Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/a64.decode      |  3 +++
 target/arm/tcg/translate-a64.c | 35 ++++++++--------------------------
 2 files changed, 11 insertions(+), 27 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 7411d4ba97..8a0251f83c 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -949,6 +949,7 @@ SQRDMLSH_v      0.10 1110 ..0 ..... 10001 1 ..... ..... @qrrr_e
 
 SDOT_v          0.00 1110 100 ..... 10010 1 ..... ..... @qrrr_s
 UDOT_v          0.10 1110 100 ..... 10010 1 ..... ..... @qrrr_s
+USDOT_v         0.00 1110 100 ..... 10011 1 ..... ..... @qrrr_s
 
 ### Advanced SIMD scalar x indexed element
 
@@ -1026,6 +1027,8 @@ SQRDMLSH_vi     0.10 1111 10 .. .... 1111 . 0 ..... .....   @qrrx_s
 
 SDOT_vi         0.00 1111 10 .. .... 1110 . 0 ..... .....   @qrrx_s
 UDOT_vi         0.10 1111 10 .. .... 1110 . 0 ..... .....   @qrrx_s
+SUDOT_vi        0.00 1111 00 .. .... 1111 . 0 ..... .....   @qrrx_s
+USDOT_vi        0.00 1111 10 .. .... 1111 . 0 ..... .....   @qrrx_s
 
 # Floating-point conditional select
 
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index f2e7d8d75c..9a658ca876 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5603,6 +5603,7 @@ static bool do_dot_vector(DisasContext *s, arg_qrrr_e *a,
 
 TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b)
 TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b)
+TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b)
 
 /*
  * Advanced SIMD scalar/vector x indexed element
@@ -5937,6 +5938,10 @@ static bool do_dot_vector_idx(DisasContext *s, arg_qrrx_e *a,
 
 TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b)
 TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b)
+TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
+           gen_helper_gvec_sudot_idx_b)
+TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
+           gen_helper_gvec_usdot_idx_b)
 
 /*
  * Advanced SIMD scalar pairwise
@@ -10914,13 +10919,6 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
     int rot;
 
     switch (u * 16 + opcode) {
-    case 0x03: /* USDOT */
-        if (size != MO_32) {
-            unallocated_encoding(s);
-            return;
-        }
-        feature = dc_isar_feature(aa64_i8mm, s);
-        break;
     case 0x04: /* SMMLA */
     case 0x14: /* UMMLA */
     case 0x05: /* USMMLA */
@@ -10964,6 +10962,7 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         break;
     default:
     case 0x02: /* SDOT (vector) */
+    case 0x03: /* USDOT */
     case 0x10: /* SQRDMLAH (vector) */
     case 0x11: /* SQRDMLSH (vector) */
     case 0x12: /* UDOT (vector) */
@@ -10979,10 +10978,6 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x3: /* USDOT */
-        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_usdot_b);
-        return;
-
     case 0x04: /* SMMLA, UMMLA */
         gen_gvec_op4_ool(s, 1, rd, rn, rm, rd, 0,
                          u ? gen_helper_gvec_ummla_b
@@ -12058,14 +12053,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
         break;
     case 0x0f:
         switch (size) {
-        case 0: /* SUDOT */
-        case 2: /* USDOT */
-            if (is_scalar || !dc_isar_feature(aa64_i8mm, s)) {
-                unallocated_encoding(s);
-                return;
-            }
-            size = MO_32;
-            break;
         case 1: /* BFDOT */
             if (is_scalar || !dc_isar_feature(aa64_bf16, s)) {
                 unallocated_encoding(s);
@@ -12082,6 +12069,8 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
             size = MO_16;
             break;
         default:
+        case 0: /* SUDOT */
+        case 2: /* USDOT */
             unallocated_encoding(s);
             return;
         }
@@ -12190,18 +12179,10 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     switch (16 * u + opcode) {
     case 0x0f:
         switch (extract32(insn, 22, 2)) {
-        case 0: /* SUDOT */
-            gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
-                             gen_helper_gvec_sudot_idx_b);
-            return;
         case 1: /* BFDOT */
             gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
                              gen_helper_gvec_bfdot_idx);
             return;
-        case 2: /* USDOT */
-            gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
-                             gen_helper_gvec_usdot_idx_b);
-            return;
         case 3: /* BFMLAL{B,T} */
             gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, 0, (index << 1) | is_q,
                               gen_helper_gvec_bfmlal_idx);
-- 
2.34.1

On Tue, 25 Jun 2024 at 06:09, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/arm/tcg/a64.decode      |  3 +++
>  target/arm/tcg/translate-a64.c | 35 ++++++++--------------------------
>  2 files changed, 11 insertions(+), 27 deletions(-)

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

thanks
-- PMM