_gvec_fn_zzz, and move to be adjacent. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-32-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, return true; } +static bool gen_gvec_fn_arg_zzz(DisasContext *s, GVecGen3Fn *fn, + arg_rrr_esz *a) +{ + return gen_gvec_fn_zzz(s, fn, a->esz, a->rd, a->rn, a->rm); +} + /* Invoke a vector expander on four Zregs. */ static void gen_gvec_fn_zzzz(DisasContext *s, GVecGen4Fn *gvec_fn, int esz, int rd, int rn, int rm, int ra) @@ -XXX,XX +XXX,XX @@ const uint64_t pred_esz_masks[4] = { *** SVE Logical - Unpredicated Group */ -static bool do_zzz_fn(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *gvec_fn) -{ - return gen_gvec_fn_zzz(s, gvec_fn, a->esz, a->rd, a->rn, a->rm); -} - static bool trans_AND_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_and); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_and, a); } static bool trans_ORR_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_or); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_or, a); } static bool trans_EOR_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_xor); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_xor, a); } static bool trans_BIC_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_andc); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_andc, a); } static void gen_xar8_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) @@ -XXX,XX +XXX,XX @@ static bool trans_NBSL(DisasContext *s, arg_rrrr_esz *a) static bool trans_ADD_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_add); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_add, a); } static bool trans_SUB_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_sub); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_sub, a); } static bool trans_SQADD_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_ssadd); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_ssadd, a); } static bool trans_SQSUB_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_sssub); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_sssub, a); } static bool trans_UQADD_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_usadd); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_usadd, a); } static bool trans_UQSUB_zzz(DisasContext *s, arg_rrr_esz *a) { - return do_zzz_fn(s, a, tcg_gen_gvec_ussub); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_ussub, a); } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Two uses of gen_gvec_fn_zzz can pass on arg_rrr_esz instead. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-33-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return gen_gvec_fn_zzz(s, tcg_gen_gvec_mul, a->esz, a->rd, a->rn, a->rm); + return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_mul, a); } static gen_helper_gvec_3 * const smulh_zzz_fns[4] = { @@ -XXX,XX +XXX,XX @@ static bool do_sve2_fn_zzz(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *fn) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return gen_gvec_fn_zzz(s, fn, a->esz, a->rd, a->rn, a->rm); + return gen_gvec_fn_arg_zzz(s, fn, a); } static bool trans_SABA(DisasContext *s, arg_rrr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions directly using gen_gvec_fn_arg_zzz to TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-34-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 66 +++++++------------------------------- 1 file changed, 11 insertions(+), 55 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ const uint64_t pred_esz_masks[4] = { *** SVE Logical - Unpredicated Group */ -static bool trans_AND_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_and, a); -} - -static bool trans_ORR_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_or, a); -} - -static bool trans_EOR_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_xor, a); -} - -static bool trans_BIC_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_andc, a); -} +TRANS_FEAT(AND_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_and, a) +TRANS_FEAT(ORR_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_or, a) +TRANS_FEAT(EOR_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_xor, a) +TRANS_FEAT(BIC_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_andc, a) static void gen_xar8_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) { @@ -XXX,XX +XXX,XX @@ static bool trans_NBSL(DisasContext *s, arg_rrrr_esz *a) *** SVE Integer Arithmetic - Unpredicated Group */ -static bool trans_ADD_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_add, a); -} - -static bool trans_SUB_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_sub, a); -} - -static bool trans_SQADD_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_ssadd, a); -} - -static bool trans_SQSUB_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_sssub, a); -} - -static bool trans_UQADD_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_usadd, a); -} - -static bool trans_UQSUB_zzz(DisasContext *s, arg_rrr_esz *a) -{ - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_ussub, a); -} +TRANS_FEAT(ADD_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_add, a) +TRANS_FEAT(SUB_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_sub, a) +TRANS_FEAT(SQADD_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_ssadd, a) +TRANS_FEAT(SQSUB_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_sssub, a) +TRANS_FEAT(UQADD_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_usadd, a) +TRANS_FEAT(UQSUB_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_ussub, a) /* *** SVE Integer Arithmetic - Binary Predicated Group @@ -XXX,XX +XXX,XX @@ static bool trans_MOVPRFX_z(DisasContext *s, arg_rpr_esz *a) * SVE2 Integer Multiply - Unpredicated */ -static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_fn_arg_zzz(s, tcg_gen_gvec_mul, a); -} +TRANS_FEAT(MUL_zzz, aa64_sve2, gen_gvec_fn_arg_zzz, tcg_gen_gvec_mul, a) static gen_helper_gvec_3 * const smulh_zzz_fns[4] = { gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_fn_zzz to use TRANS_FEAT and gen_gvec_fn_arg_zzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-35-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SLI(DisasContext *s, arg_rri_esz *a) return do_sve2_fn2i(s, a, gen_gvec_sli); } -static bool do_sve2_fn_zzz(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *fn) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_fn_arg_zzz(s, fn, a); -} - -static bool trans_SABA(DisasContext *s, arg_rrr_esz *a) -{ - return do_sve2_fn_zzz(s, a, gen_gvec_saba); -} - -static bool trans_UABA(DisasContext *s, arg_rrr_esz *a) -{ - return do_sve2_fn_zzz(s, a, gen_gvec_uaba); -} +TRANS_FEAT(SABA, aa64_sve2, gen_gvec_fn_arg_zzz, gen_gvec_saba, a) +TRANS_FEAT(UABA, aa64_sve2, gen_gvec_fn_arg_zzz, gen_gvec_uaba, a) static bool do_sve2_narrow_extract(DisasContext *s, arg_rri_esz *a, const GVecGen2 ops[3]) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The decode for RAX1 sets esz to MO_8, because that's what we use by default for "no esz present". We changed that to MO_64 during translation because it is more logical for the operation. However, the esz argument to gen_gvec_rax1 is unused and forces MO_64 within that function, so there is no need to do it here as well. Simplify to use gen_gvec_fn_arg_zzz and TRANS_FEAT. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-36-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, TRANS_FEAT(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, gen_helper_crypto_sm4ekey, a, 0) -static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2_sha3, s)) { - return false; - } - return gen_gvec_fn_zzz(s, gen_gvec_rax1, MO_64, a->rd, a->rn, a->rm); -} +TRANS_FEAT(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, gen_gvec_rax1, a) static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Merge gen_gvec_fn_zzzz with the sve access check and the dereference of arg_rrrr_esz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-37-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fn_arg_zzz(DisasContext *s, GVecGen3Fn *fn, } /* Invoke a vector expander on four Zregs. */ -static void gen_gvec_fn_zzzz(DisasContext *s, GVecGen4Fn *gvec_fn, - int esz, int rd, int rn, int rm, int ra) +static bool gen_gvec_fn_arg_zzzz(DisasContext *s, GVecGen4Fn *gvec_fn, + arg_rrrr_esz *a) { - unsigned vsz = vec_full_reg_size(s); - gvec_fn(esz, vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vec_full_reg_offset(s, ra), vsz, vsz); + if (gvec_fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + gvec_fn(a->esz, vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), vsz, vsz); + } + return true; } /* Invoke a vector move on two Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool do_sve2_zzzz_fn(DisasContext *s, arg_rrrr_esz *a, GVecGen4Fn *fn) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - gen_gvec_fn_zzzz(s, fn, a->esz, a->rd, a->rn, a->rm, a->ra); - } - return true; + return gen_gvec_fn_arg_zzzz(s, fn, a); } static void gen_eor3_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_zzzz_fn to use TRANS_FEAT and gen_gvec_fn_arg_zzzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-38-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 38 ++++++-------------------------------- 1 file changed, 6 insertions(+), 32 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_XAR(DisasContext *s, arg_rrri_esz *a) return true; } -static bool do_sve2_zzzz_fn(DisasContext *s, arg_rrrr_esz *a, GVecGen4Fn *fn) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_fn_arg_zzzz(s, fn, a); -} - static void gen_eor3_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) { tcg_gen_xor_i64(d, n, m); @@ -XXX,XX +XXX,XX @@ static void gen_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); } -static bool trans_EOR3(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sve2_zzzz_fn(s, a, gen_eor3); -} +TRANS_FEAT(EOR3, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_eor3, a) static void gen_bcax_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) { @@ -XXX,XX +XXX,XX @@ static void gen_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); } -static bool trans_BCAX(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sve2_zzzz_fn(s, a, gen_bcax); -} +TRANS_FEAT(BCAX, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_bcax, a) static void gen_bsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, uint32_t a, uint32_t oprsz, uint32_t maxsz) @@ -XXX,XX +XXX,XX @@ static void gen_bsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_bitsel(vece, d, a, n, m, oprsz, maxsz); } -static bool trans_BSL(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sve2_zzzz_fn(s, a, gen_bsl); -} +TRANS_FEAT(BSL, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_bsl, a) static void gen_bsl1n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) { @@ -XXX,XX +XXX,XX @@ static void gen_bsl1n(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); } -static bool trans_BSL1N(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sve2_zzzz_fn(s, a, gen_bsl1n); -} +TRANS_FEAT(BSL1N, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_bsl1n, a) static void gen_bsl2n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) { @@ -XXX,XX +XXX,XX @@ static void gen_bsl2n(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); } -static bool trans_BSL2N(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sve2_zzzz_fn(s, a, gen_bsl2n); -} +TRANS_FEAT(BSL2N, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_bsl2n, a) static void gen_nbsl_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) { @@ -XXX,XX +XXX,XX @@ static void gen_nbsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); } -static bool trans_NBSL(DisasContext *s, arg_rrrr_esz *a) -{ - return do_sve2_zzzz_fn(s, a, gen_nbsl); -} +TRANS_FEAT(NBSL, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_nbsl, a) /* *** SVE Integer Arithmetic - Unpredicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We have two places that perform this particular operation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-39-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zpzz(DisasContext *s, gen_helper_gvec_4 *fn, return gen_gvec_ool_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, data); } +/* Invoke a vector expander on two Zregs and an immediate. */ +static bool gen_gvec_fn_zzi(DisasContext *s, GVecGen2iFn *gvec_fn, + int esz, int rd, int rn, uint64_t imm) +{ + if (gvec_fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + gvec_fn(esz, vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), imm, vsz, vsz); + } + return true; +} + /* Invoke a vector expander on three Zregs. */ static bool gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, int esz, int rd, int rn, int rm) @@ -XXX,XX +XXX,XX @@ static bool do_zz_dbm(DisasContext *s, arg_rr_dbm *a, GVecGen2iFn *gvec_fn) extract32(a->dbm, 6, 6))) { return false; } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - gvec_fn(MO_64, vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), imm, vsz, vsz); - } - return true; + return gen_gvec_fn_zzi(s, gvec_fn, MO_64, a->rd, a->rn, imm); } static bool trans_AND_zzi(DisasContext *s, arg_rr_dbm *a) @@ -XXX,XX +XXX,XX @@ static bool do_sve2_fn2i(DisasContext *s, arg_rri_esz *a, GVecGen2iFn *fn) if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - unsigned rd_ofs = vec_full_reg_offset(s, a->rd); - unsigned rn_ofs = vec_full_reg_offset(s, a->rn); - fn(a->esz, rd_ofs, rn_ofs, a->imm, vsz, vsz); - } - return true; + return gen_gvec_fn_zzi(s, fn, a->esz, a->rd, a->rn, a->imm); } static bool trans_SSRA(DisasContext *s, arg_rri_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-40-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zz_dbm(DisasContext *s, arg_rr_dbm *a, GVecGen2iFn *gvec_fn) return gen_gvec_fn_zzi(s, gvec_fn, MO_64, a->rd, a->rn, imm); } -static bool trans_AND_zzi(DisasContext *s, arg_rr_dbm *a) -{ - return do_zz_dbm(s, a, tcg_gen_gvec_andi); -} - -static bool trans_ORR_zzi(DisasContext *s, arg_rr_dbm *a) -{ - return do_zz_dbm(s, a, tcg_gen_gvec_ori); -} - -static bool trans_EOR_zzi(DisasContext *s, arg_rr_dbm *a) -{ - return do_zz_dbm(s, a, tcg_gen_gvec_xori); -} +TRANS_FEAT(AND_zzi, aa64_sve, do_zz_dbm, a, tcg_gen_gvec_andi) +TRANS_FEAT(ORR_zzi, aa64_sve, do_zz_dbm, a, tcg_gen_gvec_ori) +TRANS_FEAT(EOR_zzi, aa64_sve, do_zz_dbm, a, tcg_gen_gvec_xori) static bool trans_DUPM(DisasContext *s, arg_DUPM *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The check is already done in gen_gvec_ool_zzzp, which is called by do_sel_z; remove from callers. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-41-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UQSUB_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_ussub, a) /* Select active elememnts from Zn and inactive elements from Zm, * storing the result in Zd. */ -static void do_sel_z(DisasContext *s, int rd, int rn, int rm, int pg, int esz) +static bool do_sel_z(DisasContext *s, int rd, int rn, int rm, int pg, int esz) { static gen_helper_gvec_4 * const fns[4] = { gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h, gen_helper_sve_sel_zpzz_s, gen_helper_sve_sel_zpzz_d }; - gen_gvec_ool_zzzp(s, fns[esz], rd, rn, rm, pg, 0); + return gen_gvec_ool_zzzp(s, fns[esz], rd, rn, rm, pg, 0); } #define DO_ZPZZ(NAME, FEAT, name) \ @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UDIV_zpzz, aa64_sve, gen_gvec_ool_arg_zpzz, udiv_fns[a->esz], a, 0) static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) { - if (sve_access_check(s)) { - do_sel_z(s, a->rd, a->rn, a->rm, a->pg, a->esz); - } - return true; + return do_sel_z(s, a->rd, a->rn, a->rm, a->pg, a->esz); } /* @@ -XXX,XX +XXX,XX @@ static bool trans_MOVPRFX(DisasContext *s, arg_MOVPRFX *a) static bool trans_MOVPRFX_m(DisasContext *s, arg_rpr_esz *a) { - if (sve_access_check(s)) { - do_sel_z(s, a->rd, a->rn, a->rd, a->pg, a->esz); - } - return true; + return do_sel_z(s, a->rd, a->rn, a->rd, a->pg, a->esz); } static bool trans_MOVPRFX_z(DisasContext *s, arg_rpr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We have two places that perform this particular operation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-42-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fn_zzi(DisasContext *s, GVecGen2iFn *gvec_fn, return true; } +static bool gen_gvec_fn_arg_zzi(DisasContext *s, GVecGen2iFn *gvec_fn, + arg_rri_esz *a) +{ + if (a->esz < 0) { + /* Invalid tsz encoding -- see tszimm_esz. */ + return false; + } + return gen_gvec_fn_zzi(s, gvec_fn, a->esz, a->rd, a->rn, a->imm); +} + /* Invoke a vector expander on three Zregs. */ static bool gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, int esz, int rd, int rn, int rm) @@ -XXX,XX +XXX,XX @@ static bool trans_ADD_zzi(DisasContext *s, arg_rri_esz *a) if (a->esz == 0 && extract32(s->insn, 13, 1)) { return false; } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_addi(a->esz, vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), a->imm, vsz, vsz); - } - return true; + return gen_gvec_fn_arg_zzi(s, tcg_gen_gvec_addi, a); } static bool trans_SUB_zzi(DisasContext *s, arg_rri_esz *a) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADCLT, aa64_sve2, do_adcl, a, true) static bool do_sve2_fn2i(DisasContext *s, arg_rri_esz *a, GVecGen2iFn *fn) { - if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + if (!dc_isar_feature(aa64_sve2, s)) { return false; } - return gen_gvec_fn_zzi(s, fn, a->esz, a->rd, a->rn, a->imm); + return gen_gvec_fn_arg_zzi(s, fn, a); } static bool trans_SSRA(DisasContext *s, arg_rri_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_sve2_fn2i to use TRANS_FEAT and gen_gvec_fn_arg_zzi. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-43-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 43 ++++++-------------------------------- 1 file changed, 6 insertions(+), 37 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_adcl(DisasContext *s, arg_rrrr_esz *a, bool sel) TRANS_FEAT(ADCLB, aa64_sve2, do_adcl, a, false) TRANS_FEAT(ADCLT, aa64_sve2, do_adcl, a, true) -static bool do_sve2_fn2i(DisasContext *s, arg_rri_esz *a, GVecGen2iFn *fn) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_fn_arg_zzi(s, fn, a); -} - -static bool trans_SSRA(DisasContext *s, arg_rri_esz *a) -{ - return do_sve2_fn2i(s, a, gen_gvec_ssra); -} - -static bool trans_USRA(DisasContext *s, arg_rri_esz *a) -{ - return do_sve2_fn2i(s, a, gen_gvec_usra); -} - -static bool trans_SRSRA(DisasContext *s, arg_rri_esz *a) -{ - return do_sve2_fn2i(s, a, gen_gvec_srsra); -} - -static bool trans_URSRA(DisasContext *s, arg_rri_esz *a) -{ - return do_sve2_fn2i(s, a, gen_gvec_ursra); -} - -static bool trans_SRI(DisasContext *s, arg_rri_esz *a) -{ - return do_sve2_fn2i(s, a, gen_gvec_sri); -} - -static bool trans_SLI(DisasContext *s, arg_rri_esz *a) -{ - return do_sve2_fn2i(s, a, gen_gvec_sli); -} +TRANS_FEAT(SSRA, aa64_sve2, gen_gvec_fn_arg_zzi, gen_gvec_ssra, a) +TRANS_FEAT(USRA, aa64_sve2, gen_gvec_fn_arg_zzi, gen_gvec_usra, a) +TRANS_FEAT(SRSRA, aa64_sve2, gen_gvec_fn_arg_zzi, gen_gvec_srsra, a) +TRANS_FEAT(URSRA, aa64_sve2, gen_gvec_fn_arg_zzi, gen_gvec_ursra, a) +TRANS_FEAT(SRI, aa64_sve2, gen_gvec_fn_arg_zzi, gen_gvec_sri, a) +TRANS_FEAT(SLI, aa64_sve2, gen_gvec_fn_arg_zzi, gen_gvec_sli, a) TRANS_FEAT(SABA, aa64_sve2, gen_gvec_fn_arg_zzz, gen_gvec_saba, a) TRANS_FEAT(UABA, aa64_sve2, gen_gvec_fn_arg_zzz, gen_gvec_uaba, a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-44-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_vpz_ool(DisasContext *s, arg_rpr_esz *a, } #define DO_VPZ(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a) \ -{ \ - static gen_helper_gvec_reduc * const fns[4] = { \ + static gen_helper_gvec_reduc * const name##_fns[4] = { \ gen_helper_sve_##name##_b, gen_helper_sve_##name##_h, \ gen_helper_sve_##name##_s, gen_helper_sve_##name##_d, \ }; \ - return do_vpz_ool(s, a, fns[a->esz]); \ -} + TRANS_FEAT(NAME, aa64_sve, do_vpz_ool, a, name##_fns[a->esz]) DO_VPZ(ORV, orv) DO_VPZ(ANDV, andv) @@ -XXX,XX +XXX,XX @@ DO_VPZ(UMAXV, umaxv) DO_VPZ(SMINV, sminv) DO_VPZ(UMINV, uminv) -static bool trans_SADDV(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_reduc * const fns[4] = { - gen_helper_sve_saddv_b, gen_helper_sve_saddv_h, - gen_helper_sve_saddv_s, NULL - }; - return do_vpz_ool(s, a, fns[a->esz]); -} +static gen_helper_gvec_reduc * const saddv_fns[4] = { + gen_helper_sve_saddv_b, gen_helper_sve_saddv_h, + gen_helper_sve_saddv_s, NULL +}; +TRANS_FEAT(SADDV, aa64_sve, do_vpz_ool, a, saddv_fns[a->esz]) #undef DO_VPZ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-45-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_shift_imm(DisasContext *s, arg_rri_esz *a, bool asr, return true; } -static bool trans_ASR_zzi(DisasContext *s, arg_rri_esz *a) -{ - return do_shift_imm(s, a, true, tcg_gen_gvec_sari); -} - -static bool trans_LSR_zzi(DisasContext *s, arg_rri_esz *a) -{ - return do_shift_imm(s, a, false, tcg_gen_gvec_shri); -} - -static bool trans_LSL_zzi(DisasContext *s, arg_rri_esz *a) -{ - return do_shift_imm(s, a, false, tcg_gen_gvec_shli); -} +TRANS_FEAT(ASR_zzi, aa64_sve, do_shift_imm, a, true, tcg_gen_gvec_sari) +TRANS_FEAT(LSR_zzi, aa64_sve, do_shift_imm, a, false, tcg_gen_gvec_shri) +TRANS_FEAT(LSL_zzi, aa64_sve, do_shift_imm, a, false, tcg_gen_gvec_shli) #define DO_ZZW(NAME, name) \ static gen_helper_gvec_3 * const name##_zzw_fns[4] = { \ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Share code between the various shifts using arg_rpri_esz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-46-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 68 +++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 38 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_movz_zpz(DisasContext *s, int rd, int rn, int pg, return gen_gvec_ool_zzp(s, fns[esz], rd, rn, pg, invert); } +static bool do_shift_zpzi(DisasContext *s, arg_rpri_esz *a, bool asr, + gen_helper_gvec_3 * const fns[4]) +{ + int max; + + if (a->esz < 0) { + /* Invalid tsz encoding -- see tszimm_esz. */ + return false; + } + + /* + * Shift by element size is architecturally valid. + * For arithmetic right-shift, it's the same as by one less. + * For logical shifts and ASRD, it is a zeroing operation. + */ + max = 8 << a->esz; + if (a->imm >= max) { + if (asr) { + a->imm = max - 1; + } else { + return do_movz_zpz(s, a->rd, a->rd, a->pg, a->esz, true); + } + } + return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); +} + static bool trans_ASR_zpzi(DisasContext *s, arg_rpri_esz *a) { static gen_helper_gvec_3 * const fns[4] = { gen_helper_sve_asr_zpzi_b, gen_helper_sve_asr_zpzi_h, gen_helper_sve_asr_zpzi_s, gen_helper_sve_asr_zpzi_d, }; - if (a->esz < 0) { - /* Invalid tsz encoding -- see tszimm_esz. */ - return false; - } - /* Shift by element size is architecturally valid. For - arithmetic right-shift, it's the same as by one less. */ - a->imm = MIN(a->imm, (8 << a->esz) - 1); - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); + return do_shift_zpzi(s, a, true, fns); } static bool trans_LSR_zpzi(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_LSR_zpzi(DisasContext *s, arg_rpri_esz *a) gen_helper_sve_lsr_zpzi_b, gen_helper_sve_lsr_zpzi_h, gen_helper_sve_lsr_zpzi_s, gen_helper_sve_lsr_zpzi_d, }; - if (a->esz < 0) { - return false; - } - /* Shift by element size is architecturally valid. - For logical shifts, it is a zeroing operation. */ - if (a->imm >= (8 << a->esz)) { - return do_movz_zpz(s, a->rd, a->rd, a->pg, a->esz, true); - } else { - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); - } + return do_shift_zpzi(s, a, false, fns); } static bool trans_LSL_zpzi(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_LSL_zpzi(DisasContext *s, arg_rpri_esz *a) gen_helper_sve_lsl_zpzi_b, gen_helper_sve_lsl_zpzi_h, gen_helper_sve_lsl_zpzi_s, gen_helper_sve_lsl_zpzi_d, }; - if (a->esz < 0) { - return false; - } - /* Shift by element size is architecturally valid. - For logical shifts, it is a zeroing operation. */ - if (a->imm >= (8 << a->esz)) { - return do_movz_zpz(s, a->rd, a->rd, a->pg, a->esz, true); - } else { - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); - } + return do_shift_zpzi(s, a, false, fns); } static bool trans_ASRD(DisasContext *s, arg_rpri_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_ASRD(DisasContext *s, arg_rpri_esz *a) gen_helper_sve_asrd_b, gen_helper_sve_asrd_h, gen_helper_sve_asrd_s, gen_helper_sve_asrd_d, }; - if (a->esz < 0) { - return false; - } - /* Shift by element size is architecturally valid. For arithmetic - right shift for division, it is a zeroing operation. */ - if (a->imm >= (8 << a->esz)) { - return do_movz_zpz(s, a->rd, a->rd, a->pg, a->esz, true); - } else { - return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); - } + return do_shift_zpzi(s, a, false, fns); } static gen_helper_gvec_3 * const sqshl_zpzi_fns[4] = { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-47-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 52 +++++++++++++++----------------------- 1 file changed, 20 insertions(+), 32 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_shift_zpzi(DisasContext *s, arg_rpri_esz *a, bool asr, return gen_gvec_ool_arg_zpzi(s, fns[a->esz], a); } -static bool trans_ASR_zpzi(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve_asr_zpzi_b, gen_helper_sve_asr_zpzi_h, - gen_helper_sve_asr_zpzi_s, gen_helper_sve_asr_zpzi_d, - }; - return do_shift_zpzi(s, a, true, fns); -} +static gen_helper_gvec_3 * const asr_zpzi_fns[4] = { + gen_helper_sve_asr_zpzi_b, gen_helper_sve_asr_zpzi_h, + gen_helper_sve_asr_zpzi_s, gen_helper_sve_asr_zpzi_d, +}; +TRANS_FEAT(ASR_zpzi, aa64_sve, do_shift_zpzi, a, true, asr_zpzi_fns) -static bool trans_LSR_zpzi(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve_lsr_zpzi_b, gen_helper_sve_lsr_zpzi_h, - gen_helper_sve_lsr_zpzi_s, gen_helper_sve_lsr_zpzi_d, - }; - return do_shift_zpzi(s, a, false, fns); -} +static gen_helper_gvec_3 * const lsr_zpzi_fns[4] = { + gen_helper_sve_lsr_zpzi_b, gen_helper_sve_lsr_zpzi_h, + gen_helper_sve_lsr_zpzi_s, gen_helper_sve_lsr_zpzi_d, +}; +TRANS_FEAT(LSR_zpzi, aa64_sve, do_shift_zpzi, a, false, lsr_zpzi_fns) -static bool trans_LSL_zpzi(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve_lsl_zpzi_b, gen_helper_sve_lsl_zpzi_h, - gen_helper_sve_lsl_zpzi_s, gen_helper_sve_lsl_zpzi_d, - }; - return do_shift_zpzi(s, a, false, fns); -} +static gen_helper_gvec_3 * const lsl_zpzi_fns[4] = { + gen_helper_sve_lsl_zpzi_b, gen_helper_sve_lsl_zpzi_h, + gen_helper_sve_lsl_zpzi_s, gen_helper_sve_lsl_zpzi_d, +}; +TRANS_FEAT(LSL_zpzi, aa64_sve, do_shift_zpzi, a, false, lsl_zpzi_fns) -static bool trans_ASRD(DisasContext *s, arg_rpri_esz *a) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve_asrd_b, gen_helper_sve_asrd_h, - gen_helper_sve_asrd_s, gen_helper_sve_asrd_d, - }; - return do_shift_zpzi(s, a, false, fns); -} +static gen_helper_gvec_3 * const asrd_fns[4] = { + gen_helper_sve_asrd_b, gen_helper_sve_asrd_h, + gen_helper_sve_asrd_s, gen_helper_sve_asrd_d, +}; +TRANS_FEAT(ASRD, aa64_sve, do_shift_zpzi, a, false, asrd_fns) static gen_helper_gvec_3 * const sqshl_zpzi_fns[4] = { gen_helper_sve2_sqshl_zpzi_b, gen_helper_sve2_sqshl_zpzi_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Remove the DO_ZPZZZ macro, as it had just the two uses. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-48-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zpzzz_ool(DisasContext *s, arg_rprrr_esz *a, return true; } -#define DO_ZPZZZ(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rprrr_esz *a) \ -{ \ - static gen_helper_gvec_5 * const fns[4] = { \ - gen_helper_sve_##name##_b, gen_helper_sve_##name##_h, \ - gen_helper_sve_##name##_s, gen_helper_sve_##name##_d, \ - }; \ - return do_zpzzz_ool(s, a, fns[a->esz]); \ -} +static gen_helper_gvec_5 * const mla_fns[4] = { + gen_helper_sve_mla_b, gen_helper_sve_mla_h, + gen_helper_sve_mla_s, gen_helper_sve_mla_d, +}; +TRANS_FEAT(MLA, aa64_sve, do_zpzzz_ool, a, mla_fns[a->esz]) -DO_ZPZZZ(MLA, mla) -DO_ZPZZZ(MLS, mls) - -#undef DO_ZPZZZ +static gen_helper_gvec_5 * const mls_fns[4] = { + gen_helper_sve_mls_b, gen_helper_sve_mls_h, + gen_helper_sve_mls_s, gen_helper_sve_mls_d, +}; +TRANS_FEAT(MLS, aa64_sve, do_zpzzz_ool, a, mls_fns[a->esz]) /* *** SVE Index Generation Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-49-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 53 ++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 28 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(MLS, aa64_sve, do_zpzzz_ool, a, mls_fns[a->esz]) *** SVE Index Generation Group */ -static void do_index(DisasContext *s, int esz, int rd, +static bool do_index(DisasContext *s, int esz, int rd, TCGv_i64 start, TCGv_i64 incr) { - unsigned vsz = vec_full_reg_size(s); - TCGv_i32 desc = tcg_constant_i32(simd_desc(vsz, vsz, 0)); - TCGv_ptr t_zd = tcg_temp_new_ptr(); + unsigned vsz; + TCGv_i32 desc; + TCGv_ptr t_zd; + + if (!sve_access_check(s)) { + return true; + } + + vsz = vec_full_reg_size(s); + desc = tcg_constant_i32(simd_desc(vsz, vsz, 0)); + t_zd = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_zd, cpu_env, vec_full_reg_offset(s, rd)); if (esz == 3) { @@ -XXX,XX +XXX,XX @@ static void do_index(DisasContext *s, int esz, int rd, tcg_temp_free_i32(i32); } tcg_temp_free_ptr(t_zd); + return true; } static bool trans_INDEX_ii(DisasContext *s, arg_INDEX_ii *a) { - if (sve_access_check(s)) { - TCGv_i64 start = tcg_constant_i64(a->imm1); - TCGv_i64 incr = tcg_constant_i64(a->imm2); - do_index(s, a->esz, a->rd, start, incr); - } - return true; + TCGv_i64 start = tcg_constant_i64(a->imm1); + TCGv_i64 incr = tcg_constant_i64(a->imm2); + return do_index(s, a->esz, a->rd, start, incr); } static bool trans_INDEX_ir(DisasContext *s, arg_INDEX_ir *a) { - if (sve_access_check(s)) { - TCGv_i64 start = tcg_constant_i64(a->imm); - TCGv_i64 incr = cpu_reg(s, a->rm); - do_index(s, a->esz, a->rd, start, incr); - } - return true; + TCGv_i64 start = tcg_constant_i64(a->imm); + TCGv_i64 incr = cpu_reg(s, a->rm); + return do_index(s, a->esz, a->rd, start, incr); } static bool trans_INDEX_ri(DisasContext *s, arg_INDEX_ri *a) { - if (sve_access_check(s)) { - TCGv_i64 start = cpu_reg(s, a->rn); - TCGv_i64 incr = tcg_constant_i64(a->imm); - do_index(s, a->esz, a->rd, start, incr); - } - return true; + TCGv_i64 start = cpu_reg(s, a->rn); + TCGv_i64 incr = tcg_constant_i64(a->imm); + return do_index(s, a->esz, a->rd, start, incr); } static bool trans_INDEX_rr(DisasContext *s, arg_INDEX_rr *a) { - if (sve_access_check(s)) { - TCGv_i64 start = cpu_reg(s, a->rn); - TCGv_i64 incr = cpu_reg(s, a->rm); - do_index(s, a->esz, a->rd, start, incr); - } - return true; + TCGv_i64 start = cpu_reg(s, a->rn); + TCGv_i64 incr = cpu_reg(s, a->rm); + return do_index(s, a->esz, a->rd, start, incr); } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-50-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 35 ++++++++--------------------------- 1 file changed, 8 insertions(+), 27 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_index(DisasContext *s, int esz, int rd, return true; } -static bool trans_INDEX_ii(DisasContext *s, arg_INDEX_ii *a) -{ - TCGv_i64 start = tcg_constant_i64(a->imm1); - TCGv_i64 incr = tcg_constant_i64(a->imm2); - return do_index(s, a->esz, a->rd, start, incr); -} - -static bool trans_INDEX_ir(DisasContext *s, arg_INDEX_ir *a) -{ - TCGv_i64 start = tcg_constant_i64(a->imm); - TCGv_i64 incr = cpu_reg(s, a->rm); - return do_index(s, a->esz, a->rd, start, incr); -} - -static bool trans_INDEX_ri(DisasContext *s, arg_INDEX_ri *a) -{ - TCGv_i64 start = cpu_reg(s, a->rn); - TCGv_i64 incr = tcg_constant_i64(a->imm); - return do_index(s, a->esz, a->rd, start, incr); -} - -static bool trans_INDEX_rr(DisasContext *s, arg_INDEX_rr *a) -{ - TCGv_i64 start = cpu_reg(s, a->rn); - TCGv_i64 incr = cpu_reg(s, a->rm); - return do_index(s, a->esz, a->rd, start, incr); -} +TRANS_FEAT(INDEX_ii, aa64_sve, do_index, a->esz, a->rd, + tcg_constant_i64(a->imm1), tcg_constant_i64(a->imm2)) +TRANS_FEAT(INDEX_ir, aa64_sve, do_index, a->esz, a->rd, + tcg_constant_i64(a->imm), cpu_reg(s, a->rm)) +TRANS_FEAT(INDEX_ri, aa64_sve, do_index, a->esz, a->rd, + cpu_reg(s, a->rn), tcg_constant_i64(a->imm)) +TRANS_FEAT(INDEX_rr, aa64_sve, do_index, a->esz, a->rd, + cpu_reg(s, a->rn), cpu_reg(s, a->rm)) /* *** SVE Stack Allocation Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-51-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 23 ++++------------------- 1 file changed, 4 insertions(+), 19 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_adr(DisasContext *s, arg_rrri *a, gen_helper_gvec_3 *fn) return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, a->imm); } -static bool trans_ADR_p32(DisasContext *s, arg_rrri *a) -{ - return do_adr(s, a, gen_helper_sve_adr_p32); -} - -static bool trans_ADR_p64(DisasContext *s, arg_rrri *a) -{ - return do_adr(s, a, gen_helper_sve_adr_p64); -} - -static bool trans_ADR_s32(DisasContext *s, arg_rrri *a) -{ - return do_adr(s, a, gen_helper_sve_adr_s32); -} - -static bool trans_ADR_u32(DisasContext *s, arg_rrri *a) -{ - return do_adr(s, a, gen_helper_sve_adr_u32); -} +TRANS_FEAT(ADR_p32, aa64_sve, do_adr, a, gen_helper_sve_adr_p32) +TRANS_FEAT(ADR_p64, aa64_sve, do_adr, a, gen_helper_sve_adr_p64) +TRANS_FEAT(ADR_s32, aa64_sve, do_adr, a, gen_helper_sve_adr_s32) +TRANS_FEAT(ADR_u32, aa64_sve, do_adr, a, gen_helper_sve_adr_u32) /* *** SVE Integer Misc - Unpredicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-52-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag) return true; } -static bool trans_PTRUE(DisasContext *s, arg_PTRUE *a) -{ - return do_predset(s, a->esz, a->rd, a->pat, a->s); -} +TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s) -static bool trans_SETFFR(DisasContext *s, arg_SETFFR *a) -{ - /* Note pat == 31 is #all, to set all elements. */ - return do_predset(s, 0, FFR_PRED_NUM, 31, false); -} +/* Note pat == 31 is #all, to set all elements. */ +TRANS_FEAT(SETFFR, aa64_sve, do_predset, 0, FFR_PRED_NUM, 31, false) -static bool trans_PFALSE(DisasContext *s, arg_PFALSE *a) -{ - /* Note pat == 32 is #unimp, to set no elements. */ - return do_predset(s, 0, a->rd, 32, false); -} +/* Note pat == 32 is #unimp, to set no elements. */ +TRANS_FEAT(PFALSE, aa64_sve, do_predset, 0, a->rd, 32, false) static bool trans_RDFFR_p(DisasContext *s, arg_RDFFR_p *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-53-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_RDFFR_p(DisasContext *s, arg_RDFFR_p *a) return trans_AND_pppp(s, &alt_a); } -static bool trans_RDFFR(DisasContext *s, arg_RDFFR *a) -{ - return do_mov_p(s, a->rd, FFR_PRED_NUM); -} - -static bool trans_WRFFR(DisasContext *s, arg_WRFFR *a) -{ - return do_mov_p(s, FFR_PRED_NUM, a->rn); -} +TRANS_FEAT(RDFFR, aa64_sve, do_mov_p, a->rd, FFR_PRED_NUM) +TRANS_FEAT(WRFFR, aa64_sve, do_mov_p, FFR_PRED_NUM, a->rn) static bool do_pfirst_pnext(DisasContext *s, arg_rr_esz *a, void (*gen_fn)(TCGv_i32, TCGv_ptr, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-54-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_pfirst_pnext(DisasContext *s, arg_rr_esz *a, return true; } -static bool trans_PFIRST(DisasContext *s, arg_rr_esz *a) -{ - return do_pfirst_pnext(s, a, gen_helper_sve_pfirst); -} - -static bool trans_PNEXT(DisasContext *s, arg_rr_esz *a) -{ - return do_pfirst_pnext(s, a, gen_helper_sve_pnext); -} +TRANS_FEAT(PFIRST, aa64_sve, do_pfirst_pnext, a, gen_helper_sve_pfirst) +TRANS_FEAT(PNEXT, aa64_sve, do_pfirst_pnext, a, gen_helper_sve_pnext) /* *** SVE Element Count Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-55-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm) return true; } -static bool trans_EXT(DisasContext *s, arg_EXT *a) -{ - return do_EXT(s, a->rd, a->rn, a->rm, a->imm); -} - -static bool trans_EXT_sve2(DisasContext *s, arg_rri *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_EXT(s, a->rd, a->rn, (a->rn + 1) % 32, a->imm); -} +TRANS_FEAT(EXT, aa64_sve, do_EXT, a->rd, a->rn, a->rm, a->imm) +TRANS_FEAT(EXT_sve2, aa64_sve2, do_EXT, a->rd, a->rn, (a->rn + 1) % 32, a->imm) /* *** SVE Permute - Unpredicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-56-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 35 ++++++----------------------------- 1 file changed, 6 insertions(+), 29 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_perm_pred2(DisasContext *s, arg_rr_esz *a, bool high_odd, return true; } -static bool trans_ZIP1_p(DisasContext *s, arg_rrr_esz *a) -{ - return do_perm_pred3(s, a, 0, gen_helper_sve_zip_p); -} - -static bool trans_ZIP2_p(DisasContext *s, arg_rrr_esz *a) -{ - return do_perm_pred3(s, a, 1, gen_helper_sve_zip_p); -} - -static bool trans_UZP1_p(DisasContext *s, arg_rrr_esz *a) -{ - return do_perm_pred3(s, a, 0, gen_helper_sve_uzp_p); -} - -static bool trans_UZP2_p(DisasContext *s, arg_rrr_esz *a) -{ - return do_perm_pred3(s, a, 1, gen_helper_sve_uzp_p); -} - -static bool trans_TRN1_p(DisasContext *s, arg_rrr_esz *a) -{ - return do_perm_pred3(s, a, 0, gen_helper_sve_trn_p); -} - -static bool trans_TRN2_p(DisasContext *s, arg_rrr_esz *a) -{ - return do_perm_pred3(s, a, 1, gen_helper_sve_trn_p); -} +TRANS_FEAT(ZIP1_p, aa64_sve, do_perm_pred3, a, 0, gen_helper_sve_zip_p) +TRANS_FEAT(ZIP2_p, aa64_sve, do_perm_pred3, a, 1, gen_helper_sve_zip_p) +TRANS_FEAT(UZP1_p, aa64_sve, do_perm_pred3, a, 0, gen_helper_sve_uzp_p) +TRANS_FEAT(UZP2_p, aa64_sve, do_perm_pred3, a, 1, gen_helper_sve_uzp_p) +TRANS_FEAT(TRN1_p, aa64_sve, do_perm_pred3, a, 0, gen_helper_sve_trn_p) +TRANS_FEAT(TRN2_p, aa64_sve, do_perm_pred3, a, 1, gen_helper_sve_trn_p) static bool trans_REV_p(DisasContext *s, arg_rr_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-57-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UZP2_p, aa64_sve, do_perm_pred3, a, 1, gen_helper_sve_uzp_p) TRANS_FEAT(TRN1_p, aa64_sve, do_perm_pred3, a, 0, gen_helper_sve_trn_p) TRANS_FEAT(TRN2_p, aa64_sve, do_perm_pred3, a, 1, gen_helper_sve_trn_p) -static bool trans_REV_p(DisasContext *s, arg_rr_esz *a) -{ - return do_perm_pred2(s, a, 0, gen_helper_sve_rev_p); -} - -static bool trans_PUNPKLO(DisasContext *s, arg_PUNPKLO *a) -{ - return do_perm_pred2(s, a, 0, gen_helper_sve_punpk_p); -} - -static bool trans_PUNPKHI(DisasContext *s, arg_PUNPKHI *a) -{ - return do_perm_pred2(s, a, 1, gen_helper_sve_punpk_p); -} +TRANS_FEAT(REV_p, aa64_sve, do_perm_pred2, a, 0, gen_helper_sve_rev_p) +TRANS_FEAT(PUNPKLO, aa64_sve, do_perm_pred2, a, 0, gen_helper_sve_punpk_p) +TRANS_FEAT(PUNPKHI, aa64_sve, do_perm_pred2, a, 1, gen_helper_sve_punpk_p) /* *** SVE Permute - Interleaving Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is in line with how we treat uzp, and will eliminate the special case code during translation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-58-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 6 ++++-- target/arm/translate-sve.c | 12 ++++++------ 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_punpk_p)(void *vd, void *vn, uint32_t pred_desc) void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ intptr_t oprsz = simd_oprsz(desc); \ + intptr_t odd_ofs = simd_data(desc); \ intptr_t i, oprsz_2 = oprsz / 2; \ ARMVectorReg tmp_n, tmp_m; \ /* We produce output faster than we consume input. \ @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ vm = memcpy(&tmp_m, vm, oprsz_2); \ } \ for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \ - *(TYPE *)(vd + H(2 * i + 0)) = *(TYPE *)(vn + H(i)); \ - *(TYPE *)(vd + H(2 * i + sizeof(TYPE))) = *(TYPE *)(vm + H(i)); \ + *(TYPE *)(vd + H(2 * i + 0)) = *(TYPE *)(vn + odd_ofs + H(i)); \ + *(TYPE *)(vd + H(2 * i + sizeof(TYPE))) = \ + *(TYPE *)(vm + odd_ofs + H(i)); \ } \ if (sizeof(TYPE) == 16 && unlikely(oprsz & 16)) { \ memset(vd + oprsz - 16, 0, 16); \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zip(DisasContext *s, arg_rrr_esz *a, bool high) unsigned vsz = vec_full_reg_size(s); unsigned high_ofs = high ? vsz / 2 : 0; tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn) + high_ofs, - vec_full_reg_offset(s, a->rm) + high_ofs, - vsz, vsz, 0, fns[a->esz]); + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, high_ofs, fns[a->esz]); } return true; } @@ -XXX,XX +XXX,XX @@ static bool do_zip_q(DisasContext *s, arg_rrr_esz *a, bool high) unsigned vsz = vec_full_reg_size(s); unsigned high_ofs = high ? QEMU_ALIGN_DOWN(vsz, 32) / 2 : 0; tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn) + high_ofs, - vec_full_reg_offset(s, a->rm) + high_ofs, - vsz, vsz, 0, gen_helper_sve2_zip_q); + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, high_ofs, gen_helper_sve2_zip_q); } return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-59-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 25 +++++++------------------ 1 file changed, 7 insertions(+), 18 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zip(DisasContext *s, arg_rrr_esz *a, bool high) gen_helper_sve_zip_b, gen_helper_sve_zip_h, gen_helper_sve_zip_s, gen_helper_sve_zip_d, }; + unsigned vsz = vec_full_reg_size(s); + unsigned high_ofs = high ? vsz / 2 : 0; - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - unsigned high_ofs = high ? vsz / 2 : 0; - tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vsz, vsz, high_ofs, fns[a->esz]); - } - return true; + return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, high_ofs); } static bool trans_ZIP1_z(DisasContext *s, arg_rrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_ZIP2_z(DisasContext *s, arg_rrr_esz *a) static bool do_zip_q(DisasContext *s, arg_rrr_esz *a, bool high) { + unsigned vsz = vec_full_reg_size(s); + unsigned high_ofs = high ? QEMU_ALIGN_DOWN(vsz, 32) / 2 : 0; + if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - unsigned high_ofs = high ? QEMU_ALIGN_DOWN(vsz, 32) / 2 : 0; - tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vsz, vsz, high_ofs, gen_helper_sve2_zip_q); - } - return true; + return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_zip_q, a, high_ofs); } static bool trans_ZIP1_q(DisasContext *s, arg_rrr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Convert SVE translation functions using do_zip* to use TRANS_FEAT and gen_gvec_ool_arg_zzz. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-60-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 54 +++++++++----------------------------- 1 file changed, 13 insertions(+), 41 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(PUNPKHI, aa64_sve, do_perm_pred2, a, 1, gen_helper_sve_punpk_p) *** SVE Permute - Interleaving Group */ -static bool do_zip(DisasContext *s, arg_rrr_esz *a, bool high) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_sve_zip_b, gen_helper_sve_zip_h, - gen_helper_sve_zip_s, gen_helper_sve_zip_d, - }; - unsigned vsz = vec_full_reg_size(s); - unsigned high_ofs = high ? vsz / 2 : 0; +static gen_helper_gvec_3 * const zip_fns[4] = { + gen_helper_sve_zip_b, gen_helper_sve_zip_h, + gen_helper_sve_zip_s, gen_helper_sve_zip_d, +}; +TRANS_FEAT(ZIP1_z, aa64_sve, gen_gvec_ool_arg_zzz, + zip_fns[a->esz], a, 0) +TRANS_FEAT(ZIP2_z, aa64_sve, gen_gvec_ool_arg_zzz, + zip_fns[a->esz], a, vec_full_reg_size(s) / 2) - return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, high_ofs); -} - -static bool trans_ZIP1_z(DisasContext *s, arg_rrr_esz *a) -{ - return do_zip(s, a, false); -} - -static bool trans_ZIP2_z(DisasContext *s, arg_rrr_esz *a) -{ - return do_zip(s, a, true); -} - -static bool do_zip_q(DisasContext *s, arg_rrr_esz *a, bool high) -{ - unsigned vsz = vec_full_reg_size(s); - unsigned high_ofs = high ? QEMU_ALIGN_DOWN(vsz, 32) / 2 : 0; - - if (!dc_isar_feature(aa64_sve_f64mm, s)) { - return false; - } - return gen_gvec_ool_arg_zzz(s, gen_helper_sve2_zip_q, a, high_ofs); -} - -static bool trans_ZIP1_q(DisasContext *s, arg_rrr_esz *a) -{ - return do_zip_q(s, a, false); -} - -static bool trans_ZIP2_q(DisasContext *s, arg_rrr_esz *a) -{ - return do_zip_q(s, a, true); -} +TRANS_FEAT(ZIP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, + gen_helper_sve2_zip_q, a, 0) +TRANS_FEAT(ZIP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, + gen_helper_sve2_zip_q, a, + QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2) static gen_helper_gvec_3 * const uzp_fns[4] = { gen_helper_sve_uzp_b, gen_helper_sve_uzp_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-61-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_clast_vector(DisasContext *s, arg_rprr_esz *a, bool before) return true; } -static bool trans_CLASTA_z(DisasContext *s, arg_rprr_esz *a) -{ - return do_clast_vector(s, a, false); -} - -static bool trans_CLASTB_z(DisasContext *s, arg_rprr_esz *a) -{ - return do_clast_vector(s, a, true); -} +TRANS_FEAT(CLASTA_z, aa64_sve, do_clast_vector, a, false) +TRANS_FEAT(CLASTB_z, aa64_sve, do_clast_vector, a, true) /* Compute CLAST for a scalar. */ static void do_clast_scalar(DisasContext *s, int esz, int pg, int rm, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-62-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_clast_fp(DisasContext *s, arg_rpr_esz *a, bool before) return true; } -static bool trans_CLASTA_v(DisasContext *s, arg_rpr_esz *a) -{ - return do_clast_fp(s, a, false); -} - -static bool trans_CLASTB_v(DisasContext *s, arg_rpr_esz *a) -{ - return do_clast_fp(s, a, true); -} +TRANS_FEAT(CLASTA_v, aa64_sve, do_clast_fp, a, false) +TRANS_FEAT(CLASTB_v, aa64_sve, do_clast_fp, a, true) /* Compute CLAST for a Xreg. */ static bool do_clast_general(DisasContext *s, arg_rpr_esz *a, bool before) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-63-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_clast_general(DisasContext *s, arg_rpr_esz *a, bool before) return true; } -static bool trans_CLASTA_r(DisasContext *s, arg_rpr_esz *a) -{ - return do_clast_general(s, a, false); -} - -static bool trans_CLASTB_r(DisasContext *s, arg_rpr_esz *a) -{ - return do_clast_general(s, a, true); -} +TRANS_FEAT(CLASTA_r, aa64_sve, do_clast_general, a, false) +TRANS_FEAT(CLASTB_r, aa64_sve, do_clast_general, a, true) /* Compute LAST for a scalar. */ static TCGv_i64 do_last_scalar(DisasContext *s, int esz, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-64-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_last_fp(DisasContext *s, arg_rpr_esz *a, bool before) return true; } -static bool trans_LASTA_v(DisasContext *s, arg_rpr_esz *a) -{ - return do_last_fp(s, a, false); -} - -static bool trans_LASTB_v(DisasContext *s, arg_rpr_esz *a) -{ - return do_last_fp(s, a, true); -} +TRANS_FEAT(LASTA_v, aa64_sve, do_last_fp, a, false) +TRANS_FEAT(LASTB_v, aa64_sve, do_last_fp, a, true) /* Compute LAST for a Xreg. */ static bool do_last_general(DisasContext *s, arg_rpr_esz *a, bool before) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-65-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_last_general(DisasContext *s, arg_rpr_esz *a, bool before) return true; } -static bool trans_LASTA_r(DisasContext *s, arg_rpr_esz *a) -{ - return do_last_general(s, a, false); -} - -static bool trans_LASTB_r(DisasContext *s, arg_rpr_esz *a) -{ - return do_last_general(s, a, true); -} +TRANS_FEAT(LASTA_r, aa64_sve, do_last_general, a, false) +TRANS_FEAT(LASTB_r, aa64_sve, do_last_general, a, true) static bool trans_CPY_m_r(DisasContext *s, arg_rpr_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-66-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(REVH, aa64_sve, gen_gvec_ool_arg_zpz, revh_fns[a->esz], a, 0) TRANS_FEAT(REVW, aa64_sve, gen_gvec_ool_arg_zpz, a->esz == 3 ? gen_helper_sve_revw_d : NULL, a, 0) -static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a) -{ - return gen_gvec_ool_zzzp(s, gen_helper_sve_splice, - a->rd, a->rn, a->rm, a->pg, a->esz); -} +TRANS_FEAT(SPLICE, aa64_sve, gen_gvec_ool_arg_zpzz, + gen_helper_sve_splice, a, a->esz) -static bool trans_SPLICE_sve2(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return gen_gvec_ool_zzzp(s, gen_helper_sve_splice, - a->rd, a->rn, (a->rn + 1) % 32, a->pg, a->esz); -} +TRANS_FEAT(SPLICE_sve2, aa64_sve2, gen_gvec_ool_zzzp, gen_helper_sve_splice, + a->rd, a->rn, (a->rn + 1) % 32, a->pg, a->esz) /* *** SVE Integer Compare - Vectors Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-67-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_ppzz_flags(DisasContext *s, arg_rprr_esz *a, } #define DO_PPZZ(NAME, name) \ -static bool trans_##NAME##_ppzz(DisasContext *s, arg_rprr_esz *a) \ -{ \ - static gen_helper_gvec_flags_4 * const fns[4] = { \ - gen_helper_sve_##name##_ppzz_b, gen_helper_sve_##name##_ppzz_h, \ - gen_helper_sve_##name##_ppzz_s, gen_helper_sve_##name##_ppzz_d, \ - }; \ - return do_ppzz_flags(s, a, fns[a->esz]); \ -} + static gen_helper_gvec_flags_4 * const name##_ppzz_fns[4] = { \ + gen_helper_sve_##name##_ppzz_b, gen_helper_sve_##name##_ppzz_h, \ + gen_helper_sve_##name##_ppzz_s, gen_helper_sve_##name##_ppzz_d, \ + }; \ + TRANS_FEAT(NAME##_ppzz, aa64_sve, do_ppzz_flags, \ + a, name##_ppzz_fns[a->esz]) DO_PPZZ(CMPEQ, cmpeq) DO_PPZZ(CMPNE, cmpne) @@ -XXX,XX +XXX,XX @@ DO_PPZZ(CMPHS, cmphs) #undef DO_PPZZ #define DO_PPZW(NAME, name) \ -static bool trans_##NAME##_ppzw(DisasContext *s, arg_rprr_esz *a) \ -{ \ - static gen_helper_gvec_flags_4 * const fns[4] = { \ - gen_helper_sve_##name##_ppzw_b, gen_helper_sve_##name##_ppzw_h, \ - gen_helper_sve_##name##_ppzw_s, NULL \ - }; \ - return do_ppzz_flags(s, a, fns[a->esz]); \ -} + static gen_helper_gvec_flags_4 * const name##_ppzw_fns[4] = { \ + gen_helper_sve_##name##_ppzw_b, gen_helper_sve_##name##_ppzw_h, \ + gen_helper_sve_##name##_ppzw_s, NULL \ + }; \ + TRANS_FEAT(NAME##_ppzw, aa64_sve, do_ppzz_flags, \ + a, name##_ppzw_fns[a->esz]) DO_PPZW(CMPEQ, cmpeq) DO_PPZW(CMPNE, cmpne) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-68-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 28 ++++++++-------------------- 1 file changed, 8 insertions(+), 20 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_NARROW(SUBHNT, subhnt) DO_SVE2_ZZZ_NARROW(RSUBHNB, rsubhnb) DO_SVE2_ZZZ_NARROW(RSUBHNT, rsubhnt) -static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a, - gen_helper_gvec_flags_4 *fn) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_ppzz_flags(s, a, fn); -} +static gen_helper_gvec_flags_4 * const match_fns[4] = { + gen_helper_sve2_match_ppzz_b, gen_helper_sve2_match_ppzz_h, NULL, NULL +}; +TRANS_FEAT(MATCH, aa64_sve2, do_ppzz_flags, a, match_fns[a->esz]) -#define DO_SVE2_PPZZ_MATCH(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ -{ \ - static gen_helper_gvec_flags_4 * const fns[4] = { \ - gen_helper_sve2_##name##_ppzz_b, gen_helper_sve2_##name##_ppzz_h, \ - NULL, NULL \ - }; \ - return do_sve2_ppzz_flags(s, a, fns[a->esz]); \ -} - -DO_SVE2_PPZZ_MATCH(MATCH, match) -DO_SVE2_PPZZ_MATCH(NMATCH, nmatch) +static gen_helper_gvec_flags_4 * const nmatch_fns[4] = { + gen_helper_sve2_nmatch_ppzz_b, gen_helper_sve2_nmatch_ppzz_h, NULL, NULL +}; +TRANS_FEAT(NMATCH, aa64_sve2, do_ppzz_flags, a, nmatch_fns[a->esz]) static gen_helper_gvec_4 * const histcnt_fns[4] = { NULL, NULL, gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-69-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_ppzi_flags(DisasContext *s, arg_rpri_esz *a, } #define DO_PPZI(NAME, name) \ -static bool trans_##NAME##_ppzi(DisasContext *s, arg_rpri_esz *a) \ -{ \ - static gen_helper_gvec_flags_3 * const fns[4] = { \ + static gen_helper_gvec_flags_3 * const name##_ppzi_fns[4] = { \ gen_helper_sve_##name##_ppzi_b, gen_helper_sve_##name##_ppzi_h, \ gen_helper_sve_##name##_ppzi_s, gen_helper_sve_##name##_ppzi_d, \ }; \ - return do_ppzi_flags(s, a, fns[a->esz]); \ -} + TRANS_FEAT(NAME##_ppzi, aa64_sve, do_ppzi_flags, a, \ + name##_ppzi_fns[a->esz]) DO_PPZI(CMPEQ, cmpeq) DO_PPZI(CMPNE, cmpne) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-70-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 45 ++++++++++++-------------------------- 1 file changed, 14 insertions(+), 31 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_brk2(DisasContext *s, arg_rpr_s *a, return true; } -static bool trans_BRKPA(DisasContext *s, arg_rprr_s *a) -{ - return do_brk3(s, a, gen_helper_sve_brkpa, gen_helper_sve_brkpas); -} +TRANS_FEAT(BRKPA, aa64_sve, do_brk3, a, + gen_helper_sve_brkpa, gen_helper_sve_brkpas) +TRANS_FEAT(BRKPB, aa64_sve, do_brk3, a, + gen_helper_sve_brkpb, gen_helper_sve_brkpbs) -static bool trans_BRKPB(DisasContext *s, arg_rprr_s *a) -{ - return do_brk3(s, a, gen_helper_sve_brkpb, gen_helper_sve_brkpbs); -} +TRANS_FEAT(BRKA_m, aa64_sve, do_brk2, a, + gen_helper_sve_brka_m, gen_helper_sve_brkas_m) +TRANS_FEAT(BRKB_m, aa64_sve, do_brk2, a, + gen_helper_sve_brkb_m, gen_helper_sve_brkbs_m) -static bool trans_BRKA_m(DisasContext *s, arg_rpr_s *a) -{ - return do_brk2(s, a, gen_helper_sve_brka_m, gen_helper_sve_brkas_m); -} +TRANS_FEAT(BRKA_z, aa64_sve, do_brk2, a, + gen_helper_sve_brka_z, gen_helper_sve_brkas_z) +TRANS_FEAT(BRKB_z, aa64_sve, do_brk2, a, + gen_helper_sve_brkb_z, gen_helper_sve_brkbs_z) -static bool trans_BRKB_m(DisasContext *s, arg_rpr_s *a) -{ - return do_brk2(s, a, gen_helper_sve_brkb_m, gen_helper_sve_brkbs_m); -} - -static bool trans_BRKA_z(DisasContext *s, arg_rpr_s *a) -{ - return do_brk2(s, a, gen_helper_sve_brka_z, gen_helper_sve_brkas_z); -} - -static bool trans_BRKB_z(DisasContext *s, arg_rpr_s *a) -{ - return do_brk2(s, a, gen_helper_sve_brkb_z, gen_helper_sve_brkbs_z); -} - -static bool trans_BRKN(DisasContext *s, arg_rpr_s *a) -{ - return do_brk2(s, a, gen_helper_sve_brkn, gen_helper_sve_brkns); -} +TRANS_FEAT(BRKN, aa64_sve, do_brk2, a, + gen_helper_sve_brkn, gen_helper_sve_brkns) /* *** SVE Predicate Count Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-71-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SUBR_zzi(DisasContext *s, arg_rri_esz *a) return true; } -static bool trans_MUL_zzi(DisasContext *s, arg_rri_esz *a) -{ - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_muli(a->esz, vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), a->imm, vsz, vsz); - } - return true; -} +TRANS_FEAT(MUL_zzi, aa64_sve, gen_gvec_fn_arg_zzi, tcg_gen_gvec_muli, a) static bool do_zzi_sat(DisasContext *s, arg_rri_esz *a, bool u, bool d) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Remove the unparsed extraction in trans_DUP_i, which is intended to reject an 8-bit shift of an 8-bit constant for 8-bit element. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-72-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 5 ++++- target/arm/translate-sve.c | 10 ++++++---- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 FDUP 00100101 esz:2 111 00 1110 imm:8 rd:5 # SVE broadcast integer immediate (unpredicated) -DUP_i 00100101 esz:2 111 00 011 . ........ rd:5 imm=%sh8_i8s +{ + INVALID 00100101 00 111 00 011 1 -------- ----- + DUP_i 00100101 esz:2 111 00 011 . ........ rd:5 imm=%sh8_i8s +} # SVE integer add/subtract immediate (unpredicated) ADD_zzi 00100101 .. 100 000 11 . ........ ..... @rdn_sh_i8u diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ const uint64_t pred_esz_masks[4] = { 0x1111111111111111ull, 0x0101010101010101ull }; +static bool trans_INVALID(DisasContext *s, arg_INVALID *a) +{ + unallocated_encoding(s); + return true; +} + /* *** SVE Logical - Unpredicated Group */ @@ -XXX,XX +XXX,XX @@ static bool trans_FDUP(DisasContext *s, arg_FDUP *a) static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a) { - if (a->esz == 0 && extract32(s->insn, 13, 1)) { - return false; - } if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); int dofs = vec_full_reg_offset(s, a->rd); - tcg_gen_gvec_dup_imm(a->esz, dofs, vsz, vsz, a->imm); } return true; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Remove the unparsed extractions in trans_ADD_zzi, trans_SUBR_zzi, and do_zzi_sat which are intended to reject an 8-bit shift of an 8-bit constant for 8-bit element. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-73-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 35 ++++++++++++++++++++++++++++------- target/arm/translate-sve.c | 9 --------- 2 files changed, 28 insertions(+), 16 deletions(-) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FDUP 00100101 esz:2 111 00 1110 imm:8 rd:5 } # SVE integer add/subtract immediate (unpredicated) -ADD_zzi 00100101 .. 100 000 11 . ........ ..... @rdn_sh_i8u -SUB_zzi 00100101 .. 100 001 11 . ........ ..... @rdn_sh_i8u -SUBR_zzi 00100101 .. 100 011 11 . ........ ..... @rdn_sh_i8u -SQADD_zzi 00100101 .. 100 100 11 . ........ ..... @rdn_sh_i8u -UQADD_zzi 00100101 .. 100 101 11 . ........ ..... @rdn_sh_i8u -SQSUB_zzi 00100101 .. 100 110 11 . ........ ..... @rdn_sh_i8u -UQSUB_zzi 00100101 .. 100 111 11 . ........ ..... @rdn_sh_i8u +{ + INVALID 00100101 00 100 000 11 1 -------- ----- + ADD_zzi 00100101 .. 100 000 11 . ........ ..... @rdn_sh_i8u +} +{ + INVALID 00100101 00 100 001 11 1 -------- ----- + SUB_zzi 00100101 .. 100 001 11 . ........ ..... @rdn_sh_i8u +} +{ + INVALID 00100101 00 100 011 11 1 -------- ----- + SUBR_zzi 00100101 .. 100 011 11 . ........ ..... @rdn_sh_i8u +} +{ + INVALID 00100101 00 100 100 11 1 -------- ----- + SQADD_zzi 00100101 .. 100 100 11 . ........ ..... @rdn_sh_i8u +} +{ + INVALID 00100101 00 100 101 11 1 -------- ----- + UQADD_zzi 00100101 .. 100 101 11 . ........ ..... @rdn_sh_i8u +} +{ + INVALID 00100101 00 100 110 11 1 -------- ----- + SQSUB_zzi 00100101 .. 100 110 11 . ........ ..... @rdn_sh_i8u +} +{ + INVALID 00100101 00 100 111 11 1 -------- ----- + UQSUB_zzi 00100101 .. 100 111 11 . ........ ..... @rdn_sh_i8u +} # SVE integer min/max immediate (unpredicated) SMAX_zzi 00100101 .. 101 000 110 ........ ..... @rdn_i8s diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a) static bool trans_ADD_zzi(DisasContext *s, arg_rri_esz *a) { - if (a->esz == 0 && extract32(s->insn, 13, 1)) { - return false; - } return gen_gvec_fn_arg_zzi(s, tcg_gen_gvec_addi, a); } @@ -XXX,XX +XXX,XX @@ static bool trans_SUBR_zzi(DisasContext *s, arg_rri_esz *a) .scalar_first = true } }; - if (a->esz == 0 && extract32(s->insn, 13, 1)) { - return false; - } if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); tcg_gen_gvec_2s(vec_full_reg_offset(s, a->rd), @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(MUL_zzi, aa64_sve, gen_gvec_fn_arg_zzi, tcg_gen_gvec_muli, a) static bool do_zzi_sat(DisasContext *s, arg_rri_esz *a, bool u, bool d) { - if (a->esz == 0 && extract32(s->insn, 13, 1)) { - return false; - } if (sve_access_check(s)) { do_sat_addsub_vec(s, a->esz, a->rd, a->rn, tcg_constant_i64(a->imm), u, d); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Remove the unparsed extractions in trans_CPY_{m,z}_i which are intended to reject an 8-bit shift of an 8-bit constant for 8-bit element. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-74-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 10 ++++++++-- target/arm/translate-sve.c | 6 ------ 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ DUPM 00000101 11 0000 dbm:13 rd:5 FCPY 00000101 .. 01 .... 110 imm:8 ..... @rdn_pg4 # SVE copy integer immediate (predicated) -CPY_m_i 00000101 .. 01 .... 01 . ........ ..... @rdn_pg4 imm=%sh8_i8s -CPY_z_i 00000101 .. 01 .... 00 . ........ ..... @rdn_pg4 imm=%sh8_i8s +{ + INVALID 00000101 00 01 ---- 01 1 -------- ----- + CPY_m_i 00000101 .. 01 .... 01 . ........ ..... @rdn_pg4 imm=%sh8_i8s +} +{ + INVALID 00000101 00 01 ---- 00 1 -------- ----- + CPY_z_i 00000101 .. 01 .... 00 . ........ ..... @rdn_pg4 imm=%sh8_i8s +} ### SVE Permute - Extract Group diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCPY(DisasContext *s, arg_FCPY *a) static bool trans_CPY_m_i(DisasContext *s, arg_rpri_esz *a) { - if (a->esz == 0 && extract32(s->insn, 13, 1)) { - return false; - } if (sve_access_check(s)) { do_cpy_m(s, a->esz, a->rd, a->rn, a->pg, tcg_constant_i64(a->imm)); } @@ -XXX,XX +XXX,XX @@ static bool trans_CPY_z_i(DisasContext *s, arg_CPY_z_i *a) gen_helper_sve_cpy_z_s, gen_helper_sve_cpy_z_d, }; - if (a->esz == 0 && extract32(s->insn, 13, 1)) { - return false; - } if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); tcg_gen_gvec_2i_ool(vec_full_reg_offset(s, a->rd), -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-75-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a) return true; } -static bool trans_ADD_zzi(DisasContext *s, arg_rri_esz *a) -{ - return gen_gvec_fn_arg_zzi(s, tcg_gen_gvec_addi, a); -} +TRANS_FEAT(ADD_zzi, aa64_sve, gen_gvec_fn_arg_zzi, tcg_gen_gvec_addi, a) static bool trans_SUB_zzi(DisasContext *s, arg_rri_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-76-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 23 ++++------------------- 1 file changed, 4 insertions(+), 19 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zzi_sat(DisasContext *s, arg_rri_esz *a, bool u, bool d) return true; } -static bool trans_SQADD_zzi(DisasContext *s, arg_rri_esz *a) -{ - return do_zzi_sat(s, a, false, false); -} - -static bool trans_UQADD_zzi(DisasContext *s, arg_rri_esz *a) -{ - return do_zzi_sat(s, a, true, false); -} - -static bool trans_SQSUB_zzi(DisasContext *s, arg_rri_esz *a) -{ - return do_zzi_sat(s, a, false, true); -} - -static bool trans_UQSUB_zzi(DisasContext *s, arg_rri_esz *a) -{ - return do_zzi_sat(s, a, true, true); -} +TRANS_FEAT(SQADD_zzi, aa64_sve, do_zzi_sat, a, false, false) +TRANS_FEAT(UQADD_zzi, aa64_sve, do_zzi_sat, a, true, false) +TRANS_FEAT(SQSUB_zzi, aa64_sve, do_zzi_sat, a, false, true) +TRANS_FEAT(UQSUB_zzi, aa64_sve, do_zzi_sat, a, true, true) static bool do_zzi_ool(DisasContext *s, arg_rri_esz *a, gen_helper_gvec_2i *fn) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-77-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zzi_ool(DisasContext *s, arg_rri_esz *a, gen_helper_gvec_2i *fn) } #define DO_ZZI(NAME, name) \ -static bool trans_##NAME##_zzi(DisasContext *s, arg_rri_esz *a) \ -{ \ - static gen_helper_gvec_2i * const fns[4] = { \ + static gen_helper_gvec_2i * const name##i_fns[4] = { \ gen_helper_sve_##name##i_b, gen_helper_sve_##name##i_h, \ gen_helper_sve_##name##i_s, gen_helper_sve_##name##i_d, \ }; \ - return do_zzi_ool(s, a, fns[a->esz]); \ -} + TRANS_FEAT(NAME##_zzi, aa64_sve, do_zzi_ool, a, name##i_fns[a->esz]) DO_ZZI(SMAX, smax) DO_ZZI(UMAX, umax) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use these for the several varieties of floating-point multiply-add instructions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-78-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 140 ++++++++++++++----------------------- 1 file changed, 53 insertions(+), 87 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zzxz(DisasContext *s, gen_helper_gvec_4 *fn, return gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index); } +/* Invoke an out-of-line helper on 4 Zregs, plus a pointer. */ +static bool gen_gvec_ptr_zzzz(DisasContext *s, gen_helper_gvec_4_ptr *fn, + int rd, int rn, int rm, int ra, + int data, TCGv_ptr ptr) +{ + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + ptr, vsz, vsz, data, fn); + } + return true; +} + +static bool gen_gvec_fpst_zzzz(DisasContext *s, gen_helper_gvec_4_ptr *fn, + int rd, int rn, int rm, int ra, + int data, ARMFPStatusFlavour flavour) +{ + TCGv_ptr status = fpstatus_ptr(flavour); + bool ret = gen_gvec_ptr_zzzz(s, fn, rd, rn, rm, ra, data, status); + tcg_temp_free_ptr(status); + return ret; +} + /* Invoke an out-of-line helper on 2 Zregs and a predicate. */ static bool gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int pg, int data) @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR_ROT(CDOT_zzxw_d, gen_helper_sve2_cdot_idx_d) static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub) { - static gen_helper_gvec_4_ptr * const fns[3] = { + static gen_helper_gvec_4_ptr * const fns[4] = { + NULL, gen_helper_gvec_fmla_idx_h, gen_helper_gvec_fmla_idx_s, gen_helper_gvec_fmla_idx_d, }; - - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - status, vsz, vsz, (a->index << 1) | sub, - fns[a->esz - 1]); - tcg_temp_free_ptr(status); - } - return true; + return gen_gvec_fpst_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, + (a->index << 1) | sub, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); } static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a) static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a) { - static gen_helper_gvec_4_ptr * const fns[2] = { + static gen_helper_gvec_4_ptr * const fns[4] = { + NULL, gen_helper_gvec_fcmlah_idx, gen_helper_gvec_fcmlas_idx, + NULL, }; - tcg_debug_assert(a->esz == 1 || a->esz == 2); tcg_debug_assert(a->rd == a->ra); - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - status, vsz, vsz, - a->index * 4 + a->rot, - fns[a->esz - 1]); - tcg_temp_free_ptr(status); - } - return true; + + return gen_gvec_fpst_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, + a->index * 4 + a->rot, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); } /* @@ -XXX,XX +XXX,XX @@ static bool trans_FMMLA(DisasContext *s, arg_rrrr_esz *a) return false; } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(FPST_FPCR); - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - status, vsz, vsz, 0, fn); - tcg_temp_free_ptr(status); - } - return true; + return gen_gvec_fpst_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR); } static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { @@ -XXX,XX +XXX,XX @@ static bool do_FMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sub, bool sel) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - cpu_env, vsz, vsz, (sel << 1) | sub, - gen_helper_sve2_fmlal_zzzw_s); - } - return true; + return gen_gvec_ptr_zzzz(s, gen_helper_sve2_fmlal_zzzw_s, + a->rd, a->rn, a->rm, a->ra, + (sel << 1) | sub, cpu_env); } static bool trans_FMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel) if (!dc_isar_feature(aa64_sve2, s)) { return false; } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - cpu_env, vsz, vsz, - (a->index << 2) | (sel << 1) | sub, - gen_helper_sve2_fmlal_zzxw_s); - } - return true; + return gen_gvec_ptr_zzzz(s, gen_helper_sve2_fmlal_zzxw_s, + a->rd, a->rn, a->rm, a->ra, + (a->index << 2) | (sel << 1) | sub, cpu_env); } static bool trans_FMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) if (!dc_isar_feature(aa64_sve_bf16, s)) { return false; } - if (sve_access_check(s)) { - TCGv_ptr status = fpstatus_ptr(FPST_FPCR); - unsigned vsz = vec_full_reg_size(s); - - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - status, vsz, vsz, sel, - gen_helper_gvec_bfmlal); - tcg_temp_free_ptr(status); - } - return true; + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlal, + a->rd, a->rn, a->rm, a->ra, sel, FPST_FPCR); } static bool trans_BFMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) if (!dc_isar_feature(aa64_sve_bf16, s)) { return false; } - if (sve_access_check(s)) { - TCGv_ptr status = fpstatus_ptr(FPST_FPCR); - unsigned vsz = vec_full_reg_size(s); - - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - vec_full_reg_offset(s, a->ra), - status, vsz, vsz, (a->index << 1) | sel, - gen_helper_gvec_bfmlal_idx); - tcg_temp_free_ptr(status); - } - return true; + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlal_idx, + a->rd, a->rn, a->rm, a->ra, + (a->index << 1) | sel, FPST_FPCR); } static bool trans_BFMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Being able to specify the feature predicate in TRANS_FEAT makes it easier to split trans_FMMLA by element size, which also happens to simplify the decode. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-79-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 7 +++---- target/arm/translate-sve.c | 27 ++++----------------------- 2 files changed, 7 insertions(+), 27 deletions(-) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm ### SVE2 floating point matrix multiply accumulate -{ - BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 - FMMLA 01100100 .. 1 ..... 111 001 ..... ..... @rda_rn_rm -} +BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 +FMMLA_s 01100100 10 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 +FMMLA_d 01100100 11 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 ### SVE2 Memory Gather Load Group diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ_FP(FMINP, fminp) * SVE Integer Multiply-Add (unpredicated) */ -static bool trans_FMMLA(DisasContext *s, arg_rrrr_esz *a) -{ - gen_helper_gvec_4_ptr *fn; - - switch (a->esz) { - case MO_32: - if (!dc_isar_feature(aa64_sve_f32mm, s)) { - return false; - } - fn = gen_helper_fmmla_s; - break; - case MO_64: - if (!dc_isar_feature(aa64_sve_f64mm, s)) { - return false; - } - fn = gen_helper_fmmla_d; - break; - default: - return false; - } - - return gen_gvec_fpst_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR); -} +TRANS_FEAT(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_s, + a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) +TRANS_FEAT(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_d, + a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { NULL, gen_helper_sve2_sqdmlal_zzzw_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Combined with the check already present in gen_mov_p, we can simplify some special cases in trans_AND_pppp and trans_BIC_pppp. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-80-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_dupi_z(DisasContext *s, int rd, uint64_t word) } /* Invoke a vector expander on three Pregs. */ -static void gen_gvec_fn_ppp(DisasContext *s, GVecGen3Fn *gvec_fn, +static bool gen_gvec_fn_ppp(DisasContext *s, GVecGen3Fn *gvec_fn, int rd, int rn, int rm) { - unsigned psz = pred_gvec_reg_size(s); - gvec_fn(MO_64, pred_full_reg_offset(s, rd), - pred_full_reg_offset(s, rn), - pred_full_reg_offset(s, rm), psz, psz); + if (sve_access_check(s)) { + unsigned psz = pred_gvec_reg_size(s); + gvec_fn(MO_64, pred_full_reg_offset(s, rd), + pred_full_reg_offset(s, rn), + pred_full_reg_offset(s, rm), psz, psz); + } + return true; } /* Invoke a vector move on two Pregs. */ @@ -XXX,XX +XXX,XX @@ static bool trans_AND_pppp(DisasContext *s, arg_rprr_s *a) }; if (!a->s) { - if (!sve_access_check(s)) { - return true; - } if (a->rn == a->rm) { if (a->pg == a->rn) { - do_mov_p(s, a->rd, a->rn); - } else { - gen_gvec_fn_ppp(s, tcg_gen_gvec_and, a->rd, a->rn, a->pg); + return do_mov_p(s, a->rd, a->rn); } - return true; + return gen_gvec_fn_ppp(s, tcg_gen_gvec_and, a->rd, a->rn, a->pg); } else if (a->pg == a->rn || a->pg == a->rm) { - gen_gvec_fn_ppp(s, tcg_gen_gvec_and, a->rd, a->rn, a->rm); - return true; + return gen_gvec_fn_ppp(s, tcg_gen_gvec_and, a->rd, a->rn, a->rm); } } return do_pppp_flags(s, a, &op); @@ -XXX,XX +XXX,XX @@ static bool trans_BIC_pppp(DisasContext *s, arg_rprr_s *a) }; if (!a->s && a->pg == a->rn) { - if (sve_access_check(s)) { - gen_gvec_fn_ppp(s, tcg_gen_gvec_andc, a->rd, a->rn, a->rm); - } - return true; + return gen_gvec_fn_ppp(s, tcg_gen_gvec_andc, a->rd, a->rn, a->rm); } return do_pppp_flags(s, a, &op); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This alias is defined on EOR (prediates). While the same operation could be performed with NAND or NOR, only bother with the official alias. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-81-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_EOR_pppp(DisasContext *s, arg_rprr_s *a) .fno = gen_helper_sve_eor_pppp, .prefer_i64 = TCG_TARGET_REG_BITS == 64, }; + + /* Alias NOT (predicate) is EOR Pd.B, Pg/Z, Pn.B, Pg.B */ + if (!a->s && a->pg == a->rm) { + return gen_gvec_fn_ppp(s, tcg_gen_gvec_andc, a->rd, a->pg, a->rn); + } return do_pppp_flags(s, a, &op); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-82-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_4 * const udiv_fns[4] = { }; TRANS_FEAT(UDIV_zpzz, aa64_sve, gen_gvec_ool_arg_zpzz, udiv_fns[a->esz], a, 0) -static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a) -{ - return do_sel_z(s, a->rd, a->rn, a->rm, a->pg, a->esz); -} +TRANS_FEAT(SEL_zpzz, aa64_sve, do_sel_z, a->rd, a->rn, a->rm, a->pg, a->esz) /* *** SVE Integer Arithmetic - Unary Predicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-83-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PRF_rr(DisasContext *s, arg_PRF_rr *a) * In the meantime, just emit the moves. */ -static bool trans_MOVPRFX(DisasContext *s, arg_MOVPRFX *a) -{ - return do_mov_z(s, a->rd, a->rn); -} - -static bool trans_MOVPRFX_m(DisasContext *s, arg_rpr_esz *a) -{ - return do_sel_z(s, a->rd, a->rn, a->rd, a->pg, a->esz); -} - -static bool trans_MOVPRFX_z(DisasContext *s, arg_rpr_esz *a) -{ - return do_movz_zpz(s, a->rd, a->rn, a->pg, a->esz, false); -} +TRANS_FEAT(MOVPRFX, aa64_sve, do_mov_z, a->rd, a->rn) +TRANS_FEAT(MOVPRFX_m, aa64_sve, do_sel_z, a->rd, a->rn, a->rd, a->pg, a->esz) +TRANS_FEAT(MOVPRFX_z, aa64_sve, do_movz_zpz, a->rd, a->rn, a->pg, a->esz, false) /* * SVE2 Integer Multiply - Unpredicated -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-84-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub) a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); } -static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) -{ - return do_FMLA_zzxz(s, a, false); -} - -static bool trans_FMLS_zzxz(DisasContext *s, arg_FMLA_zzxz *a) -{ - return do_FMLA_zzxz(s, a, true); -} +TRANS_FEAT(FMLA_zzxz, aa64_sve, do_FMLA_zzxz, a, false) +TRANS_FEAT(FMLS_zzxz, aa64_sve, do_FMLA_zzxz, a, true) /* *** SVE Floating Point Multiply Indexed Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-85-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 28 ++++------------------------ 1 file changed, 4 insertions(+), 24 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) { - if (!dc_isar_feature(aa64_sve_bf16, s)) { - return false; - } return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlal, a->rd, a->rn, a->rm, a->ra, sel, FPST_FPCR); } -static bool trans_BFMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_BFMLAL_zzzw(s, a, false); -} - -static bool trans_BFMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) -{ - return do_BFMLAL_zzzw(s, a, true); -} +TRANS_FEAT(BFMLALB_zzzw, aa64_sve_bf16, do_BFMLAL_zzzw, a, false) +TRANS_FEAT(BFMLALT_zzzw, aa64_sve_bf16, do_BFMLAL_zzzw, a, true) static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) { - if (!dc_isar_feature(aa64_sve_bf16, s)) { - return false; - } return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlal_idx, a->rd, a->rn, a->rm, a->ra, (a->index << 1) | sel, FPST_FPCR); } -static bool trans_BFMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a) -{ - return do_BFMLAL_zzxw(s, a, false); -} - -static bool trans_BFMLALT_zzxw(DisasContext *s, arg_rrxr_esz *a) -{ - return do_BFMLAL_zzxw(s, a, true); -} +TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false) +TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Rename the function to match gen_gvec_ool_arg_zzz, and move to be adjacent. Split out gen_gvec_fpst_zzz as a helper while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-86-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 50 +++++++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 20 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zzz(DisasContext *s, gen_helper_gvec_3 *fn, return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, data); } +/* Invoke an out-of-line helper on 3 Zregs, plus float_status. */ +static bool gen_gvec_fpst_zzz(DisasContext *s, gen_helper_gvec_3_ptr *fn, + int rd, int rn, int rm, + int data, ARMFPStatusFlavour flavour) +{ + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = fpstatus_ptr(flavour); + + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + status, vsz, vsz, data, fn); + + tcg_temp_free_ptr(status); + } + return true; +} + +static bool gen_gvec_fpst_arg_zzz(DisasContext *s, gen_helper_gvec_3_ptr *fn, + arg_rrr_esz *a, int data) +{ + return gen_gvec_fpst_zzz(s, fn, a->rd, a->rn, a->rm, data, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); +} + /* Invoke an out-of-line helper on 4 Zregs. */ static bool gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, int rd, int rn, int rm, int ra, int data) @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) *** SVE Floating Point Arithmetic - Unpredicated Group */ -static bool do_zzz_fp(DisasContext *s, arg_rrr_esz *a, - gen_helper_gvec_3_ptr *fn) -{ - if (fn == NULL) { - return false; - } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - status, vsz, vsz, 0, fn); - tcg_temp_free_ptr(status); - } - return true; -} - - #define DO_FP3(NAME, name) \ static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ { \ @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ NULL, gen_helper_gvec_##name##_h, \ gen_helper_gvec_##name##_s, gen_helper_gvec_##name##_d \ }; \ - return do_zzz_fp(s, a, fns[a->esz]); \ + return gen_gvec_fpst_arg_zzz(s, fns[a->esz], a, 0); \ } DO_FP3(FADD_zzz, fadd) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-87-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) */ #define DO_FP3(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ -{ \ - static gen_helper_gvec_3_ptr * const fns[4] = { \ + static gen_helper_gvec_3_ptr * const name##_fns[4] = { \ NULL, gen_helper_gvec_##name##_h, \ gen_helper_gvec_##name##_s, gen_helper_gvec_##name##_d \ }; \ - return gen_gvec_fpst_arg_zzz(s, fns[a->esz], a, 0); \ -} + TRANS_FEAT(NAME, aa64_sve, gen_gvec_fpst_arg_zzz, name##_fns[a->esz], a, 0) DO_FP3(FADD_zzz, fadd) DO_FP3(FSUB_zzz, fsub) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-88-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 26 +++++++------------------- 1 file changed, 7 insertions(+), 19 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLS_zzxz, aa64_sve, do_FMLA_zzxz, a, true) *** SVE Floating Point Multiply Indexed Group */ -static bool trans_FMUL_zzx(DisasContext *s, arg_FMUL_zzx *a) -{ - static gen_helper_gvec_3_ptr * const fns[3] = { - gen_helper_gvec_fmul_idx_h, - gen_helper_gvec_fmul_idx_s, - gen_helper_gvec_fmul_idx_d, - }; - - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - status, vsz, vsz, a->index, fns[a->esz - 1]); - tcg_temp_free_ptr(status); - } - return true; -} +static gen_helper_gvec_3_ptr * const fmul_idx_fns[4] = { + NULL, gen_helper_gvec_fmul_idx_h, + gen_helper_gvec_fmul_idx_s, gen_helper_gvec_fmul_idx_d, +}; +TRANS_FEAT(FMUL_zzx, aa64_sve, gen_gvec_fpst_zzz, + fmul_idx_fns[a->esz], a->rd, a->rn, a->rm, a->index, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) /* *** SVE Floating Point Fast Reduction Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-89-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_PPZ(FCMNE_ppz0, fcmne0) *** SVE floating-point trig multiply-add coefficient */ -static bool trans_FTMAD(DisasContext *s, arg_FTMAD *a) -{ - static gen_helper_gvec_3_ptr * const fns[3] = { - gen_helper_sve_ftmad_h, - gen_helper_sve_ftmad_s, - gen_helper_sve_ftmad_d, - }; - - if (a->esz == 0) { - return false; - } - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - vec_full_reg_offset(s, a->rm), - status, vsz, vsz, a->imm, fns[a->esz - 1]); - tcg_temp_free_ptr(status); - } - return true; -} +static gen_helper_gvec_3_ptr * const ftmad_fns[4] = { + NULL, gen_helper_sve_ftmad_h, + gen_helper_sve_ftmad_s, gen_helper_sve_ftmad_d, +}; +TRANS_FEAT(FTMAD, aa64_sve, gen_gvec_fpst_zzz, + ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) /* *** SVE Floating Point Accumulating Reduction Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-90-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMUL_zzx, aa64_sve, gen_gvec_fpst_zzz, typedef void gen_helper_fp_reduce(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); -static void do_reduce(DisasContext *s, arg_rpr_esz *a, +static bool do_reduce(DisasContext *s, arg_rpr_esz *a, gen_helper_fp_reduce *fn) { - unsigned vsz = vec_full_reg_size(s); - unsigned p2vsz = pow2ceil(vsz); - TCGv_i32 t_desc = tcg_constant_i32(simd_desc(vsz, vsz, p2vsz)); + unsigned vsz, p2vsz; + TCGv_i32 t_desc; TCGv_ptr t_zn, t_pg, status; TCGv_i64 temp; + if (fn == NULL) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vsz = vec_full_reg_size(s); + p2vsz = pow2ceil(vsz); + t_desc = tcg_constant_i32(simd_desc(vsz, vsz, p2vsz)); temp = tcg_temp_new_i64(); t_zn = tcg_temp_new_ptr(); t_pg = tcg_temp_new_ptr(); @@ -XXX,XX +XXX,XX @@ static void do_reduce(DisasContext *s, arg_rpr_esz *a, write_fp_dreg(s, a->rd, temp); tcg_temp_free_i64(temp); + return true; } #define DO_VPZ(NAME, name) \ static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a) \ { \ - static gen_helper_fp_reduce * const fns[3] = { \ - gen_helper_sve_##name##_h, \ + static gen_helper_fp_reduce * const fns[4] = { \ + NULL, gen_helper_sve_##name##_h, \ gen_helper_sve_##name##_s, \ gen_helper_sve_##name##_d, \ }; \ - if (a->esz == 0) { \ - return false; \ - } \ - if (sve_access_check(s)) { \ - do_reduce(s, a, fns[a->esz - 1]); \ - } \ - return true; \ + return do_reduce(s, a, fns[a->esz]); \ } DO_VPZ(FADDV, faddv) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-91-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_reduce(DisasContext *s, arg_rpr_esz *a, } #define DO_VPZ(NAME, name) \ -static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a) \ -{ \ - static gen_helper_fp_reduce * const fns[4] = { \ - NULL, gen_helper_sve_##name##_h, \ - gen_helper_sve_##name##_s, \ - gen_helper_sve_##name##_d, \ + static gen_helper_fp_reduce * const name##_fns[4] = { \ + NULL, gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, gen_helper_sve_##name##_d, \ }; \ - return do_reduce(s, a, fns[a->esz]); \ -} + TRANS_FEAT(NAME, aa64_sve, do_reduce, a, name##_fns[a->esz]) DO_VPZ(FADDV, faddv) DO_VPZ(FMINNMV, fminnmv) @@ -XXX,XX +XXX,XX @@ DO_VPZ(FMAXNMV, fmaxnmv) DO_VPZ(FMINV, fminv) DO_VPZ(FMAXV, fmaxv) +#undef DO_VPZ + /* *** SVE Floating Point Unary Operations - Unpredicated Group */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Rename do_zz_fp to gen_gvec_fpst_arg_zz, and move up. Split out gen_gvec_fpst_zz as a helper while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-92-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 77 ++++++++++++++++++-------------------- 1 file changed, 36 insertions(+), 41 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_zz(DisasContext *s, gen_helper_gvec_2 *fn, return true; } +static bool gen_gvec_fpst_zz(DisasContext *s, gen_helper_gvec_2_ptr *fn, + int rd, int rn, int data, + ARMFPStatusFlavour flavour) +{ + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = fpstatus_ptr(flavour); + + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + status, vsz, vsz, data, fn); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool gen_gvec_fpst_arg_zz(DisasContext *s, gen_helper_gvec_2_ptr *fn, + arg_rr_esz *a, int data) +{ + return gen_gvec_fpst_zz(s, fn, a->rd, a->rn, data, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); +} + /* Invoke an out-of-line helper on 3 Zregs. */ static bool gen_gvec_ool_zzz(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int rm, int data) @@ -XXX,XX +XXX,XX @@ DO_VPZ(FMAXV, fmaxv) *** SVE Floating Point Unary Operations - Unpredicated Group */ -static void do_zz_fp(DisasContext *s, arg_rr_esz *a, gen_helper_gvec_2_ptr *fn) -{ - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); +static gen_helper_gvec_2_ptr * const frecpe_fns[] = { + NULL, gen_helper_gvec_frecpe_h, + gen_helper_gvec_frecpe_s, gen_helper_gvec_frecpe_d, +}; +TRANS_FEAT(FRECPE, aa64_sve, gen_gvec_fpst_arg_zz, frecpe_fns[a->esz], a, 0) - tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - status, vsz, vsz, 0, fn); - tcg_temp_free_ptr(status); -} - -static bool trans_FRECPE(DisasContext *s, arg_rr_esz *a) -{ - static gen_helper_gvec_2_ptr * const fns[3] = { - gen_helper_gvec_frecpe_h, - gen_helper_gvec_frecpe_s, - gen_helper_gvec_frecpe_d, - }; - if (a->esz == 0) { - return false; - } - if (sve_access_check(s)) { - do_zz_fp(s, a, fns[a->esz - 1]); - } - return true; -} - -static bool trans_FRSQRTE(DisasContext *s, arg_rr_esz *a) -{ - static gen_helper_gvec_2_ptr * const fns[3] = { - gen_helper_gvec_frsqrte_h, - gen_helper_gvec_frsqrte_s, - gen_helper_gvec_frsqrte_d, - }; - if (a->esz == 0) { - return false; - } - if (sve_access_check(s)) { - do_zz_fp(s, a, fns[a->esz - 1]); - } - return true; -} +static gen_helper_gvec_2_ptr * const frsqrte_fns[] = { + NULL, gen_helper_gvec_frsqrte_h, + gen_helper_gvec_frsqrte_s, gen_helper_gvec_frsqrte_d, +}; +TRANS_FEAT(FRSQRTE, aa64_sve, gen_gvec_fpst_arg_zz, frsqrte_fns[a->esz], a, 0) /* *** SVE Floating Point Compare with Zero Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Simplify indexing of this array. This will allow folding of the illegal esz == 0 into the normal fn == NULL check. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-93-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTZU_dd(DisasContext *s, arg_rpr_esz *a) return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_dd); } -static gen_helper_gvec_3_ptr * const frint_fns[3] = { +static gen_helper_gvec_3_ptr * const frint_fns[] = { + NULL, gen_helper_sve_frint_h, gen_helper_sve_frint_s, gen_helper_sve_frint_d @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTI(DisasContext *s, arg_rpr_esz *a) return false; } return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, - frint_fns[a->esz - 1]); + frint_fns[a->esz]); } static bool trans_FRINTX(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTN(DisasContext *s, arg_rpr_esz *a) if (a->esz == 0) { return false; } - return do_frint_mode(s, a, float_round_nearest_even, frint_fns[a->esz - 1]); + return do_frint_mode(s, a, float_round_nearest_even, frint_fns[a->esz]); } static bool trans_FRINTP(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTP(DisasContext *s, arg_rpr_esz *a) if (a->esz == 0) { return false; } - return do_frint_mode(s, a, float_round_up, frint_fns[a->esz - 1]); + return do_frint_mode(s, a, float_round_up, frint_fns[a->esz]); } static bool trans_FRINTM(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTM(DisasContext *s, arg_rpr_esz *a) if (a->esz == 0) { return false; } - return do_frint_mode(s, a, float_round_down, frint_fns[a->esz - 1]); + return do_frint_mode(s, a, float_round_down, frint_fns[a->esz]); } static bool trans_FRINTZ(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTZ(DisasContext *s, arg_rpr_esz *a) if (a->esz == 0) { return false; } - return do_frint_mode(s, a, float_round_to_zero, frint_fns[a->esz - 1]); + return do_frint_mode(s, a, float_round_to_zero, frint_fns[a->esz]); } static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a) @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a) if (a->esz == 0) { return false; } - return do_frint_mode(s, a, float_round_ties_away, frint_fns[a->esz - 1]); + return do_frint_mode(s, a, float_round_ties_away, frint_fns[a->esz]); } static bool trans_FRECPX(DisasContext *s, arg_rpr_esz *a) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Rename the function to match other expansion function and move to be adjacent. Split out gen_gvec_fpst_zzp as a helper while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-94-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 392 ++++++++++++------------------------- 1 file changed, 129 insertions(+), 263 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_ool_arg_zpzi(DisasContext *s, gen_helper_gvec_3 *fn, return gen_gvec_ool_zzp(s, fn, a->rd, a->rn, a->pg, a->imm); } +static bool gen_gvec_fpst_zzp(DisasContext *s, gen_helper_gvec_3_ptr *fn, + int rd, int rn, int pg, int data, + ARMFPStatusFlavour flavour) +{ + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = fpstatus_ptr(flavour); + + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + pred_full_reg_offset(s, pg), + status, vsz, vsz, data, fn); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool gen_gvec_fpst_arg_zpz(DisasContext *s, gen_helper_gvec_3_ptr *fn, + arg_rpr_esz *a, int data, + ARMFPStatusFlavour flavour) +{ + return gen_gvec_fpst_zzp(s, fn, a->rd, a->rn, a->pg, data, flavour); +} + /* Invoke an out-of-line helper on 3 Zregs and a predicate. */ static bool gen_gvec_ool_zzzp(DisasContext *s, gen_helper_gvec_4 *fn, int rd, int rn, int rm, int pg, int data) @@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a) *** SVE Floating Point Unary Operations Predicated Group */ -static bool do_zpz_ptr(DisasContext *s, int rd, int rn, int pg, - bool is_fp16, gen_helper_gvec_3_ptr *fn) -{ - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - pred_full_reg_offset(s, pg), - status, vsz, vsz, 0, fn); - tcg_temp_free_ptr(status); - } - return true; -} +TRANS_FEAT(FCVT_sh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvt_sh, a, 0, FPST_FPCR) +TRANS_FEAT(FCVT_hs, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvt_hs, a, 0, FPST_FPCR) -static bool trans_FCVT_sh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_sh); -} +TRANS_FEAT(BFCVT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz, + gen_helper_sve_bfcvt, a, 0, FPST_FPCR) -static bool trans_FCVT_hs(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_hs); -} +TRANS_FEAT(FCVT_dh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvt_dh, a, 0, FPST_FPCR) +TRANS_FEAT(FCVT_hd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvt_hd, a, 0, FPST_FPCR) +TRANS_FEAT(FCVT_ds, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvt_ds, a, 0, FPST_FPCR) +TRANS_FEAT(FCVT_sd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvt_sd, a, 0, FPST_FPCR) -static bool trans_BFCVT(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_bf16, s)) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_bfcvt); -} +TRANS_FEAT(FCVTZS_hh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzs_hh, a, 0, FPST_FPCR_F16) +TRANS_FEAT(FCVTZU_hh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzu_hh, a, 0, FPST_FPCR_F16) +TRANS_FEAT(FCVTZS_hs, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzs_hs, a, 0, FPST_FPCR_F16) +TRANS_FEAT(FCVTZU_hs, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzu_hs, a, 0, FPST_FPCR_F16) +TRANS_FEAT(FCVTZS_hd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzs_hd, a, 0, FPST_FPCR_F16) +TRANS_FEAT(FCVTZU_hd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzu_hd, a, 0, FPST_FPCR_F16) -static bool trans_FCVT_dh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_dh); -} +TRANS_FEAT(FCVTZS_ss, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzs_ss, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTZU_ss, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzu_ss, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTZS_sd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzs_sd, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTZU_sd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzu_sd, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTZS_ds, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzs_ds, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTZU_ds, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzu_ds, a, 0, FPST_FPCR) -static bool trans_FCVT_hd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_hd); -} - -static bool trans_FCVT_ds(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_ds); -} - -static bool trans_FCVT_sd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_sd); -} - -static bool trans_FCVTZS_hh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzs_hh); -} - -static bool trans_FCVTZU_hh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzu_hh); -} - -static bool trans_FCVTZS_hs(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzs_hs); -} - -static bool trans_FCVTZU_hs(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzu_hs); -} - -static bool trans_FCVTZS_hd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzs_hd); -} - -static bool trans_FCVTZU_hd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzu_hd); -} - -static bool trans_FCVTZS_ss(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_ss); -} - -static bool trans_FCVTZU_ss(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_ss); -} - -static bool trans_FCVTZS_sd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_sd); -} - -static bool trans_FCVTZU_sd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_sd); -} - -static bool trans_FCVTZS_ds(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_ds); -} - -static bool trans_FCVTZU_ds(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_ds); -} - -static bool trans_FCVTZS_dd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_dd); -} - -static bool trans_FCVTZU_dd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_dd); -} +TRANS_FEAT(FCVTZS_dd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzs_dd, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTZU_dd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_fcvtzu_dd, a, 0, FPST_FPCR) static gen_helper_gvec_3_ptr * const frint_fns[] = { NULL, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const frint_fns[] = { gen_helper_sve_frint_s, gen_helper_sve_frint_d }; +TRANS_FEAT(FRINTI, aa64_sve, gen_gvec_fpst_arg_zpz, frint_fns[a->esz], + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) -static bool trans_FRINTI(DisasContext *s, arg_rpr_esz *a) -{ - if (a->esz == 0) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, - frint_fns[a->esz]); -} - -static bool trans_FRINTX(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3_ptr * const fns[3] = { - gen_helper_sve_frintx_h, - gen_helper_sve_frintx_s, - gen_helper_sve_frintx_d - }; - if (a->esz == 0) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, fns[a->esz - 1]); -} +static gen_helper_gvec_3_ptr * const frintx_fns[] = { + NULL, + gen_helper_sve_frintx_h, + gen_helper_sve_frintx_s, + gen_helper_sve_frintx_d +}; +TRANS_FEAT(FRINTX, aa64_sve, gen_gvec_fpst_arg_zpz, frintx_fns[a->esz], + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, int mode, gen_helper_gvec_3_ptr *fn) @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a) return do_frint_mode(s, a, float_round_ties_away, frint_fns[a->esz]); } -static bool trans_FRECPX(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3_ptr * const fns[3] = { - gen_helper_sve_frecpx_h, - gen_helper_sve_frecpx_s, - gen_helper_sve_frecpx_d - }; - if (a->esz == 0) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, fns[a->esz - 1]); -} +static gen_helper_gvec_3_ptr * const frecpx_fns[] = { + NULL, gen_helper_sve_frecpx_h, + gen_helper_sve_frecpx_s, gen_helper_sve_frecpx_d, +}; +TRANS_FEAT(FRECPX, aa64_sve, gen_gvec_fpst_arg_zpz, frecpx_fns[a->esz], + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) -static bool trans_FSQRT(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3_ptr * const fns[3] = { - gen_helper_sve_fsqrt_h, - gen_helper_sve_fsqrt_s, - gen_helper_sve_fsqrt_d - }; - if (a->esz == 0) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, fns[a->esz - 1]); -} +static gen_helper_gvec_3_ptr * const fsqrt_fns[] = { + NULL, gen_helper_sve_fsqrt_h, + gen_helper_sve_fsqrt_s, gen_helper_sve_fsqrt_d, +}; +TRANS_FEAT(FSQRT, aa64_sve, gen_gvec_fpst_arg_zpz, fsqrt_fns[a->esz], + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) -static bool trans_SCVTF_hh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_hh); -} +TRANS_FEAT(SCVTF_hh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_scvt_hh, a, 0, FPST_FPCR_F16) +TRANS_FEAT(SCVTF_sh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_scvt_sh, a, 0, FPST_FPCR_F16) +TRANS_FEAT(SCVTF_dh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_scvt_dh, a, 0, FPST_FPCR_F16) -static bool trans_SCVTF_sh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_sh); -} +TRANS_FEAT(SCVTF_ss, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_scvt_ss, a, 0, FPST_FPCR) +TRANS_FEAT(SCVTF_ds, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_scvt_ds, a, 0, FPST_FPCR) -static bool trans_SCVTF_dh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_dh); -} +TRANS_FEAT(SCVTF_sd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_scvt_sd, a, 0, FPST_FPCR) +TRANS_FEAT(SCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_scvt_dd, a, 0, FPST_FPCR) -static bool trans_SCVTF_ss(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_ss); -} +TRANS_FEAT(UCVTF_hh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_ucvt_hh, a, 0, FPST_FPCR_F16) +TRANS_FEAT(UCVTF_sh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_ucvt_sh, a, 0, FPST_FPCR_F16) +TRANS_FEAT(UCVTF_dh, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_ucvt_dh, a, 0, FPST_FPCR_F16) -static bool trans_SCVTF_ds(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_ds); -} +TRANS_FEAT(UCVTF_ss, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_ucvt_ss, a, 0, FPST_FPCR) +TRANS_FEAT(UCVTF_ds, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_ucvt_ds, a, 0, FPST_FPCR) +TRANS_FEAT(UCVTF_sd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_ucvt_sd, a, 0, FPST_FPCR) -static bool trans_SCVTF_sd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_sd); -} - -static bool trans_SCVTF_dd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_dd); -} - -static bool trans_UCVTF_hh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_hh); -} - -static bool trans_UCVTF_sh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_sh); -} - -static bool trans_UCVTF_dh(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_dh); -} - -static bool trans_UCVTF_ss(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_ss); -} - -static bool trans_UCVTF_ds(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_ds); -} - -static bool trans_UCVTF_sd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_sd); -} - -static bool trans_UCVTF_dd(DisasContext *s, arg_rpr_esz *a) -{ - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_dd); -} +TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, + gen_helper_sve_ucvt_dd, a, 0, FPST_FPCR) /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, TRANS_FEAT(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, gen_gvec_rax1, a) -static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_sh); -} +TRANS_FEAT(FCVTNT_sh, aa64_sve2, gen_gvec_fpst_arg_zpz, + gen_helper_sve2_fcvtnt_sh, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTNT_ds, aa64_sve2, gen_gvec_fpst_arg_zpz, + gen_helper_sve2_fcvtnt_ds, a, 0, FPST_FPCR) -static bool trans_BFCVTNT(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve_bf16, s)) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_bfcvtnt); -} +TRANS_FEAT(BFCVTNT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz, + gen_helper_sve_bfcvtnt, a, 0, FPST_FPCR) -static bool trans_FCVTNT_ds(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_ds); -} - -static bool trans_FCVTLT_hs(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtlt_hs); -} - -static bool trans_FCVTLT_sd(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtlt_sd); -} +TRANS_FEAT(FCVTLT_hs, aa64_sve2, gen_gvec_fpst_arg_zpz, + gen_helper_sve2_fcvtlt_hs, a, 0, FPST_FPCR) +TRANS_FEAT(FCVTLT_sd, aa64_sve2, gen_gvec_fpst_arg_zpz, + gen_helper_sve2_fcvtlt_sd, a, 0, FPST_FPCR) static bool trans_FCVTX_ds(DisasContext *s, arg_rpr_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-95-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 52 +++++++++++++++++--------------------- 1 file changed, 23 insertions(+), 29 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FRINTX, aa64_sve, gen_gvec_fpst_arg_zpz, frintx_fns[a->esz], static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, int mode, gen_helper_gvec_3_ptr *fn) { - if (sve_access_check(s)) { - unsigned vsz = vec_full_reg_size(s); - TCGv_i32 tmode = tcg_const_i32(mode); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + unsigned vsz; + TCGv_i32 tmode; + TCGv_ptr status; - gen_helper_set_rmode(tmode, tmode, status); - - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - pred_full_reg_offset(s, a->pg), - status, vsz, vsz, 0, fn); - - gen_helper_set_rmode(tmode, tmode, status); - tcg_temp_free_i32(tmode); - tcg_temp_free_ptr(status); + if (fn == NULL) { + return false; } + if (!sve_access_check(s)) { + return true; + } + + vsz = vec_full_reg_size(s); + tmode = tcg_const_i32(mode); + status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + + gen_helper_set_rmode(tmode, tmode, status); + + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, 0, fn); + + gen_helper_set_rmode(tmode, tmode, status); + tcg_temp_free_i32(tmode); + tcg_temp_free_ptr(status); return true; } static bool trans_FRINTN(DisasContext *s, arg_rpr_esz *a) { - if (a->esz == 0) { - return false; - } return do_frint_mode(s, a, float_round_nearest_even, frint_fns[a->esz]); } static bool trans_FRINTP(DisasContext *s, arg_rpr_esz *a) { - if (a->esz == 0) { - return false; - } return do_frint_mode(s, a, float_round_up, frint_fns[a->esz]); } static bool trans_FRINTM(DisasContext *s, arg_rpr_esz *a) { - if (a->esz == 0) { - return false; - } return do_frint_mode(s, a, float_round_down, frint_fns[a->esz]); } static bool trans_FRINTZ(DisasContext *s, arg_rpr_esz *a) { - if (a->esz == 0) { - return false; - } return do_frint_mode(s, a, float_round_to_zero, frint_fns[a->esz]); } static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a) { - if (a->esz == 0) { - return false; - } return do_frint_mode(s, a, float_round_ties_away, frint_fns[a->esz]); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-96-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 53 ++++++++++---------------------------- 1 file changed, 14 insertions(+), 39 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, return true; } -static bool trans_FRINTN(DisasContext *s, arg_rpr_esz *a) -{ - return do_frint_mode(s, a, float_round_nearest_even, frint_fns[a->esz]); -} - -static bool trans_FRINTP(DisasContext *s, arg_rpr_esz *a) -{ - return do_frint_mode(s, a, float_round_up, frint_fns[a->esz]); -} - -static bool trans_FRINTM(DisasContext *s, arg_rpr_esz *a) -{ - return do_frint_mode(s, a, float_round_down, frint_fns[a->esz]); -} - -static bool trans_FRINTZ(DisasContext *s, arg_rpr_esz *a) -{ - return do_frint_mode(s, a, float_round_to_zero, frint_fns[a->esz]); -} - -static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a) -{ - return do_frint_mode(s, a, float_round_ties_away, frint_fns[a->esz]); -} +TRANS_FEAT(FRINTN, aa64_sve, do_frint_mode, a, + float_round_nearest_even, frint_fns[a->esz]) +TRANS_FEAT(FRINTP, aa64_sve, do_frint_mode, a, + float_round_up, frint_fns[a->esz]) +TRANS_FEAT(FRINTM, aa64_sve, do_frint_mode, a, + float_round_down, frint_fns[a->esz]) +TRANS_FEAT(FRINTZ, aa64_sve, do_frint_mode, a, + float_round_to_zero, frint_fns[a->esz]) +TRANS_FEAT(FRINTA, aa64_sve, do_frint_mode, a, + float_round_ties_away, frint_fns[a->esz]) static gen_helper_gvec_3_ptr * const frecpx_fns[] = { NULL, gen_helper_sve_frecpx_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCVTLT_hs, aa64_sve2, gen_gvec_fpst_arg_zpz, TRANS_FEAT(FCVTLT_sd, aa64_sve2, gen_gvec_fpst_arg_zpz, gen_helper_sve2_fcvtlt_sd, a, 0, FPST_FPCR) -static bool trans_FCVTX_ds(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_frint_mode(s, a, float_round_to_odd, gen_helper_sve_fcvt_ds); -} - -static bool trans_FCVTXNT_ds(DisasContext *s, arg_rpr_esz *a) -{ - if (!dc_isar_feature(aa64_sve2, s)) { - return false; - } - return do_frint_mode(s, a, float_round_to_odd, gen_helper_sve2_fcvtnt_ds); -} +TRANS_FEAT(FCVTX_ds, aa64_sve2, do_frint_mode, a, + float_round_to_odd, gen_helper_sve_fcvt_ds) +TRANS_FEAT(FCVTXNT_ds, aa64_sve2, do_frint_mode, a, + float_round_to_odd, gen_helper_sve2_fcvtnt_ds) static bool trans_FLOGB(DisasContext *s, arg_rpr_esz *a) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220527181907.189259-97-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 29 ++++++----------------------- 1 file changed, 6 insertions(+), 23 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCVTX_ds, aa64_sve2, do_frint_mode, a, TRANS_FEAT(FCVTXNT_ds, aa64_sve2, do_frint_mode, a, float_round_to_odd, gen_helper_sve2_fcvtnt_ds) -static bool trans_FLOGB(DisasContext *s, arg_rpr_esz *a) -{ - static gen_helper_gvec_3_ptr * const fns[] = { - NULL, gen_helper_flogb_h, - gen_helper_flogb_s, gen_helper_flogb_d - }; - - if (!dc_isar_feature(aa64_sve2, s) || fns[a->esz] == NULL) { - return false; - } - if (sve_access_check(s)) { - TCGv_ptr status = - fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - unsigned vsz = vec_full_reg_size(s); - - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn), - pred_full_reg_offset(s, a->pg), - status, vsz, vsz, 0, fns[a->esz]); - tcg_temp_free_ptr(status); - } - return true; -} +static gen_helper_gvec_3_ptr * const flogb_fns[] = { + NULL, gen_helper_flogb_h, + gen_helper_flogb_s, gen_helper_flogb_d +}; +TRANS_FEAT(FLOGB, aa64_sve2, gen_gvec_fpst_arg_zpz, flogb_fns[a->esz], + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) static bool do_FMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sub, bool sel) { -- 2.25.1 I don't have anything else queued up at the moment, so this is just Richard's SME patches. -- PMM The following changes since commit 63b38f6c85acd312c2cab68554abf33adf4ee2b3: Merge tag 'pull-target-arm-20220707' of https://git.linaro.org/people/pmaydell/qemu-arm into staging (2022-07-08 06:17:11 +0530) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220711 for you to fetch changes up to f9982ceaf26df27d15547a3a7990a95019e9e3a8: linux-user/aarch64: Add SME related hwcap entries (2022-07-11 13:43:52 +0100) ---------------------------------------------------------------- target-arm: * Implement SME emulation, for both system and linux-user ---------------------------------------------------------------- Richard Henderson (45): target/arm: Handle SME in aarch64_cpu_dump_state target/arm: Add infrastructure for disas_sme target/arm: Trap non-streaming usage when Streaming SVE is active target/arm: Mark ADR as non-streaming target/arm: Mark RDFFR, WRFFR, SETFFR as non-streaming target/arm: Mark BDEP, BEXT, BGRP, COMPACT, FEXPA, FTSSEL as non-streaming target/arm: Mark PMULL, FMMLA as non-streaming target/arm: Mark FTSMUL, FTMAD, FADDA as non-streaming target/arm: Mark SMMLA, UMMLA, USMMLA as non-streaming target/arm: Mark string/histo/crypto as non-streaming target/arm: Mark gather/scatter load/store as non-streaming target/arm: Mark gather prefetch as non-streaming target/arm: Mark LDFF1 and LDNF1 as non-streaming target/arm: Mark LD1RO as non-streaming target/arm: Add SME enablement checks target/arm: Handle SME in sve_access_check target/arm: Implement SME RDSVL, ADDSVL, ADDSPL target/arm: Implement SME ZERO target/arm: Implement SME MOVA target/arm: Implement SME LD1, ST1 target/arm: Export unpredicated ld/st from translate-sve.c target/arm: Implement SME LDR, STR target/arm: Implement SME ADDHA, ADDVA target/arm: Implement FMOPA, FMOPS (non-widening) target/arm: Implement BFMOPA, BFMOPS target/arm: Implement FMOPA, FMOPS (widening) target/arm: Implement SME integer outer product target/arm: Implement PSEL target/arm: Implement REVD target/arm: Implement SCLAMP, UCLAMP target/arm: Reset streaming sve state on exception boundaries target/arm: Enable SME for -cpu max linux-user/aarch64: Clear tpidr2_el0 if CLONE_SETTLS linux-user/aarch64: Reset PSTATE.SM on syscalls linux-user/aarch64: Add SM bit to SVE signal context linux-user/aarch64: Tidy target_restore_sigframe error return linux-user/aarch64: Do not allow duplicate or short sve records linux-user/aarch64: Verify extra record lock succeeded linux-user/aarch64: Move sve record checks into restore linux-user/aarch64: Implement SME signal handling linux-user: Rename sve prctls linux-user/aarch64: Implement PR_SME_GET_VL, PR_SME_SET_VL target/arm: Only set ZEN in reset if SVE present target/arm: Enable SME for user-only linux-user/aarch64: Add SME related hwcap entries docs/system/arm/emulation.rst | 4 + linux-user/aarch64/target_cpu.h | 5 +- linux-user/aarch64/target_prctl.h | 62 +- target/arm/cpu.h | 7 + target/arm/helper-sme.h | 126 ++++ target/arm/helper-sve.h | 4 + target/arm/helper.h | 18 + target/arm/translate-a64.h | 45 ++ target/arm/translate.h | 16 + target/arm/sme-fa64.decode | 60 ++ target/arm/sme.decode | 88 +++ target/arm/sve.decode | 41 +- linux-user/aarch64/cpu_loop.c | 9 + linux-user/aarch64/signal.c | 243 ++++++-- linux-user/elfload.c | 20 + linux-user/syscall.c | 28 +- target/arm/cpu.c | 35 +- target/arm/cpu64.c | 11 + target/arm/helper.c | 56 +- target/arm/sme_helper.c | 1140 +++++++++++++++++++++++++++++++++++++ target/arm/sve_helper.c | 28 + target/arm/translate-a64.c | 103 +++- target/arm/translate-sme.c | 373 ++++++++++++ target/arm/translate-sve.c | 393 ++++++++++--- target/arm/translate-vfp.c | 12 + target/arm/translate.c | 2 + target/arm/vec_helper.c | 24 + target/arm/meson.build | 3 + 28 files changed, 2821 insertions(+), 135 deletions(-) create mode 100644 target/arm/sme-fa64.decode create mode 100644 target/arm/sme.decode create mode 100644 target/arm/translate-sme.c From: Richard Henderson <richard.henderson@linaro.org> Dump SVCR, plus use the correct access check for Streaming Mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) int i; int el = arm_current_el(env); const char *ns_status; + bool sve; qemu_fprintf(f, " PC=%016" PRIx64 " ", env->pc); for (i = 0; i < 32; i++) { @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) el, psr & PSTATE_SP ? 'h' : 't'); + if (cpu_isar_feature(aa64_sme, cpu)) { + qemu_fprintf(f, " SVCR=%08" PRIx64 " %c%c", + env->svcr, + (FIELD_EX64(env->svcr, SVCR, ZA) ? 'Z' : '-'), + (FIELD_EX64(env->svcr, SVCR, SM) ? 'S' : '-')); + } if (cpu_isar_feature(aa64_bti, cpu)) { qemu_fprintf(f, " BTYPE=%d", (psr & PSTATE_BTYPE) >> 10); } @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) qemu_fprintf(f, " FPCR=%08x FPSR=%08x\n", vfp_get_fpcr(env), vfp_get_fpsr(env)); - if (cpu_isar_feature(aa64_sve, cpu) && sve_exception_el(env, el) == 0) { + if (cpu_isar_feature(aa64_sme, cpu) && FIELD_EX64(env->svcr, SVCR, SM)) { + sve = sme_exception_el(env, el) == 0; + } else if (cpu_isar_feature(aa64_sve, cpu)) { + sve = sve_exception_el(env, el) == 0; + } else { + sve = false; + } + + if (sve) { int j, zcr_len = sve_vqm1_for_el(env, el); for (i = 0; i <= FFR_PRED_NUM; i++) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This includes the build rules for the decoder, and the new file for translation, but excludes any instructions. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 1 + target/arm/sme.decode | 20 ++++++++++++++++++++ target/arm/translate-a64.c | 7 ++++++- target/arm/translate-sme.c | 35 +++++++++++++++++++++++++++++++++++ target/arm/meson.build | 2 ++ 5 files changed, 64 insertions(+), 1 deletion(-) create mode 100644 target/arm/sme.decode create mode 100644 target/arm/translate-sme.c diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int pred_gvec_reg_size(DisasContext *s) } bool disas_sve(DisasContext *, uint32_t); +bool disas_sme(DisasContext *, uint32_t); void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); diff --git a/target/arm/sme.decode b/target/arm/sme.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ +# AArch64 SME instruction descriptions +# +# Copyright (c) 2022 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } switch (extract32(insn, 25, 4)) { - case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ + case 0x0: + if (!extract32(insn, 31, 1) || !disas_sme(s, insn)) { + unallocated_encoding(s); + } + break; + case 0x1: case 0x3: /* UNALLOCATED */ unallocated_encoding(s); break; case 0x2: diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ +/* + * AArch64 SME translation + * + * Copyright (c) 2022 Linaro, Ltd + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "tcg/tcg-gvec-desc.h" +#include "translate.h" +#include "exec/helper-gen.h" +#include "translate-a64.h" +#include "fpu/softfloat.h" + + +/* + * Include the generated decoder. + */ + +#include "decode-sme.c.inc" diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), + decodetree.process('sme.decode', extra_args: '--decode=disas_sme'), decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_true: files( 'sme_helper.c', 'translate-a64.c', 'translate-sve.c', + 'translate-sme.c', )) arm_softmmu_ss = ss.source_set() -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This new behaviour is in the ARM pseudocode function AArch64.CheckFPAdvSIMDEnabled, which applies to AArch32 via AArch32.CheckAdvSIMDOrFPEnabled when the EL to which the trap would be delivered is in AArch64 mode. Given that ARMv9 drops support for AArch32 outside EL0, the trap EL detection ought to be trivially true, but the pseudocode still contains a number of conditions, and QEMU has not yet committed to dropping A32 support for EL[12] when v9 features are present. Since the computation of SME_TRAP_NONSTREAMING is necessarily different for the two modes, we might as well preserve bits within TBFLAG_ANY and allocate separate bits within TBFLAG_A32 and TBFLAG_A64 instead. Note that DDI0616A.a has typos for bits [22:21] of LD1RO in the table of instructions illegal in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 7 +++ target/arm/translate.h | 4 ++ target/arm/sme-fa64.decode | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/helper.c | 41 +++++++++++++++++ target/arm/translate-a64.c | 40 ++++++++++++++++- target/arm/translate-vfp.c | 12 +++++ target/arm/translate.c | 2 + target/arm/meson.build | 1 + 8 files changed, 195 insertions(+), 2 deletions(-) create mode 100644 target/arm/sme-fa64.decode diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A32, HSTR_ACTIVE, 9, 1) * the same thing as the current security state of the processor! */ FIELD(TBFLAG_A32, NS, 10, 1) +/* + * Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. + * This requires an SME trap from AArch32 mode when using NEON. + */ +FIELD(TBFLAG_A32, SME_TRAP_NONSTREAMING, 11, 1) /* * Bit usage when in AArch32 state, for M-profile only. @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, SMEEXC_EL, 20, 2) FIELD(TBFLAG_A64, PSTATE_SM, 22, 1) FIELD(TBFLAG_A64, PSTATE_ZA, 23, 1) FIELD(TBFLAG_A64, SVL, 24, 4) +/* Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. */ +FIELD(TBFLAG_A64, SME_TRAP_NONSTREAMING, 28, 1) /* * Helpers for using the above. diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { bool pstate_sm; /* True if PSTATE.ZA is set. */ bool pstate_za; + /* True if non-streaming insns should raise an SME Streaming exception. */ + bool sme_trap_nonstreaming; + /* True if the current instruction is non-streaming. */ + bool is_nonstreaming; /* True if MVE insns are definitely not predicated by VPR or LTPSIZE */ bool mve_no_pred; /* diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ +# AArch64 SME allowed instruction decoding +# +# Copyright (c) 2022 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# + +# These patterns are taken from Appendix E1.1 of DDI0616 A.a, +# Arm Architecture Reference Manual Supplement, +# The Scalable Matrix Extension (SME), for Armv9-A + +{ + [ + OK 0-00 1110 0000 0001 0010 11-- ---- ---- # SMOV W|Xd,Vn.B[0] + OK 0-00 1110 0000 0010 0010 11-- ---- ---- # SMOV W|Xd,Vn.H[0] + OK 0100 1110 0000 0100 0010 11-- ---- ---- # SMOV Xd,Vn.S[0] + OK 0000 1110 0000 0001 0011 11-- ---- ---- # UMOV Wd,Vn.B[0] + OK 0000 1110 0000 0010 0011 11-- ---- ---- # UMOV Wd,Vn.H[0] + OK 0000 1110 0000 0100 0011 11-- ---- ---- # UMOV Wd,Vn.S[0] + OK 0100 1110 0000 1000 0011 11-- ---- ---- # UMOV Xd,Vn.D[0] + ] + FAIL 0--0 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD vector operations +} + +{ + [ + OK 0101 1110 --1- ---- 11-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar) + OK 0101 1110 -10- ---- 00-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar, FP16) + OK 01-1 1110 1-10 0001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar) + OK 01-1 1110 1111 1001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar, FP16) + ] + FAIL 01-1 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD single-element operations +} + +FAIL 0-00 110- ---- ---- ---- ---- ---- ---- # Advanced SIMD structure load/store +FAIL 1100 1110 ---- ---- ---- ---- ---- ---- # Advanced SIMD cryptography extensions +FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS + +# These are the "avoidance of doubt" final table of Illegal Advanced SIMD instructions +# We don't actually need to include these, as the default is OK. +# -001 111- ---- ---- ---- ---- ---- ---- # Scalar floating-point operations +# --10 110- ---- ---- ---- ---- ---- ---- # Load/store pair of FP registers +# --01 1100 ---- ---- ---- ---- ---- ---- # Load FP register (PC-relative literal) +# --11 1100 --0- ---- ---- ---- ---- ---- # Load/store FP register (unscaled imm) +# --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) +# --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) + +FAIL 0000 0100 --1- ---- 1010 ---- ---- ---- # ADR +FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA +FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT +FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS +FAIL 0010 0101 --10 1--- 1001 ---- ---- ---- # WRFFR, SETFFR +FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP +FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) +FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA +FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL +FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD +FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA +FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA +FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions +FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) +FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) +FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) +FAIL 1000 010- -01- ---- 1--- ---- ---- ---- # SVE 32-bit gather load (vector+imm) +FAIL 1000 0100 0-0- ---- 0--- ---- ---- ---- # SVE 32-bit gather load byte (scalar+vector) +FAIL 1000 0100 1--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load half (scalar+vector) +FAIL 1000 0101 0--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load word (scalar+vector) +FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) +FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) +FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) +FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) +FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch +FAIL 1110 010- -00- ---- 001- ---- ---- ---- # SVE2 64-bit scatter NT store (vector+scalar) +FAIL 1110 010- -10- ---- 001- ---- ---- ---- # SVE2 32-bit scatter NT store (vector+scalar) +FAIL 1110 010- ---- ---- 1-0- ---- ---- ---- # SVE scatter store (scalar+32-bit vector) +FAIL 1110 010- ---- ---- 101- ---- ---- ---- # SVE scatter store (misc) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ int sme_exception_el(CPUARMState *env, int el) return 0; } +/* This corresponds to the ARM pseudocode function IsFullA64Enabled(). */ +static bool sme_fa64(CPUARMState *env, int el) +{ + if (!cpu_isar_feature(aa64_sme_fa64, env_archcpu(env))) { + return false; + } + + if (el <= 1 && !el_is_in_host(env, el)) { + if (!FIELD_EX64(env->vfp.smcr_el[1], SMCR, FA64)) { + return false; + } + } + if (el <= 2 && arm_is_el2_enabled(env)) { + if (!FIELD_EX64(env->vfp.smcr_el[2], SMCR, FA64)) { + return false; + } + } + if (arm_feature(env, ARM_FEATURE_EL3)) { + if (!FIELD_EX64(env->vfp.smcr_el[3], SMCR, FA64)) { + return false; + } + } + + return true; +} + /* * Given that SVE is enabled, return the vector length for EL. */ @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, DP_TBFLAG_ANY(flags, PSTATE__IL, 1); } + /* + * The SME exception we are testing for is raised via + * AArch64.CheckFPAdvSIMDEnabled(), as called from + * AArch32.CheckAdvSIMDOrFPEnabled(). + */ + if (el == 0 + && FIELD_EX64(env->svcr, SVCR, SM) + && (!arm_is_el2_enabled(env) + || (arm_el_is_aa64(env, 2) && !(env->cp15.hcr_el2 & HCR_TGE))) + && arm_el_is_aa64(env, 1) + && !sme_fa64(env, el)) { + DP_TBFLAG_A32(flags, SME_TRAP_NONSTREAMING, 1); + } + return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, } if (FIELD_EX64(env->svcr, SVCR, SM)) { DP_TBFLAG_A64(flags, PSTATE_SM, 1); + DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el)); } DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA)); } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void do_vec_ld(DisasContext *s, int destidx, int element, * unallocated-encoding checks (otherwise the syndrome information * for the resulting exception will be incorrect). */ -static bool fp_access_check(DisasContext *s) +static bool fp_access_check_only(DisasContext *s) { if (s->fp_excp_el) { assert(!s->fp_access_checked); @@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s) return true; } +static bool fp_access_check(DisasContext *s) +{ + if (!fp_access_check_only(s)) { + return false; + } + if (s->sme_trap_nonstreaming && s->is_nonstreaming) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_Streaming, false)); + return false; + } + return true; +} + /* Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. */ @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, default: g_assert_not_reached(); } - if ((ri->type & ARM_CP_FPU) && !fp_access_check(s)) { + if ((ri->type & ARM_CP_FPU) && !fp_access_check_only(s)) { return; } else if ((ri->type & ARM_CP_SVE) && !sve_access_check(s)) { return; @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) } } +/* + * Include the generated SME FA64 decoder. + */ + +#include "decode-sme-fa64.c.inc" + +static bool trans_OK(DisasContext *s, arg_OK *a) +{ + return true; +} + +static bool trans_FAIL(DisasContext *s, arg_OK *a) +{ + s->is_nonstreaming = true; + return true; +} + /** * is_guarded_page: * @env: The cpu environment @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->mte_active[1] = EX_TBFLAG_A64(tb_flags, MTE0_ACTIVE); dc->pstate_sm = EX_TBFLAG_A64(tb_flags, PSTATE_SM); dc->pstate_za = EX_TBFLAG_A64(tb_flags, PSTATE_ZA); + dc->sme_trap_nonstreaming = EX_TBFLAG_A64(tb_flags, SME_TRAP_NONSTREAMING); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } } + s->is_nonstreaming = false; + if (s->sme_trap_nonstreaming) { + disas_sme_fa64(s, insn); + } + switch (extract32(insn, 25, 4)) { case 0x0: if (!extract32(insn, 31, 1) || !disas_sme(s, insn)) { diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool vfp_access_check_a(DisasContext *s, bool ignore_vfp_enabled) return false; } + /* + * Note that rebuild_hflags_a32 has already accounted for being in EL0 + * and the higher EL in A64 mode, etc. Unlike A64 mode, there do not + * appear to be any insns which touch VFP which are allowed. + */ + if (s->sme_trap_nonstreaming) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_Streaming, + s->base.pc_next - s->pc_curr == 2)); + return false; + } + if (!s->vfp_enabled && !ignore_vfp_enabled) { assert(!arm_dc_feature(s, ARM_FEATURE_M)); unallocated_encoding(s); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->vec_len = EX_TBFLAG_A32(tb_flags, VECLEN); dc->vec_stride = EX_TBFLAG_A32(tb_flags, VECSTRIDE); } + dc->sme_trap_nonstreaming = + EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING); } dc->cp_regs = cpu->cp_regs; dc->features = env->features; diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), decodetree.process('sme.decode', extra_args: '--decode=disas_sme'), + decodetree.process('sme-fa64.decode', extra_args: '--static-decode=disas_sme_fa64'), decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark ADR as a non-streaming instruction, which should trap if full a64 support is not enabled in streaming mode. Removing entries from sme-fa64.decode is an easy way to see what remains to be done. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 7 +++++++ target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 8 ++++---- 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op); static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ { return dc_isar_feature(FEAT, s) && FUNC(s, __VA_ARGS__); } +#define TRANS_FEAT_NONSTREAMING(NAME, FEAT, FUNC, ...) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { \ + s->is_nonstreaming = true; \ + return dc_isar_feature(FEAT, s) && FUNC(s, __VA_ARGS__); \ + } + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0000 0100 --1- ---- 1010 ---- ---- ---- # ADR FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_adr(DisasContext *s, arg_rrri *a, gen_helper_gvec_3 *fn) return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, a->imm); } -TRANS_FEAT(ADR_p32, aa64_sve, do_adr, a, gen_helper_sve_adr_p32) -TRANS_FEAT(ADR_p64, aa64_sve, do_adr, a, gen_helper_sve_adr_p64) -TRANS_FEAT(ADR_s32, aa64_sve, do_adr, a, gen_helper_sve_adr_s32) -TRANS_FEAT(ADR_u32, aa64_sve, do_adr, a, gen_helper_sve_adr_u32) +TRANS_FEAT_NONSTREAMING(ADR_p32, aa64_sve, do_adr, a, gen_helper_sve_adr_p32) +TRANS_FEAT_NONSTREAMING(ADR_p64, aa64_sve, do_adr, a, gen_helper_sve_adr_p64) +TRANS_FEAT_NONSTREAMING(ADR_s32, aa64_sve, do_adr, a, gen_helper_sve_adr_s32) +TRANS_FEAT_NONSTREAMING(ADR_u32, aa64_sve, do_adr, a, gen_helper_sve_adr_u32) /* *** SVE Integer Misc - Unpredicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 9 ++++++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT -FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS -FAIL 0010 0101 --10 1--- 1001 ---- ---- ---- # WRFFR, SETFFR FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag) TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s) /* Note pat == 31 is #all, to set all elements. */ -TRANS_FEAT(SETFFR, aa64_sve, do_predset, 0, FFR_PRED_NUM, 31, false) +TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve, + do_predset, 0, FFR_PRED_NUM, 31, false) /* Note pat == 32 is #unimp, to set no elements. */ TRANS_FEAT(PFALSE, aa64_sve, do_predset, 0, a->rd, 32, false) @@ -XXX,XX +XXX,XX @@ static bool trans_RDFFR_p(DisasContext *s, arg_RDFFR_p *a) .rd = a->rd, .pg = a->pg, .s = a->s, .rn = FFR_PRED_NUM, .rm = FFR_PRED_NUM, }; + + s->is_nonstreaming = true; return trans_AND_pppp(s, &alt_a); } -TRANS_FEAT(RDFFR, aa64_sve, do_mov_p, a->rd, FFR_PRED_NUM) -TRANS_FEAT(WRFFR, aa64_sve, do_mov_p, FFR_PRED_NUM, a->rn) +TRANS_FEAT_NONSTREAMING(RDFFR, aa64_sve, do_mov_p, a->rd, FFR_PRED_NUM) +TRANS_FEAT_NONSTREAMING(WRFFR, aa64_sve, do_mov_p, FFR_PRED_NUM, a->rn) static bool do_pfirst_pnext(DisasContext *s, arg_rr_esz *a, void (*gen_fn)(TCGv_i32, TCGv_ptr, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 22 ++++++++++++---------- 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA -FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT -FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_2 * const fexpa_fns[4] = { NULL, gen_helper_sve_fexpa_h, gen_helper_sve_fexpa_s, gen_helper_sve_fexpa_d, }; -TRANS_FEAT(FEXPA, aa64_sve, gen_gvec_ool_zz, - fexpa_fns[a->esz], a->rd, a->rn, 0) +TRANS_FEAT_NONSTREAMING(FEXPA, aa64_sve, gen_gvec_ool_zz, + fexpa_fns[a->esz], a->rd, a->rn, 0) static gen_helper_gvec_3 * const ftssel_fns[4] = { NULL, gen_helper_sve_ftssel_h, gen_helper_sve_ftssel_s, gen_helper_sve_ftssel_d, }; -TRANS_FEAT(FTSSEL, aa64_sve, gen_gvec_ool_arg_zzz, ftssel_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(FTSSEL, aa64_sve, gen_gvec_ool_arg_zzz, + ftssel_fns[a->esz], a, 0) /* *** SVE Predicate Logical Operations Group @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, static gen_helper_gvec_3 * const compact_fns[4] = { NULL, NULL, gen_helper_sve_compact_s, gen_helper_sve_compact_d }; -TRANS_FEAT(COMPACT, aa64_sve, gen_gvec_ool_arg_zpz, compact_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(COMPACT, aa64_sve, gen_gvec_ool_arg_zpz, + compact_fns[a->esz], a, 0) /* Call the helper that computes the ARM LastActiveElement pseudocode * function, scaled by the element size. This includes the not found @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const bext_fns[4] = { gen_helper_sve2_bext_b, gen_helper_sve2_bext_h, gen_helper_sve2_bext_s, gen_helper_sve2_bext_d, }; -TRANS_FEAT(BEXT, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bext_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BEXT, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bext_fns[a->esz], a, 0) static gen_helper_gvec_3 * const bdep_fns[4] = { gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h, gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d, }; -TRANS_FEAT(BDEP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bdep_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BDEP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bdep_fns[a->esz], a, 0) static gen_helper_gvec_3 * const bgrp_fns[4] = { gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h, gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d, }; -TRANS_FEAT(BGRP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bgrp_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BGRP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bgrp_fns[a->esz], a, 0) static gen_helper_gvec_3 * const cadd_fns[4] = { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 24 +++++++++++++++--------- 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) -FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) gen_helper_gvec_pmull_q, gen_helper_sve2_pmull_h, NULL, gen_helper_sve2_pmull_d, }; - if (a->esz == 0 - ? !dc_isar_feature(aa64_sve2_pmull128, s) - : !dc_isar_feature(aa64_sve, s)) { + + if (a->esz == 0) { + if (!dc_isar_feature(aa64_sve2_pmull128, s)) { + return false; + } + s->is_nonstreaming = true; + } else if (!dc_isar_feature(aa64_sve, s)) { return false; } return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, sel); @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz) * SVE Integer Multiply-Add (unpredicated) */ -TRANS_FEAT(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_s, - a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) -TRANS_FEAT(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_d, - a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, + gen_helper_fmmla_s, a->rd, a->rn, a->rm, a->ra, + 0, FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, + gen_helper_fmmla_d, a->rd, a->rn, a->rm, a->ra, + 0, FPST_FPCR) static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { NULL, gen_helper_sve2_sqdmlal_zzzw_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, TRANS_FEAT(BFDOT_zzxz, aa64_sve_bf16, gen_gvec_ool_arg_zzxz, gen_helper_gvec_bfdot_idx, a) -TRANS_FEAT(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_bfmmla, a, 0) +TRANS_FEAT_NONSTREAMING(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_bfmmla, a, 0) static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 15 +++++++++++---- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL -FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD -FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const ftmad_fns[4] = { NULL, gen_helper_sve_ftmad_h, gen_helper_sve_ftmad_s, gen_helper_sve_ftmad_d, }; -TRANS_FEAT(FTMAD, aa64_sve, gen_gvec_fpst_zzz, - ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FTMAD, aa64_sve, gen_gvec_fpst_zzz, + ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) /* *** SVE Floating Point Accumulating Reduction Group @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) if (a->esz == 0 || !dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) DO_FP3(FADD_zzz, fadd) DO_FP3(FSUB_zzz, fsub) DO_FP3(FMUL_zzz, fmul) -DO_FP3(FTSMUL, ftsmul) DO_FP3(FRECPS, recps) DO_FP3(FRSQRTS, rsqrts) #undef DO_FP3 +static gen_helper_gvec_3_ptr * const ftsmul_fns[4] = { + NULL, gen_helper_gvec_ftsmul_h, + gen_helper_gvec_ftsmul_s, gen_helper_gvec_ftsmul_d +}; +TRANS_FEAT_NONSTREAMING(FTSMUL, aa64_sve, gen_gvec_fpst_arg_zzz, + ftsmul_fns[a->esz], a, 0) + /* *** SVE Floating Point Arithmetic - Predicated Group */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 12 ++++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLALT_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, true) TRANS_FEAT(FMLSLB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, true, false) TRANS_FEAT(FMLSLT_zzxw, aa64_sve2, do_FMLAL_zzxw, a, true, true) -TRANS_FEAT(SMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_smmla_b, a, 0) -TRANS_FEAT(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_usmmla_b, a, 0) -TRANS_FEAT(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_ummla_b, a, 0) +TRANS_FEAT_NONSTREAMING(SMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_smmla_b, a, 0) +TRANS_FEAT_NONSTREAMING(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_usmmla_b, a, 0) +TRANS_FEAT_NONSTREAMING(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_ummla_b, a, 0) TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, gen_helper_gvec_bfdot, a, 0) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 35 ++++++++++++++++++----------------- 2 files changed, 18 insertions(+), 18 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_NARROW(RSUBHNT, rsubhnt) static gen_helper_gvec_flags_4 * const match_fns[4] = { gen_helper_sve2_match_ppzz_b, gen_helper_sve2_match_ppzz_h, NULL, NULL }; -TRANS_FEAT(MATCH, aa64_sve2, do_ppzz_flags, a, match_fns[a->esz]) +TRANS_FEAT_NONSTREAMING(MATCH, aa64_sve2, do_ppzz_flags, a, match_fns[a->esz]) static gen_helper_gvec_flags_4 * const nmatch_fns[4] = { gen_helper_sve2_nmatch_ppzz_b, gen_helper_sve2_nmatch_ppzz_h, NULL, NULL }; -TRANS_FEAT(NMATCH, aa64_sve2, do_ppzz_flags, a, nmatch_fns[a->esz]) +TRANS_FEAT_NONSTREAMING(NMATCH, aa64_sve2, do_ppzz_flags, a, nmatch_fns[a->esz]) static gen_helper_gvec_4 * const histcnt_fns[4] = { NULL, NULL, gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d }; -TRANS_FEAT(HISTCNT, aa64_sve2, gen_gvec_ool_arg_zpzz, - histcnt_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(HISTCNT, aa64_sve2, gen_gvec_ool_arg_zpzz, + histcnt_fns[a->esz], a, 0) -TRANS_FEAT(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, - a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) +TRANS_FEAT_NONSTREAMING(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, + a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) DO_ZPZZ_FP(FADDP, aa64_sve2, sve2_faddp_zpzz) DO_ZPZZ_FP(FMAXNMP, aa64_sve2, sve2_fmaxnmp_zpzz) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0) -TRANS_FEAT(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, - gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) +TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, + gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) -TRANS_FEAT(AESE, aa64_sve2_aes, gen_gvec_ool_arg_zzz, - gen_helper_crypto_aese, a, false) -TRANS_FEAT(AESD, aa64_sve2_aes, gen_gvec_ool_arg_zzz, - gen_helper_crypto_aese, a, true) +TRANS_FEAT_NONSTREAMING(AESE, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, false) +TRANS_FEAT_NONSTREAMING(AESD, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, true) -TRANS_FEAT(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, - gen_helper_crypto_sm4e, a, 0) -TRANS_FEAT(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, - gen_helper_crypto_sm4ekey, a, 0) +TRANS_FEAT_NONSTREAMING(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4e, a, 0) +TRANS_FEAT_NONSTREAMING(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4ekey, a, 0) -TRANS_FEAT(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, gen_gvec_rax1, a) +TRANS_FEAT_NONSTREAMING(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, + gen_gvec_rax1, a) TRANS_FEAT(FCVTNT_sh, aa64_sve2, gen_gvec_fpst_arg_zpz, gen_helper_sve2_fcvtnt_sh, a, 0, FPST_FPCR) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 9 --------- target/arm/translate-sve.c | 6 ++++++ 2 files changed, 6 insertions(+), 9 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) -FAIL 1000 010- -01- ---- 1--- ---- ---- ---- # SVE 32-bit gather load (vector+imm) -FAIL 1000 0100 0-0- ---- 0--- ---- ---- ---- # SVE 32-bit gather load byte (scalar+vector) -FAIL 1000 0100 1--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load half (scalar+vector) -FAIL 1000 0101 0--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load word (scalar+vector) FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch -FAIL 1110 010- -00- ---- 001- ---- ---- ---- # SVE2 64-bit scatter NT store (vector+scalar) -FAIL 1110 010- -10- ---- 001- ---- ---- ---- # SVE2 32-bit scatter NT store (vector+scalar) -FAIL 1110 010- ---- ---- 1-0- ---- ---- ---- # SVE scatter store (scalar+32-bit vector) -FAIL 1110 010- ---- ---- 101- ---- ---- ---- # SVE scatter store (misc) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDNT1_zprz(DisasContext *s, arg_LD1_zprz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STNT1_zprz(DisasContext *s, arg_ST1_zprz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. In this case, introduce PRF_ns (prefetch non-streaming) to handle the checks. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/sve.decode | 10 +++++----- target/arm/translate-sve.c | 11 +++++++++++ 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) -FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) -FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LD1RO_zpri 1010010 .. 01 0.... 001 ... ..... ..... \ @rpri_load_msz nreg=0 # SVE 32-bit gather prefetch (scalar plus 32-bit scaled offsets) -PRF 1000010 00 -1 ----- 0-- --- ----- 0 ---- +PRF_ns 1000010 00 -1 ----- 0-- --- ----- 0 ---- # SVE 32-bit gather prefetch (vector plus immediate) -PRF 1000010 -- 00 ----- 111 --- ----- 0 ---- +PRF_ns 1000010 -- 00 ----- 111 --- ----- 0 ---- # SVE contiguous prefetch (scalar plus immediate) PRF 1000010 11 1- ----- 0-- --- ----- 0 ---- @@ -XXX,XX +XXX,XX @@ LD1_zpiz 1100010 .. 01 ..... 1.. ... ..... ..... \ @rpri_g_load esz=3 # SVE 64-bit gather prefetch (scalar plus 64-bit scaled offsets) -PRF 1100010 00 11 ----- 1-- --- ----- 0 ---- +PRF_ns 1100010 00 11 ----- 1-- --- ----- 0 ---- # SVE 64-bit gather prefetch (scalar plus unpacked 32-bit scaled offsets) -PRF 1100010 00 -1 ----- 0-- --- ----- 0 ---- +PRF_ns 1100010 00 -1 ----- 0-- --- ----- 0 ---- # SVE 64-bit gather prefetch (vector plus immediate) -PRF 1100010 -- 00 ----- 111 --- ----- 0 ---- +PRF_ns 1100010 -- 00 ----- 111 --- ----- 0 ---- ### SVE Memory Store Group diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PRF_rr(DisasContext *s, arg_PRF_rr *a) return true; } +static bool trans_PRF_ns(DisasContext *s, arg_PRF_ns *a) +{ + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + /* Prefetch is a nop within QEMU. */ + s->is_nonstreaming = true; + (void)sve_access_check(s); + return true; +} + /* * Move Prefix * -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) -FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -XXX,XX +XXX,XX @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { int vsz = vec_full_reg_size(s); int elements = vsz >> dtype_esz[a->dtype]; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --0- ---- ---- ---- ---- ---- # Load/store FP register (unscaled imm) # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) - -FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) -FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1RO_zprr(DisasContext *s, arg_rprr_load *a) if (a->rm == 31) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -XXX,XX +XXX,XX @@ static bool trans_LD1RO_zpri(DisasContext *s, arg_rpri_load *a) if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), a->imm * 32); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These functions will be used to verify that the cpu is in the correct state for a given instruction. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 21 +++++++++++++++++++++ target/arm/translate-a64.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v); bool logic_imm_decode_wmask(uint64_t *result, unsigned int immn, unsigned int imms, unsigned int immr); bool sve_access_check(DisasContext *s); +bool sme_enabled_check(DisasContext *s); +bool sme_enabled_check_with_svcr(DisasContext *s, unsigned); + +/* This function corresponds to CheckStreamingSVEEnabled. */ +static inline bool sme_sm_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_SM_MASK); +} + +/* This function corresponds to CheckSMEAndZAEnabled. */ +static inline bool sme_za_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_ZA_MASK); +} + +/* Note that this function corresponds to CheckStreamingSVEAndZAEnabled. */ +static inline bool sme_smza_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_SM_MASK | R_SVCR_ZA_MASK); +} + TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr); TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, bool tag_checked, int log2_size); diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool sme_access_check(DisasContext *s) return true; } +/* This function corresponds to CheckSMEEnabled. */ +bool sme_enabled_check(DisasContext *s) +{ + /* + * Note that unlike sve_excp_el, we have not constrained sme_excp_el + * to be zero when fp_excp_el has priority. This is because we need + * sme_excp_el by itself for cpregs access checks. + */ + if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) { + s->fp_access_checked = true; + return sme_access_check(s); + } + return fp_access_check_only(s); +} + +/* Common subroutine for CheckSMEAnd*Enabled. */ +bool sme_enabled_check_with_svcr(DisasContext *s, unsigned req) +{ + if (!sme_enabled_check(s)) { + return false; + } + if (FIELD_EX64(req, SVCR, SM) && !s->pstate_sm) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_NotStreaming, false)); + return false; + } + if (FIELD_EX64(req, SVCR, ZA) && !s->pstate_za) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_InactiveZA, false)); + return false; + } + return true; +} + /* * This utility function is for doing register extension with an * optional shift. You will likely want to pass a temporary for the -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The pseudocode for CheckSVEEnabled gains a check for Streaming SVE mode, and for SME present but SVE absent. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s) return true; } -/* Check that SVE access is enabled. If it is, return true. +/* + * Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. + * This function corresponds to CheckSVEEnabled(). */ bool sve_access_check(DisasContext *s) { - if (s->sve_excp_el) { - assert(!s->sve_access_checked); - s->sve_access_checked = true; - + if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) { + assert(dc_isar_feature(aa64_sme, s)); + if (!sme_sm_enabled_check(s)) { + goto fail_exit; + } + } else if (s->sve_excp_el) { gen_exception_insn_el(s, s->pc_curr, EXCP_UDEF, syn_sve_access_trap(), s->sve_excp_el); - return false; + goto fail_exit; } s->sve_access_checked = true; return fp_access_check(s); + + fail_exit: + /* Assert that we only raise one exception per instruction. */ + assert(!s->sve_access_checked); + s->sve_access_checked = true; + return false; } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These SME instructions are nominally within the SVE decode space, so we add them to sve.decode and translate-sve.c. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 12 ++++++++++++ target/arm/sve.decode | 5 ++++- target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 54 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s) return s->vl; } +/* Return the byte size of the vector register, SVL / 8. */ +static inline int streaming_vec_reg_size(DisasContext *s) +{ + return s->svl; +} + /* * Return the offset info CPUARMState of the predicate vector register Pn. * Note for this purpose, FFR is P16. @@ -XXX,XX +XXX,XX @@ static inline int pred_full_reg_size(DisasContext *s) return s->vl >> 3; } +/* Return the byte size of the predicate register, SVL / 64. */ +static inline int streaming_pred_reg_size(DisasContext *s) +{ + return s->svl >> 3; +} + /* * Round up the size of a register to a size allowed by * the tcg vector infrastructure. Any operation which uses this diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ INDEX_ri 00000100 esz:2 1 imm:s5 010001 rn:5 rd:5 # SVE index generation (register start, register increment) INDEX_rr 00000100 .. 1 ..... 010011 ..... ..... @rd_rn_rm -### SVE Stack Allocation Group +### SVE / Streaming SVE Stack Allocation Group # SVE stack frame adjustment ADDVL 00000100 001 ..... 01010 ...... ..... @rd_rn_i6 +ADDSVL 00000100 001 ..... 01011 ...... ..... @rd_rn_i6 ADDPL 00000100 011 ..... 01010 ...... ..... @rd_rn_i6 +ADDSPL 00000100 011 ..... 01011 ...... ..... @rd_rn_i6 # SVE stack frame size RDVL 00000100 101 11111 01010 imm:s6 rd:5 +RDSVL 00000100 101 11111 01011 imm:s6 rd:5 ### SVE Bitwise Shift - Unpredicated Group diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_ADDVL(DisasContext *s, arg_ADDVL *a) return true; } +static bool trans_ADDSVL(DisasContext *s, arg_ADDSVL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 rd = cpu_reg_sp(s, a->rd); + TCGv_i64 rn = cpu_reg_sp(s, a->rn); + tcg_gen_addi_i64(rd, rn, a->imm * streaming_vec_reg_size(s)); + } + return true; +} + static bool trans_ADDPL(DisasContext *s, arg_ADDPL *a) { if (!dc_isar_feature(aa64_sve, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_ADDPL(DisasContext *s, arg_ADDPL *a) return true; } +static bool trans_ADDSPL(DisasContext *s, arg_ADDSPL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 rd = cpu_reg_sp(s, a->rd); + TCGv_i64 rn = cpu_reg_sp(s, a->rn); + tcg_gen_addi_i64(rd, rn, a->imm * streaming_pred_reg_size(s)); + } + return true; +} + static bool trans_RDVL(DisasContext *s, arg_RDVL *a) { if (!dc_isar_feature(aa64_sve, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_RDVL(DisasContext *s, arg_RDVL *a) return true; } +static bool trans_RDSVL(DisasContext *s, arg_RDSVL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 reg = cpu_reg(s, a->rd); + tcg_gen_movi_i64(reg, a->imm * streaming_vec_reg_size(s)); + } + return true; +} + /* *** SVE Compute Vector Address Group */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 4 ++++ target/arm/sme_helper.c | 25 +++++++++++++++++++++++++ target/arm/translate-sme.c | 13 +++++++++++++ 4 files changed, 44 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(set_pstate_sm, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_2(set_pstate_za, TCG_CALL_NO_RWG, void, env, i32) + +DEF_HELPER_FLAGS_3(sme_zero, TCG_CALL_NO_RWG, void, env, i32, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ # # This file is processed by scripts/decodetree.py # + +### SME Misc + +ZERO 11000000 00 001 00000000000 imm:8 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void helper_set_pstate_za(CPUARMState *env, uint32_t i) memset(env->zarray, 0, sizeof(env->zarray)); } } + +void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) +{ + uint32_t i; + + /* + * Special case clearing the entire ZA space. + * This falls into the CONSTRAINED UNPREDICTABLE zeroing of any + * parts of the ZA storage outside of SVL. + */ + if (imm == 0xff) { + memset(env->zarray, 0, sizeof(env->zarray)); + return; + } + + /* + * Recall that ZAnH.D[m] is spread across ZA[n+8*m], + * so each row is discontiguous within ZA[]. + */ + for (i = 0; i < svl; i++) { + if (imm & (1 << (i % 8))) { + memset(&env->zarray[i], 0, svl); + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ */ #include "decode-sme.c.inc" + + +static bool trans_ZERO(DisasContext *s, arg_ZERO *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_za_enabled_check(s)) { + gen_helper_sme_zero(cpu_env, tcg_constant_i32(a->imm), + tcg_constant_i32(streaming_vec_reg_size(s))); + } + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can reuse the SVE functions for implementing moves to/from horizontal tile slices, but we need new ones for moves to/from vertical tile slices. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 12 +++ target/arm/helper-sve.h | 2 + target/arm/translate-a64.h | 8 ++ target/arm/translate.h | 5 ++ target/arm/sme.decode | 15 ++++ target/arm/sme_helper.c | 151 ++++++++++++++++++++++++++++++++++++- target/arm/sve_helper.c | 12 +++ target/arm/translate-sme.c | 127 +++++++++++++++++++++++++++++++ 8 files changed, 331 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(set_pstate_sm, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_2(set_pstate_za, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_3(sme_zero, TCG_CALL_NO_RWG, void, env, i32, i32) + +/* Move to/from vertical array slices, i.e. columns, so 'c'. */ +DEF_HELPER_FLAGS_4(sme_mova_cz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_sel_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_sel_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_sel_zpzz_q, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_addp_zpzz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int pred_gvec_reg_size(DisasContext *s) return size_for_gvec(pred_full_reg_size(s)); } +/* Return a newly allocated pointer to the predicate register. */ +static inline TCGv_ptr pred_full_reg_ptr(DisasContext *s, int regno) +{ + TCGv_ptr ret = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ret, cpu_env, pred_full_reg_offset(s, regno)); + return ret; +} + bool disas_sve(DisasContext *, uint32_t); bool disas_sme(DisasContext *, uint32_t); diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int plus_2(DisasContext *s, int x) return x + 2; } +static inline int plus_12(DisasContext *s, int x) +{ + return x + 12; +} + static inline int times_2(DisasContext *s, int x) { return x * 2; diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ### SME Misc ZERO 11000000 00 001 00000000000 imm:8 + +### SME Move into/from Array + +%mova_rs 13:2 !function=plus_12 +&mova esz rs pg zr za_imm v:bool to_vec:bool + +MOVA 11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4 \ + &mova to_vec=0 rs=%mova_rs +MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za_imm:4 \ + &mova to_vec=0 rs=%mova_rs esz=4 + +MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs +MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=4 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" -#include "internals.h" +#include "tcg/tcg-gvec-desc.h" #include "exec/helper-proto.h" +#include "qemu/int128.h" +#include "vec_internal.h" /* ResetSVEState */ void arm_reset_sve_state(CPUARMState *env) @@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) } } } + + +/* + * When considering the ZA storage as an array of elements of + * type T, the index within that array of the Nth element of + * a vertical slice of a tile can be calculated like this, + * regardless of the size of type T. This is because the tiles + * are interleaved, so if type T is size N bytes then row 1 of + * the tile is N rows away from row 0. The division by N to + * convert a byte offset into an array index and the multiplication + * by N to convert from vslice-index-within-the-tile to + * the index within the ZA storage cancel out. + */ +#define tile_vslice_index(i) ((i) * sizeof(ARMVectorReg)) + +/* + * When doing byte arithmetic on the ZA storage, the element + * byteoff bytes away in a tile vertical slice is always this + * many bytes away in the ZA storage, regardless of the + * size of the tile element, assuming that byteoff is a multiple + * of the element size. Again this is because of the interleaving + * of the tiles. For instance if we have 1 byte per element then + * each row of the ZA storage has one byte of the vslice data, + * and (counting from 0) byte 8 goes in row 8 of the storage + * at offset (8 * row-size-in-bytes). + * If we have 8 bytes per element then each row of the ZA storage + * has 8 bytes of the data, but there are 8 interleaved tiles and + * so byte 8 of the data goes into row 1 of the tile, + * which is again row 8 of the storage, so the offset is still + * (8 * row-size-in-bytes). Similarly for other element sizes. + */ +#define tile_vslice_offset(byteoff) ((byteoff) * sizeof(ARMVectorReg)) + + +/* + * Move Zreg vector to ZArray column. + */ +#define DO_MOVA_C(NAME, TYPE, H) \ +void HELPER(NAME)(void *za, void *vn, void *vg, uint32_t desc) \ +{ \ + int i, oprsz = simd_oprsz(desc); \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + *(TYPE *)(za + tile_vslice_offset(i)) = *(TYPE *)(vn + H(i)); \ + } \ + i += sizeof(TYPE); \ + pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_MOVA_C(sme_mova_cz_b, uint8_t, H1) +DO_MOVA_C(sme_mova_cz_h, uint16_t, H1_2) +DO_MOVA_C(sme_mova_cz_s, uint32_t, H1_4) + +void HELPER(sme_mova_cz_d)(void *za, void *vn, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 8; + uint8_t *pg = vg; + uint64_t *n = vn; + uint64_t *a = za; + + for (i = 0; i < oprsz; i++) { + if (pg[H1(i)] & 1) { + a[tile_vslice_index(i)] = n[i]; + } + } +} + +void HELPER(sme_mova_cz_q)(void *za, void *vn, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 16; + uint16_t *pg = vg; + Int128 *n = vn; + Int128 *a = za; + + /* + * Int128 is used here simply to copy 16 bytes, and to simplify + * the address arithmetic. + */ + for (i = 0; i < oprsz; i++) { + if (pg[H2(i)] & 1) { + a[tile_vslice_index(i)] = n[i]; + } + } +} + +#undef DO_MOVA_C + +/* + * Move ZArray column to Zreg vector. + */ +#define DO_MOVA_Z(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *za, void *vg, uint32_t desc) \ +{ \ + int i, oprsz = simd_oprsz(desc); \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = *(TYPE *)(za + tile_vslice_offset(i)); \ + } \ + i += sizeof(TYPE); \ + pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_MOVA_Z(sme_mova_zc_b, uint8_t, H1) +DO_MOVA_Z(sme_mova_zc_h, uint16_t, H1_2) +DO_MOVA_Z(sme_mova_zc_s, uint32_t, H1_4) + +void HELPER(sme_mova_zc_d)(void *vd, void *za, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 8; + uint8_t *pg = vg; + uint64_t *d = vd; + uint64_t *a = za; + + for (i = 0; i < oprsz; i++) { + if (pg[H1(i)] & 1) { + d[i] = a[tile_vslice_index(i)]; + } + } +} + +void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 16; + uint16_t *pg = vg; + Int128 *d = vd; + Int128 *a = za; + + /* + * Int128 is used here simply to copy 16 bytes, and to simplify + * the address arithmetic. + */ + for (i = 0; i < oprsz; i++, za += sizeof(ARMVectorReg)) { + if (pg[H2(i)] & 1) { + d[i] = a[tile_vslice_index(i)]; + } + } +} + +#undef DO_MOVA_Z diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sel_zpzz_d)(void *vd, void *vn, void *vm, } } +void HELPER(sve_sel_zpzz_q)(void *vd, void *vn, void *vm, + void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 16; + Int128 *d = vd, *n = vn, *m = vm; + uint16_t *pg = vg; + + for (i = 0; i < opr_sz; i += 1) { + d[i] = (pg[H2(i)] & 1 ? n : m)[i]; + } +} + /* Two operand comparison controlled by a predicate. * ??? It is very tempting to want to be able to expand this inline * with x86 instructions, e.g. diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ #include "decode-sme.c.inc" +/* + * Resolve tile.size[index] to a host pointer, where tile and index + * are always decoded together, dependent on the element size. + */ +static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, + int tile_index, bool vertical) +{ + int tile = tile_index >> (4 - esz); + int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz); + int pos, len, offset; + TCGv_i32 tmp; + TCGv_ptr addr; + + /* Compute the final index, which is Rs+imm. */ + tmp = tcg_temp_new_i32(); + tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs)); + tcg_gen_addi_i32(tmp, tmp, index); + + /* Prepare a power-of-two modulo via extraction of @len bits. */ + len = ctz32(streaming_vec_reg_size(s)) - esz; + + if (vertical) { + /* + * Compute the byte offset of the index within the tile: + * (index % (svl / size)) * size + * = (index % (svl >> esz)) << esz + * Perform the power-of-two modulo via extraction of the low @len bits. + * Perform the multiply by shifting left by @pos bits. + * Perform these operations simultaneously via deposit into zero. + */ + pos = esz; + tcg_gen_deposit_z_i32(tmp, tmp, pos, len); + + /* + * For big-endian, adjust the indexed column byte offset within + * the uint64_t host words that make up env->zarray[]. + */ + if (HOST_BIG_ENDIAN && esz < MO_64) { + tcg_gen_xori_i32(tmp, tmp, 8 - (1 << esz)); + } + } else { + /* + * Compute the byte offset of the index within the tile: + * (index % (svl / size)) * (size * sizeof(row)) + * = (index % (svl >> esz)) << (esz + log2(sizeof(row))) + */ + pos = esz + ctz32(sizeof(ARMVectorReg)); + tcg_gen_deposit_z_i32(tmp, tmp, pos, len); + + /* Row slices are always aligned and need no endian adjustment. */ + } + + /* The tile byte offset within env->zarray is the row. */ + offset = tile * sizeof(ARMVectorReg); + + /* Include the byte offset of zarray to make this relative to env. */ + offset += offsetof(CPUARMState, zarray); + tcg_gen_addi_i32(tmp, tmp, offset); + + /* Add the byte offset to env to produce the final pointer. */ + addr = tcg_temp_new_ptr(); + tcg_gen_ext_i32_ptr(addr, tmp); + tcg_temp_free_i32(tmp); + tcg_gen_add_ptr(addr, addr, cpu_env); + + return addr; +} + static bool trans_ZERO(DisasContext *s, arg_ZERO *a) { if (!dc_isar_feature(aa64_sme, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a) } return true; } + +static bool trans_MOVA(DisasContext *s, arg_MOVA *a) +{ + static gen_helper_gvec_4 * const h_fns[5] = { + gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h, + gen_helper_sve_sel_zpzz_s, gen_helper_sve_sel_zpzz_d, + gen_helper_sve_sel_zpzz_q + }; + static gen_helper_gvec_3 * const cz_fns[5] = { + gen_helper_sme_mova_cz_b, gen_helper_sme_mova_cz_h, + gen_helper_sme_mova_cz_s, gen_helper_sme_mova_cz_d, + gen_helper_sme_mova_cz_q, + }; + static gen_helper_gvec_3 * const zc_fns[5] = { + gen_helper_sme_mova_zc_b, gen_helper_sme_mova_zc_h, + gen_helper_sme_mova_zc_s, gen_helper_sme_mova_zc_d, + gen_helper_sme_mova_zc_q, + }; + + TCGv_ptr t_za, t_zr, t_pg; + TCGv_i32 t_desc; + int svl; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sme_smza_enabled_check(s)) { + return true; + } + + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_zr = vec_full_reg_ptr(s, a->zr); + t_pg = pred_full_reg_ptr(s, a->pg); + + svl = streaming_vec_reg_size(s); + t_desc = tcg_constant_i32(simd_desc(svl, svl, 0)); + + if (a->v) { + /* Vertical slice -- use sme mova helpers. */ + if (a->to_vec) { + zc_fns[a->esz](t_zr, t_za, t_pg, t_desc); + } else { + cz_fns[a->esz](t_za, t_zr, t_pg, t_desc); + } + } else { + /* Horizontal slice -- reuse sve sel helpers. */ + if (a->to_vec) { + h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc); + } else { + h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc); + } + } + + tcg_temp_free_ptr(t_za); + tcg_temp_free_ptr(t_zr); + tcg_temp_free_ptr(t_pg); + + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We cannot reuse the SVE functions for LD[1-4] and ST[1-4], because those functions accept only a Zreg register number. For SME, we want to pass a pointer into ZA storage. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 82 +++++ target/arm/sme.decode | 9 + target/arm/sme_helper.c | 595 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 70 +++++ 4 files changed, 756 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1h_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1s_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1d_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1q_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1h_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1s_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1d_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1q_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ &mova to_vec=1 rs=%mova_rs MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ &mova to_vec=1 rs=%mova_rs esz=4 + +### SME Memory + +&ldst esz rs pg rn rm za_imm v:bool st:bool + +LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ + &ldst rs=%mova_rs +LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ + &ldst esz=4 rs=%mova_rs diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" +#include "internals.h" #include "tcg/tcg-gvec-desc.h" #include "exec/helper-proto.h" +#include "exec/cpu_ldst.h" +#include "exec/exec-all.h" #include "qemu/int128.h" #include "vec_internal.h" +#include "sve_ldst_internal.h" /* ResetSVEState */ void arm_reset_sve_state(CPUARMState *env) @@ -XXX,XX +XXX,XX @@ void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) } #undef DO_MOVA_Z + +/* + * Clear elements in a tile slice comprising len bytes. + */ + +typedef void ClearFn(void *ptr, size_t off, size_t len); + +static void clear_horizontal(void *ptr, size_t off, size_t len) +{ + memset(ptr + off, 0, len); +} + +static void clear_vertical_b(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; ++i) { + *(uint8_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_h(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 2) { + *(uint16_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_s(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 4) { + *(uint32_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_d(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 8) { + *(uint64_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_q(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 16) { + memset(vptr + tile_vslice_offset(i + off), 0, 16); + } +} + +/* + * Copy elements from an array into a tile slice comprising len bytes. + */ + +typedef void CopyFn(void *dst, const void *src, size_t len); + +static void copy_horizontal(void *dst, const void *src, size_t len) +{ + memcpy(dst, src, len); +} + +static void copy_vertical_b(void *vdst, const void *vsrc, size_t len) +{ + const uint8_t *src = vsrc; + uint8_t *dst = vdst; + size_t i; + + for (i = 0; i < len; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_h(void *vdst, const void *vsrc, size_t len) +{ + const uint16_t *src = vsrc; + uint16_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 2; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_s(void *vdst, const void *vsrc, size_t len) +{ + const uint32_t *src = vsrc; + uint32_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 4; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_d(void *vdst, const void *vsrc, size_t len) +{ + const uint64_t *src = vsrc; + uint64_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 8; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_q(void *vdst, const void *vsrc, size_t len) +{ + for (size_t i = 0; i < len; i += 16) { + memcpy(vdst + tile_vslice_offset(i), vsrc + i, 16); + } +} + +/* + * Host and TLB primitives for vertical tile slice addressing. + */ + +#define DO_LD(NAME, TYPE, HOST, TLB) \ +static inline void sme_##NAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + TYPE val = HOST(host); \ + *(TYPE *)(za + tile_vslice_offset(off)) = val; \ +} \ +static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ + intptr_t off, target_ulong addr, uintptr_t ra) \ +{ \ + TYPE val = TLB(env, useronly_clean_ptr(addr), ra); \ + *(TYPE *)(za + tile_vslice_offset(off)) = val; \ +} + +#define DO_ST(NAME, TYPE, HOST, TLB) \ +static inline void sme_##NAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + TYPE val = *(TYPE *)(za + tile_vslice_offset(off)); \ + HOST(host, val); \ +} \ +static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ + intptr_t off, target_ulong addr, uintptr_t ra) \ +{ \ + TYPE val = *(TYPE *)(za + tile_vslice_offset(off)); \ + TLB(env, useronly_clean_ptr(addr), val, ra); \ +} + +/* + * The ARMVectorReg elements are stored in host-endian 64-bit units. + * For 128-bit quantities, the sequence defined by the Elem[] pseudocode + * corresponds to storing the two 64-bit pieces in little-endian order. + */ +#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB) \ +static inline void HNAME##_host(void *za, intptr_t off, void *host) \ +{ \ + uint64_t val0 = HOST(host), val1 = HOST(host + 8); \ + uint64_t *ptr = za + off; \ + ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ +} \ +static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + HNAME##_host(za, tile_vslice_offset(off), host); \ +} \ +static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra); \ + uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra); \ + uint64_t *ptr = za + off; \ + ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ +} \ +static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ +} + +#define DO_STQ(HNAME, VNAME, BE, HOST, TLB) \ +static inline void HNAME##_host(void *za, intptr_t off, void *host) \ +{ \ + uint64_t *ptr = za + off; \ + HOST(host, ptr[BE]); \ + HOST(host + 1, ptr[!BE]); \ +} \ +static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + HNAME##_host(za, tile_vslice_offset(off), host); \ +} \ +static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + uint64_t *ptr = za + off; \ + TLB(env, useronly_clean_ptr(addr), ptr[BE], ra); \ + TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra); \ +} \ +static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ +} + +DO_LD(ld1b, uint8_t, ldub_p, cpu_ldub_data_ra) +DO_LD(ld1h_be, uint16_t, lduw_be_p, cpu_lduw_be_data_ra) +DO_LD(ld1h_le, uint16_t, lduw_le_p, cpu_lduw_le_data_ra) +DO_LD(ld1s_be, uint32_t, ldl_be_p, cpu_ldl_be_data_ra) +DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra) +DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra) +DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra) + +DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra) +DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra) + +DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra) +DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra) +DO_ST(st1h_le, uint16_t, stw_le_p, cpu_stw_le_data_ra) +DO_ST(st1s_be, uint32_t, stl_be_p, cpu_stl_be_data_ra) +DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra) +DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra) +DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra) + +DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra) +DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra) + +#undef DO_LD +#undef DO_ST +#undef DO_LDQ +#undef DO_STQ + +/* + * Common helper for all contiguous predicated loads. + */ + +static inline QEMU_ALWAYS_INLINE +void sme_ld1(CPUARMState *env, void *za, uint64_t *vg, + const target_ulong addr, uint32_t desc, const uintptr_t ra, + const int esz, uint32_t mtedesc, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn, + ClearFn *clr_fn, + CopyFn *cpy_fn) +{ + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t esize = 1 << esz; + intptr_t reg_off, reg_last; + SVEContLdSt info; + void *host; + int flags; + + /* Find the active elements. */ + if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, esize)) { + /* The entire predicate was false; no load occurs. */ + clr_fn(za, 0, reg_max); + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra); + + /* Handle watchpoints for all active elements. */ + sve_cont_ldst_watchpoints(&info, env, vg, addr, esize, esize, + BP_MEM_READ, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, esize, esize, + mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { +#ifdef CONFIG_USER_ONLY + g_assert_not_reached(); +#else + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. Perform the load + * into scratch memory to preserve register state until the end. + */ + ARMVectorReg scratch = { }; + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[1]; + if (reg_last < 0) { + reg_last = info.reg_off_split; + if (reg_last < 0) { + reg_last = info.reg_off_last[0]; + } + } + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + tlb_fn(env, &scratch, reg_off, addr + reg_off, ra); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + + cpy_fn(za, &scratch, reg_max); + return; +#endif + } + + /* The entire operation is in RAM, on valid pages. */ + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[0]; + host = info.page[0].host; + + if (!vertical) { + memset(za, 0, reg_max); + } else if (reg_off) { + clr_fn(za, 0, reg_off); + } + + while (reg_off <= reg_last) { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } else if (vertical) { + clr_fn(za, reg_off, esize); + } + reg_off += esize; + } while (reg_off <= reg_last && (reg_off & 63)); + } + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + reg_off = info.reg_off_split; + if (unlikely(reg_off >= 0)) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + + reg_off = info.reg_off_first[1]; + if (unlikely(reg_off >= 0)) { + reg_last = info.reg_off_last[1]; + host = info.page[1].host; + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } else if (vertical) { + clr_fn(za, reg_off, esize); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sme_ld1_mte(CPUARMState *env, void *za, uint64_t *vg, + target_ulong addr, uint32_t desc, uintptr_t ra, + const int esz, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn, + ClearFn *clr_fn, + CopyFn *cpy_fn) +{ + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + int bit55 = extract64(addr, 55, 1); + + /* Remove mtedesc from the normal sve descriptor. */ + desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + + /* Perform gross MTE suppression early. */ + if (!tbi_check(desc, bit55) || + tcma_check(desc, bit55, allocation_tag_from_addr(addr))) { + mtedesc = 0; + } + + sme_ld1(env, za, vg, addr, desc, ra, esz, mtedesc, vertical, + host_fn, tlb_fn, clr_fn, cpy_fn); +} + +#define DO_LD(L, END, ESZ) \ +void HELPER(sme_ld1##L##END##_h)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1(env, za, vg, addr, desc, GETPC(), ESZ, 0, false, \ + sve_ld1##L##L##END##_host, sve_ld1##L##L##END##_tlb, \ + clear_horizontal, copy_horizontal); \ +} \ +void HELPER(sme_ld1##L##END##_v)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1(env, za, vg, addr, desc, GETPC(), ESZ, 0, true, \ + sme_ld1##L##END##_v_host, sme_ld1##L##END##_v_tlb, \ + clear_vertical_##L, copy_vertical_##L); \ +} \ +void HELPER(sme_ld1##L##END##_h_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1_mte(env, za, vg, addr, desc, GETPC(), ESZ, false, \ + sve_ld1##L##L##END##_host, sve_ld1##L##L##END##_tlb, \ + clear_horizontal, copy_horizontal); \ +} \ +void HELPER(sme_ld1##L##END##_v_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1_mte(env, za, vg, addr, desc, GETPC(), ESZ, true, \ + sme_ld1##L##END##_v_host, sme_ld1##L##END##_v_tlb, \ + clear_vertical_##L, copy_vertical_##L); \ +} + +DO_LD(b, , MO_8) +DO_LD(h, _be, MO_16) +DO_LD(h, _le, MO_16) +DO_LD(s, _be, MO_32) +DO_LD(s, _le, MO_32) +DO_LD(d, _be, MO_64) +DO_LD(d, _le, MO_64) +DO_LD(q, _be, MO_128) +DO_LD(q, _le, MO_128) + +#undef DO_LD + +/* + * Common helper for all contiguous predicated stores. + */ + +static inline QEMU_ALWAYS_INLINE +void sme_st1(CPUARMState *env, void *za, uint64_t *vg, + const target_ulong addr, uint32_t desc, const uintptr_t ra, + const int esz, uint32_t mtedesc, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t esize = 1 << esz; + intptr_t reg_off, reg_last; + SVEContLdSt info; + void *host; + int flags; + + /* Find the active elements. */ + if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, esize)) { + /* The entire predicate was false; no store occurs. */ + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra); + + /* Handle watchpoints for all active elements. */ + sve_cont_ldst_watchpoints(&info, env, vg, addr, esize, esize, + BP_MEM_WRITE, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, esize, esize, + mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { +#ifdef CONFIG_USER_ONLY + g_assert_not_reached(); +#else + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. We cannot avoid + * this fault and will leave with the store incomplete. + */ + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[1]; + if (reg_last < 0) { + reg_last = info.reg_off_split; + if (reg_last < 0) { + reg_last = info.reg_off_last[0]; + } + } + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + return; +#endif + } + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[0]; + host = info.page[0].host; + + while (reg_off <= reg_last) { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } + reg_off += 1 << esz; + } while (reg_off <= reg_last && (reg_off & 63)); + } + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + reg_off = info.reg_off_split; + if (unlikely(reg_off >= 0)) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + + reg_off = info.reg_off_first[1]; + if (unlikely(reg_off >= 0)) { + reg_last = info.reg_off_last[1]; + host = info.page[1].host; + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } + reg_off += 1 << esz; + } while (reg_off & 63); + } while (reg_off <= reg_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sme_st1_mte(CPUARMState *env, void *za, uint64_t *vg, target_ulong addr, + uint32_t desc, uintptr_t ra, int esz, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + int bit55 = extract64(addr, 55, 1); + + /* Remove mtedesc from the normal sve descriptor. */ + desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + + /* Perform gross MTE suppression early. */ + if (!tbi_check(desc, bit55) || + tcma_check(desc, bit55, allocation_tag_from_addr(addr))) { + mtedesc = 0; + } + + sme_st1(env, za, vg, addr, desc, ra, esz, mtedesc, + vertical, host_fn, tlb_fn); +} + +#define DO_ST(L, END, ESZ) \ +void HELPER(sme_st1##L##END##_h)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1(env, za, vg, addr, desc, GETPC(), ESZ, 0, false, \ + sve_st1##L##L##END##_host, sve_st1##L##L##END##_tlb); \ +} \ +void HELPER(sme_st1##L##END##_v)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1(env, za, vg, addr, desc, GETPC(), ESZ, 0, true, \ + sme_st1##L##END##_v_host, sme_st1##L##END##_v_tlb); \ +} \ +void HELPER(sme_st1##L##END##_h_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1_mte(env, za, vg, addr, desc, GETPC(), ESZ, false, \ + sve_st1##L##L##END##_host, sve_st1##L##L##END##_tlb); \ +} \ +void HELPER(sme_st1##L##END##_v_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1_mte(env, za, vg, addr, desc, GETPC(), ESZ, true, \ + sme_st1##L##END##_v_host, sme_st1##L##END##_v_tlb); \ +} + +DO_ST(b, , MO_8) +DO_ST(h, _be, MO_16) +DO_ST(h, _le, MO_16) +DO_ST(s, _be, MO_32) +DO_ST(s, _le, MO_32) +DO_ST(d, _be, MO_64) +DO_ST(d, _le, MO_64) +DO_ST(q, _be, MO_128) +DO_ST(q, _le, MO_128) + +#undef DO_ST diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) return true; } + +static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) +{ + typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32); + + /* + * Indexed by [esz][be][v][mte][st], which is (except for load/store) + * also the order in which the elements appear in the function names, + * and so how we must concatenate the pieces. + */ + +#define FN_LS(F) { gen_helper_sme_ld1##F, gen_helper_sme_st1##F } +#define FN_MTE(F) { FN_LS(F), FN_LS(F##_mte) } +#define FN_HV(F) { FN_MTE(F##_h), FN_MTE(F##_v) } +#define FN_END(L, B) { FN_HV(L), FN_HV(B) } + + static GenLdSt1 * const fns[5][2][2][2][2] = { + FN_END(b, b), + FN_END(h_le, h_be), + FN_END(s_le, s_be), + FN_END(d_le, d_be), + FN_END(q_le, q_be), + }; + +#undef FN_LS +#undef FN_MTE +#undef FN_HV +#undef FN_END + + TCGv_ptr t_za, t_pg; + TCGv_i64 addr; + int svl, desc = 0; + bool be = s->be_data == MO_BE; + bool mte = s->mte_active[0]; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sme_smza_enabled_check(s)) { + return true; + } + + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_pg = pred_full_reg_ptr(s, a->pg); + addr = tcg_temp_new_i64(); + + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + + if (mte) { + desc = FIELD_DP32(desc, MTEDESC, MIDX, get_mem_index(s)); + desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); + desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); + desc = FIELD_DP32(desc, MTEDESC, WRITE, a->st); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (1 << a->esz) - 1); + desc <<= SVE_MTEDESC_SHIFT; + } else { + addr = clean_data_tbi(s, addr); + } + svl = streaming_vec_reg_size(s); + desc = simd_desc(svl, svl, desc); + + fns[a->esz][be][a->v][mte][a->st](cpu_env, t_za, t_pg, addr, + tcg_constant_i32(desc)); + + tcg_temp_free_ptr(t_za); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_i64(addr); + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add a TCGv_ptr base argument, which will be cpu_env for SVE. We will reuse this for SME save and restore array insns. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 3 +++ target/arm/translate-sve.c | 48 ++++++++++++++++++++++++++++---------- 2 files changed, 39 insertions(+), 12 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); +void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); + #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, * The load should begin at the address Rn + IMM. */ -static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) +void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, + int len, int rn, int imm) { int len_align = QEMU_ALIGN_DOWN(len, 8); int len_remain = len % 8; @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) t0 = tcg_temp_new_i64(); for (i = 0; i < len_align; i += 8) { tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ); - tcg_gen_st_i64(t0, cpu_env, vofs + i); + tcg_gen_st_i64(t0, base, vofs + i); tcg_gen_addi_i64(clean_addr, clean_addr, 8); } tcg_temp_free_i64(t0); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) clean_addr = new_tmp_a64_local(s); tcg_gen_mov_i64(clean_addr, t0); + if (base != cpu_env) { + TCGv_ptr b = tcg_temp_local_new_ptr(); + tcg_gen_mov_ptr(b, base); + base = b; + } + gen_set_label(loop); t0 = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_addi_i64(clean_addr, clean_addr, 8); tp = tcg_temp_new_ptr(); - tcg_gen_add_ptr(tp, cpu_env, i); + tcg_gen_add_ptr(tp, base, i); tcg_gen_addi_ptr(i, i, 8); tcg_gen_st_i64(t0, tp, vofs); tcg_temp_free_ptr(tp); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); tcg_temp_free_ptr(i); + + if (base != cpu_env) { + tcg_temp_free_ptr(base); + assert(len_remain == 0); + } } /* @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) default: g_assert_not_reached(); } - tcg_gen_st_i64(t0, cpu_env, vofs + len_align); + tcg_gen_st_i64(t0, base, vofs + len_align); tcg_temp_free_i64(t0); } } /* Similarly for stores. */ -static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) +void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, + int len, int rn, int imm) { int len_align = QEMU_ALIGN_DOWN(len, 8); int len_remain = len % 8; @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) t0 = tcg_temp_new_i64(); for (i = 0; i < len_align; i += 8) { - tcg_gen_ld_i64(t0, cpu_env, vofs + i); + tcg_gen_ld_i64(t0, base, vofs + i); tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ); tcg_gen_addi_i64(clean_addr, clean_addr, 8); } @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) clean_addr = new_tmp_a64_local(s); tcg_gen_mov_i64(clean_addr, t0); + if (base != cpu_env) { + TCGv_ptr b = tcg_temp_local_new_ptr(); + tcg_gen_mov_ptr(b, base); + base = b; + } + gen_set_label(loop); t0 = tcg_temp_new_i64(); tp = tcg_temp_new_ptr(); - tcg_gen_add_ptr(tp, cpu_env, i); + tcg_gen_add_ptr(tp, base, i); tcg_gen_ld_i64(t0, tp, vofs); tcg_gen_addi_ptr(i, i, 8); tcg_temp_free_ptr(tp); @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); tcg_temp_free_ptr(i); + + if (base != cpu_env) { + tcg_temp_free_ptr(base); + assert(len_remain == 0); + } } /* Predicate register stores can be any multiple of 2. */ if (len_remain) { t0 = tcg_temp_new_i64(); - tcg_gen_ld_i64(t0, cpu_env, vofs + len_align); + tcg_gen_ld_i64(t0, base, vofs + len_align); switch (len_remain) { case 2: @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - do_ldr(s, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - do_ldr(s, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - do_str(s, off, size, a->rn, a->imm * size); + gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - do_str(s, off, size, a->rn, a->imm * size); + gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can reuse the SVE functions for LDR and STR, passing in the base of the ZA vector and a zero offset. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme.decode | 7 +++++++ target/arm/translate-sme.c | 24 ++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ &ldst rs=%mova_rs LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ &ldst esz=4 rs=%mova_rs + +&ldstr rv rn imm +@ldstr ....... ... . ...... .. ... rn:5 . imm:4 \ + &ldstr rv=%mova_rs + +LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr +STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) tcg_temp_free_i64(addr); return true; } + +typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int); + +static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) +{ + int svl = streaming_vec_reg_size(s); + int imm = a->imm; + TCGv_ptr base; + + if (!sme_za_enabled_check(s)) { + return true; + } + + /* ZA[n] equates to ZA0H.B[n]. */ + base = get_tile_rowcol(s, MO_8, a->rv, imm, false); + + fn(s, base, 0, svl, a->rn, imm * svl); + + tcg_temp_free_ptr(base); + return true; +} + +TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) +TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 5 +++ target/arm/sme.decode | 11 +++++ target/arm/sme_helper.c | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 31 +++++++++++++ 4 files changed, 137 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_st1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i DEF_HELPER_FLAGS_5(sme_st1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_st1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_st1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_addha_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr + +### SME Add Vector to Array + +&adda zad zn pm pn +@adda_32 ........ .. ..... . pm:3 pn:3 zn:5 ... zad:2 &adda +@adda_64 ........ .. ..... . pm:3 pn:3 zn:5 .. zad:3 &adda + +ADDHA_s 11000000 10 01000 0 ... ... ..... 000 .. @adda_32 +ADDVA_s 11000000 10 01000 1 ... ... ..... 000 .. @adda_32 +ADDHA_d 11000000 11 01000 0 ... ... ..... 00 ... @adda_64 +ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ DO_ST(q, _be, MO_128) DO_ST(q, _le, MO_128) #undef DO_ST + +void HELPER(sme_addha_s)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 4; + uint64_t *pn = vpn, *pm = vpm; + uint32_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ) { + uint64_t pa = pn[row >> 4]; + do { + if (pa & 1) { + for (col = 0; col < oprsz; ) { + uint64_t pb = pm[col >> 4]; + do { + if (pb & 1) { + zda[tile_vslice_index(row) + H4(col)] += zn[H4(col)]; + } + pb >>= 4; + } while (++col & 15); + } + } + pa >>= 4; + } while (++row & 15); + } +} + +void HELPER(sme_addha_d)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint8_t *pn = vpn, *pm = vpm; + uint64_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + zda[tile_vslice_index(row) + col] += zn[col]; + } + } + } + } +} + +void HELPER(sme_addva_s)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 4; + uint64_t *pn = vpn, *pm = vpm; + uint32_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ) { + uint64_t pa = pn[row >> 4]; + do { + if (pa & 1) { + uint32_t zn_row = zn[H4(row)]; + for (col = 0; col < oprsz; ) { + uint64_t pb = pm[col >> 4]; + do { + if (pb & 1) { + zda[tile_vslice_index(row) + H4(col)] += zn_row; + } + pb >>= 4; + } while (++col & 15); + } + } + pa >>= 4; + } while (++row & 15); + } +} + +void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint8_t *pn = vpn, *pm = vpm; + uint64_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + uint64_t zn_row = zn[row]; + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + zda[tile_vslice_index(row) + col] += zn_row; + } + } + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) + +static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz, + gen_helper_gvec_4 *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, 0); + TCGv_ptr za, zn, pn, pm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + + fn(za, zn, pn, pm, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + return true; +} + +TRANS_FEAT(ADDHA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addha_s) +TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) +TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) +TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 5 +++ target/arm/sme.decode | 9 +++++ target/arm/sme_helper.c | 69 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 32 ++++++++++++++++++ 4 files changed, 115 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addha_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ADDHA_s 11000000 10 01000 0 ... ... ..... 000 .. @adda_32 ADDVA_s 11000000 10 01000 1 ... ... ..... 000 .. @adda_32 ADDHA_d 11000000 11 01000 0 ... ... ..... 00 ... @adda_64 ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 + +### SME Outer Product + +&op zad zn zm pm pn sub:bool +@op_32 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .. zad:2 &op +@op_64 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 . zad:3 &op + +FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 +FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "qemu/int128.h" +#include "fpu/softfloat.h" #include "vec_internal.h" #include "sve_ldst_internal.h" @@ -XXX,XX +XXX,XX @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn, } } } + +void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) << 31; + uint16_t *pn = vpn, *pm = vpm; + float_status fpst; + + /* + * Make a copy of float_status because this operation does not + * update the cumulative fp exception status. It also produces + * default nans. + */ + fpst = *(float_status *)vst; + set_default_nan_mode(true, &fpst); + + for (row = 0; row < oprsz; ) { + uint16_t pa = pn[H2(row >> 4)]; + do { + if (pa & 1) { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ neg; + + for (col = 0; col < oprsz; ) { + uint16_t pb = pm[H2(col >> 4)]; + do { + if (pb & 1) { + uint32_t *a = vza_row + H1_4(col); + uint32_t *m = vzm + H1_4(col); + *a = float32_muladd(n, *m, *a, 0, vst); + } + col += 4; + pb >>= 4; + } while (col & 15); + } + } + row += 4; + pa >>= 4; + } while (row & 15); + } +} + +void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint64_t neg = (uint64_t)simd_data(desc) << 63; + uint64_t *za = vza, *zn = vzn, *zm = vzm; + uint8_t *pn = vpn, *pm = vpm; + float_status fpst = *(float_status *)vst; + + set_default_nan_mode(true, &fpst); + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + uint64_t *za_row = &za[tile_vslice_index(row)]; + uint64_t n = zn[row] ^ neg; + + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + uint64_t *a = &za_row[col]; + *a = float64_muladd(n, zm[col], *a, 0, &fpst); + } + } + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADDHA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addha_s) TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) + +static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, + gen_helper_gvec_5_ptr *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->sub); + TCGv_ptr za, zn, zm, pn, pm, fpst; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + zm = vec_full_reg_ptr(s, a->zm); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + fpst = fpstatus_ptr(FPST_FPCR); + + fn(za, zn, zm, pn, pm, fpst, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + tcg_temp_free_ptr(fpst); + return true; +} + +TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) +TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 2 ++ target/arm/sme_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 30 ++++++++++++++++++++ 4 files changed, 90 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 + +BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, } } } + +/* + * Alter PAIR as needed for controlling predicates being false, + * and for NEG on an enabled row element. + */ +static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) +{ + /* + * The pseudocode uses a conditional negate after the conditional zero. + * It is simpler here to unconditionally negate before conditional zero. + */ + pair ^= neg; + if (!(pg & 1)) { + pair &= 0xffff0000u; + } + if (!(pg & 4)) { + pair &= 0x0000ffffu; + } + return pair; +} + +void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) * 0x80008000u; + uint16_t *pn = vpn, *pm = vpm; + + for (row = 0; row < oprsz; ) { + uint16_t prow = pn[H2(row >> 4)]; + do { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)); + + n = f16mop_adj_pair(n, prow, neg); + + for (col = 0; col < oprsz; ) { + uint16_t pcol = pm[H2(col >> 4)]; + do { + if (prow & pcol & 0b0101) { + uint32_t *a = vza_row + H1_4(col); + uint32_t m = *(uint32_t *)(vzm + H1_4(col)); + + m = f16mop_adj_pair(m, pcol, 0); + *a = bfdotadd(*a, n, m); + + col += 4; + pcol >>= 4; + } + } while (col & 15); + } + row += 4; + prow >>= 4; + } while (row & 15); + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) +static bool do_outprod(DisasContext *s, arg_op *a, MemOp esz, + gen_helper_gvec_5 *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->sub); + TCGv_ptr za, zn, zm, pn, pm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + zm = vec_full_reg_ptr(s, a->zm); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + + fn(za, zn, zm, pn, pm, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + return true; +} + static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, gen_helper_gvec_5_ptr *fn) { @@ -XXX,XX +XXX,XX @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) + +/* TODO: FEAT_EBF16 */ +TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 1 + target/arm/sme_helper.c | 74 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 1 + 4 files changed, 78 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 +FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) return pair; } +static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, + float_status *s_std, float_status *s_odd) +{ + float64 e1r = float16_to_float64(e1 & 0xffff, true, s_std); + float64 e1c = float16_to_float64(e1 >> 16, true, s_std); + float64 e2r = float16_to_float64(e2 & 0xffff, true, s_std); + float64 e2c = float16_to_float64(e2 >> 16, true, s_std); + float64 t64; + float32 t32; + + /* + * The ARM pseudocode function FPDot performs both multiplies + * and the add with a single rounding operation. Emulate this + * by performing the first multiply in round-to-odd, then doing + * the second multiply as fused multiply-add, and rounding to + * float32 all in one step. + */ + t64 = float64_mul(e1r, e2r, s_odd); + t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std); + + /* This conversion is exact, because we've already rounded. */ + t32 = float64_to_float32(t64, s_std); + + /* The final accumulation step is not fused. */ + return float32_add(sum, t32, s_std); +} + +void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) * 0x80008000u; + uint16_t *pn = vpn, *pm = vpm; + float_status fpst_odd, fpst_std; + + /* + * Make a copy of float_status because this operation does not + * update the cumulative fp exception status. It also produces + * default nans. Make a second copy with round-to-odd -- see above. + */ + fpst_std = *(float_status *)vst; + set_default_nan_mode(true, &fpst_std); + fpst_odd = fpst_std; + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (row = 0; row < oprsz; ) { + uint16_t prow = pn[H2(row >> 4)]; + do { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)); + + n = f16mop_adj_pair(n, prow, neg); + + for (col = 0; col < oprsz; ) { + uint16_t pcol = pm[H2(col >> 4)]; + do { + if (prow & pcol & 0b0101) { + uint32_t *a = vza_row + H1_4(col); + uint32_t m = *(uint32_t *)(vzm + H1_4(col)); + + m = f16mop_adj_pair(m, pcol, 0); + *a = f16_dotadd(*a, n, m, &fpst_std, &fpst_odd); + + col += 4; + pcol >>= 4; + } + } while (col & 15); + } + row += 4; + prow >>= 4; + } while (row & 15); + } +} + void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, void *vpm, uint32_t desc) { diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, return true; } +TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_h) TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is SMOPA, SUMOPA, USMOPA_s, UMOPA, for both Int8 and Int16. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 16 ++++++++ target/arm/sme.decode | 10 +++++ target/arm/sme_helper.c | 82 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 10 +++++ 4 files changed, 118 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_sumopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_usmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_smopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_umopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_sumopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 + +SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32 +SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32 +USMOPA_s 1010000 1 10 0 ..... ... ... ..... . 00 .. @op_32 +UMOPA_s 1010000 1 10 1 ..... ... ... ..... . 00 .. @op_32 + +SMOPA_d 1010000 0 11 0 ..... ... ... ..... . 0 ... @op_64 +SUMOPA_d 1010000 0 11 1 ..... ... ... ..... . 0 ... @op_64 +USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64 +UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, } while (row & 15); } } + +typedef uint64_t IMOPFn(uint64_t, uint64_t, uint64_t, uint8_t, bool); + +static inline void do_imopa(uint64_t *za, uint64_t *zn, uint64_t *zm, + uint8_t *pn, uint8_t *pm, + uint32_t desc, IMOPFn *fn) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + bool neg = simd_data(desc); + + for (row = 0; row < oprsz; ++row) { + uint8_t pa = pn[H1(row)]; + uint64_t *za_row = &za[tile_vslice_index(row)]; + uint64_t n = zn[row]; + + for (col = 0; col < oprsz; ++col) { + uint8_t pb = pm[H1(col)]; + uint64_t *a = &za_row[col]; + + *a = fn(n, zm[col], *a, pa & pb, neg); + } + } +} + +#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \ +static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ +{ \ + uint32_t sum0 = 0, sum1 = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_b(p); \ + sum0 += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum0 += (NTYPE)(n >> 8) * (MTYPE)(m >> 8); \ + sum0 += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + sum0 += (NTYPE)(n >> 24) * (MTYPE)(m >> 24); \ + sum1 += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \ + sum1 += (NTYPE)(n >> 40) * (MTYPE)(m >> 40); \ + sum1 += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \ + sum1 += (NTYPE)(n >> 56) * (MTYPE)(m >> 56); \ + if (neg) { \ + sum0 = (uint32_t)a - sum0, sum1 = (uint32_t)(a >> 32) - sum1; \ + } else { \ + sum0 = (uint32_t)a + sum0, sum1 = (uint32_t)(a >> 32) + sum1; \ + } \ + return ((uint64_t)sum1 << 32) | sum0; \ +} + +#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \ +static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ +{ \ + uint64_t sum = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_h(p); \ + sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + sum += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \ + sum += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \ + return neg ? a - sum : a + sum; \ +} + +DEF_IMOP_32(smopa_s, int8_t, int8_t) +DEF_IMOP_32(umopa_s, uint8_t, uint8_t) +DEF_IMOP_32(sumopa_s, int8_t, uint8_t) +DEF_IMOP_32(usmopa_s, uint8_t, int8_t) + +DEF_IMOP_64(smopa_d, int16_t, int16_t) +DEF_IMOP_64(umopa_d, uint16_t, uint16_t) +DEF_IMOP_64(sumopa_d, int16_t, uint16_t) +DEF_IMOP_64(usmopa_d, uint16_t, int16_t) + +#define DEF_IMOPH(NAME) \ + void HELPER(sme_##NAME)(void *vza, void *vzn, void *vzm, void *vpn, \ + void *vpm, uint32_t desc) \ + { do_imopa(vza, vzn, vzm, vpn, vpm, desc, NAME); } + +DEF_IMOPH(smopa_s) +DEF_IMOPH(umopa_s) +DEF_IMOPH(sumopa_s) +DEF_IMOPH(usmopa_s) +DEF_IMOPH(smopa_d) +DEF_IMOPH(umopa_d) +DEF_IMOPH(sumopa_d) +DEF_IMOPH(usmopa_d) diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_f /* TODO: FEAT_EBF16 */ TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa) + +TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s) +TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s) +TRANS_FEAT(SUMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_sumopa_s) +TRANS_FEAT(USMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_usmopa_s) + +TRANS_FEAT(SMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_smopa_d) +TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_umopa_d) +TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumopa_d) +TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 20 +++++++++++++ target/arm/translate-sve.c | 57 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 ### SVE2 floating-point bfloat16 dot-product (indexed) BFDOT_zzxz 01100100 01 1 ..... 010000 ..... ..... @rrxr_2 esz=2 + +### SVE broadcast predicate element + +&psel esz pd pn pm rv imm +%psel_rv 16:2 !function=plus_12 +%psel_imm_b 22:2 19:2 +%psel_imm_h 22:2 20:1 +%psel_imm_s 22:2 +%psel_imm_d 23:1 +@psel ........ .. . ... .. .. pn:4 . pm:4 . pd:4 \ + &psel rv=%psel_rv + +PSEL 00100101 .. 1 ..1 .. 01 .... 0 .... 0 .... \ + @psel esz=0 imm=%psel_imm_b +PSEL 00100101 .. 1 .10 .. 01 .... 0 .... 0 .... \ + @psel esz=1 imm=%psel_imm_h +PSEL 00100101 .. 1 100 .. 01 .... 0 .... 0 .... \ + @psel esz=2 imm=%psel_imm_s +PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ + @psel esz=3 imm=%psel_imm_d diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false) TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true) + +static bool trans_PSEL(DisasContext *s, arg_psel *a) +{ + int vl = vec_full_reg_size(s); + int pl = pred_gvec_reg_size(s); + int elements = vl >> a->esz; + TCGv_i64 tmp, didx, dbit; + TCGv_ptr ptr; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i64(); + dbit = tcg_temp_new_i64(); + didx = tcg_temp_new_i64(); + ptr = tcg_temp_new_ptr(); + + /* Compute the predicate element. */ + tcg_gen_addi_i64(tmp, cpu_reg(s, a->rv), a->imm); + if (is_power_of_2(elements)) { + tcg_gen_andi_i64(tmp, tmp, elements - 1); + } else { + tcg_gen_remu_i64(tmp, tmp, tcg_constant_i64(elements)); + } + + /* Extract the predicate byte and bit indices. */ + tcg_gen_shli_i64(tmp, tmp, a->esz); + tcg_gen_andi_i64(dbit, tmp, 7); + tcg_gen_shri_i64(didx, tmp, 3); + if (HOST_BIG_ENDIAN) { + tcg_gen_xori_i64(didx, didx, 7); + } + + /* Load the predicate word. */ + tcg_gen_trunc_i64_ptr(ptr, didx); + tcg_gen_add_ptr(ptr, ptr, cpu_env); + tcg_gen_ld8u_i64(tmp, ptr, pred_full_reg_offset(s, a->pm)); + + /* Extract the predicate bit and replicate to MO_64. */ + tcg_gen_shr_i64(tmp, tmp, dbit); + tcg_gen_andi_i64(tmp, tmp, 1); + tcg_gen_neg_i64(tmp, tmp); + + /* Apply to either copy the source, or write zeros. */ + tcg_gen_gvec_ands(MO_64, pred_full_reg_offset(s, a->pd), + pred_full_reg_offset(s, a->pn), tmp, pl, pl); + + tcg_temp_free_i64(tmp); + tcg_temp_free_i64(dbit); + tcg_temp_free_i64(didx); + tcg_temp_free_ptr(ptr); + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 2 ++ target/arm/sve.decode | 1 + target/arm/sve_helper.c | 16 ++++++++++++++++ target/arm/translate-sve.c | 2 ++ 4 files changed, 21 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_revh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_revw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_revd_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_rbit_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ REVB 00000101 .. 1001 00 100 ... ..... ..... @rd_pg_rn REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn +REVD 00000101 00 1011 10 100 ... ..... ..... @rd_pg_rn_e0 # SVE vector splice (predicated, destructive) SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZ_D(sve_revh_d, uint64_t, hswap64) DO_ZPZ_D(sve_revw_d, uint64_t, wswap64) +void HELPER(sme_revd_q)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i += 2) { + if (pg[H1(i)] & 1) { + uint64_t n0 = n[i + 0]; + uint64_t n1 = n[i + 1]; + d[i + 0] = n1; + d[i + 1] = n0; + } + } +} + DO_ZPZ(sve_rbit_b, uint8_t, H1, revbit8) DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16) DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(REVH, aa64_sve, gen_gvec_ool_arg_zpz, revh_fns[a->esz], a, 0) TRANS_FEAT(REVW, aa64_sve, gen_gvec_ool_arg_zpz, a->esz == 3 ? gen_helper_sve_revw_d : NULL, a, 0) +TRANS_FEAT(REVD, aa64_sme, gen_gvec_ool_arg_zpz, gen_helper_sme_revd_q, a, 0) + TRANS_FEAT(SPLICE, aa64_sve, gen_gvec_ool_arg_zpzz, gen_helper_sve_splice, a, a->esz) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 18 +++++++ target/arm/sve.decode | 5 ++ target/arm/translate-sve.c | 102 +++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 24 +++++++++ 4 files changed, 149 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_uclamp_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ PSEL 00100101 .. 1 100 .. 01 .... 0 .... 0 .... \ @psel esz=2 imm=%psel_imm_s PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ @psel esz=3 imm=%psel_imm_d + +### SVE clamp + +SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm +UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PSEL(DisasContext *s, arg_psel *a) tcg_temp_free_ptr(ptr); return true; } + +static void gen_sclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) +{ + tcg_gen_smax_i32(d, a, n); + tcg_gen_smin_i32(d, d, m); +} + +static void gen_sclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a) +{ + tcg_gen_smax_i64(d, a, n); + tcg_gen_smin_i64(d, d, m); +} + +static void gen_sclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec a) +{ + tcg_gen_smax_vec(vece, d, a, n); + tcg_gen_smin_vec(vece, d, d, m); +} + +static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const TCGOpcode vecop[] = { + INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_sclamp_i32, + .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_sclamp_i64, + .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_d, + .opt_opc = vecop, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64 } + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); +} + +TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a) + +static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) +{ + tcg_gen_umax_i32(d, a, n); + tcg_gen_umin_i32(d, d, m); +} + +static void gen_uclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a) +{ + tcg_gen_umax_i64(d, a, n); + tcg_gen_umin_i64(d, d, m); +} + +static void gen_uclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec a) +{ + tcg_gen_umax_vec(vece, d, a, n); + tcg_gen_umin_vec(vece, d, d, m); +} + +static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const TCGOpcode vecop[] = { + INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_uclamp_i32, + .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_uclamp_i64, + .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_d, + .opt_opc = vecop, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64 } + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); +} + +TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +#define DO_CLAMP(NAME, TYPE) \ +void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE aa = *(TYPE *)(a + i); \ + TYPE nn = *(TYPE *)(n + i); \ + TYPE mm = *(TYPE *)(m + i); \ + TYPE dd = MIN(MAX(aa, nn), mm); \ + *(TYPE *)(d + i) = dd; \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_CLAMP(gvec_sclamp_b, int8_t) +DO_CLAMP(gvec_sclamp_h, int16_t) +DO_CLAMP(gvec_sclamp_s, int32_t) +DO_CLAMP(gvec_sclamp_d, int64_t) + +DO_CLAMP(gvec_uclamp_b, uint8_t) +DO_CLAMP(gvec_uclamp_h, uint16_t) +DO_CLAMP(gvec_uclamp_s, uint32_t) +DO_CLAMP(gvec_uclamp_d, uint64_t) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can handle both exception entry and exception return by hooking into aarch64_sve_change_el. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void aarch64_sve_change_el(CPUARMState *env, int old_el, return; } + old_a64 = old_el ? arm_el_is_aa64(env, old_el) : el0_a64; + new_a64 = new_el ? arm_el_is_aa64(env, new_el) : el0_a64; + + /* + * Both AArch64.TakeException and AArch64.ExceptionReturn + * invoke ResetSVEState when taking an exception from, or + * returning to, AArch32 state when PSTATE.SM is enabled. + */ + if (old_a64 != new_a64 && FIELD_EX64(env->svcr, SVCR, SM)) { + arm_reset_sve_state(env); + return; + } + /* * DDI0584A.d sec 3.2: "If SVE instructions are disabled or trapped * at ELx, or not available because the EL is in AArch32 state, then @@ -XXX,XX +XXX,XX @@ void aarch64_sve_change_el(CPUARMState *env, int old_el, * we already have the correct register contents when encountering the * vq0->vq0 transition between EL0->EL1. */ - old_a64 = old_el ? arm_el_is_aa64(env, old_el) : el0_a64; old_len = (old_a64 && !sve_exception_el(env, old_el) ? sve_vqm1_for_el(env, old_el) : 0); - new_a64 = new_el ? arm_el_is_aa64(env, new_el) : el0_a64; new_len = (new_a64 && !sve_exception_el(env, new_el) ? sve_vqm1_for_el(env, new_el) : 0); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Note that SME remains effectively disabled for user-only, because we do not yet set CPACR_EL1.SMEN. This needs to wait until the kernel ABI is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 4 ++++ target/arm/cpu64.c | 11 +++++++++++ 2 files changed, 15 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_SHA512 (Advanced SIMD SHA512 instructions) - FEAT_SM3 (Advanced SIMD SM3 instructions) - FEAT_SM4 (Advanced SIMD SM4 instructions) +- FEAT_SME (Scalable Matrix Extension) +- FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode) +- FEAT_SME_F64F64 (Double-precision floating-point outer product instructions) +- FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) - FEAT_SPECRES (Speculation restriction instructions) - FEAT_SSBS (Speculative Store Bypass Safe) - FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) */ t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ + t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_2 */ cpu->isar.id_aa64pfr1 = t; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_aa64dfr0 = t; + t = cpu->isar.id_aa64smfr0; + t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1); /* FEAT_SME_F64F64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1); /* FEAT_SME_FA64 */ + cpu->isar.id_aa64smfr0 = t; + /* Replicate the same data to the 32-bit id registers. */ aa32_max_features(cpu); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_cpu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/target_cpu.h b/linux-user/aarch64/target_cpu.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_cpu.h +++ b/linux-user/aarch64/target_cpu.h @@ -XXX,XX +XXX,XX @@ static inline void cpu_clone_regs_parent(CPUARMState *env, unsigned flags) static inline void cpu_set_tls(CPUARMState *env, target_ulong newtls) { - /* Note that AArch64 Linux keeps the TLS pointer in TPIDR; this is + /* + * Note that AArch64 Linux keeps the TLS pointer in TPIDR; this is * different from AArch32 Linux, which uses TPIDRRO. */ env->cp15.tpidr_el[0] = newtls; + /* TPIDR2_EL0 is cleared with CLONE_SETTLS. */ + env->cp15.tpidr2_el0 = 0; } static inline abi_ulong get_sp_from_cpustate(CPUARMState *state) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/cpu_loop.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -XXX,XX +XXX,XX @@ void cpu_loop(CPUARMState *env) switch (trapnr) { case EXCP_SWI: + /* + * On syscall, PSTATE.ZA is preserved, along with the ZA matrix. + * PSTATE.SM is cleared, per SMSTOP, which does ResetSVEState. + */ + if (FIELD_EX64(env->svcr, SVCR, SM)) { + env->svcr = FIELD_DP64(env->svcr, SVCR, SM, 0); + arm_rebuild_hflags(env); + arm_reset_sve_state(env); + } ret = do_syscall(env, env->xregs[8], env->xregs[0], -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Make sure to zero the currently reserved fields. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ struct target_extra_context { struct target_sve_context { struct target_aarch64_ctx head; uint16_t vl; - uint16_t reserved[3]; + uint16_t flags; + uint16_t reserved[2]; /* The actual SVE data immediately follows. It is laid out * according to TARGET_SVE_SIG_{Z,P}REG_OFFSET, based off of * the original struct pointer. @@ -XXX,XX +XXX,XX @@ struct target_sve_context { #define TARGET_SVE_SIG_CONTEXT_SIZE(VQ) \ (TARGET_SVE_SIG_PREG_OFFSET(VQ, 17)) +#define TARGET_SVE_SIG_FLAG_SM 1 + struct target_rt_sigframe { struct target_siginfo info; struct target_ucontext uc; @@ -XXX,XX +XXX,XX @@ static void target_setup_sve_record(struct target_sve_context *sve, { int i, j; + memset(sve, 0, sizeof(*sve)); __put_user(TARGET_SVE_MAGIC, &sve->head.magic); __put_user(size, &sve->head.size); __put_user(vq * TARGET_SVE_VQ_BYTES, &sve->vl); + if (FIELD_EX64(env->svcr, SVCR, SM)) { + __put_user(TARGET_SVE_SIG_FLAG_SM, &sve->flags); + } /* Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian store -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Fold the return value setting into the goto, so each point of failure need not do both. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-37-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, struct target_sve_context *sve = NULL; uint64_t extra_datap = 0; bool used_extra = false; - bool err = false; int vq = 0, sve_size = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, switch (magic) { case 0: if (size != 0) { - err = true; - goto exit; + goto err; } if (used_extra) { ctx = NULL; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, case TARGET_FPSIMD_MAGIC: if (fpsimd || size != sizeof(struct target_fpsimd_context)) { - err = true; - goto exit; + goto err; } fpsimd = (struct target_fpsimd_context *)ctx; break; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; } } - err = true; - goto exit; + goto err; case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { - err = true; - goto exit; + goto err; } __get_user(extra_datap, &((struct target_extra_context *)ctx)->datap); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, /* Unknown record -- we certainly didn't generate it. * Did we in fact get out of sync? */ - err = true; - goto exit; + goto err; } ctx = (void *)ctx + size; } @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, if (fpsimd) { target_restore_fpsimd_record(env, fpsimd); } else { - err = true; + goto err; } /* SVE data, if present, overwrites FPSIMD data. */ if (sve) { target_restore_sve_record(env, sve, vq); } - - exit: unlock_user(extra, extra_datap, 0); - return err; + return 0; + + err: + unlock_user(extra, extra_datap, 0); + return 1; } static abi_ulong get_sigframe(struct target_sigaction *ka, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> In parse_user_sigframe, the kernel rejects duplicate sve records, or records that are smaller than the header. We were silently allowing these cases to pass, dropping the record. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-38-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; case TARGET_SVE_MAGIC: + if (sve || size < sizeof(struct target_sve_context)) { + goto err; + } if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { vq = sve_vq(env); sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); - if (!sve && size == sve_size) { + if (size == sve_size) { sve = (struct target_sve_context *)ctx; break; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-39-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, __get_user(extra_size, &((struct target_extra_context *)ctx)->size); extra = lock_user(VERIFY_READ, extra_datap, extra_size, 0); + if (!extra) { + return 1; + } break; default: -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Move the checks out of the parsing loop and into the restore function. This more closely mirrors the code structure in the kernel, and is slightly clearer. Reject rather than silently skip incorrect VL and SVE record sizes, bringing our checks in to line with those the kernel does. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-40-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 51 +++++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 16 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static void target_restore_fpsimd_record(CPUARMState *env, } } -static void target_restore_sve_record(CPUARMState *env, - struct target_sve_context *sve, int vq) +static bool target_restore_sve_record(CPUARMState *env, + struct target_sve_context *sve, + int size) { - int i, j; + int i, j, vl, vq; - /* Note that SVE regs are stored as a byte stream, with each byte element + if (!cpu_isar_feature(aa64_sve, env_archcpu(env))) { + return false; + } + + __get_user(vl, &sve->vl); + vq = sve_vq(env); + + /* Reject mismatched VL. */ + if (vl != vq * TARGET_SVE_VQ_BYTES) { + return false; + } + + /* Accept empty record -- used to clear PSTATE.SM. */ + if (size <= sizeof(*sve)) { + return true; + } + + /* Reject non-empty but incomplete record. */ + if (size < TARGET_SVE_SIG_CONTEXT_SIZE(vq)) { + return false; + } + + /* + * Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian load * of our 64-bit hunks. */ @@ -XXX,XX +XXX,XX @@ static void target_restore_sve_record(CPUARMState *env, } } } + return true; } static int target_restore_sigframe(CPUARMState *env, @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, struct target_sve_context *sve = NULL; uint64_t extra_datap = 0; bool used_extra = false; - int vq = 0, sve_size = 0; + int sve_size = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, if (sve || size < sizeof(struct target_sve_context)) { goto err; } - if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { - vq = sve_vq(env); - sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); - if (size == sve_size) { - sve = (struct target_sve_context *)ctx; - break; - } - } - goto err; + sve = (struct target_sve_context *)ctx; + sve_size = size; + break; case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, } /* SVE data, if present, overwrites FPSIMD data. */ - if (sve) { - target_restore_sve_record(env, sve, vq); + if (sve && !target_restore_sve_record(env, sve, sve_size)) { + goto err; } unlock_user(extra, extra_datap, 0); return 0; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Set the SM bit in the SVE record on signal delivery, create the ZA record. Restore SM and ZA state according to the records present on return. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-41-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 167 +++++++++++++++++++++++++++++++++--- 1 file changed, 154 insertions(+), 13 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ struct target_sve_context { #define TARGET_SVE_SIG_FLAG_SM 1 +#define TARGET_ZA_MAGIC 0x54366345 + +struct target_za_context { + struct target_aarch64_ctx head; + uint16_t vl; + uint16_t reserved[3]; + /* The actual ZA data immediately follows. */ +}; + +#define TARGET_ZA_SIG_REGS_OFFSET \ + QEMU_ALIGN_UP(sizeof(struct target_za_context), TARGET_SVE_VQ_BYTES) +#define TARGET_ZA_SIG_ZAV_OFFSET(VQ, N) \ + (TARGET_ZA_SIG_REGS_OFFSET + (VQ) * TARGET_SVE_VQ_BYTES * (N)) +#define TARGET_ZA_SIG_CONTEXT_SIZE(VQ) \ + TARGET_ZA_SIG_ZAV_OFFSET(VQ, VQ * TARGET_SVE_VQ_BYTES) + struct target_rt_sigframe { struct target_siginfo info; struct target_ucontext uc; @@ -XXX,XX +XXX,XX @@ static void target_setup_end_record(struct target_aarch64_ctx *end) } static void target_setup_sve_record(struct target_sve_context *sve, - CPUARMState *env, int vq, int size) + CPUARMState *env, int size) { - int i, j; + int i, j, vq = sve_vq(env); memset(sve, 0, sizeof(*sve)); __put_user(TARGET_SVE_MAGIC, &sve->head.magic); @@ -XXX,XX +XXX,XX @@ static void target_setup_sve_record(struct target_sve_context *sve, } } +static void target_setup_za_record(struct target_za_context *za, + CPUARMState *env, int size) +{ + int vq = sme_vq(env); + int vl = vq * TARGET_SVE_VQ_BYTES; + int i, j; + + memset(za, 0, sizeof(*za)); + __put_user(TARGET_ZA_MAGIC, &za->head.magic); + __put_user(size, &za->head.size); + __put_user(vl, &za->vl); + + if (size == TARGET_ZA_SIG_CONTEXT_SIZE(0)) { + return; + } + assert(size == TARGET_ZA_SIG_CONTEXT_SIZE(vq)); + + /* + * Note that ZA vectors are stored as a byte stream, + * with each byte element at a subsequent address. + */ + for (i = 0; i < vl; ++i) { + uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); + for (j = 0; j < vq * 2; ++j) { + __put_user_e(env->zarray[i].d[j], z + j, le); + } + } +} + static void target_restore_general_frame(CPUARMState *env, struct target_rt_sigframe *sf) { @@ -XXX,XX +XXX,XX @@ static void target_restore_fpsimd_record(CPUARMState *env, static bool target_restore_sve_record(CPUARMState *env, struct target_sve_context *sve, - int size) + int size, int *svcr) { - int i, j, vl, vq; + int i, j, vl, vq, flags; + bool sm; - if (!cpu_isar_feature(aa64_sve, env_archcpu(env))) { + __get_user(vl, &sve->vl); + __get_user(flags, &sve->flags); + + sm = flags & TARGET_SVE_SIG_FLAG_SM; + + /* The cpu must support Streaming or Non-streaming SVE. */ + if (sm + ? !cpu_isar_feature(aa64_sme, env_archcpu(env)) + : !cpu_isar_feature(aa64_sve, env_archcpu(env))) { return false; } - __get_user(vl, &sve->vl); - vq = sve_vq(env); + /* + * Note that we cannot use sve_vq() because that depends on the + * current setting of PSTATE.SM, not the state to be restored. + */ + vq = sve_vqm1_for_el_sm(env, 0, sm) + 1; /* Reject mismatched VL. */ if (vl != vq * TARGET_SVE_VQ_BYTES) { @@ -XXX,XX +XXX,XX @@ static bool target_restore_sve_record(CPUARMState *env, return false; } + *svcr = FIELD_DP64(*svcr, SVCR, SM, sm); + /* * Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian load @@ -XXX,XX +XXX,XX @@ static bool target_restore_sve_record(CPUARMState *env, return true; } +static bool target_restore_za_record(CPUARMState *env, + struct target_za_context *za, + int size, int *svcr) +{ + int i, j, vl, vq; + + if (!cpu_isar_feature(aa64_sme, env_archcpu(env))) { + return false; + } + + __get_user(vl, &za->vl); + vq = sme_vq(env); + + /* Reject mismatched VL. */ + if (vl != vq * TARGET_SVE_VQ_BYTES) { + return false; + } + + /* Accept empty record -- used to clear PSTATE.ZA. */ + if (size <= TARGET_ZA_SIG_CONTEXT_SIZE(0)) { + return true; + } + + /* Reject non-empty but incomplete record. */ + if (size < TARGET_ZA_SIG_CONTEXT_SIZE(vq)) { + return false; + } + + *svcr = FIELD_DP64(*svcr, SVCR, ZA, 1); + + for (i = 0; i < vl; ++i) { + uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); + for (j = 0; j < vq * 2; ++j) { + __get_user_e(env->zarray[i].d[j], z + j, le); + } + } + return true; +} + static int target_restore_sigframe(CPUARMState *env, struct target_rt_sigframe *sf) { struct target_aarch64_ctx *ctx, *extra = NULL; struct target_fpsimd_context *fpsimd = NULL; struct target_sve_context *sve = NULL; + struct target_za_context *za = NULL; uint64_t extra_datap = 0; bool used_extra = false; int sve_size = 0; + int za_size = 0; + int svcr = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, sve_size = size; break; + case TARGET_ZA_MAGIC: + if (za || size < sizeof(struct target_za_context)) { + goto err; + } + za = (struct target_za_context *)ctx; + za_size = size; + break; + case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { goto err; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, } /* SVE data, if present, overwrites FPSIMD data. */ - if (sve && !target_restore_sve_record(env, sve, sve_size)) { + if (sve && !target_restore_sve_record(env, sve, sve_size, &svcr)) { goto err; } + if (za && !target_restore_za_record(env, za, za_size, &svcr)) { + goto err; + } + if (env->svcr != svcr) { + env->svcr = svcr; + arm_rebuild_hflags(env); + } unlock_user(extra, extra_datap, 0); return 0; @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, .total_size = offsetof(struct target_rt_sigframe, uc.tuc_mcontext.__reserved), }; - int fpsimd_ofs, fr_ofs, sve_ofs = 0, vq = 0, sve_size = 0; + int fpsimd_ofs, fr_ofs, sve_ofs = 0, za_ofs = 0; + int sve_size = 0, za_size = 0; struct target_rt_sigframe *frame; struct target_rt_frame_record *fr; abi_ulong frame_addr, return_addr; @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, &layout); /* SVE state needs saving only if it exists. */ - if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { - vq = sve_vq(env); - sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); + if (cpu_isar_feature(aa64_sve, env_archcpu(env)) || + cpu_isar_feature(aa64_sme, env_archcpu(env))) { + sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(sve_vq(env)), 16); sve_ofs = alloc_sigframe_space(sve_size, &layout); } + if (cpu_isar_feature(aa64_sme, env_archcpu(env))) { + /* ZA state needs saving only if it is enabled. */ + if (FIELD_EX64(env->svcr, SVCR, ZA)) { + za_size = TARGET_ZA_SIG_CONTEXT_SIZE(sme_vq(env)); + } else { + za_size = TARGET_ZA_SIG_CONTEXT_SIZE(0); + } + za_ofs = alloc_sigframe_space(za_size, &layout); + } if (layout.extra_ofs) { /* Reserve space for the extra end marker. The standard end marker @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, target_setup_end_record((void *)frame + layout.extra_end_ofs); } if (sve_ofs) { - target_setup_sve_record((void *)frame + sve_ofs, env, vq, sve_size); + target_setup_sve_record((void *)frame + sve_ofs, env, sve_size); + } + if (za_ofs) { + target_setup_za_record((void *)frame + za_ofs, env, za_size); } /* Set up the stack frame for unwinding. */ @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, env->btype = 2; } + /* + * Invoke the signal handler with both SM and ZA disabled. + * When clearing SM, ResetSVEState, per SMSTOP. + */ + if (FIELD_EX64(env->svcr, SVCR, SM)) { + arm_reset_sve_state(env); + } + if (env->svcr) { + env->svcr = 0; + arm_rebuild_hflags(env); + } + if (info) { tswap_siginfo(&frame->info, info); env->xregs[1] = frame_addr + offsetof(struct target_rt_sigframe, info); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add "sve" to the sve prctl functions, to distinguish them from the coming "sme" prctls with similar names. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-42-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_prctl.h | 8 ++++---- linux-user/syscall.c | 12 ++++++------ 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ #ifndef AARCH64_TARGET_PRCTL_H #define AARCH64_TARGET_PRCTL_H -static abi_long do_prctl_get_vl(CPUArchState *env) +static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); if (cpu_isar_feature(aa64_sve, cpu)) { @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_get_vl(CPUArchState *env) } return -TARGET_EINVAL; } -#define do_prctl_get_vl do_prctl_get_vl +#define do_prctl_sve_get_vl do_prctl_sve_get_vl -static abi_long do_prctl_set_vl(CPUArchState *env, abi_long arg2) +static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) { /* * We cannot support either PR_SVE_SET_VL_ONEXEC or PR_SVE_VL_INHERIT. @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_set_vl(CPUArchState *env, abi_long arg2) } return -TARGET_EINVAL; } -#define do_prctl_set_vl do_prctl_set_vl +#define do_prctl_sve_set_vl do_prctl_sve_set_vl static abi_long do_prctl_reset_keys(CPUArchState *env, abi_long arg2) { diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_inval1(CPUArchState *env, abi_long arg2) #ifndef do_prctl_set_fp_mode #define do_prctl_set_fp_mode do_prctl_inval1 #endif -#ifndef do_prctl_get_vl -#define do_prctl_get_vl do_prctl_inval0 +#ifndef do_prctl_sve_get_vl +#define do_prctl_sve_get_vl do_prctl_inval0 #endif -#ifndef do_prctl_set_vl -#define do_prctl_set_vl do_prctl_inval1 +#ifndef do_prctl_sve_set_vl +#define do_prctl_sve_set_vl do_prctl_inval1 #endif #ifndef do_prctl_reset_keys #define do_prctl_reset_keys do_prctl_inval1 @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, case PR_SET_FP_MODE: return do_prctl_set_fp_mode(env, arg2); case PR_SVE_GET_VL: - return do_prctl_get_vl(env); + return do_prctl_sve_get_vl(env); case PR_SVE_SET_VL: - return do_prctl_set_vl(env, arg2); + return do_prctl_sve_set_vl(env, arg2); case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) { return -TARGET_EINVAL; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These prctl set the Streaming SVE vector length, which may be completely different from the Normal SVE vector length. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-43-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_prctl.h | 54 +++++++++++++++++++++++++++++++ linux-user/syscall.c | 16 +++++++++ 2 files changed, 70 insertions(+) diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); if (cpu_isar_feature(aa64_sve, cpu)) { + /* PSTATE.SM is always unset on syscall entry. */ return sve_vq(env) * 16; } return -TARGET_EINVAL; @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { uint32_t vq, old_vq; + /* PSTATE.SM is always unset on syscall entry. */ old_vq = sve_vq(env); /* @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) } #define do_prctl_sve_set_vl do_prctl_sve_set_vl +static abi_long do_prctl_sme_get_vl(CPUArchState *env) +{ + ARMCPU *cpu = env_archcpu(env); + if (cpu_isar_feature(aa64_sme, cpu)) { + return sme_vq(env) * 16; + } + return -TARGET_EINVAL; +} +#define do_prctl_sme_get_vl do_prctl_sme_get_vl + +static abi_long do_prctl_sme_set_vl(CPUArchState *env, abi_long arg2) +{ + /* + * We cannot support either PR_SME_SET_VL_ONEXEC or PR_SME_VL_INHERIT. + * Note the kernel definition of sve_vl_valid allows for VQ=512, + * i.e. VL=8192, even though the architectural maximum is VQ=16. + */ + if (cpu_isar_feature(aa64_sme, env_archcpu(env)) + && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { + int vq, old_vq; + + old_vq = sme_vq(env); + + /* + * Bound the value of vq, so that we know that it fits into + * the 4-bit field in SMCR_EL1. Because PSTATE.SM is cleared + * on syscall entry, we are not modifying the current SVE + * vector length. + */ + vq = MAX(arg2 / 16, 1); + vq = MIN(vq, 16); + env->vfp.smcr_el[1] = + FIELD_DP64(env->vfp.smcr_el[1], SMCR, LEN, vq - 1); + + /* Delay rebuilding hflags until we know if ZA must change. */ + vq = sve_vqm1_for_el_sm(env, 0, true) + 1; + + if (vq != old_vq) { + /* + * PSTATE.ZA state is cleared on any change to SVL. + * We need not call arm_rebuild_hflags because PSTATE.SM was + * cleared on syscall entry, so this hasn't changed VL. + */ + env->svcr = FIELD_DP64(env->svcr, SVCR, ZA, 0); + arm_rebuild_hflags(env); + } + return vq * 16; + } + return -TARGET_EINVAL; +} +#define do_prctl_sme_set_vl do_prctl_sme_set_vl + static abi_long do_prctl_reset_keys(CPUArchState *env, abi_long arg2) { ARMCPU *cpu = env_archcpu(env); diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ abi_long do_arch_prctl(CPUX86State *env, int code, abi_ulong addr) #ifndef PR_SET_SYSCALL_USER_DISPATCH # define PR_SET_SYSCALL_USER_DISPATCH 59 #endif +#ifndef PR_SME_SET_VL +# define PR_SME_SET_VL 63 +# define PR_SME_GET_VL 64 +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) +#endif #include "target_prctl.h" @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_inval1(CPUArchState *env, abi_long arg2) #ifndef do_prctl_set_unalign #define do_prctl_set_unalign do_prctl_inval1 #endif +#ifndef do_prctl_sme_get_vl +#define do_prctl_sme_get_vl do_prctl_inval0 +#endif +#ifndef do_prctl_sme_set_vl +#define do_prctl_sme_set_vl do_prctl_inval1 +#endif static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5) @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, return do_prctl_sve_get_vl(env); case PR_SVE_SET_VL: return do_prctl_sve_set_vl(env, arg2); + case PR_SME_GET_VL: + return do_prctl_sme_get_vl(env); + case PR_SME_SET_VL: + return do_prctl_sme_set_vl(env, arg2); case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) { return -TARGET_EINVAL; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> There's no reason to set CPACR_EL1.ZEN if SVE disabled. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-44-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) /* and to the FP/Neon instructions */ env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, CPACR_EL1, FPEN, 3); - /* and to the SVE instructions */ - env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, - CPACR_EL1, ZEN, 3); - /* with reasonable vector length */ + /* and to the SVE instructions, with default vector length */ if (cpu_isar_feature(aa64_sve, cpu)) { + env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, + CPACR_EL1, ZEN, 3); env->vfp.zcr_el[1] = cpu->sve_default_vq - 1; } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Enable SME, TPIDR2_EL0, and FA64 if supported by the cpu. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-45-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) CPACR_EL1, ZEN, 3); env->vfp.zcr_el[1] = cpu->sve_default_vq - 1; } + /* and for SME instructions, with default vector length, and TPIDR2 */ + if (cpu_isar_feature(aa64_sme, cpu)) { + env->cp15.sctlr_el[1] |= SCTLR_EnTP2; + env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, + CPACR_EL1, SMEN, 3); + env->vfp.smcr_el[1] = cpu->sme_default_vq - 1; + if (cpu_isar_feature(aa64_sme_fa64, cpu)) { + env->vfp.smcr_el[1] = FIELD_DP64(env->vfp.smcr_el[1], + SMCR, FA64, 1); + } + } /* * Enable 48-bit address space (TODO: take reserved_va into account). * Enable TBI0 but not TBI1. -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-46-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ enum { ARM_HWCAP2_A64_RNG = 1 << 16, ARM_HWCAP2_A64_BTI = 1 << 17, ARM_HWCAP2_A64_MTE = 1 << 18, + ARM_HWCAP2_A64_ECV = 1 << 19, + ARM_HWCAP2_A64_AFP = 1 << 20, + ARM_HWCAP2_A64_RPRES = 1 << 21, + ARM_HWCAP2_A64_MTE3 = 1 << 22, + ARM_HWCAP2_A64_SME = 1 << 23, + ARM_HWCAP2_A64_SME_I16I64 = 1 << 24, + ARM_HWCAP2_A64_SME_F64F64 = 1 << 25, + ARM_HWCAP2_A64_SME_I8I32 = 1 << 26, + ARM_HWCAP2_A64_SME_F16F32 = 1 << 27, + ARM_HWCAP2_A64_SME_B16F32 = 1 << 28, + ARM_HWCAP2_A64_SME_F32F32 = 1 << 29, + ARM_HWCAP2_A64_SME_FA64 = 1 << 30, }; #define ELF_HWCAP get_elf_hwcap() @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); + GET_FEATURE_ID(aa64_sme, (ARM_HWCAP2_A64_SME | + ARM_HWCAP2_A64_SME_F32F32 | + ARM_HWCAP2_A64_SME_B16F32 | + ARM_HWCAP2_A64_SME_F16F32 | + ARM_HWCAP2_A64_SME_I8I32)); + GET_FEATURE_ID(aa64_sme_f64f64, ARM_HWCAP2_A64_SME_F64F64); + GET_FEATURE_ID(aa64_sme_i16i64, ARM_HWCAP2_A64_SME_I16I64); + GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64); return hwcaps; } -- 2.25.1