target/arm: Split decode of VSDOT and VUDOT

Now that we have a common helper, sharing decode does not
save much.  Also, this will solve an upcoming naming problem.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-89-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
index facb621450dcea7b1aa151f081f554a0a6534215..2d94369750dfa54665333686e310d762f94670d4 100644 (file)
--- a/target/arm/neon-shared.decode
+++ b/target/arm/neon-shared.decode
@@ -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

diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index dfa33912ab1a15715d4300add3d4ac239b0a9fbb..386b42fe4b058ef87c4f259caee10413e7fd576f 100644 (file)
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -269,15 +269,22 @@ 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)
@@ -329,15 +336,22 @@ 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,
+                        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,
-                        a->u
-                        ? gen_helper_gvec_udot_idx_b
-                        : gen_helper_gvec_sdot_idx_b);
+                        gen_helper_gvec_udot_idx_b);
 }
 
 static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a)