target/arm: Convert sq{, r}dmulh to gvec for aa64 advsimd

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20200815013145.539409-21-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 48 insertions, 0 deletions

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 9e93a8a154..a6c53d2ab6 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -109,6 +109,30 @@ void HELPER(gvec_qrdmlsh_s16)(void *vd, void *vn, void *vm,
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
+void HELPER(neon_sqdmulh_h)(void *vd, void *vn, void *vm,
+                            void *vq, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int16_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 2; ++i) {
+        d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, false, vq);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(neon_sqrdmulh_h)(void *vd, void *vn, void *vm,
+                             void *vq, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int16_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 2; ++i) {
+        d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, true, vq);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
 /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */
 static int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
                              bool neg, bool round, uint32_t *sat)
@@ -172,6 +196,30 @@ void HELPER(gvec_qrdmlsh_s32)(void *vd, void *vn, void *vm,
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
+void HELPER(neon_sqdmulh_s)(void *vd, void *vn, void *vm,
+                            void *vq, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int32_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, false, vq);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(neon_sqrdmulh_s)(void *vd, void *vn, void *vm,
+                             void *vq, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int32_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, true, vq);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
 /* Integer 8 and 16-bit dot-product.
  *
  * Note that for the loops herein, host endianness does not matter