[PATCH v2 4/7] target/ppc: add vmulh{su}w instructions

[Lijun Pan <ljp@linux.ibm.com>]

vmulhsw: Vector Multiply High Signed Word
vmulhuw: Vector Multiply High Unsigned Word

Signed-off-by: Lijun Pan <ljp@linux.ibm.com>
---
v2: fix coding style
    use Power ISA 3.1 flag

 target/ppc/helper.h                 |  2 ++
 target/ppc/int_helper.c             | 14 ++++++++++++++
 target/ppc/translate/vmx-impl.inc.c |  6 ++++++
 target/ppc/translate/vmx-ops.inc.c  |  4 ++--
 4 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index c3f087ccb3..6d4a3536eb 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -186,6 +186,8 @@ DEF_HELPER_3(vmulouh, void, avr, avr, avr)
 DEF_HELPER_3(vmulouw, void, avr, avr, avr)
 DEF_HELPER_3(vmuluwm, void, avr, avr, avr)
 DEF_HELPER_3(vmulld, void, avr, avr, avr)
+DEF_HELPER_3(vmulhsw, void, avr, avr, avr)
+DEF_HELPER_3(vmulhuw, void, avr, avr, avr)
 DEF_HELPER_3(vslo, void, avr, avr, avr)
 DEF_HELPER_3(vsro, void, avr, avr, avr)
 DEF_HELPER_3(vsrv, void, avr, avr, avr)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index afbcdd05b4..7a3219887d 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -523,6 +523,20 @@ void helper_vprtybq(ppc_avr_t *r, ppc_avr_t *b)
     r->VsrD(0) = 0;
 }
 
+#define VMULH_DO(name, op, element, cast_orig, cast_temp)               \
+    void helper_vmulh##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)   \
+    {                                                                   \
+        int i;                                                          \
+                                                                        \
+        for (i = 0; i < ARRAY_SIZE(r->element); i++) {                  \
+            r->element[i] = (cast_orig)(((cast_temp)a->element[i] op    \
+                            (cast_temp)b->element[i]) >> 32);           \
+        }                                                               \
+    }
+VMULH_DO(sw, *, s32, int32_t, int64_t)
+VMULH_DO(uw, *, u32, uint32_t, uint64_t)
+#undef VMULH_DO
+
 #define VARITH_DO(name, op, element)                                    \
     void helper_v##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)       \
     {                                                                   \
diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c
index 4ee1df48f2..03b5712d01 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -811,9 +811,15 @@ GEN_VXFORM(vmulld,  4, 7);
 GEN_VXFORM(vmuleub, 4, 8);
 GEN_VXFORM(vmuleuh, 4, 9);
 GEN_VXFORM(vmuleuw, 4, 10);
+GEN_VXFORM(vmulhuw, 4, 10);
+GEN_VXFORM_DUAL(vmuleuw, PPC_ALTIVEC, PPC_NONE,
+                vmulhuw, PPC_NONE, PPC2_ISA310);
 GEN_VXFORM(vmulesb, 4, 12);
 GEN_VXFORM(vmulesh, 4, 13);
 GEN_VXFORM(vmulesw, 4, 14);
+GEN_VXFORM(vmulhsw, 4, 14);
+GEN_VXFORM_DUAL(vmulesw, PPC_ALTIVEC, PPC_NONE,
+                vmulhsw, PPC_NONE, PPC2_ISA310);
 GEN_VXFORM_V(vslb, MO_8, tcg_gen_gvec_shlv, 2, 4);
 GEN_VXFORM_V(vslh, MO_16, tcg_gen_gvec_shlv, 2, 5);
 GEN_VXFORM_V(vslw, MO_32, tcg_gen_gvec_shlv, 2, 6);
diff --git a/target/ppc/translate/vmx-ops.inc.c b/target/ppc/translate/vmx-ops.inc.c
index b49787ac97..29701ad778 100644
--- a/target/ppc/translate/vmx-ops.inc.c
+++ b/target/ppc/translate/vmx-ops.inc.c
@@ -110,10 +110,10 @@ GEN_VXFORM_207(vmulosw, 4, 6),
 GEN_VXFORM_310(vmulld, 4, 7),
 GEN_VXFORM(vmuleub, 4, 8),
 GEN_VXFORM(vmuleuh, 4, 9),
-GEN_VXFORM_207(vmuleuw, 4, 10),
+GEN_VXFORM_DUAL(vmuleuw, vmulhuw, 4, 10, PPC_ALTIVEC, PPC_NONE),
 GEN_VXFORM(vmulesb, 4, 12),
 GEN_VXFORM(vmulesh, 4, 13),
-GEN_VXFORM_207(vmulesw, 4, 14),
+GEN_VXFORM_DUAL(vmulesw, vmulhsw, 4, 14, PPC_ALTIVEC, PPC_NONE),
 GEN_VXFORM(vslb, 2, 4),
 GEN_VXFORM(vslh, 2, 5),
 GEN_VXFORM_DUAL(vslw, vrlwnm, 2, 6, PPC_ALTIVEC, PPC_NONE),
-- 
2.23.0