[PATCH v2 073/100] target/arm: Implement SVE2 integer multiply-add (indexed)

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h        | 14 ++++++++++++++
 target/arm/sve.decode      |  8 ++++++++
 target/arm/translate-sve.c | 23 +++++++++++++++++++++++
 target/arm/vec_helper.c    | 25 +++++++++++++++++++++++++
 4 files changed, 70 insertions(+)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index ce81a16a58..7964d299f6 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -793,6 +793,20 @@ 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/sve.decode b/target/arm/sve.decode
index fa0a572da6..467a93052f 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -785,6 +785,14 @@ SDOT_zzxw_d     01000100 .. 1 ..... 000000 ..... .....          @rrxr_d
 UDOT_zzxw_s     01000100 .. 1 ..... 000001 ..... .....          @rrxr_s
 UDOT_zzxw_d     01000100 .. 1 ..... 000001 ..... .....          @rrxr_d
 
+# SVE2 integer multiply-add (indexed)
+MLA_zzxz_h      01000100 .. 1 ..... 000010 ..... .....          @rrxr_h
+MLA_zzxz_s      01000100 .. 1 ..... 000010 ..... .....          @rrxr_s
+MLA_zzxz_d      01000100 .. 1 ..... 000010 ..... .....          @rrxr_d
+MLS_zzxz_h      01000100 .. 1 ..... 000011 ..... .....          @rrxr_h
+MLS_zzxz_s      01000100 .. 1 ..... 000011 ..... .....          @rrxr_s
+MLS_zzxz_d      01000100 .. 1 ..... 000011 ..... .....          @rrxr_d
+
 # SVE2 integer multiply (indexed)
 MUL_zzx_h       01000100 .. 1 ..... 111110 ..... .....          @rrx_h
 MUL_zzx_s       01000100 .. 1 ..... 111110 ..... .....          @rrx_s
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index dd2cd22061..0fb88f4aa5 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3870,6 +3870,29 @@ DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
 
 #undef DO_SVE2_RRX
 
+static bool do_sve2_zzxz_ool(DisasContext *s, arg_rrxr_esz *a,
+                             gen_helper_gvec_4 *fn)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    return do_zzxz_ool(s, a, fn);
+}
+
+#define DO_SVE2_RRXR(NAME, FUNC) \
+    static bool NAME(DisasContext *s, arg_rrxr_esz *a)  \
+    { return do_sve2_zzxz_ool(s, a, FUNC); }
+
+DO_SVE2_RRXR(trans_MLA_zzxz_h, gen_helper_gvec_mla_idx_h)
+DO_SVE2_RRXR(trans_MLA_zzxz_s, gen_helper_gvec_mla_idx_s)
+DO_SVE2_RRXR(trans_MLA_zzxz_d, gen_helper_gvec_mla_idx_d)
+
+DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h)
+DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s)
+DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d)
+
+#undef DO_SVE2_RRXR
+
 /*
  *** SVE Floating Point Multiply-Add Indexed Group
  */
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 08eadf06fc..fb8596c1fd 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -883,6 +883,31 @@ 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