[PATCH 19/20] target/arm: Convert integer multiply-add (indexed) to gvec for aa64 advsimd

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h        | 14 ++++++++++++++
 target/arm/translate-a64.c | 34 ++++++++++++++++++++++++++++++++++
 target/arm/vec_helper.c    | 25 +++++++++++++++++++++++++
 3 files changed, 73 insertions(+)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index d0573a53c8..378bb1898b 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -762,6 +762,20 @@ DEF_HELPER_FLAGS_4(gvec_mul_idx_h, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_mul_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_mul_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_mla_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mla_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mla_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_mls_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mls_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_mls_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 #ifdef TARGET_AARCH64
 #include "helper-a64.h"
 #include "helper-sve.h"
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index d08960a1c8..c74c6e854c 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -13523,6 +13523,40 @@ static void disas_simd_indexed(DisasContext *s, 
uint32_t insn)
             return;
         }
         break;
+
+    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) {
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index aa1de36921..fb53684ce3 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -731,6 +731,31 @@ DO_MUL_IDX(gvec_mul_idx_d, uint64_t, )
 
 #undef DO_MUL_IDX
 
+#define DO_MLA_IDX(NAME, TYPE, OP, H) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)   \
+{                                                                          \
+    intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE);  \
+    intptr_t idx = simd_data(desc);                                        \
+    TYPE *d = vd, *n = vn, *m = vm, *a = va;                               \
+    for (i = 0; i < oprsz / sizeof(TYPE); i += segment) {                  \
+        TYPE mm = m[H(i + idx)];                                           \
+        for (j = 0; j < segment; j++) {                                    \
+            d[i + j] = a[i + j] OP n[i + j] * mm;                          \
+        }                                                                  \
+    }                                                                      \
+    clear_tail(d, oprsz, simd_maxsz(desc));                                \
+}
+
+DO_MLA_IDX(gvec_mla_idx_h, uint16_t, +, H2)
+DO_MLA_IDX(gvec_mla_idx_s, uint32_t, +, H4)
+DO_MLA_IDX(gvec_mla_idx_d, uint64_t, +,   )
+
+DO_MLA_IDX(gvec_mls_idx_h, uint16_t, -, H2)
+DO_MLA_IDX(gvec_mls_idx_s, uint32_t, -, H4)
+DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -,   )
+
+#undef DO_MLA_IDX
+
 #define DO_FMUL_IDX(NAME, TYPE, H) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
 {                                                                          \
-- 
2.25.1