[PATCH v2 64/67] target/arm: Tidy SQDMULH, SQRDMULH (vector)

Richard Henderson posted 67 patches 6 months ago
Maintainers: Peter Maydell <peter.maydell@linaro.org>
[PATCH v2 64/67] target/arm: Tidy SQDMULH, SQRDMULH (vector)
Posted by Richard Henderson 6 months ago
We already have a gvec helper for the operations, but we aren't
using it on the aa32 neon side.  Create a unified expander for
use by both aa32 and aa64 translators.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate.h      |  4 ++++
 target/arm/tcg/gengvec.c        | 20 ++++++++++++++++++++
 target/arm/tcg/translate-a64.c  | 23 ++++-------------------
 target/arm/tcg/translate-neon.c | 23 +++--------------------
 4 files changed, 31 insertions(+), 39 deletions(-)

diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 3b1e68b779..aba21f730f 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -539,6 +539,10 @@ void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
 void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
                   int64_t shift, uint32_t opr_sz, uint32_t max_sz);
 
+void gen_gvec_sqdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                         uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_sqrdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                          uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                           uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index 32caabd126..462c185f9a 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -34,6 +34,26 @@ static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs,
                        opr_sz, max_sz, 0, fn);
 }
 
+void gen_gvec_sqdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                         uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_3_ptr * const fns[2] = {
+        gen_helper_neon_sqdmulh_h, gen_helper_neon_sqdmulh_s
+    };
+    tcg_debug_assert(vece >= 1 && vece <= 2);
+    gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
+}
+
+void gen_gvec_sqrdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                         uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_3_ptr * const fns[2] = {
+        gen_helper_neon_sqrdmulh_h, gen_helper_neon_sqrdmulh_s
+    };
+    tcg_debug_assert(vece >= 1 && vece <= 2);
+    gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
+}
+
 void gen_gvec_sqrdmlah_qc(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/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index c4601cde2f..c673b95ec7 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -724,19 +724,6 @@ static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn,
                        is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
 }
 
-/* Expand a 3-operand + qc + operation using an out-of-line helper.  */
-static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn,
-                            int rm, gen_helper_gvec_3_ptr *fn)
-{
-    TCGv_ptr qc_ptr = tcg_temp_new_ptr();
-
-    tcg_gen_addi_ptr(qc_ptr, tcg_env, offsetof(CPUARMState, vfp.qc));
-    tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
-                       vec_full_reg_offset(s, rn),
-                       vec_full_reg_offset(s, rm), qc_ptr,
-                       is_q ? 16 : 8, vec_full_reg_size(s), 0, fn);
-}
-
 /* Expand a 4-operand operation using an out-of-line helper.  */
 static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
                              int rm, int ra, int data, gen_helper_gvec_4 *fn)
@@ -11007,12 +10994,10 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
 
     switch (opcode) {
     case 0x16: /* SQDMULH, SQRDMULH */
-        {
-            static gen_helper_gvec_3_ptr * const fns[2][2] = {
-                { gen_helper_neon_sqdmulh_h, gen_helper_neon_sqrdmulh_h },
-                { gen_helper_neon_sqdmulh_s, gen_helper_neon_sqrdmulh_s },
-            };
-            gen_gvec_op3_qc(s, is_q, rd, rn, rm, fns[size - 1][u]);
+        if (u) {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmulh_qc, size);
+        } else {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqdmulh_qc, size);
         }
         return;
     }
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index f9a8753906..915c9e56db 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -937,28 +937,11 @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1)
     }
 
 #define DO_3SAME_VQDMULH(INSN, FUNC)                                    \
-    WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16);    \
-    WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32);    \
-    static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs,         \
-                                uint32_t rn_ofs, uint32_t rm_ofs,       \
-                                uint32_t oprsz, uint32_t maxsz)         \
-    {                                                                   \
-        static const GVecGen3 ops[2] = {                                \
-            { .fni4 = gen_##INSN##_tramp16 },                           \
-            { .fni4 = gen_##INSN##_tramp32 },                           \
-        };                                                              \
-        tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece - 1]); \
-    }                                                                   \
     static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a)        \
-    {                                                                   \
-        if (a->size != 1 && a->size != 2) {                             \
-            return false;                                               \
-        }                                                               \
-        return do_3same(s, a, gen_##INSN##_3s);                         \
-    }
+    { return a->size >= 1 && a->size <= 2 && do_3same(s, a, FUNC); }
 
-DO_3SAME_VQDMULH(VQDMULH, qdmulh)
-DO_3SAME_VQDMULH(VQRDMULH, qrdmulh)
+DO_3SAME_VQDMULH(VQDMULH, gen_gvec_sqdmulh_qc)
+DO_3SAME_VQDMULH(VQRDMULH, gen_gvec_sqrdmulh_qc)
 
 #define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC)                              \
     static void WRAPNAME(unsigned vece, uint32_t rd_ofs,                \
-- 
2.34.1
Re: [PATCH v2 64/67] target/arm: Tidy SQDMULH, SQRDMULH (vector)
Posted by Peter Maydell 6 months ago
On Sat, 25 May 2024 at 00:30, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> We already have a gvec helper for the operations, but we aren't
> using it on the aa32 neon side.  Create a unified expander for
> use by both aa32 and aa64 translators.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

thanks
-- PMM