[PULL 111/114] target/arm: Implement aarch32 VSUDOT, VUSDOT

[Peter Maydell <peter.maydell@linaro.org>]

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-90-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h              |  5 +++++
 target/arm/neon-shared.decode |  6 ++++++
 target/arm/translate-neon.c   | 27 +++++++++++++++++++++++++++
 3 files changed, 38 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 8ecb2a1c89e..04f8be35bf0 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -3783,6 +3783,11 @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id)
     return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0;
 }
 
+static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id)
+{
+    return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0;
+}
+
 static inline bool isar_feature_aa32_ras(const ARMISARegisters *id)
 {
     return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0;
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
index 2d94369750d..5befaec87b1 100644
--- a/target/arm/neon-shared.decode
+++ b/target/arm/neon-shared.decode
@@ -50,6 +50,8 @@ 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
+VUSDOT         1111 110 01 . 10 .... .... 1101 . q:1 . 0 .... \
+               vm=%vm_dp vn=%vn_dp vd=%vd_dp
 
 # VFM[AS]L
 VFML           1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \
@@ -66,6 +68,10 @@ 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
+VUSDOT_scalar  1111 1110 1 . 00 .... .... 1101 . q:1 index:1 0 vm:4 \
+               vn=%vn_dp vd=%vd_dp
+VSUDOT_scalar  1111 1110 1 . 00 .... .... 1101 . q:1 index:1 1 vm:4 \
+               vn=%vn_dp vd=%vd_dp
 
 %vfml_scalar_q0_rm 0:3 5:1
 %vfml_scalar_q1_index 5:1 3:1
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index 386b42fe4b0..b6ca29c25ca 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -287,6 +287,15 @@ static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
                         gen_helper_gvec_udot_b);
 }
 
+static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
+{
+    if (!dc_isar_feature(aa32_i8mm, s)) {
+        return false;
+    }
+    return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
+                        gen_helper_gvec_usdot_b);
+}
+
 static bool trans_VFML(DisasContext *s, arg_VFML *a)
 {
     int opr_sz;
@@ -354,6 +363,24 @@ static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
                         gen_helper_gvec_udot_idx_b);
 }
 
+static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a)
+{
+    if (!dc_isar_feature(aa32_i8mm, s)) {
+        return false;
+    }
+    return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
+                        gen_helper_gvec_usdot_idx_b);
+}
+
+static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
+{
+    if (!dc_isar_feature(aa32_i8mm, s)) {
+        return false;
+    }
+    return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
+                        gen_helper_gvec_sudot_idx_b);
+}
+
 static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a)
 {
     int opr_sz;
-- 
2.20.1