diff mbox

[v2,4/6] target-ppc: add vrldnm and vrlwnm instructions

Message ID 1477463189-26971-5-git-send-email-nikunj@linux.vnet.ibm.com (mailing list archive)
State New, archived
Headers show

Commit Message

Nikunj A. Dadhania Oct. 26, 2016, 6:26 a.m. UTC 
From: Bharata B Rao <bharata@linux.vnet.ibm.com>

vrldnm: Vector Rotate Left Doubleword then AND with Mask
vrlwnm: Vector Rotate Left Word then AND with Mask

Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
---
 disas/ppc.c                         |  2 ++
 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 ++--
 5 files changed, 22 insertions(+), 6 deletions(-)

Comments

David Gibson Oct. 27, 2016, 3:39 a.m. UTC | #1 
On Wed, Oct 26, 2016 at 11:56:27AM +0530, Nikunj A Dadhania wrote:
> From: Bharata B Rao <bharata@linux.vnet.ibm.com>
> 
> vrldnm: Vector Rotate Left Doubleword then AND with Mask
> vrlwnm: Vector Rotate Left Word then AND with Mask
> 
> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
> Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

With the caveat that I'd like to see the previous patch it's based on
share, rather than duplicate the mask generation with translate.c

> ---
>  disas/ppc.c                         |  2 ++
>  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 ++--
>  5 files changed, 22 insertions(+), 6 deletions(-)
> 
> diff --git a/disas/ppc.c b/disas/ppc.c
> index 32f0d8d..bd05623 100644
> --- a/disas/ppc.c
> +++ b/disas/ppc.c
> @@ -2287,7 +2287,9 @@ const struct powerpc_opcode powerpc_opcodes[] = {
>  { "vrlw",      VX(4,  132), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
>  { "vrsqrtefp", VX(4,  330), VX_MASK,	PPCVEC,		{ VD, VB } },
>  { "vrldmi",    VX(4,  197), VX_MASK,    PPCVEC,         { VD, VA, VB } },
> +{ "vrldnm",    VX(4,  453), VX_MASK,    PPCVEC,         { VD, VA, VB } },
>  { "vrlwmi",    VX(4,  133), VX_MASK,    PPCVEC,         { VD, VA, VB} },
> +{ "vrlwnm",    VX(4,  389), VX_MASK,    PPCVEC,         { VD, VA, VB } },
>  { "vsel",      VXA(4,  42), VXA_MASK,	PPCVEC,		{ VD, VA, VB, VC } },
>  { "vsl",       VX(4,  452), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
>  { "vslb",      VX(4,  260), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
> diff --git a/target-ppc/helper.h b/target-ppc/helper.h
> index 9fb8f0d..d6ee26e 100644
> --- a/target-ppc/helper.h
> +++ b/target-ppc/helper.h
> @@ -327,6 +327,8 @@ DEF_HELPER_3(vrefp, void, env, avr, avr)
>  DEF_HELPER_3(vrsqrtefp, void, env, avr, avr)
>  DEF_HELPER_3(vrlwmi, void, avr, avr, avr)
>  DEF_HELPER_3(vrldmi, void, avr, avr, avr)
> +DEF_HELPER_3(vrldnm, void, avr, avr, avr)
> +DEF_HELPER_3(vrlwnm, void, avr, avr, avr)
>  DEF_HELPER_5(vmaddfp, void, env, avr, avr, avr, avr)
>  DEF_HELPER_5(vnmsubfp, void, env, avr, avr, avr, avr)
>  DEF_HELPER_3(vexptefp, void, env, avr, avr)
> diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
> index b54cd7c..0fd92ed 100644
> --- a/target-ppc/int_helper.c
> +++ b/target-ppc/int_helper.c
> @@ -1741,7 +1741,7 @@ static inline uint##size##_t mask_u##size(uint##size##_t start, \
>  MASK(32, UINT32_MAX);
>  MASK(64, UINT64_MAX);
>  
> -#define VRLMI(name, size, element)                                    \
> +#define VRLMI(name, size, element, insert)                            \
>  void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)          \
>  {                                                                     \
>      int i;                                                            \
> @@ -1756,12 +1756,18 @@ void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)          \
>          begin = extract##size(src2, 16, 6);                           \
>          rot_val = rol##size(src1, shift);                             \
>          mask = mask_u##size(begin, end);                              \
> -        r->element[i] = (rot_val & mask) | (src3 & ~mask);            \
> +        if (insert) {                                                 \
> +            r->element[i] = (rot_val & mask) | (src3 & ~mask);        \
> +        } else {                                                      \
> +            r->element[i] = (rot_val & mask);                         \
> +        }                                                             \
>      }                                                                 \
>  }
>  
> -VRLMI(vrldmi, 64, u64);
> -VRLMI(vrlwmi, 32, u32);
> +VRLMI(vrldmi, 64, u64, 1);
> +VRLMI(vrlwmi, 32, u32, 1);
> +VRLMI(vrldnm, 64, u64, 0);
> +VRLMI(vrlwnm, 32, u32, 0);
>  
>  void helper_vsel(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 fdfbd6a..500c43f 100644
> --- a/target-ppc/translate/vmx-impl.inc.c
> +++ b/target-ppc/translate/vmx-impl.inc.c
> @@ -442,6 +442,9 @@ GEN_VXFORM(vmulesw, 4, 14);
>  GEN_VXFORM(vslb, 2, 4);
>  GEN_VXFORM(vslh, 2, 5);
>  GEN_VXFORM(vslw, 2, 6);
> +GEN_VXFORM(vrlwnm, 2, 6);
> +GEN_VXFORM_DUAL(vslw, PPC_ALTIVEC, PPC_NONE, \
> +                vrlwnm, PPC_NONE, PPC2_ISA300)
>  GEN_VXFORM(vsld, 2, 23);
>  GEN_VXFORM(vsrb, 2, 8);
>  GEN_VXFORM(vsrh, 2, 9);
> @@ -496,6 +499,9 @@ GEN_VXFORM(vrldmi, 2, 3);
>  GEN_VXFORM_DUAL(vrld, PPC_NONE, PPC2_ALTIVEC_207, \
>                  vrldmi, PPC_NONE, PPC2_ISA300)
>  GEN_VXFORM(vsl, 2, 7);
> +GEN_VXFORM(vrldnm, 2, 7);
> +GEN_VXFORM_DUAL(vsl, PPC_ALTIVEC, PPC_NONE, \
> +                vrldnm, PPC_NONE, PPC2_ISA300)
>  GEN_VXFORM(vsr, 2, 11);
>  GEN_VXFORM_ENV(vpkuhum, 7, 0);
>  GEN_VXFORM_ENV(vpkuwum, 7, 1);
> diff --git a/target-ppc/translate/vmx-ops.inc.c b/target-ppc/translate/vmx-ops.inc.c
> index 76b3593..a5ad4d4 100644
> --- a/target-ppc/translate/vmx-ops.inc.c
> +++ b/target-ppc/translate/vmx-ops.inc.c
> @@ -107,7 +107,7 @@ GEN_VXFORM(vmulesh, 4, 13),
>  GEN_VXFORM_207(vmulesw, 4, 14),
>  GEN_VXFORM(vslb, 2, 4),
>  GEN_VXFORM(vslh, 2, 5),
> -GEN_VXFORM(vslw, 2, 6),
> +GEN_VXFORM_DUAL(vslw, vrlwnm, 2, 6, PPC_ALTIVEC, PPC_NONE),
>  GEN_VXFORM_207(vsld, 2, 23),
>  GEN_VXFORM(vsrb, 2, 8),
>  GEN_VXFORM(vsrh, 2, 9),
> @@ -145,7 +145,7 @@ GEN_VXFORM(vrlb, 2, 0),
>  GEN_VXFORM(vrlh, 2, 1),
>  GEN_VXFORM_DUAL(vrlw, vrlwmi, 2, 2, PPC_ALTIVEC, PPC_NONE),
>  GEN_VXFORM_DUAL(vrld, vrldmi, 2, 3, PPC_NONE, PPC2_ALTIVEC_207),
> -GEN_VXFORM(vsl, 2, 7),
> +GEN_VXFORM_DUAL(vsl, vrldnm, 2, 7, PPC_ALTIVEC, PPC_NONE),
>  GEN_VXFORM(vsr, 2, 11),
>  GEN_VXFORM(vpkuhum, 7, 0),
>  GEN_VXFORM(vpkuwum, 7, 1),
diff mbox

Patch

diff --git a/disas/ppc.c b/disas/ppc.c
index 32f0d8d..bd05623 100644
--- a/disas/ppc.c
+++ b/disas/ppc.c
@@ -2287,7 +2287,9 @@  const struct powerpc_opcode powerpc_opcodes[] = {
 { "vrlw",      VX(4,  132), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
 { "vrsqrtefp", VX(4,  330), VX_MASK,	PPCVEC,		{ VD, VB } },
 { "vrldmi",    VX(4,  197), VX_MASK,    PPCVEC,         { VD, VA, VB } },
+{ "vrldnm",    VX(4,  453), VX_MASK,    PPCVEC,         { VD, VA, VB } },
 { "vrlwmi",    VX(4,  133), VX_MASK,    PPCVEC,         { VD, VA, VB} },
+{ "vrlwnm",    VX(4,  389), VX_MASK,    PPCVEC,         { VD, VA, VB } },
 { "vsel",      VXA(4,  42), VXA_MASK,	PPCVEC,		{ VD, VA, VB, VC } },
 { "vsl",       VX(4,  452), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
 { "vslb",      VX(4,  260), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 9fb8f0d..d6ee26e 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -327,6 +327,8 @@  DEF_HELPER_3(vrefp, void, env, avr, avr)
 DEF_HELPER_3(vrsqrtefp, void, env, avr, avr)
 DEF_HELPER_3(vrlwmi, void, avr, avr, avr)
 DEF_HELPER_3(vrldmi, void, avr, avr, avr)
+DEF_HELPER_3(vrldnm, void, avr, avr, avr)
+DEF_HELPER_3(vrlwnm, void, avr, avr, avr)
 DEF_HELPER_5(vmaddfp, void, env, avr, avr, avr, avr)
 DEF_HELPER_5(vnmsubfp, void, env, avr, avr, avr, avr)
 DEF_HELPER_3(vexptefp, void, env, avr, avr)
diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
index b54cd7c..0fd92ed 100644
--- a/target-ppc/int_helper.c
+++ b/target-ppc/int_helper.c
@@ -1741,7 +1741,7 @@  static inline uint##size##_t mask_u##size(uint##size##_t start, \
 MASK(32, UINT32_MAX);
 MASK(64, UINT64_MAX);
 
-#define VRLMI(name, size, element)                                    \
+#define VRLMI(name, size, element, insert)                            \
 void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)          \
 {                                                                     \
     int i;                                                            \
@@ -1756,12 +1756,18 @@  void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)          \
         begin = extract##size(src2, 16, 6);                           \
         rot_val = rol##size(src1, shift);                             \
         mask = mask_u##size(begin, end);                              \
-        r->element[i] = (rot_val & mask) | (src3 & ~mask);            \
+        if (insert) {                                                 \
+            r->element[i] = (rot_val & mask) | (src3 & ~mask);        \
+        } else {                                                      \
+            r->element[i] = (rot_val & mask);                         \
+        }                                                             \
     }                                                                 \
 }
 
-VRLMI(vrldmi, 64, u64);
-VRLMI(vrlwmi, 32, u32);
+VRLMI(vrldmi, 64, u64, 1);
+VRLMI(vrlwmi, 32, u32, 1);
+VRLMI(vrldnm, 64, u64, 0);
+VRLMI(vrlwnm, 32, u32, 0);
 
 void helper_vsel(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 fdfbd6a..500c43f 100644
--- a/target-ppc/translate/vmx-impl.inc.c
+++ b/target-ppc/translate/vmx-impl.inc.c
@@ -442,6 +442,9 @@  GEN_VXFORM(vmulesw, 4, 14);
 GEN_VXFORM(vslb, 2, 4);
 GEN_VXFORM(vslh, 2, 5);
 GEN_VXFORM(vslw, 2, 6);
+GEN_VXFORM(vrlwnm, 2, 6);
+GEN_VXFORM_DUAL(vslw, PPC_ALTIVEC, PPC_NONE, \
+                vrlwnm, PPC_NONE, PPC2_ISA300)
 GEN_VXFORM(vsld, 2, 23);
 GEN_VXFORM(vsrb, 2, 8);
 GEN_VXFORM(vsrh, 2, 9);
@@ -496,6 +499,9 @@  GEN_VXFORM(vrldmi, 2, 3);
 GEN_VXFORM_DUAL(vrld, PPC_NONE, PPC2_ALTIVEC_207, \
                 vrldmi, PPC_NONE, PPC2_ISA300)
 GEN_VXFORM(vsl, 2, 7);
+GEN_VXFORM(vrldnm, 2, 7);
+GEN_VXFORM_DUAL(vsl, PPC_ALTIVEC, PPC_NONE, \
+                vrldnm, PPC_NONE, PPC2_ISA300)
 GEN_VXFORM(vsr, 2, 11);
 GEN_VXFORM_ENV(vpkuhum, 7, 0);
 GEN_VXFORM_ENV(vpkuwum, 7, 1);
diff --git a/target-ppc/translate/vmx-ops.inc.c b/target-ppc/translate/vmx-ops.inc.c
index 76b3593..a5ad4d4 100644
--- a/target-ppc/translate/vmx-ops.inc.c
+++ b/target-ppc/translate/vmx-ops.inc.c
@@ -107,7 +107,7 @@  GEN_VXFORM(vmulesh, 4, 13),
 GEN_VXFORM_207(vmulesw, 4, 14),
 GEN_VXFORM(vslb, 2, 4),
 GEN_VXFORM(vslh, 2, 5),
-GEN_VXFORM(vslw, 2, 6),
+GEN_VXFORM_DUAL(vslw, vrlwnm, 2, 6, PPC_ALTIVEC, PPC_NONE),
 GEN_VXFORM_207(vsld, 2, 23),
 GEN_VXFORM(vsrb, 2, 8),
 GEN_VXFORM(vsrh, 2, 9),
@@ -145,7 +145,7 @@  GEN_VXFORM(vrlb, 2, 0),
 GEN_VXFORM(vrlh, 2, 1),
 GEN_VXFORM_DUAL(vrlw, vrlwmi, 2, 2, PPC_ALTIVEC, PPC_NONE),
 GEN_VXFORM_DUAL(vrld, vrldmi, 2, 3, PPC_NONE, PPC2_ALTIVEC_207),
-GEN_VXFORM(vsl, 2, 7),
+GEN_VXFORM_DUAL(vsl, vrldnm, 2, 7, PPC_ALTIVEC, PPC_NONE),
 GEN_VXFORM(vsr, 2, 11),
 GEN_VXFORM(vpkuhum, 7, 0),
 GEN_VXFORM(vpkuwum, 7, 1),