[PATCH v2 35/67] target/arm: Convert FMLAL, FMLSL to decodetree

Richard Henderson posted 67 patches 6 months ago
Maintainers: Peter Maydell <peter.maydell@linaro.org>
[PATCH v2 35/67] target/arm: Convert FMLAL, FMLSL to decodetree
Posted by Richard Henderson 6 months ago
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/a64.decode      |  10 +++
 target/arm/tcg/translate-a64.c | 144 ++++++++++-----------------------
 2 files changed, 51 insertions(+), 103 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 22dfe8568d..7e993ed345 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -797,6 +797,11 @@ FMLA_v          0.00 1110 0.1 ..... 11001 1 ..... ..... @qrrr_sd
 FMLS_v          0.00 1110 110 ..... 00001 1 ..... ..... @qrrr_h
 FMLS_v          0.00 1110 1.1 ..... 11001 1 ..... ..... @qrrr_sd
 
+FMLAL_v         0.00 1110 001 ..... 11101 1 ..... ..... @qrrr_h
+FMLSL_v         0.00 1110 101 ..... 11101 1 ..... ..... @qrrr_h
+FMLAL2_v        0.10 1110 001 ..... 11001 1 ..... ..... @qrrr_h
+FMLSL2_v        0.10 1110 101 ..... 11001 1 ..... ..... @qrrr_h
+
 FCMEQ_v         0.00 1110 010 ..... 00100 1 ..... ..... @qrrr_h
 FCMEQ_v         0.00 1110 0.1 ..... 11100 1 ..... ..... @qrrr_sd
 
@@ -877,3 +882,8 @@ FMLS_vi         0.00 1111 11 0 ..... 0101 . 0 ..... .....   @qrrx_d
 FMULX_vi        0.10 1111 00 .. .... 1001 . 0 ..... .....   @qrrx_h
 FMULX_vi        0.10 1111 10 . ..... 1001 . 0 ..... .....   @qrrx_s
 FMULX_vi        0.10 1111 11 0 ..... 1001 . 0 ..... .....   @qrrx_d
+
+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
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 9fe70a939b..a4ff1fd202 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5256,6 +5256,24 @@ static gen_helper_gvec_3_ptr * const f_vector_fminnmp[3] = {
 };
 TRANS(FMINNMP_v, do_fp3_vector, a, f_vector_fminnmp)
 
+static bool do_fmlal(DisasContext *s, arg_qrrr_e *a, bool is_s, bool is_2)
+{
+    if (fp_access_check(s)) {
+        int data = (is_2 << 1) | is_s;
+        tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm), tcg_env,
+                           a->q ? 16 : 8, vec_full_reg_size(s),
+                           data, gen_helper_gvec_fmlal_a64);
+    }
+    return true;
+}
+
+TRANS_FEAT(FMLAL_v, aa64_fhm, do_fmlal, a, false, false)
+TRANS_FEAT(FMLSL_v, aa64_fhm, do_fmlal, a, true, false)
+TRANS_FEAT(FMLAL2_v, aa64_fhm, do_fmlal, a, false, true)
+TRANS_FEAT(FMLSL2_v, aa64_fhm, do_fmlal, a, true, true)
+
 TRANS(ADDP_v, do_gvec_fn3, a, gen_gvec_addp)
 TRANS(SMAXP_v, do_gvec_fn3_no64, a, gen_gvec_smaxp)
 TRANS(SMINP_v, do_gvec_fn3_no64, a, gen_gvec_sminp)
@@ -5447,6 +5465,24 @@ static bool do_fmla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool neg)
 TRANS(FMLA_vi, do_fmla_vector_idx, a, false)
 TRANS(FMLS_vi, do_fmla_vector_idx, a, true)
 
+static bool do_fmlal_idx(DisasContext *s, arg_qrrx_e *a, bool is_s, bool is_2)
+{
+    if (fp_access_check(s)) {
+        int data = (a->idx << 2) | (is_2 << 1) | is_s;
+        tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm), tcg_env,
+                           a->q ? 16 : 8, vec_full_reg_size(s),
+                           data, gen_helper_gvec_fmlal_idx_a64);
+    }
+    return true;
+}
+
+TRANS_FEAT(FMLAL_vi, aa64_fhm, do_fmlal_idx, a, false, false)
+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)
+
 /*
  * Advanced SIMD scalar pairwise
  */
@@ -10911,78 +10947,6 @@ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Floating point op subgroup of C3.6.16. */
-static void disas_simd_3same_float(DisasContext *s, uint32_t insn)
-{
-    /* For floating point ops, the U, size[1] and opcode bits
-     * together indicate the operation. size[0] indicates single
-     * or double.
-     */
-    int fpopcode = extract32(insn, 11, 5)
-        | (extract32(insn, 23, 1) << 5)
-        | (extract32(insn, 29, 1) << 6);
-    int is_q = extract32(insn, 30, 1);
-    int size = extract32(insn, 22, 1);
-    int rm = extract32(insn, 16, 5);
-    int rn = extract32(insn, 5, 5);
-    int rd = extract32(insn, 0, 5);
-
-    if (size == 1 && !is_q) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    switch (fpopcode) {
-    case 0x1d: /* FMLAL  */
-    case 0x3d: /* FMLSL  */
-    case 0x59: /* FMLAL2 */
-    case 0x79: /* FMLSL2 */
-        if (size & 1 || !dc_isar_feature(aa64_fhm, s)) {
-            unallocated_encoding(s);
-            return;
-        }
-        if (fp_access_check(s)) {
-            int is_s = extract32(insn, 23, 1);
-            int is_2 = extract32(insn, 29, 1);
-            int data = (is_2 << 1) | is_s;
-            tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm), tcg_env,
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               data, gen_helper_gvec_fmlal_a64);
-        }
-        return;
-
-    default:
-    case 0x18: /* FMAXNM */
-    case 0x19: /* FMLA */
-    case 0x1a: /* FADD */
-    case 0x1b: /* FMULX */
-    case 0x1c: /* FCMEQ */
-    case 0x1e: /* FMAX */
-    case 0x1f: /* FRECPS */
-    case 0x38: /* FMINNM */
-    case 0x39: /* FMLS */
-    case 0x3a: /* FSUB */
-    case 0x3e: /* FMIN */
-    case 0x3f: /* FRSQRTS */
-    case 0x58: /* FMAXNMP */
-    case 0x5a: /* FADDP */
-    case 0x5b: /* FMUL */
-    case 0x5c: /* FCMGE */
-    case 0x5d: /* FACGE */
-    case 0x5e: /* FMAXP */
-    case 0x5f: /* FDIV */
-    case 0x78: /* FMINNMP */
-    case 0x7a: /* FABD */
-    case 0x7d: /* FACGT */
-    case 0x7c: /* FCMGT */
-    case 0x7e: /* FMINP */
-        unallocated_encoding(s);
-        return;
-    }
-}
-
 /* Integer op subgroup of C3.6.16. */
 static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
 {
@@ -11251,16 +11215,13 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
     case 0x3: /* logic ops */
         disas_simd_3same_logic(s, insn);
         break;
-    case 0x18 ... 0x31:
-        /* floating point ops, sz[1] and U are part of opcode */
-        disas_simd_3same_float(s, insn);
-        break;
     default:
         disas_simd_3same_int(s, insn);
         break;
     case 0x14: /* SMAXP, UMAXP */
     case 0x15: /* SMINP, UMINP */
     case 0x17: /* ADDP */
+    case 0x18 ... 0x31: /* floating point ops */
         unallocated_encoding(s);
         break;
     }
@@ -12526,22 +12487,15 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
         }
         is_fp = 2;
         break;
-    case 0x00: /* FMLAL */
-    case 0x04: /* FMLSL */
-    case 0x18: /* FMLAL2 */
-    case 0x1c: /* FMLSL2 */
-        if (is_scalar || size != MO_32 || !dc_isar_feature(aa64_fhm, s)) {
-            unallocated_encoding(s);
-            return;
-        }
-        size = MO_16;
-        /* is_fp, but we pass tcg_env not fp_status.  */
-        break;
     default:
+    case 0x00: /* FMLAL */
     case 0x01: /* FMLA */
+    case 0x04: /* FMLSL */
     case 0x05: /* FMLS */
     case 0x09: /* FMUL */
+    case 0x18: /* FMLAL2 */
     case 0x19: /* FMULX */
+    case 0x1c: /* FMLSL2 */
         unallocated_encoding(s);
         return;
     }
@@ -12660,22 +12614,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
         }
         return;
 
-    case 0x00: /* FMLAL */
-    case 0x04: /* FMLSL */
-    case 0x18: /* FMLAL2 */
-    case 0x1c: /* FMLSL2 */
-        {
-            int is_s = extract32(opcode, 2, 1);
-            int is_2 = u;
-            int data = (index << 2) | (is_2 << 1) | is_s;
-            tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm), tcg_env,
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               data, gen_helper_gvec_fmlal_idx_a64);
-        }
-        return;
-
     case 0x08: /* MUL */
         if (!is_long && !is_scalar) {
             static gen_helper_gvec_3 * const fns[3] = {
-- 
2.34.1