diff mbox

[v3,3/5] target-ppc: add vector count trailing zeros instructions

Message ID 1470901008-3284-4-git-send-email-raji@linux.vnet.ibm.com
State New
Headers show

Commit Message

Rajalakshmi Srinivasaraghavan Aug. 11, 2016, 7:36 a.m. UTC
The following vector count trailing zeros instructions are
added from ISA 3.0.

vctzb - Vector Count Trailing Zeros Byte
vctzh - Vector Count Trailing Zeros Halfword
vctzw - Vector Count Trailing Zeros Word
vctzd - Vector Count Trailing Zeros Doubleword

Signed-off-by: Rajalakshmi Srinivasaraghavan <raji@linux.vnet.ibm.com>
---
 target-ppc/helper.h             |    4 ++++
 target-ppc/int_helper.c         |   15 +++++++++++++++
 target-ppc/translate/vmx-impl.c |   19 +++++++++++++++++++
 target-ppc/translate/vmx-ops.c  |    8 ++++++++
 4 files changed, 46 insertions(+), 0 deletions(-)

Comments

David Gibson Aug. 16, 2016, 4:46 a.m. UTC | #1
On Thu, Aug 11, 2016 at 01:06:46PM +0530, Rajalakshmi Srinivasaraghavan wrote:
> The following vector count trailing zeros instructions are
> added from ISA 3.0.
> 
> vctzb - Vector Count Trailing Zeros Byte
> vctzh - Vector Count Trailing Zeros Halfword
> vctzw - Vector Count Trailing Zeros Word
> vctzd - Vector Count Trailing Zeros Doubleword
> 
> Signed-off-by: Rajalakshmi Srinivasaraghavan <raji@linux.vnet.ibm.com>

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

However, it needs a rebase.

> ---
>  target-ppc/helper.h             |    4 ++++
>  target-ppc/int_helper.c         |   15 +++++++++++++++
>  target-ppc/translate/vmx-impl.c |   19 +++++++++++++++++++
>  target-ppc/translate/vmx-ops.c  |    8 ++++++++
>  4 files changed, 46 insertions(+), 0 deletions(-)
> 
> diff --git a/target-ppc/helper.h b/target-ppc/helper.h
> index 59e7b88..6e6e7b3 100644
> --- a/target-ppc/helper.h
> +++ b/target-ppc/helper.h
> @@ -327,6 +327,10 @@ DEF_HELPER_2(vclzb, void, avr, avr)
>  DEF_HELPER_2(vclzh, void, avr, avr)
>  DEF_HELPER_2(vclzw, void, avr, avr)
>  DEF_HELPER_2(vclzd, void, avr, avr)
> +DEF_HELPER_2(vctzb, void, avr, avr)
> +DEF_HELPER_2(vctzh, void, avr, avr)
> +DEF_HELPER_2(vctzw, void, avr, avr)
> +DEF_HELPER_2(vctzd, void, avr, avr)
>  DEF_HELPER_2(vpopcntb, void, avr, avr)
>  DEF_HELPER_2(vpopcnth, void, avr, avr)
>  DEF_HELPER_2(vpopcntw, void, avr, avr)
> diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
> index a917bd5..162f1e9 100644
> --- a/target-ppc/int_helper.c
> +++ b/target-ppc/int_helper.c
> @@ -2091,6 +2091,21 @@ VGENERIC_DO(clzd, u64)
>  #undef clzw
>  #undef clzd
>  
> +#define ctzb(v) ((v) ? ctz32(v) : 8)
> +#define ctzh(v) ((v) ? ctz32(v) : 16)
> +#define ctzw(v) ctz32((v))
> +#define ctzd(v) ctz64((v))
> +
> +VGENERIC_DO(ctzb, u8)
> +VGENERIC_DO(ctzh, u16)
> +VGENERIC_DO(ctzw, u32)
> +VGENERIC_DO(ctzd, u64)
> +
> +#undef ctzb
> +#undef ctzh
> +#undef ctzw
> +#undef ctzd
> +
>  #define popcntb(v) ctpop8(v)
>  #define popcnth(v) ctpop16(v)
>  #define popcntw(v) ctpop32(v)
> diff --git a/target-ppc/translate/vmx-impl.c b/target-ppc/translate/vmx-impl.c
> index 766a645..ebf123f 100644
> --- a/target-ppc/translate/vmx-impl.c
> +++ b/target-ppc/translate/vmx-impl.c
> @@ -553,6 +553,21 @@ static void glue(gen_, name)(DisasContext *ctx)                         \
>          tcg_temp_free_ptr(rd);                                          \
>      }
>  
> +#define GEN_VXFORM_NOA_2(name, opc2, opc3, opc4)                        \
> +static void glue(gen_, name)(DisasContext *ctx)                         \
> +    {                                                                   \
> +        TCGv_ptr rb, rd;                                                \
> +        if (unlikely(!ctx->altivec_enabled)) {                          \
> +            gen_exception(ctx, POWERPC_EXCP_VPU);                       \
> +            return;                                                     \
> +        }                                                               \
> +        rb = gen_avr_ptr(rB(ctx->opcode));                              \
> +        rd = gen_avr_ptr(rD(ctx->opcode));                              \
> +        gen_helper_##name(rd, rb);                                      \
> +        tcg_temp_free_ptr(rb);                                          \
> +        tcg_temp_free_ptr(rd);                                          \
> +    }
> +
>  GEN_VXFORM_NOA(vupkhsb, 7, 8);
>  GEN_VXFORM_NOA(vupkhsh, 7, 9);
>  GEN_VXFORM_NOA(vupkhsw, 7, 25);
> @@ -745,6 +760,10 @@ GEN_VXFORM_NOA(vclzb, 1, 28)
>  GEN_VXFORM_NOA(vclzh, 1, 29)
>  GEN_VXFORM_NOA(vclzw, 1, 30)
>  GEN_VXFORM_NOA(vclzd, 1, 31)
> +GEN_VXFORM_NOA_2(vctzb, 1, 24, 28)
> +GEN_VXFORM_NOA_2(vctzh, 1, 24, 29)
> +GEN_VXFORM_NOA_2(vctzw, 1, 24, 30)
> +GEN_VXFORM_NOA_2(vctzd, 1, 24, 31)
>  GEN_VXFORM_NOA(vpopcntb, 1, 28)
>  GEN_VXFORM_NOA(vpopcnth, 1, 29)
>  GEN_VXFORM_NOA(vpopcntw, 1, 30)
> diff --git a/target-ppc/translate/vmx-ops.c b/target-ppc/translate/vmx-ops.c
> index aafe70b..5b2826e 100644
> --- a/target-ppc/translate/vmx-ops.c
> +++ b/target-ppc/translate/vmx-ops.c
> @@ -44,6 +44,10 @@ GEN_HANDLER_E(name, 0x04, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ISA300)
>  #define GEN_VXFORM_300_EXT(name, opc2, opc3, inval)                     \
>  GEN_HANDLER_E(name, 0x04, opc2, opc3, inval, PPC_NONE, PPC2_ISA300)
>  
> +#define GEN_VXFORM_300_EO(name, opc2, opc3, opc4)                     \
> +GEN_HANDLER_E_2(name, 0x04, opc2, opc3, opc4, 0x00000000, PPC_NONE,     \
> +                                                       PPC2_ISA300)
> +
>  #define GEN_VXFORM_DUAL(name0, name1, opc2, opc3, type0, type1) \
>  GEN_HANDLER_E(name0##_##name1, 0x4, opc2, opc3, 0x00000000, type0, type1)
>  
> @@ -211,6 +215,10 @@ GEN_VXFORM_DUAL_INV(vspltish, vinserth, 6, 13, 0x00000000, 0x100000,
>  GEN_VXFORM_DUAL_INV(vspltisw, vinsertw, 6, 14, 0x00000000, 0x100000,
>                                                 PPC2_ALTIVEC_207),
>  GEN_VXFORM_300_EXT(vinsertd, 6, 15, 0x100000),
> +GEN_VXFORM_300_EO(vctzb, 0x01, 0x18, 0x1C),
> +GEN_VXFORM_300_EO(vctzh, 0x01, 0x18, 0x1D),
> +GEN_VXFORM_300_EO(vctzw, 0x01, 0x18, 0x1E),
> +GEN_VXFORM_300_EO(vctzd, 0x01, 0x18, 0x1F),
>  
>  #define GEN_VXFORM_NOA(name, opc2, opc3)                                \
>      GEN_HANDLER(name, 0x04, opc2, opc3, 0x001f0000, PPC_ALTIVEC)
diff mbox

Patch

diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 59e7b88..6e6e7b3 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -327,6 +327,10 @@  DEF_HELPER_2(vclzb, void, avr, avr)
 DEF_HELPER_2(vclzh, void, avr, avr)
 DEF_HELPER_2(vclzw, void, avr, avr)
 DEF_HELPER_2(vclzd, void, avr, avr)
+DEF_HELPER_2(vctzb, void, avr, avr)
+DEF_HELPER_2(vctzh, void, avr, avr)
+DEF_HELPER_2(vctzw, void, avr, avr)
+DEF_HELPER_2(vctzd, void, avr, avr)
 DEF_HELPER_2(vpopcntb, void, avr, avr)
 DEF_HELPER_2(vpopcnth, void, avr, avr)
 DEF_HELPER_2(vpopcntw, void, avr, avr)
diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
index a917bd5..162f1e9 100644
--- a/target-ppc/int_helper.c
+++ b/target-ppc/int_helper.c
@@ -2091,6 +2091,21 @@  VGENERIC_DO(clzd, u64)
 #undef clzw
 #undef clzd
 
+#define ctzb(v) ((v) ? ctz32(v) : 8)
+#define ctzh(v) ((v) ? ctz32(v) : 16)
+#define ctzw(v) ctz32((v))
+#define ctzd(v) ctz64((v))
+
+VGENERIC_DO(ctzb, u8)
+VGENERIC_DO(ctzh, u16)
+VGENERIC_DO(ctzw, u32)
+VGENERIC_DO(ctzd, u64)
+
+#undef ctzb
+#undef ctzh
+#undef ctzw
+#undef ctzd
+
 #define popcntb(v) ctpop8(v)
 #define popcnth(v) ctpop16(v)
 #define popcntw(v) ctpop32(v)
diff --git a/target-ppc/translate/vmx-impl.c b/target-ppc/translate/vmx-impl.c
index 766a645..ebf123f 100644
--- a/target-ppc/translate/vmx-impl.c
+++ b/target-ppc/translate/vmx-impl.c
@@ -553,6 +553,21 @@  static void glue(gen_, name)(DisasContext *ctx)                         \
         tcg_temp_free_ptr(rd);                                          \
     }
 
+#define GEN_VXFORM_NOA_2(name, opc2, opc3, opc4)                        \
+static void glue(gen_, name)(DisasContext *ctx)                         \
+    {                                                                   \
+        TCGv_ptr rb, rd;                                                \
+        if (unlikely(!ctx->altivec_enabled)) {                          \
+            gen_exception(ctx, POWERPC_EXCP_VPU);                       \
+            return;                                                     \
+        }                                                               \
+        rb = gen_avr_ptr(rB(ctx->opcode));                              \
+        rd = gen_avr_ptr(rD(ctx->opcode));                              \
+        gen_helper_##name(rd, rb);                                      \
+        tcg_temp_free_ptr(rb);                                          \
+        tcg_temp_free_ptr(rd);                                          \
+    }
+
 GEN_VXFORM_NOA(vupkhsb, 7, 8);
 GEN_VXFORM_NOA(vupkhsh, 7, 9);
 GEN_VXFORM_NOA(vupkhsw, 7, 25);
@@ -745,6 +760,10 @@  GEN_VXFORM_NOA(vclzb, 1, 28)
 GEN_VXFORM_NOA(vclzh, 1, 29)
 GEN_VXFORM_NOA(vclzw, 1, 30)
 GEN_VXFORM_NOA(vclzd, 1, 31)
+GEN_VXFORM_NOA_2(vctzb, 1, 24, 28)
+GEN_VXFORM_NOA_2(vctzh, 1, 24, 29)
+GEN_VXFORM_NOA_2(vctzw, 1, 24, 30)
+GEN_VXFORM_NOA_2(vctzd, 1, 24, 31)
 GEN_VXFORM_NOA(vpopcntb, 1, 28)
 GEN_VXFORM_NOA(vpopcnth, 1, 29)
 GEN_VXFORM_NOA(vpopcntw, 1, 30)
diff --git a/target-ppc/translate/vmx-ops.c b/target-ppc/translate/vmx-ops.c
index aafe70b..5b2826e 100644
--- a/target-ppc/translate/vmx-ops.c
+++ b/target-ppc/translate/vmx-ops.c
@@ -44,6 +44,10 @@  GEN_HANDLER_E(name, 0x04, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ISA300)
 #define GEN_VXFORM_300_EXT(name, opc2, opc3, inval)                     \
 GEN_HANDLER_E(name, 0x04, opc2, opc3, inval, PPC_NONE, PPC2_ISA300)
 
+#define GEN_VXFORM_300_EO(name, opc2, opc3, opc4)                     \
+GEN_HANDLER_E_2(name, 0x04, opc2, opc3, opc4, 0x00000000, PPC_NONE,     \
+                                                       PPC2_ISA300)
+
 #define GEN_VXFORM_DUAL(name0, name1, opc2, opc3, type0, type1) \
 GEN_HANDLER_E(name0##_##name1, 0x4, opc2, opc3, 0x00000000, type0, type1)
 
@@ -211,6 +215,10 @@  GEN_VXFORM_DUAL_INV(vspltish, vinserth, 6, 13, 0x00000000, 0x100000,
 GEN_VXFORM_DUAL_INV(vspltisw, vinsertw, 6, 14, 0x00000000, 0x100000,
                                                PPC2_ALTIVEC_207),
 GEN_VXFORM_300_EXT(vinsertd, 6, 15, 0x100000),
+GEN_VXFORM_300_EO(vctzb, 0x01, 0x18, 0x1C),
+GEN_VXFORM_300_EO(vctzh, 0x01, 0x18, 0x1D),
+GEN_VXFORM_300_EO(vctzw, 0x01, 0x18, 0x1E),
+GEN_VXFORM_300_EO(vctzd, 0x01, 0x18, 0x1F),
 
 #define GEN_VXFORM_NOA(name, opc2, opc3)                                \
     GEN_HANDLER(name, 0x04, opc2, opc3, 0x001f0000, PPC_ALTIVEC)