[PATCH 55/57] target/arm: Convert MLA, MLS to decodetree

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/a64.decode      |  8 ++++
 target/arm/tcg/translate-a64.c | 77 ++++++++++------------------------
 2 files changed, 31 insertions(+), 54 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index dbeb5667fd..8f7ae63e17 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -928,6 +928,8 @@ 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
+MLA_v           0.00 1110 ..1 ..... 10010 1 ..... ..... @qrrr_e
+MLS_v           0.10 1110 ..1 ..... 10010 1 ..... ..... @qrrr_e
 
 ### Advanced SIMD scalar x indexed element
 
@@ -972,3 +974,9 @@ 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
+
+MLA_vi          0.10 1111 01 .. .... 0000 . 0 ..... .....   @qrrx_h
+MLA_vi          0.10 1111 10 . ..... 0000 . 0 ..... .....   @qrrx_s
+
+MLS_vi          0.10 1111 01 .. .... 0100 . 0 ..... .....   @qrrx_h
+MLS_vi          0.10 1111 10 . ..... 0100 . 0 ..... .....   @qrrx_s
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index cd39fa1f20..c217522b2b 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5471,6 +5471,8 @@ 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)
+TRANS(MLA_v, do_gvec_fn3_no64, a, gen_gvec_mla)
+TRANS(MLS_v, do_gvec_fn3_no64, a, gen_gvec_mls)
 
 static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond)
 {
@@ -5713,6 +5715,24 @@ static gen_helper_gvec_3 * const f_vector_idx_mul[2] = {
 };
 TRANS(MUL_vi, do_int3_vector_idx, a, f_vector_idx_mul)
 
+static bool do_mla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool sub)
+{
+    static gen_helper_gvec_4 * const fns[2][2] = {
+        { gen_helper_gvec_mla_idx_h, gen_helper_gvec_mls_idx_h },
+        { gen_helper_gvec_mla_idx_s, gen_helper_gvec_mls_idx_s },
+    };
+
+    assert(a->esz == MO_16 || a->esz == MO_32);
+    if (fp_access_check(s)) {
+        gen_gvec_op4_ool(s, a->q, a->rd, a->rn, a->rm, a->rd,
+                         a->idx, fns[a->esz - 1][sub]);
+    }
+    return true;
+}
+
+TRANS(MLA_vi, do_mla_vector_idx, a, false)
+TRANS(MLS_vi, do_mla_vector_idx, a, true)
+
 /*
  * Advanced SIMD scalar pairwise
  */
@@ -10939,12 +10959,6 @@ static void disas_simd_3same_int(DisasContext *s, 
uint32_t insn)
     int rd = extract32(insn, 0, 5);
 
     switch (opcode) {
-    case 0x12: /* MLA, MLS */
-        if (size == 3) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
     case 0x16: /* SQDMULH, SQRDMULH */
         if (size == 0 || size == 3) {
             unallocated_encoding(s);
@@ -10975,6 +10989,7 @@ static void disas_simd_3same_int(DisasContext *s, 
uint32_t insn)
     case 0x0f: /* SABA, UABA */
     case 0x10: /* ADD, SUB */
     case 0x11: /* CMTST, CMEQ */
+    case 0x12: /* MLA, MLS */
     case 0x13: /* MUL, PMUL */
         unallocated_encoding(s);
         return;
@@ -10985,13 +11000,6 @@ static void disas_simd_3same_int(DisasContext *s, 
uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x12: /* MLA, MLS */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mla, size);
-        }
-        return;
     case 0x16: /* SQDMULH, SQRDMULH */
         {
             static gen_helper_gvec_3_ptr * const fns[2][2] = {
@@ -12198,13 +12206,6 @@ static void disas_simd_indexed(DisasContext *s, 
uint32_t insn)
     TCGv_ptr fpst;
 
     switch (16 * u + opcode) {
-    case 0x10: /* MLA */
-    case 0x14: /* MLS */
-        if (is_scalar) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
     case 0x02: /* SMLAL, SMLAL2 */
     case 0x12: /* UMLAL, UMLAL2 */
     case 0x06: /* SMLSL, SMLSL2 */
@@ -12286,6 +12287,8 @@ static void disas_simd_indexed(DisasContext *s, 
uint32_t insn)
     case 0x05: /* FMLS */
     case 0x08: /* MUL */
     case 0x09: /* FMUL */
+    case 0x10: /* MLA */
+    case 0x14: /* MLS */
     case 0x18: /* FMLAL2 */
     case 0x19: /* FMULX */
     case 0x1c: /* FMLSL2 */
@@ -12406,40 +12409,6 @@ static void disas_simd_indexed(DisasContext *s, 
uint32_t insn)
                                : gen_helper_gvec_fcmlah_idx);
         }
         return;
-
-    case 0x10: /* MLA */
-        if (!is_long && !is_scalar) {
-            static gen_helper_gvec_4 * const fns[3] = {
-                gen_helper_gvec_mla_idx_h,
-                gen_helper_gvec_mla_idx_s,
-                gen_helper_gvec_mla_idx_d,
-            };
-            tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm),
-                               vec_full_reg_offset(s, rd),
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               index, fns[size - 1]);
-            return;
-        }
-        break;
-
-    case 0x14: /* MLS */
-        if (!is_long && !is_scalar) {
-            static gen_helper_gvec_4 * const fns[3] = {
-                gen_helper_gvec_mls_idx_h,
-                gen_helper_gvec_mls_idx_s,
-                gen_helper_gvec_mls_idx_d,
-            };
-            tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm),
-                               vec_full_reg_offset(s, rd),
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               index, fns[size - 1]);
-            return;
-        }
-        break;
     }
 
     if (size == 3) {
-- 
2.34.1