diff mbox

[v4] target-ppc: add vextu[bhw][lr]x instructions

Message ID 1480319802-22842-1-git-send-email-nikunj@linux.vnet.ibm.com (mailing list archive)
State New, archived
Headers show

Commit Message

Nikunj A. Dadhania Nov. 28, 2016, 7:56 a.m. UTC 
From: Avinesh Kumar <avinesku@linux.vnet.ibm.com>

vextublx: Vector Extract Unsigned Byte Left
vextuhlx: Vector Extract Unsigned Halfword Left
vextuwlx: Vector Extract Unsigned Word Left
vextubrx: Vector Extract Unsigned Byte Right-Indexed VX-form
vextuhrx: Vector Extract Unsigned  Halfword Right-Indexed VX-form
vextuwrx: Vector Extract Unsigned Word Right-Indexed VX-form

Signed-off-by: Avinesh Kumar <avinesku@linux.vnet.ibm.com>
Signed-off-by: Hariharan T.S. <hari@linux.vnet.ibm.com>
[ implement using int128_rshift ]
Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
---

v3:
* Add the missing int128_getlo in the routine
---
 target-ppc/cpu.h                    |  2 ++
 target-ppc/helper.h                 |  6 ++++++
 target-ppc/int_helper.c             | 36 ++++++++++++++++++++++++++++++++++++
 target-ppc/translate/vmx-impl.inc.c | 23 +++++++++++++++++++++++
 target-ppc/translate/vmx-ops.inc.c  |  8 ++++++--
 5 files changed, 73 insertions(+), 2 deletions(-)

Comments

Richard Henderson Nov. 28, 2016, 1:48 p.m. UTC | #1 
On 11/27/2016 11:56 PM, Nikunj A Dadhania wrote:
> From: Avinesh Kumar <avinesku@linux.vnet.ibm.com>
> 
> vextublx: Vector Extract Unsigned Byte Left
> vextuhlx: Vector Extract Unsigned Halfword Left
> vextuwlx: Vector Extract Unsigned Word Left
> vextubrx: Vector Extract Unsigned Byte Right-Indexed VX-form
> vextuhrx: Vector Extract Unsigned  Halfword Right-Indexed VX-form
> vextuwrx: Vector Extract Unsigned Word Right-Indexed VX-form
> 
> Signed-off-by: Avinesh Kumar <avinesku@linux.vnet.ibm.com>
> Signed-off-by: Hariharan T.S. <hari@linux.vnet.ibm.com>
> [ implement using int128_rshift ]
> Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
> ---
> 
> v3:
> * Add the missing int128_getlo in the routine
> ---
>  target-ppc/cpu.h                    |  2 ++
>  target-ppc/helper.h                 |  6 ++++++
>  target-ppc/int_helper.c             | 36 ++++++++++++++++++++++++++++++++++++
>  target-ppc/translate/vmx-impl.inc.c | 23 +++++++++++++++++++++++
>  target-ppc/translate/vmx-ops.inc.c  |  8 ++++++--
>  5 files changed, 73 insertions(+), 2 deletions(-)

Reviewed-by: Richard Henderson <rth@twiddle.net>


r~
David Gibson Nov. 29, 2016, 2:49 a.m. UTC | #2 
On Mon, Nov 28, 2016 at 01:26:42PM +0530, Nikunj A Dadhania wrote:
> From: Avinesh Kumar <avinesku@linux.vnet.ibm.com>
> 
> vextublx: Vector Extract Unsigned Byte Left
> vextuhlx: Vector Extract Unsigned Halfword Left
> vextuwlx: Vector Extract Unsigned Word Left
> vextubrx: Vector Extract Unsigned Byte Right-Indexed VX-form
> vextuhrx: Vector Extract Unsigned  Halfword Right-Indexed VX-form
> vextuwrx: Vector Extract Unsigned Word Right-Indexed VX-form
> 
> Signed-off-by: Avinesh Kumar <avinesku@linux.vnet.ibm.com>
> Signed-off-by: Hariharan T.S. <hari@linux.vnet.ibm.com>
> [ implement using int128_rshift ]
> Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
> ---
> 
> v3:
> * Add the missing int128_getlo in the routine
> ---
>  target-ppc/cpu.h                    |  2 ++
>  target-ppc/helper.h                 |  6 ++++++
>  target-ppc/int_helper.c             | 36 ++++++++++++++++++++++++++++++++++++
>  target-ppc/translate/vmx-impl.inc.c | 23 +++++++++++++++++++++++
>  target-ppc/translate/vmx-ops.inc.c  |  8 ++++++--
>  5 files changed, 73 insertions(+), 2 deletions(-)

Applied to ppc-for-2.9, thanks.


> diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h
> index 5a5355c..72a8321 100644
> --- a/target-ppc/cpu.h
> +++ b/target-ppc/cpu.h
> @@ -21,6 +21,7 @@
>  #define PPC_CPU_H
>  
>  #include "qemu-common.h"
> +#include "qemu/int128.h"
>  
>  //#define PPC_EMULATE_32BITS_HYPV
>  
> @@ -262,6 +263,7 @@ union ppc_avr_t {
>  #ifdef CONFIG_INT128
>      __uint128_t u128;
>  #endif
> +    Int128 s128;
>  };
>  
>  #if !defined(CONFIG_USER_ONLY)
> diff --git a/target-ppc/helper.h b/target-ppc/helper.h
> index 3b26678..a6e04cb 100644
> --- a/target-ppc/helper.h
> +++ b/target-ppc/helper.h
> @@ -366,6 +366,12 @@ DEF_HELPER_3(vpmsumb, void, avr, avr, avr)
>  DEF_HELPER_3(vpmsumh, void, avr, avr, avr)
>  DEF_HELPER_3(vpmsumw, void, avr, avr, avr)
>  DEF_HELPER_3(vpmsumd, void, avr, avr, avr)
> +DEF_HELPER_2(vextublx, tl, tl, avr)
> +DEF_HELPER_2(vextuhlx, tl, tl, avr)
> +DEF_HELPER_2(vextuwlx, tl, tl, avr)
> +DEF_HELPER_2(vextubrx, tl, tl, avr)
> +DEF_HELPER_2(vextuhrx, tl, tl, avr)
> +DEF_HELPER_2(vextuwrx, tl, tl, avr)
>  
>  DEF_HELPER_2(vsbox, void, avr, avr)
>  DEF_HELPER_3(vcipher, void, avr, avr, avr)
> diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
> index fbf477f..a60d42b 100644
> --- a/target-ppc/int_helper.c
> +++ b/target-ppc/int_helper.c
> @@ -1805,6 +1805,42 @@ void helper_vlogefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
>      }
>  }
>  
> +#if defined(HOST_WORDS_BIGENDIAN)
> +#define VEXTU_X_DO(name, size, left)                                \
> +    target_ulong glue(helper_, name)(target_ulong a, ppc_avr_t *b)  \
> +    {                                                               \
> +        int index;                                                  \
> +        if (left) {                                                 \
> +            index = (a & 0xf) * 8;                                  \
> +        } else {                                                    \
> +            index = ((15 - (a & 0xf) + 1) * 8) - size;              \
> +        }                                                           \
> +        return int128_getlo(int128_rshift(b->s128, index)) &        \
> +            MAKE_64BIT_MASK(0, size);                               \
> +    }
> +#else
> +#define VEXTU_X_DO(name, size, left)                                \
> +    target_ulong glue(helper_, name)(target_ulong a, ppc_avr_t *b)  \
> +    {                                                               \
> +        int index;                                                  \
> +        if (left) {                                                 \
> +            index = ((15 - (a & 0xf) + 1) * 8) - size;              \
> +        } else {                                                    \
> +            index = (a & 0xf) * 8;                                  \
> +        }                                                           \
> +        return int128_getlo(int128_rshift(b->s128, index)) &        \
> +            MAKE_64BIT_MASK(0, size);                               \
> +    }
> +#endif
> +
> +VEXTU_X_DO(vextublx,  8, 1)
> +VEXTU_X_DO(vextuhlx, 16, 1)
> +VEXTU_X_DO(vextuwlx, 32, 1)
> +VEXTU_X_DO(vextubrx,  8, 0)
> +VEXTU_X_DO(vextuhrx, 16, 0)
> +VEXTU_X_DO(vextuwrx, 32, 0)
> +#undef VEXTU_X_DO
> +
>  /* The specification says that the results are undefined if all of the
>   * shift counts are not identical.  We check to make sure that they are
>   * to conform to what real hardware appears to do.  */
> diff --git a/target-ppc/translate/vmx-impl.inc.c b/target-ppc/translate/vmx-impl.inc.c
> index 7143eb3..3dea465 100644
> --- a/target-ppc/translate/vmx-impl.inc.c
> +++ b/target-ppc/translate/vmx-impl.inc.c
> @@ -340,6 +340,19 @@ static void glue(gen_, name0##_##name1)(DisasContext *ctx)              \
>      }                                                                   \
>  }
>  
> +#define GEN_VXFORM_HETRO(name, opc2, opc3)                              \
> +static void glue(gen_, name)(DisasContext *ctx)                         \
> +{                                                                       \
> +    TCGv_ptr rb;                                                        \
> +    if (unlikely(!ctx->altivec_enabled)) {                              \
> +        gen_exception(ctx, POWERPC_EXCP_VPU);                           \
> +        return;                                                         \
> +    }                                                                   \
> +    rb = gen_avr_ptr(rB(ctx->opcode));                                  \
> +    gen_helper_##name(cpu_gpr[rD(ctx->opcode)], cpu_gpr[rA(ctx->opcode)], rb); \
> +    tcg_temp_free_ptr(rb);                                              \
> +}
> +
>  GEN_VXFORM(vaddubm, 0, 0);
>  GEN_VXFORM_DUAL_EXT(vaddubm, PPC_ALTIVEC, PPC_NONE, 0,       \
>                      vmul10cuq, PPC_NONE, PPC2_ISA300, 0x0000F800)
> @@ -525,6 +538,16 @@ GEN_VXFORM_ENV(vaddfp, 5, 0);
>  GEN_VXFORM_ENV(vsubfp, 5, 1);
>  GEN_VXFORM_ENV(vmaxfp, 5, 16);
>  GEN_VXFORM_ENV(vminfp, 5, 17);
> +GEN_VXFORM_HETRO(vextublx, 6, 24)
> +GEN_VXFORM_HETRO(vextuhlx, 6, 25)
> +GEN_VXFORM_HETRO(vextuwlx, 6, 26)
> +GEN_VXFORM_DUAL(vmrgow, PPC_NONE, PPC2_ALTIVEC_207,
> +                vextuwlx, PPC_NONE, PPC2_ISA300)
> +GEN_VXFORM_HETRO(vextubrx, 6, 28)
> +GEN_VXFORM_HETRO(vextuhrx, 6, 29)
> +GEN_VXFORM_HETRO(vextuwrx, 6, 30)
> +GEN_VXFORM_DUAL(vmrgew, PPC_NONE, PPC2_ALTIVEC_207, \
> +                vextuwrx, PPC_NONE, PPC2_ISA300)
>  
>  #define GEN_VXRFORM1(opname, name, str, opc2, opc3)                     \
>  static void glue(gen_, name)(DisasContext *ctx)                         \
> diff --git a/target-ppc/translate/vmx-ops.inc.c b/target-ppc/translate/vmx-ops.inc.c
> index f02b3be..a3c9d05 100644
> --- a/target-ppc/translate/vmx-ops.inc.c
> +++ b/target-ppc/translate/vmx-ops.inc.c
> @@ -91,8 +91,12 @@ GEN_VXFORM(vmrghw, 6, 2),
>  GEN_VXFORM(vmrglb, 6, 4),
>  GEN_VXFORM(vmrglh, 6, 5),
>  GEN_VXFORM(vmrglw, 6, 6),
> -GEN_VXFORM_207(vmrgew, 6, 30),
> -GEN_VXFORM_207(vmrgow, 6, 26),
> +GEN_VXFORM_300(vextublx, 6, 24),
> +GEN_VXFORM_300(vextuhlx, 6, 25),
> +GEN_VXFORM_DUAL(vmrgow, vextuwlx, 6, 26, PPC_NONE, PPC2_ALTIVEC_207),
> +GEN_VXFORM_300(vextubrx, 6, 28),
> +GEN_VXFORM_300(vextuhrx, 6, 29),
> +GEN_VXFORM_DUAL(vmrgew, vextuwrx, 6, 30, PPC_NONE, PPC2_ALTIVEC_207),
>  GEN_VXFORM(vmuloub, 4, 0),
>  GEN_VXFORM(vmulouh, 4, 1),
>  GEN_VXFORM_DUAL(vmulouw, vmuluwm, 4, 2, PPC_ALTIVEC, PPC_NONE),
diff mbox

Patch

diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h
index 5a5355c..72a8321 100644
--- a/target-ppc/cpu.h
+++ b/target-ppc/cpu.h
@@ -21,6 +21,7 @@ 
 #define PPC_CPU_H
 
 #include "qemu-common.h"
+#include "qemu/int128.h"
 
 //#define PPC_EMULATE_32BITS_HYPV
 
@@ -262,6 +263,7 @@  union ppc_avr_t {
 #ifdef CONFIG_INT128
     __uint128_t u128;
 #endif
+    Int128 s128;
 };
 
 #if !defined(CONFIG_USER_ONLY)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 3b26678..a6e04cb 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -366,6 +366,12 @@  DEF_HELPER_3(vpmsumb, void, avr, avr, avr)
 DEF_HELPER_3(vpmsumh, void, avr, avr, avr)
 DEF_HELPER_3(vpmsumw, void, avr, avr, avr)
 DEF_HELPER_3(vpmsumd, void, avr, avr, avr)
+DEF_HELPER_2(vextublx, tl, tl, avr)
+DEF_HELPER_2(vextuhlx, tl, tl, avr)
+DEF_HELPER_2(vextuwlx, tl, tl, avr)
+DEF_HELPER_2(vextubrx, tl, tl, avr)
+DEF_HELPER_2(vextuhrx, tl, tl, avr)
+DEF_HELPER_2(vextuwrx, tl, tl, avr)
 
 DEF_HELPER_2(vsbox, void, avr, avr)
 DEF_HELPER_3(vcipher, void, avr, avr, avr)
diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
index fbf477f..a60d42b 100644
--- a/target-ppc/int_helper.c
+++ b/target-ppc/int_helper.c
@@ -1805,6 +1805,42 @@  void helper_vlogefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
     }
 }
 
+#if defined(HOST_WORDS_BIGENDIAN)
+#define VEXTU_X_DO(name, size, left)                                \
+    target_ulong glue(helper_, name)(target_ulong a, ppc_avr_t *b)  \
+    {                                                               \
+        int index;                                                  \
+        if (left) {                                                 \
+            index = (a & 0xf) * 8;                                  \
+        } else {                                                    \
+            index = ((15 - (a & 0xf) + 1) * 8) - size;              \
+        }                                                           \
+        return int128_getlo(int128_rshift(b->s128, index)) &        \
+            MAKE_64BIT_MASK(0, size);                               \
+    }
+#else
+#define VEXTU_X_DO(name, size, left)                                \
+    target_ulong glue(helper_, name)(target_ulong a, ppc_avr_t *b)  \
+    {                                                               \
+        int index;                                                  \
+        if (left) {                                                 \
+            index = ((15 - (a & 0xf) + 1) * 8) - size;              \
+        } else {                                                    \
+            index = (a & 0xf) * 8;                                  \
+        }                                                           \
+        return int128_getlo(int128_rshift(b->s128, index)) &        \
+            MAKE_64BIT_MASK(0, size);                               \
+    }
+#endif
+
+VEXTU_X_DO(vextublx,  8, 1)
+VEXTU_X_DO(vextuhlx, 16, 1)
+VEXTU_X_DO(vextuwlx, 32, 1)
+VEXTU_X_DO(vextubrx,  8, 0)
+VEXTU_X_DO(vextuhrx, 16, 0)
+VEXTU_X_DO(vextuwrx, 32, 0)
+#undef VEXTU_X_DO
+
 /* The specification says that the results are undefined if all of the
  * shift counts are not identical.  We check to make sure that they are
  * to conform to what real hardware appears to do.  */
diff --git a/target-ppc/translate/vmx-impl.inc.c b/target-ppc/translate/vmx-impl.inc.c
index 7143eb3..3dea465 100644
--- a/target-ppc/translate/vmx-impl.inc.c
+++ b/target-ppc/translate/vmx-impl.inc.c
@@ -340,6 +340,19 @@  static void glue(gen_, name0##_##name1)(DisasContext *ctx)              \
     }                                                                   \
 }
 
+#define GEN_VXFORM_HETRO(name, opc2, opc3)                              \
+static void glue(gen_, name)(DisasContext *ctx)                         \
+{                                                                       \
+    TCGv_ptr rb;                                                        \
+    if (unlikely(!ctx->altivec_enabled)) {                              \
+        gen_exception(ctx, POWERPC_EXCP_VPU);                           \
+        return;                                                         \
+    }                                                                   \
+    rb = gen_avr_ptr(rB(ctx->opcode));                                  \
+    gen_helper_##name(cpu_gpr[rD(ctx->opcode)], cpu_gpr[rA(ctx->opcode)], rb); \
+    tcg_temp_free_ptr(rb);                                              \
+}
+
 GEN_VXFORM(vaddubm, 0, 0);
 GEN_VXFORM_DUAL_EXT(vaddubm, PPC_ALTIVEC, PPC_NONE, 0,       \
                     vmul10cuq, PPC_NONE, PPC2_ISA300, 0x0000F800)
@@ -525,6 +538,16 @@  GEN_VXFORM_ENV(vaddfp, 5, 0);
 GEN_VXFORM_ENV(vsubfp, 5, 1);
 GEN_VXFORM_ENV(vmaxfp, 5, 16);
 GEN_VXFORM_ENV(vminfp, 5, 17);
+GEN_VXFORM_HETRO(vextublx, 6, 24)
+GEN_VXFORM_HETRO(vextuhlx, 6, 25)
+GEN_VXFORM_HETRO(vextuwlx, 6, 26)
+GEN_VXFORM_DUAL(vmrgow, PPC_NONE, PPC2_ALTIVEC_207,
+                vextuwlx, PPC_NONE, PPC2_ISA300)
+GEN_VXFORM_HETRO(vextubrx, 6, 28)
+GEN_VXFORM_HETRO(vextuhrx, 6, 29)
+GEN_VXFORM_HETRO(vextuwrx, 6, 30)
+GEN_VXFORM_DUAL(vmrgew, PPC_NONE, PPC2_ALTIVEC_207, \
+                vextuwrx, PPC_NONE, PPC2_ISA300)
 
 #define GEN_VXRFORM1(opname, name, str, opc2, opc3)                     \
 static void glue(gen_, name)(DisasContext *ctx)                         \
diff --git a/target-ppc/translate/vmx-ops.inc.c b/target-ppc/translate/vmx-ops.inc.c
index f02b3be..a3c9d05 100644
--- a/target-ppc/translate/vmx-ops.inc.c
+++ b/target-ppc/translate/vmx-ops.inc.c
@@ -91,8 +91,12 @@  GEN_VXFORM(vmrghw, 6, 2),
 GEN_VXFORM(vmrglb, 6, 4),
 GEN_VXFORM(vmrglh, 6, 5),
 GEN_VXFORM(vmrglw, 6, 6),
-GEN_VXFORM_207(vmrgew, 6, 30),
-GEN_VXFORM_207(vmrgow, 6, 26),
+GEN_VXFORM_300(vextublx, 6, 24),
+GEN_VXFORM_300(vextuhlx, 6, 25),
+GEN_VXFORM_DUAL(vmrgow, vextuwlx, 6, 26, PPC_NONE, PPC2_ALTIVEC_207),
+GEN_VXFORM_300(vextubrx, 6, 28),
+GEN_VXFORM_300(vextuhrx, 6, 29),
+GEN_VXFORM_DUAL(vmrgew, vextuwrx, 6, 30, PPC_NONE, PPC2_ALTIVEC_207),
 GEN_VXFORM(vmuloub, 4, 0),
 GEN_VXFORM(vmulouh, 4, 1),
 GEN_VXFORM_DUAL(vmulouw, vmuluwm, 4, 2, PPC_ALTIVEC, PPC_NONE),