[PATCH v2 6/7] target/ppc: add vmulh{su}d instructions

[Lijun Pan]

vmulhsd: Vector Multiply High Signed Doubleword
vmulhud: Vector Multiply High Unsigned Doubleword

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             | 24 ++++++++++++++++++++++++
 target/ppc/translate/vmx-impl.inc.c |  2 ++
 target/ppc/translate/vmx-ops.inc.c  |  2 ++
 4 files changed, 30 insertions(+)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 6d4a3536eb..1aed2087cf 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -188,6 +188,8 @@ 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(vmulhsd, void, avr, avr, avr)
+DEF_HELPER_3(vmulhud, 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 7a3219887d..9a0937810f 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -523,6 +523,30 @@ void helper_vprtybq(ppc_avr_t *r, ppc_avr_t *b)
     r->VsrD(0) = 0;
 }
 
+void helper_vmulhsd(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+    int i;
+    uint64_t h64 = 0;
+    uint64_t l64 = 0;
+
+    for (i = 0; i < 2; i++) {
+        muls64(&l64, &h64, a->s64[i], b->s64[i]);
+        r->s64[i] = h64;
+    }
+}
+
+void helper_vmulhud(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+    int i;
+    uint64_t h64 = 0;
+    uint64_t l64 = 0;
+
+    for (i = 0; i < 2; i++) {
+        mulu64(&l64, &h64, a->s64[i], b->s64[i]);
+        r->u64[i] = h64;
+    }
+}
+
 #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)   \
     {                                                                   \
diff --git a/target/ppc/translate/vmx-impl.inc.c 
b/target/ppc/translate/vmx-impl.inc.c
index 03b5712d01..c494a7aebb 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -812,6 +812,7 @@ GEN_VXFORM(vmuleub, 4, 8);
 GEN_VXFORM(vmuleuh, 4, 9);
 GEN_VXFORM(vmuleuw, 4, 10);
 GEN_VXFORM(vmulhuw, 4, 10);
+GEN_VXFORM(vmulhud, 4, 11);
 GEN_VXFORM_DUAL(vmuleuw, PPC_ALTIVEC, PPC_NONE,
                 vmulhuw, PPC_NONE, PPC2_ISA310);
 GEN_VXFORM(vmulesb, 4, 12);
@@ -820,6 +821,7 @@ 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(vmulhsd, 4, 15);
 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 29701ad778..f3f4855111 100644
--- a/target/ppc/translate/vmx-ops.inc.c
+++ b/target/ppc/translate/vmx-ops.inc.c
@@ -111,9 +111,11 @@ GEN_VXFORM_310(vmulld, 4, 7),
 GEN_VXFORM(vmuleub, 4, 8),
 GEN_VXFORM(vmuleuh, 4, 9),
 GEN_VXFORM_DUAL(vmuleuw, vmulhuw, 4, 10, PPC_ALTIVEC, PPC_NONE),
+GEN_VXFORM_310(vmulhud, 4, 11),
 GEN_VXFORM(vmulesb, 4, 12),
 GEN_VXFORM(vmulesh, 4, 13),
 GEN_VXFORM_DUAL(vmulesw, vmulhsw, 4, 14, PPC_ALTIVEC, PPC_NONE),
+GEN_VXFORM_310(vmulhsd, 4, 15),
 GEN_VXFORM(vslb, 2, 4),
 GEN_VXFORM(vslh, 2, 5),
 GEN_VXFORM_DUAL(vslw, vrlwnm, 2, 6, PPC_ALTIVEC, PPC_NONE),
-- 
2.23.0