target/arm: Implement bfloat widening fma (vector)

This is BFMLAL{B,T} for both AArch64 AdvSIMD and SVE,
and VFMA{B,T}.BF16 for AArch32 NEON.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 16 insertions, 0 deletions

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 27e9bdd329..d82736b5e6 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -2512,3 +2512,19 @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va,
+                         void *stat, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    intptr_t sel = simd_data(desc);
+    float32 *d = vd, *a = va;
+    bfloat16 *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        float32 nn = n[H2(i * 2 + sel)] << 16;
+        float32 mm = m[H2(i * 2 + sel)] << 16;
+        d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], 0, stat);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}