Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/a64.decode      |  2 +
 target/arm/tcg/translate-a64.c | 77 +++++++++++++---------------------
 2 files changed, 31 insertions(+), 48 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 6819fd2587..15344a73de 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -951,6 +951,7 @@ 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
 BFDOT_v         0.10 1110 010 ..... 11111 1 ..... ..... @qrrr_s
+BFMLAL_v        0.10 1110 110 ..... 11111 1 ..... ..... @qrrr_h
 
 ### Advanced SIMD scalar x indexed element
 
@@ -1031,6 +1032,7 @@ 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
 BFDOT_vi        0.00 1111 01 .. .... 1111 . 0 ..... .....   @qrrx_s
+BFMLAL_vi       0.00 1111 11 .. .... 1111 . 0 ..... .....   @qrrx_h
 
 # Floating-point conditional select
 
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 0f44cd5aee..95be862dde 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5606,6 +5606,19 @@ 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)
 TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector, a, gen_helper_gvec_bfdot)
 
+static bool trans_BFMLAL_v(DisasContext *s, arg_qrrr_e *a)
+{
+    if (!dc_isar_feature(aa64_bf16, s)) {
+        return false;
+    }
+    if (fp_access_check(s)) {
+        /* Q bit selects BFMLALB vs BFMLALT. */
+        gen_gvec_op4_fpst(s, true, a->rd, a->rn, a->rm, a->rd, false, a->q,
+                          gen_helper_gvec_bfmlal);
+    }
+    return true;
+}
+
 /*
  * Advanced SIMD scalar/vector x indexed element
  */
@@ -5946,6 +5959,20 @@ TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
 TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx, a,
            gen_helper_gvec_bfdot_idx)
 
+static bool trans_BFMLAL_vi(DisasContext *s, arg_qrrx_e *a)
+{
+    if (!dc_isar_feature(aa64_bf16, s)) {
+        return false;
+    }
+    if (fp_access_check(s)) {
+        /* Q bit selects BFMLALB vs BFMLALT. */
+        gen_gvec_op4_fpst(s, true, a->rd, a->rn, a->rm, a->rd, 0,
+                          (a->idx << 1) | a->q,
+                          gen_helper_gvec_bfmlal_idx);
+    }
+    return true;
+}
+
 /*
  * Advanced SIMD scalar pairwise
  */
@@ -10952,23 +10979,13 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         }
         feature = dc_isar_feature(aa64_bf16, s);
         break;
-    case 0x1f:
-        switch (size) {
-        case 3: /* BFMLAL{B,T} */
-            feature = dc_isar_feature(aa64_bf16, s);
-            break;
-        default:
-        case 1: /* BFDOT */
-            unallocated_encoding(s);
-            return;
-        }
-        break;
     default:
     case 0x02: /* SDOT (vector) */
     case 0x03: /* USDOT */
     case 0x10: /* SQRDMLAH (vector) */
     case 0x11: /* SQRDMLSH (vector) */
     case 0x12: /* UDOT (vector) */
+    case 0x1f: /* BFDOT / BFMLAL */
         unallocated_encoding(s);
         return;
     }
@@ -11037,17 +11054,6 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
     case 0xd: /* BFMMLA */
         gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfmmla);
         return;
-    case 0xf:
-        switch (size) {
-        case 3: /* BFMLAL{B,T} */
-            gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, false, is_q,
-                              gen_helper_gvec_bfmlal);
-            break;
-        default:
-            g_assert_not_reached();
-        }
-        return;
-
     default:
         g_assert_not_reached();
     }
@@ -12051,24 +12057,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     case 0x0b: /* SQDMULL, SQDMULL2 */
         is_long = true;
         break;
-    case 0x0f:
-        switch (size) {
-        case 3: /* BFMLAL{B,T} */
-            if (is_scalar || !dc_isar_feature(aa64_bf16, s)) {
-                unallocated_encoding(s);
-                return;
-            }
-            /* can't set is_fp without other incorrect size checks */
-            size = MO_16;
-            break;
-        default:
-        case 0: /* SUDOT */
-        case 1: /* BFDOT */
-        case 2: /* USDOT */
-            unallocated_encoding(s);
-            return;
-        }
-        break;
     case 0x11: /* FCMLA #0 */
     case 0x13: /* FCMLA #90 */
     case 0x15: /* FCMLA #180 */
@@ -12089,6 +12077,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     case 0x0c: /* SQDMULH */
     case 0x0d: /* SQRDMULH */
     case 0x0e: /* SDOT */
+    case 0x0f: /* SUDOT / BFDOT / USDOT / BFMLAL */
     case 0x10: /* MLA */
     case 0x14: /* MLS */
     case 0x18: /* FMLAL2 */
@@ -12171,14 +12160,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     }
 
     switch (16 * u + opcode) {
-    case 0x0f:
-        switch (extract32(insn, 22, 2)) {
-        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);
-            return;
-        }
-        g_assert_not_reached();
     case 0x11: /* FCMLA #0 */
     case 0x13: /* FCMLA #90 */
     case 0x15: /* FCMLA #180 */
-- 
2.34.1

On Tue, 25 Jun 2024 at 06:10, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/arm/tcg/a64.decode      |  2 +
>  target/arm/tcg/translate-a64.c | 77 +++++++++++++---------------------
>  2 files changed, 31 insertions(+), 48 deletions(-)
>

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

thanks
-- PMM