[PATCH v5 58/81] target/arm: Implement SVE2 saturating multiply high (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 |  8 ++++
 target/arm/vec_helper.c    | 88 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 118 insertions(+)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index eb94b6b1e6..e7c463fff5 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -967,6 +967,20 @@ DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 #ifdef TARGET_AARCH64
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 407d3019d1..35010d755f 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -829,6 +829,14 @@ SQDMULLB_zzx_d  01000100 11 1 ..... 1110.0 ..... .....   @rrx_2a esz=3
 SQDMULLT_zzx_s  01000100 10 1 ..... 1110.1 ..... .....   @rrx_3a esz=2
 SQDMULLT_zzx_d  01000100 11 1 ..... 1110.1 ..... .....   @rrx_2a esz=3
 
+# SVE2 saturating multiply high (indexed)
+SQDMULH_zzx_h   01000100 0. 1 ..... 111100 ..... .....   @rrx_3 esz=1
+SQDMULH_zzx_s   01000100 10 1 ..... 111100 ..... .....   @rrx_2 esz=2
+SQDMULH_zzx_d   01000100 11 1 ..... 111100 ..... .....   @rrx_1 esz=3
+SQRDMULH_zzx_h  01000100 0. 1 ..... 111101 ..... .....   @rrx_3 esz=1
+SQRDMULH_zzx_s  01000100 10 1 ..... 111101 ..... .....   @rrx_2 esz=2
+SQRDMULH_zzx_d  01000100 11 1 ..... 111101 ..... .....   @rrx_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/translate-sve.c b/target/arm/translate-sve.c
index dd4de9e57f..b43bf939f5 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3864,6 +3864,14 @@ DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h)
 DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s)
 DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
 
+DO_SVE2_RRX(trans_SQDMULH_zzx_h, gen_helper_sve2_sqdmulh_idx_h)
+DO_SVE2_RRX(trans_SQDMULH_zzx_s, gen_helper_sve2_sqdmulh_idx_s)
+DO_SVE2_RRX(trans_SQDMULH_zzx_d, gen_helper_sve2_sqdmulh_idx_d)
+
+DO_SVE2_RRX(trans_SQRDMULH_zzx_h, gen_helper_sve2_sqrdmulh_idx_h)
+DO_SVE2_RRX(trans_SQRDMULH_zzx_s, gen_helper_sve2_sqrdmulh_idx_s)
+DO_SVE2_RRX(trans_SQRDMULH_zzx_d, gen_helper_sve2_sqrdmulh_idx_d)
+
 #undef DO_SVE2_RRX
 
 #define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 25061c15e1..8b7269d8e1 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -240,6 +240,36 @@ void HELPER(sve2_sqrdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
     }
 }
 
+void HELPER(sve2_sqdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    int idx = simd_data(desc);
+    int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+    uint32_t discard;
+
+    for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+        int16_t mm = m[i];
+        for (j = 0; j < 16 / 2; ++j) {
+            d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, &discard);
+        }
+    }
+}
+
+void HELPER(sve2_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    int idx = simd_data(desc);
+    int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+    uint32_t discard;
+
+    for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+        int16_t mm = m[i];
+        for (j = 0; j < 16 / 2; ++j) {
+            d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, &discard);
+        }
+    }
+}
+
 /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */
 int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
                       bool neg, bool round, uint32_t *sat)
@@ -373,6 +403,36 @@ void HELPER(sve2_sqrdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
     }
 }
 
+void HELPER(sve2_sqdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    int idx = simd_data(desc);
+    int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+    uint32_t discard;
+
+    for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+        int32_t mm = m[i];
+        for (j = 0; j < 16 / 4; ++j) {
+            d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, &discard);
+        }
+    }
+}
+
+void HELPER(sve2_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    int idx = simd_data(desc);
+    int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+    uint32_t discard;
+
+    for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+        int32_t mm = m[i];
+        for (j = 0; j < 16 / 4; ++j) {
+            d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, &discard);
+        }
+    }
+}
+
 /* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */
 static int64_t do_sat128_d(Int128 r)
 {
@@ -452,6 +512,34 @@ void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
     }
 }
 
+void HELPER(sve2_sqdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    int idx = simd_data(desc);
+    int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx;
+
+    for (i = 0; i < opr_sz / 8; i += 16 / 8) {
+        int64_t mm = m[i];
+        for (j = 0; j < 16 / 8; ++j) {
+            d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, false);
+        }
+    }
+}
+
+void HELPER(sve2_sqrdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    int idx = simd_data(desc);
+    int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx;
+
+    for (i = 0; i < opr_sz / 8; i += 16 / 8) {
+        int64_t mm = m[i];
+        for (j = 0; j < 16 / 8; ++j) {
+            d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, true);
+        }
+    }
+}
+
 /* Integer 8 and 16-bit dot-product.
  *
  * Note that for the loops herein, host endianness does not matter
-- 
2.25.1