target/arm: Implement bfloat widening fma (indexed)

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: 20210525225817.400336-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 30 insertions, 0 deletions

diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index ba8f5d7b7d..46210eb696 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8719,3 +8719,33 @@ static bool trans_BFMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a)
 {
     return do_BFMLAL_zzzw(s, a, true);
 }
+
+static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        TCGv_ptr status = fpstatus_ptr(FPST_FPCR);
+        unsigned vsz = vec_full_reg_size(s);
+
+        tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
+                           status, vsz, vsz, (a->index << 1) | sel,
+                           gen_helper_gvec_bfmlal_idx);
+        tcg_temp_free_ptr(status);
+    }
+    return true;
+}
+
+static bool trans_BFMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+    return do_BFMLAL_zzxw(s, a, false);
+}
+
+static bool trans_BFMLALT_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+    return do_BFMLAL_zzxw(s, a, true);
+}