[PATCH v5 54/81] target/arm: Implement SVE2 saturating multiply-add high (indexed)

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-sve.h    | 14 +++++++++++++
 target/arm/sve.decode      |  8 ++++++++
 target/arm/sve_helper.c    | 40 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c |  8 ++++++++
 4 files changed, 70 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 7e99dcd119..fe67574741 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2665,3 +2665,17 @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, 
TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, 
i32)
 DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, 
i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 9bfaf737b7..1956d96ad5 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -791,6 +791,14 @@ MLS_zzxz_h      01000100 0. 1 ..... 000011 ..... .....   
@rrxr_3 esz=1
 MLS_zzxz_s      01000100 10 1 ..... 000011 ..... .....   @rrxr_2 esz=2
 MLS_zzxz_d      01000100 11 1 ..... 000011 ..... .....   @rrxr_1 esz=3
 
+# SVE2 saturating multiply-add high (indexed)
+SQRDMLAH_zzxz_h 01000100 0. 1 ..... 000100 ..... .....   @rrxr_3 esz=1
+SQRDMLAH_zzxz_s 01000100 10 1 ..... 000100 ..... .....   @rrxr_2 esz=2
+SQRDMLAH_zzxz_d 01000100 11 1 ..... 000100 ..... .....   @rrxr_1 esz=3
+SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... .....   @rrxr_3 esz=1
+SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... .....   @rrxr_2 esz=2
+SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... .....   @rrxr_1 esz=3
+
 # SVE2 integer multiply (indexed)
 MUL_zzx_h       01000100 0. 1 ..... 111110 ..... .....   @rrx_3 esz=1
 MUL_zzx_s       01000100 10 1 ..... 111110 ..... .....   @rrx_2 esz=2
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index f285c90b70..fc4a943029 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1487,9 +1487,49 @@ DO_CMLA(sve2_sqrdcmlah_zzzz_h, int16_t, H2, 
DO_SQRDMLAH_H)
 DO_CMLA(sve2_sqrdcmlah_zzzz_s, int32_t, H4, DO_SQRDMLAH_S)
 DO_CMLA(sve2_sqrdcmlah_zzzz_d, int64_t,   , DO_SQRDMLAH_D)
 
+#undef DO_SQRDMLAH_B
+#undef DO_SQRDMLAH_H
+#undef DO_SQRDMLAH_S
+#undef DO_SQRDMLAH_D
 #undef do_cmla
 #undef DO_CMLA
 
+#define DO_ZZXZ(NAME, TYPE, H, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                                       \
+    intptr_t oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE);     \
+    intptr_t i, j, idx = simd_data(desc);                               \
+    TYPE *d = vd, *a = va, *n = vn, *m = (TYPE *)vm + H(idx);           \
+    for (i = 0; i < oprsz / sizeof(TYPE); i += segment) {               \
+        TYPE mm = m[i];                                                 \
+        for (j = 0; j < segment; j++) {                                 \
+            d[i + j] = OP(n[i + j], mm, a[i + j]);                      \
+        }                                                               \
+    }                                                                   \
+}
+
+#define DO_SQRDMLAH_H(N, M, A) \
+    ({ uint32_t discard; do_sqrdmlah_h(N, M, A, false, true, &discard); })
+#define DO_SQRDMLAH_S(N, M, A) \
+    ({ uint32_t discard; do_sqrdmlah_s(N, M, A, false, true, &discard); })
+#define DO_SQRDMLAH_D(N, M, A) do_sqrdmlah_d(N, M, A, false, true)
+
+DO_ZZXZ(sve2_sqrdmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H)
+DO_ZZXZ(sve2_sqrdmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S)
+DO_ZZXZ(sve2_sqrdmlah_idx_d, int64_t,   , DO_SQRDMLAH_D)
+
+#define DO_SQRDMLSH_H(N, M, A) \
+    ({ uint32_t discard; do_sqrdmlah_h(N, M, A, true, true, &discard); })
+#define DO_SQRDMLSH_S(N, M, A) \
+    ({ uint32_t discard; do_sqrdmlah_s(N, M, A, true, true, &discard); })
+#define DO_SQRDMLSH_D(N, M, A) do_sqrdmlah_d(N, M, A, true, true)
+
+DO_ZZXZ(sve2_sqrdmlsh_idx_h, int16_t, H2, DO_SQRDMLSH_H)
+DO_ZZXZ(sve2_sqrdmlsh_idx_s, int32_t, H4, DO_SQRDMLSH_S)
+DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t,   , DO_SQRDMLSH_D)
+
+#undef DO_ZZXZ
+
 #define DO_BITPERM(NAME, TYPE, OP) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
 {                                                              \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 25dadabe28..42d8582707 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3887,6 +3887,14 @@ 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)
 
+DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_h, gen_helper_sve2_sqrdmlah_idx_h)
+DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_s, gen_helper_sve2_sqrdmlah_idx_s)
+DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_d, gen_helper_sve2_sqrdmlah_idx_d)
+
+DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_h, gen_helper_sve2_sqrdmlsh_idx_h)
+DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_s, gen_helper_sve2_sqrdmlsh_idx_s)
+DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d)
+
 #undef DO_SVE2_RRXR
 
 /*
-- 
2.25.1