+2017-11-10 Julia Koval <julia.koval@intel.com>
+
+ * config/i386/gfniintrin.h (_mm_gf2p8affine_epi64_epi8,
+ _mm256_gf2p8affine_epi64_epi8, _mm_mask_gf2p8affine_epi64_epi8,
+ _mm_maskz_gf2p8affine_epi64_epi8, _mm256_mask_gf2p8affine_epi64_epi8,
+ _mm256_maskz_gf2p8affine_epi64_epi8,
+ _mm512_mask_gf2p8affine_epi64_epi8, _mm512_gf2p8affine_epi64_epi8
+ _mm512_maskz_gf2p8affine_epi64_epi8): New intrinsics.
+ * config/i386/i386-builtin.def (__builtin_ia32_vgf2p8affineqb_v64qi,
+ __builtin_ia32_vgf2p8affineqb_v32qi,
+ __builtin_ia32_vgf2p8affineqb_v16qi): New builtins.
+ * config/i386/sse.md (vgf2p8affineqb_<mode><mask_name>): New pattern.
+
2017-11-10 Tamar Christina <tamar.christina@arm.com>
PR target/82641
(__v16qi) __B,
__C);
}
+
+extern __inline __m128i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_gf2p8affine_epi64_epi8 (__m128i __A, __m128i __B, const int __C)
+{
+ return (__m128i) __builtin_ia32_vgf2p8affineqb_v16qi ((__v16qi) __A,
+ (__v16qi) __B, __C);
+}
#else
#define _mm_gf2p8affineinv_epi64_epi8(A, B, C) \
((__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi((__v16qi)(__m128i)(A), \
(__v16qi)(__m128i)(B), (int)(C)))
+#define _mm_gf2p8affine_epi64_epi8(A, B, C) \
+ ((__m128i) __builtin_ia32_vgf2p8affineqb_v16qi ((__v16qi)(__m128i)(A), \
+ (__v16qi)(__m128i)(B), (int)(C)))
#endif
#ifdef __DISABLE_GFNI__
(__v32qi) __B,
__C);
}
+
+extern __inline __m256i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_gf2p8affine_epi64_epi8 (__m256i __A, __m256i __B, const int __C)
+{
+ return (__m256i) __builtin_ia32_vgf2p8affineqb_v32qi ((__v32qi) __A,
+ (__v32qi) __B, __C);
+}
#else
#define _mm256_gf2p8affineinv_epi64_epi8(A, B, C) \
((__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi((__v32qi)(__m256i)(A), \
(__v32qi)(__m256i)(B), \
(int)(C)))
+#define _mm256_gf2p8affine_epi64_epi8(A, B, C) \
+ ((__m256i) __builtin_ia32_vgf2p8affineqb_v32qi ((__v32qi)(__m256i)(A), \
+ ( __v32qi)(__m256i)(B), (int)(C)))
#endif
#ifdef __DISABLE_GFNIAVX__
(__v16qi) _mm_setzero_si128 (),
__A);
}
+
+extern __inline __m128i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_gf2p8affine_epi64_epi8 (__m128i __A, __mmask16 __B, __m128i __C,
+ __m128i __D, const int __E)
+{
+ return (__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask ((__v16qi) __C,
+ (__v16qi) __D, __E, (__v16qi)__A, __B);
+}
+
+extern __inline __m128i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_gf2p8affine_epi64_epi8 (__mmask16 __A, __m128i __B, __m128i __C,
+ const int __D)
+{
+ return (__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask ((__v16qi) __B,
+ (__v16qi) __C, __D, (__v16qi) _mm_setzero_si128 (), __A);
+}
#else
#define _mm_mask_gf2p8affineinv_epi64_epi8(A, B, C, D, E) \
((__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask( \
(__v16qi)(__m128i)(B), (__v16qi)(__m128i)(C), \
(int)(D), (__v16qi)(__m128i) _mm_setzero_si128 (), \
(__mmask16)(A)))
+#define _mm_mask_gf2p8affine_epi64_epi8(A, B, C, D, E) \
+ ((__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask((__v16qi)(__m128i)(C),\
+ (__v16qi)(__m128i)(D), (int)(E), (__v16qi)(__m128i)(A), (__mmask16)(B)))
+#define _mm_maskz_gf2p8affine_epi64_epi8(A, B, C, D) \
+ ((__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask((__v16qi)(__m128i)(B),\
+ (__v16qi)(__m128i)(C), (int)(D), \
+ (__v16qi)(__m128i) _mm_setzero_si128 (), (__mmask16)(A)))
#endif
#ifdef __DISABLE_GFNIAVX512VL__
(__v32qi) __C, __D,
(__v32qi) _mm256_setzero_si256 (), __A);
}
+
+extern __inline __m256i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_gf2p8affine_epi64_epi8 (__m256i __A, __mmask32 __B, __m256i __C,
+ __m256i __D, const int __E)
+{
+ return (__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask ((__v32qi) __C,
+ (__v32qi) __D,
+ __E,
+ (__v32qi)__A,
+ __B);
+}
+
+extern __inline __m256i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_gf2p8affine_epi64_epi8 (__mmask32 __A, __m256i __B,
+ __m256i __C, const int __D)
+{
+ return (__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask ((__v32qi) __B,
+ (__v32qi) __C, __D, (__v32qi)_mm256_setzero_si256 (), __A);
+}
#else
#define _mm256_mask_gf2p8affineinv_epi64_epi8(A, B, C, D, E) \
((__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask( \
((__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask( \
(__v32qi)(__m256i)(B), (__v32qi)(__m256i)(C), (int)(D), \
(__v32qi)(__m256i) _mm256_setzero_si256 (), (__mmask32)(A)))
+#define _mm256_mask_gf2p8affine_epi64_epi8(A, B, C, D, E) \
+ ((__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask((__v32qi)(__m256i)(C),\
+ (__v32qi)(__m256i)(D), (int)(E), (__v32qi)(__m256i)(A), (__mmask32)(B)))
+#define _mm256_maskz_gf2p8affine_epi64_epi8(A, B, C, D) \
+ ((__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask((__v32qi)(__m256i)(B),\
+ (__v32qi)(__m256i)(C), (int)(D), \
+ (__v32qi)(__m256i) _mm256_setzero_si256 (), (__mmask32)(A)))
#endif
#ifdef __DISABLE_GFNIAVX512VLBW__
return (__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi ((__v64qi) __A,
(__v64qi) __B, __C);
}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_gf2p8affine_epi64_epi8 (__m512i __A, __mmask64 __B, __m512i __C,
+ __m512i __D, const int __E)
+{
+ return (__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask ((__v64qi) __C,
+ (__v64qi) __D, __E, (__v64qi)__A, __B);
+}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_gf2p8affine_epi64_epi8 (__mmask64 __A, __m512i __B, __m512i __C,
+ const int __D)
+{
+ return (__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask ((__v64qi) __B,
+ (__v64qi) __C, __D, (__v64qi) _mm512_setzero_si512 (), __A);
+}
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_gf2p8affine_epi64_epi8 (__m512i __A, __m512i __B, const int __C)
+{
+ return (__m512i) __builtin_ia32_vgf2p8affineqb_v64qi ((__v64qi) __A,
+ (__v64qi) __B, __C);
+}
#else
#define _mm512_mask_gf2p8affineinv_epi64_epi8(A, B, C, D, E) \
((__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask( \
#define _mm512_gf2p8affineinv_epi64_epi8(A, B, C) \
((__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi ( \
(__v64qi)(__m512i)(A), (__v64qi)(__m512i)(B), (int)(C)))
+#define _mm512_mask_gf2p8affine_epi64_epi8(A, B, C, D, E) \
+ ((__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask((__v64qi)(__m512i)(C),\
+ (__v64qi)(__m512i)(D), (int)(E), (__v64qi)(__m512i)(A), (__mmask64)(B)))
+#define _mm512_maskz_gf2p8affine_epi64_epi8(A, B, C, D) \
+ ((__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask((__v64qi)(__m512i)(B),\
+ (__v64qi)(__m512i)(C), (int)(D), \
+ (__v64qi)(__m512i) _mm512_setzero_si512 (), (__mmask64)(A)))
+#define _mm512_gf2p8affine_epi64_epi8(A, B, C) \
+ ((__m512i) __builtin_ia32_vgf2p8affineqb_v64qi ((__v64qi)(__m512i)(A), \
+ (__v64qi)(__m512i)(B), (int)(C)))
#endif
#ifdef __DISABLE_GFNIAVX512FBW__
BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_AVX512BW | OPTION_MASK_ISA_AVX512VL, CODE_FOR_vgf2p8affineinvqb_v32qi_mask, "__builtin_ia32_vgf2p8affineinvqb_v32qi_mask", IX86_BUILTIN_VGF2P8AFFINEINVQB256MASK, UNKNOWN, (int) V32QI_FTYPE_V32QI_V32QI_INT_V32QI_USI)
BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_SSE, CODE_FOR_vgf2p8affineinvqb_v16qi, "__builtin_ia32_vgf2p8affineinvqb_v16qi", IX86_BUILTIN_VGF2P8AFFINEINVQB128, UNKNOWN, (int) V16QI_FTYPE_V16QI_V16QI_INT)
BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_SSE, CODE_FOR_vgf2p8affineinvqb_v16qi_mask, "__builtin_ia32_vgf2p8affineinvqb_v16qi_mask", IX86_BUILTIN_VGF2P8AFFINEINVQB128MASK, UNKNOWN, (int) V16QI_FTYPE_V16QI_V16QI_INT_V16QI_UHI)
+BDESC (OPTION_MASK_ISA_GFNI, CODE_FOR_vgf2p8affineqb_v64qi, "__builtin_ia32_vgf2p8affineqb_v64qi", IX86_BUILTIN_VGF2P8AFFINEQB512, UNKNOWN, (int) V64QI_FTYPE_V64QI_V64QI_INT)
+BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_AVX512BW, CODE_FOR_vgf2p8affineqb_v64qi_mask, "__builtin_ia32_vgf2p8affineqb_v64qi_mask", IX86_BUILTIN_VGF2P8AFFINEQB512MASK, UNKNOWN, (int) V64QI_FTYPE_V64QI_V64QI_INT_V64QI_UDI)
+BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_AVX, CODE_FOR_vgf2p8affineqb_v32qi, "__builtin_ia32_vgf2p8affineqb_v32qi", IX86_BUILTIN_VGF2P8AFFINEQB256, UNKNOWN, (int) V32QI_FTYPE_V32QI_V32QI_INT)
+BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_AVX512BW | OPTION_MASK_ISA_AVX512VL, CODE_FOR_vgf2p8affineqb_v32qi_mask, "__builtin_ia32_vgf2p8affineqb_v32qi_mask", IX86_BUILTIN_VGF2P8AFFINEQB256MASK, UNKNOWN, (int) V32QI_FTYPE_V32QI_V32QI_INT_V32QI_USI)
+BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_SSE, CODE_FOR_vgf2p8affineqb_v16qi, "__builtin_ia32_vgf2p8affineqb_v16qi", IX86_BUILTIN_VGF2P8AFFINEQB128, UNKNOWN, (int) V16QI_FTYPE_V16QI_V16QI_INT)
+BDESC (OPTION_MASK_ISA_GFNI | OPTION_MASK_ISA_SSE, CODE_FOR_vgf2p8affineqb_v16qi_mask, "__builtin_ia32_vgf2p8affineqb_v16qi_mask", IX86_BUILTIN_VGF2P8AFFINEQB128MASK, UNKNOWN, (int) V16QI_FTYPE_V16QI_V16QI_INT_V16QI_UHI)
/* Builtins with rounding support. */
BDESC_END (ARGS, ROUND_ARGS)
;; For GFNI support
UNSPEC_GF2P8AFFINEINV
+ UNSPEC_GF2P8AFFINE
])
(define_c_enum "unspecv" [
(set_attr "prefix_extra" "1")
(set_attr "prefix" "orig,maybe_evex,evex")
(set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "vgf2p8affineqb_<mode><mask_name>"
+ [(set (match_operand:VI1_AVX512F 0 "register_operand" "=x,x,v")
+ (unspec:VI1_AVX512F [(match_operand:VI1_AVX512F 1 "register_operand" "%0,x,v")
+ (match_operand:VI1_AVX512F 2 "nonimmediate_operand" "xBm,xm,vm")
+ (match_operand:QI 3 "const_0_to_255_operand" "n,n,n")]
+ UNSPEC_GF2P8AFFINE))]
+ "TARGET_GFNI"
+ "@
+ gf2p8affineqb\t{%3, %2, %0| %0, %2, %3}
+ vgf2p8affineqb\t{%3, %2, %1, %0<mask_operand4>| %0<mask_operand4>, %1, %2, %3}
+ vgf2p8affineqb\t{%3, %2, %1, %0<mask_operand4>| %0<mask_operand4>, %1, %2, %3}"
+ [(set_attr "isa" "noavx,avx,avx512bw")
+ (set_attr "prefix_data16" "1,*,*")
+ (set_attr "prefix_extra" "1")
+ (set_attr "prefix" "orig,maybe_evex,evex")
+ (set_attr "mode" "<sseinsnmode>")])
+2017-11-10 Julia Koval <julia.koval@intel.com>
+
+ * gcc.target/i386/avx-1.c: Handle new intrinsics.
+ * gcc.target/i386/avx512f-gf2p8affineqb-2.c: New runtime tests.
+ * gcc.target/i386/avx512vl-gf2p8affineqb-2.c: Ditto.
+ * gcc.target/i386/gfni-1.c: Add tests for GF2P8AFFINE.
+ * gcc.target/i386/gfni-2.c: Ditto.
+ * gcc.target/i386/gfni-3.c: Ditto.
+ * gcc.target/i386/gfni-4.c: Ditto.
+ * gcc.target/i386/sse-13.c: Handle new tests.
+ * gcc.target/i386/sse-14.c: Handle new tests.
+ * gcc.target/i386/sse-23.c: Handle new tests.
+
2017-11-10 Thomas Preud'homme <thomas.preudhomme@arm.com>
* gcc.target/arm/cmse/bitfield-4.x: New file.
#define __builtin_ia32_vgf2p8affineinvqb_v16qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask(A, B, 1, D, E)
#define __builtin_ia32_vgf2p8affineinvqb_v32qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask(A, B, 1, D, E)
#define __builtin_ia32_vgf2p8affineinvqb_v64qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v16qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v16qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v32qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v32qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v64qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v64qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v16qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v16qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v32qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v32qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v64qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v64qi_mask(A, B, 1, D, E)
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%zmm\[0-9\]+\[^\\n\\r]*%zmm\[0-9\]+\[^\\n\\r\]*%zmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%zmm\[0-9\]+\[^\\n\\r]*%zmm\[0-9\]+\[^\\n\\r\]*%zmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%zmm\[0-9\]+\[^\\n\\r]*%zmm\[0-9\]+\[^\\n\\r\]*%zmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%zmm\[0-9\]+\[^\\n\\r]*%zmm\[0-9\]+\[^\\n\\r\]*%zmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
#include <x86intrin.h>
x1 = _mm512_gf2p8affineinv_epi64_epi8(x1, x2, 3);
x1 = _mm512_mask_gf2p8affineinv_epi64_epi8(x1, m64, x2, x1, 3);
x1 = _mm512_maskz_gf2p8affineinv_epi64_epi8(m64, x1, x2, 3);
+ x1 = _mm512_gf2p8affine_epi64_epi8(x1, x2, 3);
+ x1 = _mm512_mask_gf2p8affine_epi64_epi8(x1, m64, x2, x1, 3);
+ x1 = _mm512_maskz_gf2p8affine_epi64_epi8(m64, x1, x2, 3);
}
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\\n\\r]*%xmm\[0-9\]+\[^\\n\\r\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\\n\\r]*%xmm\[0-9\]+\[^\\n\\r\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%ymm\[0-9\]+\[^\\n\\r]*%ymm\[0-9\]+\[^\\n\\r\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%ymm\[0-9\]+\[^\\n\\r]*%ymm\[0-9\]+\[^\\n\\r\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\\n\\r]*%xmm\[0-9\]+\[^\\n\\r\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\\n\\r]*%xmm\[0-9\]+\[^\\n\\r\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
#include <x86intrin.h>
x5 = _mm_gf2p8affineinv_epi64_epi8(x5, x6, 3);
x5 = _mm_mask_gf2p8affineinv_epi64_epi8(x5, m16, x6, x5, 3);
x5 = _mm_maskz_gf2p8affineinv_epi64_epi8(m16, x5, x6, 3);
+ x3 = _mm256_gf2p8affine_epi64_epi8(x3, x4, 3);
+ x3 = _mm256_mask_gf2p8affine_epi64_epi8(x3, m32, x4, x3, 3);
+ x3 = _mm256_maskz_gf2p8affine_epi64_epi8(m32, x3, x4, 3);
+ x5 = _mm_gf2p8affine_epi64_epi8(x5, x6, 3);
+ x5 = _mm_mask_gf2p8affine_epi64_epi8(x5, m16, x6, x5, 3);
+ x5 = _mm_maskz_gf2p8affine_epi64_epi8(m16, x5, x6, 3);
}
/* { dg-options "-mgfni -mavx -O2" } */
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vgf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vgf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
#include <x86intrin.h>
{
x3 = _mm256_gf2p8affineinv_epi64_epi8(x3, x4, 3);
x5 = _mm_gf2p8affineinv_epi64_epi8(x5, x6, 3);
+ x3 = _mm256_gf2p8affine_epi64_epi8(x3, x4, 3);
+ x5 = _mm_gf2p8affine_epi64_epi8(x5, x6, 3);
}
/* { dg-do compile } */
-/* { dg-options "-mgfni -O2" } */
+/* { dg-options "-mgfni -O2 -msse" } */
/* { dg-final { scan-assembler-times "gf2p8affineinvqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "gf2p8affineqb\[ \\t\]+\[^\{\n\]*\\\$3\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
#include <x86intrin.h>
avx512vl_test (void)
{
x5 = _mm_gf2p8affineinv_epi64_epi8(x5, x6, 3);
+ x5 = _mm_gf2p8affine_epi64_epi8(x5, x6, 3);
}
#define __builtin_ia32_vgf2p8affineinvqb_v16qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask(A, B, 1, D, E)
#define __builtin_ia32_vgf2p8affineinvqb_v32qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask(A, B, 1, D, E)
#define __builtin_ia32_vgf2p8affineinvqb_v64qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v16qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v16qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v32qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v32qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v64qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v64qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v16qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v16qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v32qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v32qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v64qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v64qi_mask(A, B, 1, D, E)
+
#include <x86intrin.h>
test_2 (_mm_gf2p8affineinv_epi64_epi8, __m128i, __m128i, __m128i, 1)
test_2 (_mm256_gf2p8affineinv_epi64_epi8, __m256i, __m256i, __m256i, 1)
test_2 (_mm512_gf2p8affineinv_epi64_epi8, __m512i, __m512i, __m512i, 1)
+test_2 (_mm_gf2p8affine_epi64_epi8, __m128i, __m128i, __m128i, 1)
+test_2 (_mm256_gf2p8affine_epi64_epi8, __m256i, __m256i, __m256i, 1)
+test_2 (_mm512_gf2p8affine_epi64_epi8, __m512i, __m512i, __m512i, 1)
#define __builtin_ia32_vgf2p8affineinvqb_v16qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask(A, B, 1, D, E)
#define __builtin_ia32_vgf2p8affineinvqb_v32qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask(A, B, 1, D, E)
#define __builtin_ia32_vgf2p8affineinvqb_v64qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v16qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v16qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v32qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v32qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v64qi(A, B, C) __builtin_ia32_vgf2p8affineqb_v64qi(A, B, 1)
+#define __builtin_ia32_vgf2p8affineqb_v16qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v16qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v32qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v32qi_mask(A, B, 1, D, E)
+#define __builtin_ia32_vgf2p8affineqb_v64qi_mask(A, B, C, D, E) __builtin_ia32_vgf2p8affineqb_v64qi_mask(A, B, 1, D, E)
#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,xsavec,xsaves,clflushopt,avx512bw,avx512dq,avx512vl,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,clwb,mwaitx,clzero,pku,sgx,rdpid,gfni")
projects / gcc.git / commitdiff