diff mbox series

[v3,5/8] target/ppc: add vmulh{su}w instructions

Message ID 20200625170018.64265-6-ljp@linux.ibm.com (mailing list archive)
State New, archived
Headers show
Series Add several Power ISA 3.1 32/64-bit vector instructions | expand

Commit Message

Lijun Pan June 25, 2020, 5 p.m. UTC 
vmulhsw: Vector Multiply High Signed Word
vmulhuw: Vector Multiply High Unsigned Word

Signed-off-by: Lijun Pan <ljp@linux.ibm.com>
---
v3: inline the helper_vmulh{su}w multiply directly instead of using macro

 target/ppc/helper.h                 |  2 ++
 target/ppc/int_helper.c             | 19 +++++++++++++++++++
 target/ppc/translate/vmx-impl.inc.c |  6 ++++++
 target/ppc/translate/vmx-ops.inc.c  |  4 ++--
 4 files changed, 29 insertions(+), 2 deletions(-)

Comments

Richard Henderson June 25, 2020, 6:26 p.m. UTC | #1 
On 6/25/20 10:00 AM, Lijun Pan wrote:
> vmulhsw: Vector Multiply High Signed Word
> vmulhuw: Vector Multiply High Unsigned Word
> 
> Signed-off-by: Lijun Pan <ljp@linux.ibm.com>
> ---
> v3: inline the helper_vmulh{su}w multiply directly instead of using macro
> 
>  target/ppc/helper.h                 |  2 ++
>  target/ppc/int_helper.c             | 19 +++++++++++++++++++
>  target/ppc/translate/vmx-impl.inc.c |  6 ++++++
>  target/ppc/translate/vmx-ops.inc.c  |  4 ++--
>  4 files changed, 29 insertions(+), 2 deletions(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>


r~
diff mbox series

Patch

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 69416b6d7c..3b3013866a 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -184,6 +184,8 @@  DEF_HELPER_3(vmulosw, void, avr, avr, avr)
 DEF_HELPER_3(vmuloub, void, avr, avr, avr)
 DEF_HELPER_3(vmulouh, void, avr, avr, avr)
 DEF_HELPER_3(vmulouw, 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 bd3e6d7cc7..a3a20821fc 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1086,6 +1086,25 @@  VMUL(uw, u32, VsrW, VsrD, uint64_t)
 #undef VMUL_DO_ODD
 #undef VMUL
 
+void helper_vmulhsw(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+    int i;
+
+    for (i = 0; i < 4; i++) {
+        r->s32[i] = (int32_t)(((int64_t)a->s32[i] * (int64_t)b->s32[i]) >> 32);
+    }
+}
+
+void helper_vmulhuw(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+    int i;
+
+    for (i = 0; i < 4; i++) {
+        r->u32[i] = (uint32_t)(((uint64_t)a->u32[i] *
+                               (uint64_t)b->u32[i]) >> 32);
+    }
+}
+
 void helper_vperm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b,
                   ppc_avr_t *c)
 {
diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c
index 8c89738552..50bac375fc 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -811,9 +811,15 @@  GEN_VXFORM_V(vmulld, MO_64, tcg_gen_gvec_mul, 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),