avx512pfintrin.h (_mm512_mask_prefetch_i32gather_pd): New.

gcc/
        * config/i386/avx512pfintrin.h (_mm512_mask_prefetch_i32gather_pd): New.
	(_mm512_mask_prefetch_i64gather_pd): Ditto.
	(_mm512_prefetch_i32scatter_pd): Ditto.
	(_mm512_mask_prefetch_i32scatter_pd): Ditto.
	(_mm512_prefetch_i64scatter_pd): Ditto.
	(_mm512_mask_prefetch_i64scatter_pd): Ditto.
	(_mm512_mask_prefetch_i32gather_ps): Fix operand type.
	(_mm512_mask_prefetch_i64gather_ps): Ditto.
	(_mm512_prefetch_i32scatter_ps): Ditto.
	(_mm512_mask_prefetch_i32scatter_ps): Ditto.
	(_mm512_prefetch_i64scatter_ps): Ditto.
	(_mm512_mask_prefetch_i64scatter_ps): Ditto.
	* config/i386/i386-builtin-types.def: Define
	VOID_FTYPE_QI_V8SI_PCINT64_INT_INT and VOID_FTYPE_QI_V8DI_PCINT64_INT_INT.
	* config/i386/i386.c (ix86_builtins): Define IX86_BUILTIN_GATHERPFQPD,
	IX86_BUILTIN_GATHERPFDPD, IX86_BUILTIN_SCATTERPFDPD,
	IX86_BUILTIN_SCATTERPFQPD.
	(ix86_init_mmx_sse_builtins): Define __builtin_ia32_gatherpfdpd,
	__builtin_ia32_gatherpfdps, __builtin_ia32_gatherpfqpd,
	__builtin_ia32_gatherpfqps, __builtin_ia32_scatterpfdpd,
	__builtin_ia32_scatterpfdps, __builtin_ia32_scatterpfqpd,
	__builtin_ia32_scatterpfqps.
	(ix86_expand_builtin): Expand new built-ins.
	* config/i386/sse.md (avx512pf_gatherpf<mode>): Add SF suffix,
	fix memory access data type.
	(*avx512pf_gatherpf<mode>_mask): Ditto.
	(*avx512pf_gatherpf<mode>): Ditto.
	(avx512pf_scatterpf<mode>): Ditto.
	(*avx512pf_scatterpf<mode>_mask): Ditto.
	(*avx512pf_scatterpf<mode>): Ditto.
	(GATHER_SCATTER_SF_MEM_MODE): New.
	(avx512pf_gatherpf<mode>df): Ditto.
	(*avx512pf_gatherpf<mode>df_mask): Ditto.
	(*avx512pf_scatterpf<mode>df): Ditto.

testsuite/
        * gcc.target/i386/avx512pf-vgatherpf0dpd-1.c: New.
	* gcc.target/i386/avx512pf-vgatherpf0qpd-1.c: Ditto.
	* gcc.target/i386/avx512pf-vgatherpf1dpd-1.c: Ditto.
	* gcc.target/i386/avx512pf-vgatherpf1qpd-1.c: Ditto.
	* gcc.target/i386/avx512pf-vscatterpf0dpd-1.c: Ditto.
	* gcc.target/i386/avx512pf-vscatterpf0qpd-1.c: Ditto.
	* gcc.target/i386/avx512pf-vscatterpf1dpd-1.c: Ditto.
	* gcc.target/i386/avx512pf-vscatterpf1qpd-1.c: Ditto.
	* gcc.target/i386/sse-14.c: Add new built-ins, fix AVX-512ER
	built-ins roudning immediate.
	* gcc.target/i386/sse-22.c: Add new built-ins.
	* gcc.target/i386/sse-23.c: Ditto.
	* gcc.target/i386/avx-1.c: Ditto.

From-SVN: r207149
This commit is contained in:
Kirill Yukhin 2014-01-27 19:21:02 +00:00 committed by Kirill Yukhin
parent fb1ca954c0
commit e711dffdfe
18 changed files with 500 additions and 38 deletions

View file

@ -1,3 +1,40 @@
2014-01-27 Kirill Yukhin <kirill.yukhin@intel.com>
* config/i386/avx512pfintrin.h (_mm512_mask_prefetch_i32gather_pd): New.
(_mm512_mask_prefetch_i64gather_pd): Ditto.
(_mm512_prefetch_i32scatter_pd): Ditto.
(_mm512_mask_prefetch_i32scatter_pd): Ditto.
(_mm512_prefetch_i64scatter_pd): Ditto.
(_mm512_mask_prefetch_i64scatter_pd): Ditto.
(_mm512_mask_prefetch_i32gather_ps): Fix operand type.
(_mm512_mask_prefetch_i64gather_ps): Ditto.
(_mm512_prefetch_i32scatter_ps): Ditto.
(_mm512_mask_prefetch_i32scatter_ps): Ditto.
(_mm512_prefetch_i64scatter_ps): Ditto.
(_mm512_mask_prefetch_i64scatter_ps): Ditto.
* config/i386/i386-builtin-types.def: Define
VOID_FTYPE_QI_V8SI_PCINT64_INT_INT and VOID_FTYPE_QI_V8DI_PCINT64_INT_INT.
* config/i386/i386.c (ix86_builtins): Define IX86_BUILTIN_GATHERPFQPD,
IX86_BUILTIN_GATHERPFDPD, IX86_BUILTIN_SCATTERPFDPD,
IX86_BUILTIN_SCATTERPFQPD.
(ix86_init_mmx_sse_builtins): Define __builtin_ia32_gatherpfdpd,
__builtin_ia32_gatherpfdps, __builtin_ia32_gatherpfqpd,
__builtin_ia32_gatherpfqps, __builtin_ia32_scatterpfdpd,
__builtin_ia32_scatterpfdps, __builtin_ia32_scatterpfqpd,
__builtin_ia32_scatterpfqps.
(ix86_expand_builtin): Expand new built-ins.
* config/i386/sse.md (avx512pf_gatherpf<mode>): Add SF suffix,
fix memory access data type.
(*avx512pf_gatherpf<mode>_mask): Ditto.
(*avx512pf_gatherpf<mode>): Ditto.
(avx512pf_scatterpf<mode>): Ditto.
(*avx512pf_scatterpf<mode>_mask): Ditto.
(*avx512pf_scatterpf<mode>): Ditto.
(GATHER_SCATTER_SF_MEM_MODE): New.
(avx512pf_gatherpf<mode>df): Ditto.
(*avx512pf_gatherpf<mode>df_mask): Ditto.
(*avx512pf_scatterpf<mode>df): Ditto.
2014-01-27 Jakub Jelinek <jakub@redhat.com>
PR bootstrap/59934

View file

@ -48,74 +48,157 @@ typedef unsigned short __mmask16;
#ifdef __OPTIMIZE__
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i32gather_ps (__m512i index, __mmask16 mask,
int const *addr, int scale, int hint)
_mm512_mask_prefetch_i32gather_pd (__m256i index, __mmask8 mask,
void *addr, int scale, int hint)
{
__builtin_ia32_gatherpfdps (mask, (__v16si) index, addr, scale, hint);
__builtin_ia32_gatherpfdpd (mask, (__v8si) index, (long long const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i32gather_ps (__m512i index, __mmask16 mask,
void *addr, int scale, int hint)
{
__builtin_ia32_gatherpfdps (mask, (__v16si) index, (int const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i64gather_pd (__m512i index, __mmask8 mask,
void *addr, int scale, int hint)
{
__builtin_ia32_gatherpfqpd (mask, (__v8di) index, (long long const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i64gather_ps (__m512i index, __mmask8 mask,
int const *addr, int scale, int hint)
void *addr, int scale, int hint)
{
__builtin_ia32_gatherpfqps (mask, (__v8di) index, addr, scale, hint);
__builtin_ia32_gatherpfqps (mask, (__v8di) index, (int const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_prefetch_i32scatter_ps (int const *addr, __m512i index, int scale,
_mm512_prefetch_i32scatter_pd (void *addr, __m256i index, int scale,
int hint)
{
__builtin_ia32_scatterpfdps ((__mmask16) 0xFFFF, (__v16si) index, addr, scale,
hint);
__builtin_ia32_scatterpfdpd ((__mmask8) 0xFF, (__v8si) index,
(long long const *)addr, scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i32scatter_ps (int const *addr, __mmask16 mask,
__m512i index, int scale, int hint)
{
__builtin_ia32_scatterpfdps (mask, (__v16si) index, addr, scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_prefetch_i64scatter_ps (int const *addr, __m512i index, int scale,
_mm512_prefetch_i32scatter_ps (void *addr, __m512i index, int scale,
int hint)
{
__builtin_ia32_scatterpfqps ((__mmask8) 0xFF, (__v8di) index, addr, scale,
hint);
__builtin_ia32_scatterpfdps ((__mmask16) 0xFFFF, (__v16si) index, (int const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i64scatter_ps (int const *addr, __mmask16 mask,
_mm512_mask_prefetch_i32scatter_pd (void *addr, __mmask8 mask,
__m256i index, int scale, int hint)
{
__builtin_ia32_scatterpfdpd (mask, (__v8si) index, (long long const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i32scatter_ps (void *addr, __mmask16 mask,
__m512i index, int scale, int hint)
{
__builtin_ia32_scatterpfqps (mask, (__v8di) index, addr, scale, hint);
__builtin_ia32_scatterpfdps (mask, (__v16si) index, (int const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_prefetch_i64scatter_pd (void *addr, __m512i index, int scale,
int hint)
{
__builtin_ia32_scatterpfqpd ((__mmask8) 0xFF, (__v8di) index, (long long const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_prefetch_i64scatter_ps (void *addr, __m512i index, int scale,
int hint)
{
__builtin_ia32_scatterpfqps ((__mmask8) 0xFF, (__v8di) index, (int const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i64scatter_pd (void *addr, __mmask16 mask,
__m512i index, int scale, int hint)
{
__builtin_ia32_scatterpfqpd (mask, (__v8di) index, (long long const *) addr,
scale, hint);
}
extern __inline void
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_prefetch_i64scatter_ps (void *addr, __mmask16 mask,
__m512i index, int scale, int hint)
{
__builtin_ia32_scatterpfqps (mask, (__v8di) index, (int const *) addr,
scale, hint);
}
#else
#define _mm512_mask_prefetch_i32gather_pd(INDEX, MASK, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfdpd ((__mmask8)MASK, (__v8si)(__m256i)INDEX, \
(long long const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_mask_prefetch_i32gather_ps(INDEX, MASK, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \
__builtin_ia32_gatherpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \
(int const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_mask_prefetch_i64gather_pd(INDEX, MASK, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfqpd ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(long long const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_mask_prefetch_i64gather_ps(INDEX, MASK, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfqps ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(int const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_prefetch_i32scatter_pd(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdpd ((__mmask8)0xFF, (__v8si)(__m256i)INDEX, \
(long long const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_prefetch_i32scatter_ps(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdps ((__mmask16)0xFFFF, (__v16si)(__m512i)INDEX, \
(int const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_mask_prefetch_i32scatter_pd(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdpd ((__mmask8)MASK, (__v8si)(__m256i)INDEX, \
(long long const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_mask_prefetch_i32scatter_ps(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \
(int const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_prefetch_i64scatter_pd(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqpd ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \
(long long const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_prefetch_i64scatter_ps(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqps ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \
(int const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_mask_prefetch_i64scatter_pd(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqpd ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(long long const *)ADDR, (int)SCALE, (int)HINT)
#define _mm512_mask_prefetch_i64scatter_ps(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqps ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(int const *)ADDR, (int)SCALE, (int)HINT)

View file

@ -733,7 +733,9 @@ DEF_FUNCTION_TYPE (VOID, PLONGLONG, QI, V8SI, V8DI, INT)
DEF_FUNCTION_TYPE (VOID, PINT, QI, V8DI, V8SI, INT)
DEF_FUNCTION_TYPE (VOID, PLONGLONG, QI, V8DI, V8DI, INT)
DEF_FUNCTION_TYPE (VOID, QI, V8SI, PCINT64, INT, INT)
DEF_FUNCTION_TYPE (VOID, HI, V16SI, PCINT, INT, INT)
DEF_FUNCTION_TYPE (VOID, QI, V8DI, PCINT64, INT, INT)
DEF_FUNCTION_TYPE (VOID, QI, V8DI, PCINT, INT, INT)
DEF_FUNCTION_TYPE_ALIAS (V2DF_FTYPE_V2DF, ROUND)

View file

@ -28406,9 +28406,13 @@ enum ix86_builtins
IX86_BUILTIN_SCATTERSIV8DI,
/* AVX512PF */
IX86_BUILTIN_GATHERPFQPD,
IX86_BUILTIN_GATHERPFDPS,
IX86_BUILTIN_GATHERPFDPD,
IX86_BUILTIN_GATHERPFQPS,
IX86_BUILTIN_SCATTERPFDPD,
IX86_BUILTIN_SCATTERPFDPS,
IX86_BUILTIN_SCATTERPFQPD,
IX86_BUILTIN_SCATTERPFQPS,
/* AVX-512ER */
@ -30939,15 +30943,27 @@ ix86_init_mmx_sse_builtins (void)
IX86_BUILTIN_SCATTERDIV8DI);
/* AVX512PF */
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_gatherpfdpd",
VOID_FTYPE_QI_V8SI_PCINT64_INT_INT,
IX86_BUILTIN_GATHERPFDPD);
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_gatherpfdps",
VOID_FTYPE_HI_V16SI_PCINT_INT_INT,
IX86_BUILTIN_GATHERPFDPS);
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_gatherpfqpd",
VOID_FTYPE_QI_V8DI_PCINT64_INT_INT,
IX86_BUILTIN_GATHERPFQPD);
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_gatherpfqps",
VOID_FTYPE_QI_V8DI_PCINT_INT_INT,
IX86_BUILTIN_GATHERPFQPS);
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_scatterpfdpd",
VOID_FTYPE_QI_V8SI_PCINT64_INT_INT,
IX86_BUILTIN_SCATTERPFDPD);
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_scatterpfdps",
VOID_FTYPE_HI_V16SI_PCINT_INT_INT,
IX86_BUILTIN_SCATTERPFDPS);
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_scatterpfqpd",
VOID_FTYPE_QI_V8DI_PCINT64_INT_INT,
IX86_BUILTIN_SCATTERPFQPD);
def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_scatterpfqps",
VOID_FTYPE_QI_V8DI_PCINT_INT_INT,
IX86_BUILTIN_SCATTERPFQPS);
@ -35593,17 +35609,30 @@ addcarryx:
case IX86_BUILTIN_SCATTERDIV8DI:
icode = CODE_FOR_avx512f_scatterdiv8di;
goto scatter_gen;
case IX86_BUILTIN_GATHERPFDPD:
icode = CODE_FOR_avx512pf_gatherpfv8sidf;
goto vec_prefetch_gen;
case IX86_BUILTIN_GATHERPFDPS:
icode = CODE_FOR_avx512pf_gatherpfv16si;
icode = CODE_FOR_avx512pf_gatherpfv16sisf;
goto vec_prefetch_gen;
case IX86_BUILTIN_GATHERPFQPD:
icode = CODE_FOR_avx512pf_gatherpfv8didf;
goto vec_prefetch_gen;
case IX86_BUILTIN_GATHERPFQPS:
icode = CODE_FOR_avx512pf_gatherpfv8di;
icode = CODE_FOR_avx512pf_gatherpfv8disf;
goto vec_prefetch_gen;
case IX86_BUILTIN_SCATTERPFDPD:
icode = CODE_FOR_avx512pf_scatterpfv8sidf;
goto vec_prefetch_gen;
case IX86_BUILTIN_SCATTERPFDPS:
icode = CODE_FOR_avx512pf_scatterpfv16si;
icode = CODE_FOR_avx512pf_scatterpfv16sisf;
goto vec_prefetch_gen;
case IX86_BUILTIN_SCATTERPFQPD:
icode = CODE_FOR_avx512pf_scatterpfv8didf;
goto vec_prefetch_gen;
case IX86_BUILTIN_SCATTERPFQPS:
icode = CODE_FOR_avx512pf_scatterpfv8di;
icode = CODE_FOR_avx512pf_scatterpfv8disf;
goto vec_prefetch_gen;
gather_gen:

View file

@ -417,6 +417,7 @@
[V32QI V16HI V8SI (V8DI "TARGET_AVX512F") (V16SI "TARGET_AVX512F")])
(define_mode_iterator VI48_256 [V8SI V4DI])
(define_mode_iterator VI48_512 [V16SI V8DI])
(define_mode_iterator VI4_256_8_512 [V8SI V8DI])
;; Int-float size matches
(define_mode_iterator VI4F_128 [V4SI V4SF])
@ -12495,10 +12496,14 @@
(set_attr "btver2_decode" "vector,vector,vector,vector")
(set_attr "mode" "TI")])
(define_expand "avx512pf_gatherpf<mode>"
;; Packed float variants
(define_mode_attr GATHER_SCATTER_SF_MEM_MODE
[(V8DI "V8SF") (V16SI "V16SF")])
(define_expand "avx512pf_gatherpf<mode>sf"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand")
(mem:<ssescalarmode>
(mem:<GATHER_SCATTER_SF_MEM_MODE>
(match_par_dup 5
[(match_operand 2 "vsib_address_operand")
(match_operand:VI48_512 1 "register_operand")
@ -12512,10 +12517,10 @@
operands[3]), UNSPEC_VSIBADDR);
})
(define_insn "*avx512pf_gatherpf<mode>_mask"
(define_insn "*avx512pf_gatherpf<mode>sf_mask"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_operand" "k")
(match_operator:<ssescalarmode> 5 "vsib_mem_operator"
(match_operator:<GATHER_SCATTER_SF_MEM_MODE> 5 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 2 "vsib_address_operand" "Tv")
(match_operand:VI48_512 1 "register_operand" "v")
@ -12539,10 +12544,10 @@
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
(define_insn "*avx512pf_gatherpf<mode>"
(define_insn "*avx512pf_gatherpf<mode>sf"
[(unspec
[(const_int -1)
(match_operator:<ssescalarmode> 4 "vsib_mem_operator"
(match_operator:<GATHER_SCATTER_SF_MEM_MODE> 4 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 1 "vsib_address_operand" "Tv")
(match_operand:VI48_512 0 "register_operand" "v")
@ -12566,10 +12571,83 @@
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
(define_expand "avx512pf_scatterpf<mode>"
;; Packed double variants
(define_expand "avx512pf_gatherpf<mode>df"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand")
(mem:<ssescalarmode>
(mem:V8DF
(match_par_dup 5
[(match_operand 2 "vsib_address_operand")
(match_operand:VI4_256_8_512 1 "register_operand")
(match_operand:SI 3 "const1248_operand")]))
(match_operand:SI 4 "const_0_to_1_operand")]
UNSPEC_GATHER_PREFETCH)]
"TARGET_AVX512PF"
{
operands[5]
= gen_rtx_UNSPEC (Pmode, gen_rtvec (3, operands[2], operands[1],
operands[3]), UNSPEC_VSIBADDR);
})
(define_insn "*avx512pf_gatherpf<mode>df_mask"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_operand" "k")
(match_operator:V8DF 5 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 2 "vsib_address_operand" "Tv")
(match_operand:VI4_256_8_512 1 "register_operand" "v")
(match_operand:SI 3 "const1248_operand" "n")]
UNSPEC_VSIBADDR)])
(match_operand:SI 4 "const_0_to_1_operand" "n")]
UNSPEC_GATHER_PREFETCH)]
"TARGET_AVX512PF"
{
switch (INTVAL (operands[4]))
{
case 0:
return "vgatherpf0<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}";
case 1:
return "vgatherpf1<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}";
default:
gcc_unreachable ();
}
}
[(set_attr "type" "sse")
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
(define_insn "*avx512pf_gatherpf<mode>df"
[(unspec
[(const_int -1)
(match_operator:V8DF 4 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 1 "vsib_address_operand" "Tv")
(match_operand:VI4_256_8_512 0 "register_operand" "v")
(match_operand:SI 2 "const1248_operand" "n")]
UNSPEC_VSIBADDR)])
(match_operand:SI 3 "const_0_to_1_operand" "n")]
UNSPEC_GATHER_PREFETCH)]
"TARGET_AVX512PF"
{
switch (INTVAL (operands[3]))
{
case 0:
return "vgatherpf0<ssemodesuffix>pd\t{%4|%4}";
case 1:
return "vgatherpf1<ssemodesuffix>pd\t{%4|%4}";
default:
gcc_unreachable ();
}
}
[(set_attr "type" "sse")
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
;; Packed float variants
(define_expand "avx512pf_scatterpf<mode>sf"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand")
(mem:<GATHER_SCATTER_SF_MEM_MODE>
(match_par_dup 5
[(match_operand 2 "vsib_address_operand")
(match_operand:VI48_512 1 "register_operand")
@ -12583,10 +12661,10 @@
operands[3]), UNSPEC_VSIBADDR);
})
(define_insn "*avx512pf_scatterpf<mode>_mask"
(define_insn "*avx512pf_scatterpf<mode>sf_mask"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_operand" "k")
(match_operator:<ssescalarmode> 5 "vsib_mem_operator"
(match_operator:<GATHER_SCATTER_SF_MEM_MODE> 5 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 2 "vsib_address_operand" "Tv")
(match_operand:VI48_512 1 "register_operand" "v")
@ -12610,10 +12688,10 @@
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
(define_insn "*avx512pf_scatterpf<mode>"
(define_insn "*avx512pf_scatterpf<mode>sf"
[(unspec
[(const_int -1)
(match_operator:<ssescalarmode> 4 "vsib_mem_operator"
(match_operator:<GATHER_SCATTER_SF_MEM_MODE> 4 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 1 "vsib_address_operand" "Tv")
(match_operand:VI48_512 0 "register_operand" "v")
@ -12637,6 +12715,78 @@
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
;; Packed double variants
(define_expand "avx512pf_scatterpf<mode>df"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand")
(mem:V8DF
(match_par_dup 5
[(match_operand 2 "vsib_address_operand")
(match_operand:VI4_256_8_512 1 "register_operand")
(match_operand:SI 3 "const1248_operand")]))
(match_operand:SI 4 "const_0_to_1_operand")]
UNSPEC_SCATTER_PREFETCH)]
"TARGET_AVX512PF"
{
operands[5]
= gen_rtx_UNSPEC (Pmode, gen_rtvec (3, operands[2], operands[1],
operands[3]), UNSPEC_VSIBADDR);
})
(define_insn "*avx512pf_scatterpf<mode>df_mask"
[(unspec
[(match_operand:<avx512fmaskmode> 0 "register_operand" "k")
(match_operator:V8DF 5 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 2 "vsib_address_operand" "Tv")
(match_operand:VI4_256_8_512 1 "register_operand" "v")
(match_operand:SI 3 "const1248_operand" "n")]
UNSPEC_VSIBADDR)])
(match_operand:SI 4 "const_0_to_1_operand" "n")]
UNSPEC_SCATTER_PREFETCH)]
"TARGET_AVX512PF"
{
switch (INTVAL (operands[4]))
{
case 0:
return "vscatterpf0<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}";
case 1:
return "vscatterpf1<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}";
default:
gcc_unreachable ();
}
}
[(set_attr "type" "sse")
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
(define_insn "*avx512pf_scatterpf<mode>df"
[(unspec
[(const_int -1)
(match_operator:V8DF 4 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 1 "vsib_address_operand" "Tv")
(match_operand:VI4_256_8_512 0 "register_operand" "v")
(match_operand:SI 2 "const1248_operand" "n")]
UNSPEC_VSIBADDR)])
(match_operand:SI 3 "const_0_to_1_operand" "n")]
UNSPEC_SCATTER_PREFETCH)]
"TARGET_AVX512PF"
{
switch (INTVAL (operands[3]))
{
case 0:
return "vscatterpf0<ssemodesuffix>pd\t{%4|%4}";
case 1:
return "vscatterpf1<ssemodesuffix>pd\t{%4|%4}";
default:
gcc_unreachable ();
}
}
[(set_attr "type" "sse")
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
(define_insn "avx512er_exp2<mode><mask_name><round_saeonly_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(unspec:VF_512

View file

@ -1,3 +1,19 @@
2014-01-27 Kirill Yukhin <kirill.yukhin@intel.com>
* gcc.target/i386/avx512pf-vgatherpf0dpd-1.c: New.
* gcc.target/i386/avx512pf-vgatherpf0qpd-1.c: Ditto.
* gcc.target/i386/avx512pf-vgatherpf1dpd-1.c: Ditto.
* gcc.target/i386/avx512pf-vgatherpf1qpd-1.c: Ditto.
* gcc.target/i386/avx512pf-vscatterpf0dpd-1.c: Ditto.
* gcc.target/i386/avx512pf-vscatterpf0qpd-1.c: Ditto.
* gcc.target/i386/avx512pf-vscatterpf1dpd-1.c: Ditto.
* gcc.target/i386/avx512pf-vscatterpf1qpd-1.c: Ditto.
* gcc.target/i386/sse-14.c: Add new built-ins, fix AVX-512ER
built-ins roudning immediate.
* gcc.target/i386/sse-22.c: Add new built-ins.
* gcc.target/i386/sse-23.c: Ditto.
* gcc.target/i386/avx-1.c: Ditto.
2014-01-27 Christian Bruel <christian.bruel@st.com>
* gcc.target/sh/torture/strncmp.c: New tests.

View file

@ -362,6 +362,10 @@
#define __builtin_ia32_gatherpfqps(A, B, C, D, E) __builtin_ia32_gatherpfqps(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfdps(A, B, C, D, E) __builtin_ia32_scatterpfdps(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfqps(A, B, C, D, E) __builtin_ia32_scatterpfqps(A, B, C, 1, 1)
#define __builtin_ia32_gatherpfdpd(A, B, C, D, E) __builtin_ia32_gatherpfdpd(A, B, C, 1, 1)
#define __builtin_ia32_gatherpfqpd(A, B, C, D, E) __builtin_ia32_gatherpfqpd(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfdpd(A, B, C, D, E) __builtin_ia32_scatterpfdpd(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfqpd(A, B, C, D, E) __builtin_ia32_scatterpfqpd(A, B, C, 1, 1)
/* shaintrin.h */
#define __builtin_ia32_sha1rnds4(A, B, C) __builtin_ia32_sha1rnds4(A, B, 1)

View file

@ -0,0 +1,15 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vgatherpf0dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m256i idx;
volatile __mmask8 m8;
void *base;
void extern
avx512pf_test (void)
{
_mm512_mask_prefetch_i32gather_pd (idx, m8, base, 8, 0);
}

View file

@ -0,0 +1,15 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vgatherpf0qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m512i idx;
volatile __mmask8 m8;
int *base;
void extern
avx512pf_test (void)
{
_mm512_mask_prefetch_i64gather_pd (idx, m8, base, 8, 0);
}

View file

@ -0,0 +1,15 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vgatherpf1dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m256i idx;
volatile __mmask8 m8;
int *base;
void extern
avx512pf_test (void)
{
_mm512_mask_prefetch_i32gather_pd (idx, m8, base, 8, 1);
}

View file

@ -0,0 +1,15 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vgatherpf1qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m512i idx;
volatile __mmask8 m8;
int *base;
void extern
avx512pf_test (void)
{
_mm512_mask_prefetch_i64gather_pd (idx, m8, base, 8, 1);
}

View file

@ -0,0 +1,17 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vscatterpf0dpd\[ \\t\]+\[^\n\]*%ymm\[0-9\]" 2 } } */
/* { dg-final { scan-assembler-times "vscatterpf0dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m256i idx;
volatile __mmask8 m8;
void *base;
void extern
avx512pf_test (void)
{
_mm512_prefetch_i32scatter_pd (base, idx, 8, 0);
_mm512_mask_prefetch_i32scatter_pd (base, m8, idx, 8, 0);
}

View file

@ -0,0 +1,17 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vscatterpf0qpd\[ \\t\]+\[^\n\]*%zmm\[0-9\]" 2 } } */
/* { dg-final { scan-assembler-times "vscatterpf0qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m512i idx;
volatile __mmask8 m8;
void *base;
void extern
avx512pf_test (void)
{
_mm512_prefetch_i64scatter_pd (base, idx, 8, 0);
_mm512_mask_prefetch_i64scatter_pd (base, m8, idx, 8, 0);
}

View file

@ -0,0 +1,17 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vscatterpf1dpd\[ \\t\]+\[^\n\]*%ymm\[0-9\]" 2 } } */
/* { dg-final { scan-assembler-times "vscatterpf1dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m256i idx;
volatile __mmask8 m8;
void *base;
void extern
avx512pf_test (void)
{
_mm512_prefetch_i32scatter_pd (base, idx, 8, 1);
_mm512_mask_prefetch_i32scatter_pd (base, m8, idx, 8, 1);
}

View file

@ -0,0 +1,17 @@
/* { dg-do compile } */
/* { dg-options "-mavx512pf -O2" } */
/* { dg-final { scan-assembler-times "vscatterpf1qpd\[ \\t\]+\[^\n\]*%zmm\[0-9\]" 2 } } */
/* { dg-final { scan-assembler-times "vscatterpf1qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */
#include <immintrin.h>
volatile __m512i idx;
volatile __mmask8 m8;
int *base;
void extern
avx512pf_test (void)
{
_mm512_prefetch_i64scatter_pd (base, idx, 8, 1);
_mm512_mask_prefetch_i64scatter_pd (base, m8, idx, 8, 1);
}

View file

@ -523,6 +523,10 @@ test_3vx (_mm512_mask_prefetch_i32gather_ps, __m512i, __mmask16, void const *, 1
test_3vx (_mm512_mask_prefetch_i32scatter_ps, void const *, __mmask16, __m512i, 1, 1)
test_3vx (_mm512_mask_prefetch_i64gather_ps, __m512i, __mmask8, void const *, 1, 1)
test_3vx (_mm512_mask_prefetch_i64scatter_ps, void const *, __mmask8, __m512i, 1, 1)
test_3vx (_mm512_mask_prefetch_i32gather_pd, __m256i, __mmask8, void const *, 1, 1)
test_3vx (_mm512_mask_prefetch_i32scatter_pd, void const *, __mmask8, __m256i, 1, 1)
test_3vx (_mm512_mask_prefetch_i64gather_pd, __m512i, __mmask8, void const *, 1, 1)
test_3vx (_mm512_mask_prefetch_i64scatter_pd, void const *, __mmask8, __m512i, 1, 1)
/* avx512erintrin.h */
test_1 (_mm512_exp2a23_round_pd, __m512d, __m512d, 5)

View file

@ -646,6 +646,11 @@ test_3vx (_mm512_mask_prefetch_i32scatter_ps, void const *, __mmask16, __m512i,
test_3vx (_mm512_mask_prefetch_i64gather_ps, __m512i, __mmask8, void const *, 1, 1)
test_3vx (_mm512_mask_prefetch_i64scatter_ps, void const *, __mmask8, __m512i, 1, 1)
test_3vx (_mm512_mask_prefetch_i32gather_pd, __m256i, __mmask8, void const *, 1, 1)
test_3vx (_mm512_mask_prefetch_i32scatter_pd, void const *, __mmask8, __m256i, 1, 1)
test_3vx (_mm512_mask_prefetch_i64gather_pd, __m512i, __mmask8, long long *, 1, 1)
test_3vx (_mm512_mask_prefetch_i64scatter_pd, void const *, __mmask8, __m512i, 1, 1)
/* avx512erintrin.h */
test_1 (_mm512_exp2a23_round_pd, __m512d, __m512d, 5)
test_1 (_mm512_exp2a23_round_ps, __m512, __m512, 5)

View file

@ -365,6 +365,10 @@
#define __builtin_ia32_gatherpfqps(A, B, C, D, E) __builtin_ia32_gatherpfqps(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfdps(A, B, C, D, E) __builtin_ia32_scatterpfdps(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfqps(A, B, C, D, E) __builtin_ia32_scatterpfqps(A, B, C, 1, 1)
#define __builtin_ia32_gatherpfdpd(A, B, C, D, E) __builtin_ia32_gatherpfdpd(A, B, C, 1, 1)
#define __builtin_ia32_gatherpfqpd(A, B, C, D, E) __builtin_ia32_gatherpfqpd(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfdpd(A, B, C, D, E) __builtin_ia32_scatterpfdpd(A, B, C, 1, 1)
#define __builtin_ia32_scatterpfqpd(A, B, C, D, E) __builtin_ia32_scatterpfqpd(A, B, C, 1, 1)
/* avx512erintrin.h */
#define __builtin_ia32_exp2pd_mask(A, B, C, D) __builtin_ia32_exp2pd_mask (A, B, C, 5)