@@ -46,8 +46,9 @@ VCMLA 1111 110 rot:2 . 1 . .... .... 1000 . q:1 . 0 .... \
VCADD 1111 110 rot:1 1 . 0 . .... .... 1000 . q:1 . 0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size
-# VUDOT and VSDOT
-VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \
+VSDOT 1111 110 00 . 10 .... .... 1101 . q:1 . 0 .... \
+ vm=%vm_dp vn=%vn_dp vd=%vd_dp
+VUDOT 1111 110 00 . 10 .... .... 1101 . q:1 . 1 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp
# VFM[AS]L
@@ -61,7 +62,9 @@ VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \
VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \
vm=%vm_dp vn=%vn_dp vd=%vd_dp size=2 index=0
-VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 vm:4 \
+VSDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 0 vm:4 \
+ vn=%vn_dp vd=%vd_dp
+VUDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 1 vm:4 \
vn=%vn_dp vd=%vd_dp
%vfml_scalar_q0_rm 0:3 5:1
@@ -260,15 +260,22 @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
return true;
}
-static bool trans_VDOT(DisasContext *s, arg_VDOT *a)
+static bool trans_VSDOT(DisasContext *s, arg_VSDOT *a)
{
if (!dc_isar_feature(aa32_dp, s)) {
return false;
}
return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
- a->u
- ? gen_helper_gvec_udot_b
- : gen_helper_gvec_sdot_b);
+ gen_helper_gvec_sdot_b);
+}
+
+static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
+{
+ if (!dc_isar_feature(aa32_dp, s)) {
+ return false;
+ }
+ return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
+ gen_helper_gvec_udot_b);
}
static bool trans_VFML(DisasContext *s, arg_VFML *a)
@@ -320,15 +327,22 @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
FPST_STD, gen_helper_gvec_fcmlas_idx);
}
-static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
+static bool trans_VSDOT_scalar(DisasContext *s, arg_VSDOT_scalar *a)
{
if (!dc_isar_feature(aa32_dp, s)) {
return false;
}
return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
- a->u
- ? gen_helper_gvec_udot_idx_b
- : gen_helper_gvec_sdot_idx_b);
+ gen_helper_gvec_sdot_idx_b);
+}
+
+static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
+{
+ if (!dc_isar_feature(aa32_dp, s)) {
+ return false;
+ }
+ return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
+ gen_helper_gvec_udot_idx_b);
}
static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a)
Now that we have a common helper, sharing decode does not save much. Also, this will solve an upcoming naming problem. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-shared.decode | 9 ++++++--- target/arm/translate-neon.c.inc | 30 ++++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 11 deletions(-) -- 2.25.1