From nobody Wed Apr 16 04:32:52 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1539008137741659.5848542582085; Mon, 8 Oct 2018 07:15:37 -0700 (PDT) Received: from localhost ([::1]:46432 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1g9WJs-0004Bq-8I for importer@patchew.org; Mon, 08 Oct 2018 10:15:36 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:46142) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1g9W5V-0001B8-9l for qemu-devel@nongnu.org; Mon, 08 Oct 2018 10:00:48 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1g9W5K-00076p-Qs for qemu-devel@nongnu.org; Mon, 08 Oct 2018 10:00:44 -0400 Received: from orth.archaic.org.uk ([2001:8b0:1d0::2]:51692) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1g9W5K-0006uy-DE for qemu-devel@nongnu.org; Mon, 08 Oct 2018 10:00:34 -0400 Received: from pm215 by orth.archaic.org.uk with local (Exim 4.89) (envelope-from ) id 1g9W5C-0003hv-J0 for qemu-devel@nongnu.org; Mon, 08 Oct 2018 15:00:26 +0100 From: Peter Maydell To: qemu-devel@nongnu.org Date: Mon, 8 Oct 2018 14:59:48 +0100 Message-Id: <20181008140004.12612-18-peter.maydell@linaro.org> X-Mailer: git-send-email 2.19.0 In-Reply-To: <20181008140004.12612-1-peter.maydell@linaro.org> References: <20181008140004.12612-1-peter.maydell@linaro.org> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2001:8b0:1d0::2 Subject: [Qemu-devel] [PULL 17/33] target/arm: Rewrite vector gather stores X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RDMRC_1 RSF_0 Z_629925259 SPT_0 Content-Type: text/plain; charset="utf-8" From: Richard Henderson This fixes the endianness problem for softmmu, and moves the main loop out of a macro and into an inlined function. Reviewed-by: Peter Maydell Tested-by: Laurent Desnogues Signed-off-by: Richard Henderson Message-id: 20181005175350.30752-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper-sve.h | 52 ++++++++++---- target/arm/sve_helper.c | 139 ++++++++++++++++++++++++------------- target/arm/translate-sve.c | 74 +++++++++++++------- 3 files changed, 177 insertions(+), 88 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 49d1c09e30c..6b9b93af45e 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -1468,41 +1468,67 @@ DEF_HELPER_FLAGS_6(sve_ldffsds_zd, TCG_CALL_NO_WG, =20 DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sths_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stss_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) =20 DEF_HELPER_FLAGS_6(sve_stbs_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sths_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stss_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) =20 DEF_HELPER_FLAGS_6(sve_stbd_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) =20 DEF_HELPER_FLAGS_6(sve_stbd_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) =20 DEF_HELPER_FLAGS_6(sve_stbd_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index c225cd04881..a95e445b226 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -5136,61 +5136,100 @@ DO_LDFF1_ZPZ_D(sve_ldffsds_zd, uint64_t, int32_t, = cpu_ldl_data_ra) =20 /* Stores with a vector index. */ =20 -#define DO_ST1_ZPZ_S(NAME, TYPEI, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz =3D simd_oprsz(desc); \ - unsigned scale =3D simd_data(desc); \ - uintptr_t ra =3D GETPC(); \ - for (i =3D 0; i < oprsz; ) { \ - uint16_t pg =3D *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (likely(pg & 1)) { \ - target_ulong off =3D *(TYPEI *)(vm + H1_4(i)); \ - uint32_t d =3D *(uint32_t *)(vd + H1_4(i)); \ - FN(env, base + (off << scale), d, ra); \ - } \ - i +=3D sizeof(uint32_t), pg >>=3D sizeof(uint32_t); = \ - } while (i & 15); \ - } \ +static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx =3D cpu_mmu_index(env, false); + intptr_t i, oprsz =3D simd_oprsz(desc); + unsigned scale =3D simd_data(desc); + + set_helper_retaddr(ra); + for (i =3D 0; i < oprsz; ) { + uint16_t pg =3D *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (likely(pg & 1)) { + target_ulong off =3D off_fn(vm, i); + tlb_fn(env, vd, i, base + (off << scale), mmu_idx, ra); + } + i +=3D 4, pg >>=3D 4; + } while (i & 15); + } + set_helper_retaddr(0); } =20 -#define DO_ST1_ZPZ_D(NAME, TYPEI, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz =3D simd_oprsz(desc) / 8; \ - unsigned scale =3D simd_data(desc); \ - uintptr_t ra =3D GETPC(); \ - uint64_t *d =3D vd, *m =3D vm; uint8_t *pg =3D vg; = \ - for (i =3D 0; i < oprsz; i++) { \ - if (likely(pg[H1(i)] & 1)) { \ - target_ulong off =3D (target_ulong)(TYPEI)m[i] << scale; \ - FN(env, base + off, d[i], ra); \ - } \ - } \ +static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx =3D cpu_mmu_index(env, false); + intptr_t i, oprsz =3D simd_oprsz(desc) / 8; + unsigned scale =3D simd_data(desc); + + set_helper_retaddr(ra); + for (i =3D 0; i < oprsz; i++) { + uint8_t pg =3D *(uint8_t *)(vg + H1(i)); + if (likely(pg & 1)) { + target_ulong off =3D off_fn(vm, i * 8); + tlb_fn(env, vd, i * 8, base + (off << scale), mmu_idx, ra); + } + } + set_helper_retaddr(0); } =20 -DO_ST1_ZPZ_S(sve_stbs_zsu, uint32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_S(sve_sths_zsu, uint32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_S(sve_stss_zsu, uint32_t, cpu_stl_data_ra) +#define DO_ST1_ZPZ_S(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_st1_zs(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_s, sve_st1##MEM##_tlb); \ +} =20 -DO_ST1_ZPZ_S(sve_stbs_zss, int32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_S(sve_sths_zss, int32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_S(sve_stss_zss, int32_t, cpu_stl_data_ra) +#define DO_ST1_ZPZ_D(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_st1_zd(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_d, sve_st1##MEM##_tlb); \ +} =20 -DO_ST1_ZPZ_D(sve_stbd_zsu, uint32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zsu, uint32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zsu, uint32_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zsu, uint32_t, cpu_stq_data_ra) +DO_ST1_ZPZ_S(bs, zsu) +DO_ST1_ZPZ_S(hs_le, zsu) +DO_ST1_ZPZ_S(hs_be, zsu) +DO_ST1_ZPZ_S(ss_le, zsu) +DO_ST1_ZPZ_S(ss_be, zsu) =20 -DO_ST1_ZPZ_D(sve_stbd_zss, int32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zss, int32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zss, int32_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zss, int32_t, cpu_stq_data_ra) +DO_ST1_ZPZ_S(bs, zss) +DO_ST1_ZPZ_S(hs_le, zss) +DO_ST1_ZPZ_S(hs_be, zss) +DO_ST1_ZPZ_S(ss_le, zss) +DO_ST1_ZPZ_S(ss_be, zss) =20 -DO_ST1_ZPZ_D(sve_stbd_zd, uint64_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zd, uint64_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zd, uint64_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zd, uint64_t, cpu_stq_data_ra) +DO_ST1_ZPZ_D(bd, zsu) +DO_ST1_ZPZ_D(hd_le, zsu) +DO_ST1_ZPZ_D(hd_be, zsu) +DO_ST1_ZPZ_D(sd_le, zsu) +DO_ST1_ZPZ_D(sd_be, zsu) +DO_ST1_ZPZ_D(dd_le, zsu) +DO_ST1_ZPZ_D(dd_be, zsu) + +DO_ST1_ZPZ_D(bd, zss) +DO_ST1_ZPZ_D(hd_le, zss) +DO_ST1_ZPZ_D(hd_be, zss) +DO_ST1_ZPZ_D(sd_le, zss) +DO_ST1_ZPZ_D(sd_be, zss) +DO_ST1_ZPZ_D(dd_le, zss) +DO_ST1_ZPZ_D(dd_be, zss) + +DO_ST1_ZPZ_D(bd, zd) +DO_ST1_ZPZ_D(hd_le, zd) +DO_ST1_ZPZ_D(hd_be, zd) +DO_ST1_ZPZ_D(sd_le, zd) +DO_ST1_ZPZ_D(sd_be, zd) +DO_ST1_ZPZ_D(dd_le, zd) +DO_ST1_ZPZ_D(dd_be, zd) + +#undef DO_ST1_ZPZ_S +#undef DO_ST1_ZPZ_D diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index f68b77c5163..86aeec1ca90 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -5299,35 +5299,58 @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1= _zpiz *a, uint32_t insn) return true; } =20 -/* Indexed by [xs][msz]. */ -static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][3] =3D { - { gen_helper_sve_stbs_zsu, - gen_helper_sve_sths_zsu, - gen_helper_sve_stss_zsu, }, - { gen_helper_sve_stbs_zss, - gen_helper_sve_sths_zss, - gen_helper_sve_stss_zss, }, +/* Indexed by [be][xs][msz]. */ +static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][2][3] =3D= { + /* Little-endian */ + { { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_le_zsu, + gen_helper_sve_stss_le_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_le_zss, + gen_helper_sve_stss_le_zss, } }, + /* Big-endian */ + { { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_be_zsu, + gen_helper_sve_stss_be_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_be_zss, + gen_helper_sve_stss_be_zss, } }, }; =20 /* Note that we overload xs=3D2 to indicate 64-bit offset. */ -static gen_helper_gvec_mem_scatter * const scatter_store_fn64[3][4] =3D { - { gen_helper_sve_stbd_zsu, - gen_helper_sve_sthd_zsu, - gen_helper_sve_stsd_zsu, - gen_helper_sve_stdd_zsu, }, - { gen_helper_sve_stbd_zss, - gen_helper_sve_sthd_zss, - gen_helper_sve_stsd_zss, - gen_helper_sve_stdd_zss, }, - { gen_helper_sve_stbd_zd, - gen_helper_sve_sthd_zd, - gen_helper_sve_stsd_zd, - gen_helper_sve_stdd_zd, }, +static gen_helper_gvec_mem_scatter * const scatter_store_fn64[2][3][4] =3D= { + /* Little-endian */ + { { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_le_zsu, + gen_helper_sve_stsd_le_zsu, + gen_helper_sve_stdd_le_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_le_zss, + gen_helper_sve_stsd_le_zss, + gen_helper_sve_stdd_le_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_le_zd, + gen_helper_sve_stsd_le_zd, + gen_helper_sve_stdd_le_zd, } }, + /* Big-endian */ + { { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_be_zsu, + gen_helper_sve_stsd_be_zsu, + gen_helper_sve_stdd_be_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_be_zss, + gen_helper_sve_stsd_be_zss, + gen_helper_sve_stdd_be_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_be_zd, + gen_helper_sve_stsd_be_zd, + gen_helper_sve_stdd_be_zd, } }, }; =20 static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn; + int be =3D s->be_data =3D=3D MO_BE; =20 if (a->esz < a->msz || (a->msz =3D=3D 0 && a->scale)) { return false; @@ -5337,10 +5360,10 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1= _zprz *a, uint32_t insn) } switch (a->esz) { case MO_32: - fn =3D scatter_store_fn32[a->xs][a->msz]; + fn =3D scatter_store_fn32[be][a->xs][a->msz]; break; case MO_64: - fn =3D scatter_store_fn64[a->xs][a->msz]; + fn =3D scatter_store_fn64[be][a->xs][a->msz]; break; default: g_assert_not_reached(); @@ -5353,6 +5376,7 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_z= prz *a, uint32_t insn) static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn =3D NULL; + int be =3D s->be_data =3D=3D MO_BE; TCGv_i64 imm; =20 if (a->esz < a->msz) { @@ -5364,10 +5388,10 @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1= _zpiz *a, uint32_t insn) =20 switch (a->esz) { case MO_32: - fn =3D scatter_store_fn32[0][a->msz]; + fn =3D scatter_store_fn32[be][0][a->msz]; break; case MO_64: - fn =3D scatter_store_fn64[2][a->msz]; + fn =3D scatter_store_fn64[be][2][a->msz]; break; } assert(fn !=3D NULL); --=20 2.19.0