target/arm: Implement SVE2 FMMLA

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-47-richard.henderson@linaro.org
Message-Id: <20200422165503.13511-1-steplong@quicinc.com>
[rth: Fix indexing in helpers, expand macro to straight functions.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 74 insertions, 0 deletions

diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 5b6292929e..fa96e28639 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -7241,3 +7241,77 @@ void HELPER(sve2_xar_s)(void *vd, void *vn, void *vm, uint32_t desc)
         d[i] = ror32(n[i] ^ m[i], shr);
     }
 }
+
+void HELPER(fmmla_s)(void *vd, void *vn, void *vm, void *va,
+                     void *status, uint32_t desc)
+{
+    intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float32) * 4);
+
+    for (s = 0; s < opr_sz; ++s) {
+        float32 *n = vn + s * sizeof(float32) * 4;
+        float32 *m = vm + s * sizeof(float32) * 4;
+        float32 *a = va + s * sizeof(float32) * 4;
+        float32 *d = vd + s * sizeof(float32) * 4;
+        float32 n00 = n[H4(0)], n01 = n[H4(1)];
+        float32 n10 = n[H4(2)], n11 = n[H4(3)];
+        float32 m00 = m[H4(0)], m01 = m[H4(1)];
+        float32 m10 = m[H4(2)], m11 = m[H4(3)];
+        float32 p0, p1;
+
+        /* i = 0, j = 0 */
+        p0 = float32_mul(n00, m00, status);
+        p1 = float32_mul(n01, m01, status);
+        d[H4(0)] = float32_add(a[H4(0)], float32_add(p0, p1, status), status);
+
+        /* i = 0, j = 1 */
+        p0 = float32_mul(n00, m10, status);
+        p1 = float32_mul(n01, m11, status);
+        d[H4(1)] = float32_add(a[H4(1)], float32_add(p0, p1, status), status);
+
+        /* i = 1, j = 0 */
+        p0 = float32_mul(n10, m00, status);
+        p1 = float32_mul(n11, m01, status);
+        d[H4(2)] = float32_add(a[H4(2)], float32_add(p0, p1, status), status);
+
+        /* i = 1, j = 1 */
+        p0 = float32_mul(n10, m10, status);
+        p1 = float32_mul(n11, m11, status);
+        d[H4(3)] = float32_add(a[H4(3)], float32_add(p0, p1, status), status);
+    }
+}
+
+void HELPER(fmmla_d)(void *vd, void *vn, void *vm, void *va,
+                     void *status, uint32_t desc)
+{
+    intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float64) * 4);
+
+    for (s = 0; s < opr_sz; ++s) {
+        float64 *n = vn + s * sizeof(float64) * 4;
+        float64 *m = vm + s * sizeof(float64) * 4;
+        float64 *a = va + s * sizeof(float64) * 4;
+        float64 *d = vd + s * sizeof(float64) * 4;
+        float64 n00 = n[0], n01 = n[1], n10 = n[2], n11 = n[3];
+        float64 m00 = m[0], m01 = m[1], m10 = m[2], m11 = m[3];
+        float64 p0, p1;
+
+        /* i = 0, j = 0 */
+        p0 = float64_mul(n00, m00, status);
+        p1 = float64_mul(n01, m01, status);
+        d[0] = float64_add(a[0], float64_add(p0, p1, status), status);
+
+        /* i = 0, j = 1 */
+        p0 = float64_mul(n00, m10, status);
+        p1 = float64_mul(n01, m11, status);
+        d[1] = float64_add(a[1], float64_add(p0, p1, status), status);
+
+        /* i = 1, j = 0 */
+        p0 = float64_mul(n10, m00, status);
+        p1 = float64_mul(n11, m01, status);
+        d[2] = float64_add(a[2], float64_add(p0, p1, status), status);
+
+        /* i = 1, j = 1 */
+        p0 = float64_mul(n10, m10, status);
+        p1 = float64_mul(n11, m11, status);
+        d[3] = float64_add(a[3], float64_add(p0, p1, status), status);
+    }
+}