diff mbox series

[v2,62/67] target/arm: Convert MUL, PMUL to decodetree

Message ID 20240524232121.284515-63-richard.henderson@linaro.org
State Superseded
Headers show
Series target/arm: Convert a64 advsimd to decodetree (part 1) | expand

Commit Message

Richard Henderson May 24, 2024, 11:21 p.m. UTC 
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/a64.decode      |  5 ++++
 target/arm/tcg/translate-a64.c | 51 +++++++++++++---------------------
 2 files changed, 25 insertions(+), 31 deletions(-)

Comments

Peter Maydell May 28, 2024, 4:06 p.m. UTC | #1 
On Sat, 25 May 2024 at 00:26, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/arm/tcg/a64.decode      |  5 ++++
>  target/arm/tcg/translate-a64.c | 51 +++++++++++++---------------------
>  2 files changed, 25 insertions(+), 31 deletions(-)

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

thanks
-- PMM
diff mbox series

Patch

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 07b604ec30..3ea0643370 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -926,6 +926,8 @@  SABD_v          0.00 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e
 UABD_v          0.10 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e
 SABA_v          0.00 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e
 UABA_v          0.10 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e
+MUL_v           0.00 1110 ..1 ..... 10011 1 ..... ..... @qrrr_e
+PMUL_v          0.10 1110 001 ..... 10011 1 ..... ..... @qrrr_b
 
 ### Advanced SIMD scalar x indexed element
 
@@ -967,3 +969,6 @@  FMLAL_vi        0.00 1111 10 .. .... 0000 . 0 ..... .....   @qrrx_h
 FMLSL_vi        0.00 1111 10 .. .... 0100 . 0 ..... .....   @qrrx_h
 FMLAL2_vi       0.10 1111 10 .. .... 1000 . 0 ..... .....   @qrrx_h
 FMLSL2_vi       0.10 1111 10 .. .... 1100 . 0 ..... .....   @qrrx_h
+
+MUL_vi          0.00 1111 01 .. .... 1000 . 0 ..... .....   @qrrx_h
+MUL_vi          0.00 1111 10 . ..... 1000 . 0 ..... .....   @qrrx_s
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 61afbc434f..1909d1426c 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5468,6 +5468,8 @@  TRANS(SABA_v, do_gvec_fn3_no64, a, gen_gvec_saba)
 TRANS(UABA_v, do_gvec_fn3_no64, a, gen_gvec_uaba)
 TRANS(SABD_v, do_gvec_fn3_no64, a, gen_gvec_sabd)
 TRANS(UABD_v, do_gvec_fn3_no64, a, gen_gvec_uabd)
+TRANS(MUL_v, do_gvec_fn3_no64, a, tcg_gen_gvec_mul)
+TRANS(PMUL_v, do_gvec_op3_ool, a, 0, gen_helper_gvec_pmul_b)
 
 static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond)
 {
@@ -5694,6 +5696,22 @@  TRANS_FEAT(FMLSL_vi, aa64_fhm, do_fmlal_idx, a, true, false)
 TRANS_FEAT(FMLAL2_vi, aa64_fhm, do_fmlal_idx, a, false, true)
 TRANS_FEAT(FMLSL2_vi, aa64_fhm, do_fmlal_idx, a, true, true)
 
+static bool do_int3_vector_idx(DisasContext *s, arg_qrrx_e *a,
+                               gen_helper_gvec_3 * const fns[2])
+{
+    assert(a->esz == MO_16 || a->esz == MO_32);
+    if (fp_access_check(s)) {
+        gen_gvec_op3_ool(s, a->q, a->rd, a->rn, a->rm, a->idx, fns[a->esz - 1]);
+    }
+    return true;
+}
+
+static gen_helper_gvec_3 * const f_vector_idx_mul[2] = {
+    gen_helper_gvec_mul_idx_h,
+    gen_helper_gvec_mul_idx_s,
+};
+TRANS(MUL_vi, do_int3_vector_idx, a, f_vector_idx_mul)
+
 /*
  * Advanced SIMD scalar pairwise
  */
@@ -10927,12 +10945,6 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     int rd = extract32(insn, 0, 5);
 
     switch (opcode) {
-    case 0x13: /* MUL, PMUL */
-        if (u && size != 0) {
-            unallocated_encoding(s);
-            return;
-        }
-        /* fall through */
     case 0x12: /* MLA, MLS */
         if (size == 3) {
             unallocated_encoding(s);
@@ -10969,6 +10981,7 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     case 0x0f: /* SABA, UABA */
     case 0x10: /* ADD, SUB */
     case 0x11: /* CMTST, CMEQ */
+    case 0x13: /* MUL, PMUL */
         unallocated_encoding(s);
         return;
     }
@@ -10978,13 +10991,6 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x13: /* MUL, PMUL */
-        if (!u) { /* MUL */
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_mul, size);
-        } else {  /* PMUL */
-            gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, gen_helper_gvec_pmul_b);
-        }
-        return;
     case 0x12: /* MLA, MLS */
         if (u) {
             gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size);
@@ -12198,7 +12204,6 @@  static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     TCGv_ptr fpst;
 
     switch (16 * u + opcode) {
-    case 0x08: /* MUL */
     case 0x10: /* MLA */
     case 0x14: /* MLS */
         if (is_scalar) {
@@ -12285,6 +12290,7 @@  static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     case 0x01: /* FMLA */
     case 0x04: /* FMLSL */
     case 0x05: /* FMLS */
+    case 0x08: /* MUL */
     case 0x09: /* FMUL */
     case 0x18: /* FMLAL2 */
     case 0x19: /* FMULX */
@@ -12407,22 +12413,6 @@  static void disas_simd_indexed(DisasContext *s, uint32_t insn)
         }
         return;
 
-    case 0x08: /* MUL */
-        if (!is_long && !is_scalar) {
-            static gen_helper_gvec_3 * const fns[3] = {
-                gen_helper_gvec_mul_idx_h,
-                gen_helper_gvec_mul_idx_s,
-                gen_helper_gvec_mul_idx_d,
-            };
-            tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm),
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               index, fns[size - 1]);
-            return;
-        }
-        break;
-
     case 0x10: /* MLA */
         if (!is_long && !is_scalar) {
             static gen_helper_gvec_4 * const fns[3] = {
@@ -12491,7 +12481,6 @@  static void disas_simd_indexed(DisasContext *s, uint32_t insn)
             read_vec_element_i32(s, tcg_op, rn, pass, is_scalar ? size : MO_32);
 
             switch (16 * u + opcode) {
-            case 0x08: /* MUL */
             case 0x10: /* MLA */
             case 0x14: /* MLS */
             {