On Fri, Aug 19, 2016 at 12:56 PM, Jakub Jelinek <ja...@redhat.com> wrote:
> On Fri, Aug 19, 2016 at 11:48:16AM +0200, Uros Bizjak wrote:
>> > * config/i386/pkuintrin.h (_wrpkru): Likewise. Add space after
>> > function name.
>> > (_rdpkru_u32): Add space after function name.
>>
>> OK as obvious patch.
>
> Thanks. When changing this part, I've noticed the argument name key.
> While most of the inline function arguments and local variables are properly
> uglified (using __* names), some of them aren't, so if one e.g. does
> #define key ({ ... })
> #include <x86intrin.h>
> or similar, it will fail to compile.
> E.g. the glibc and libstdc++ headers try hard to uglify everything that
> isn't part of the namespace reserved for what the header provides and
> implementation and IMNSHO so should do the intrinsics.
>
> I've used -g -dA -fno-merge-debug-strings -S -fkeep-inline-functions
> -D__always_inline__= -D__artificial__=
> to compile sse-13.c (in addition to its dg-options) and then
> grep -A3 'DW_TAG_formal_parameter\|DW_TAG_variable' sse-13.s
> and searched in there for "[^_ ] regexp.
>
> Ok for trunk if testing succeeds?
Yes, also OK.
Thanks,
Uros.
>
> 2016-08-19 Jakub Jelinek <ja...@redhat.com>
>
> * config/i386/rdseedintrin.h (_rdseed16_step, _rdseed32_step,
> _rdseed64_step): Uglify argument names and/or local variable names
> in inline functions.
> * config/i386/rtmintrin.h (_xabort): Likewise.
> * config/i386/avx512vlintrin.h (_mm256_ternarylogic_epi64,
> _mm256_mask_ternarylogic_epi64, _mm256_maskz_ternarylogic_epi64,
> _mm256_ternarylogic_epi32, _mm256_mask_ternarylogic_epi32,
> _mm256_maskz_ternarylogic_epi32, _mm_ternarylogic_epi64,
> _mm_mask_ternarylogic_epi64, _mm_maskz_ternarylogic_epi64,
> _mm_ternarylogic_epi32, _mm_mask_ternarylogic_epi32,
> _mm_maskz_ternarylogic_epi32): Likewise.
> * config/i386/lwpintrin.h (__llwpcb, __lwpval32, __lwpval64,
> __lwpins32, __lwpins64): Likewise.
> * config/i386/avx2intrin.h (_mm_i32gather_pd, _mm_mask_i32gather_pd,
> _mm256_i32gather_pd, _mm256_mask_i32gather_pd, _mm_i64gather_pd,
> _mm_mask_i64gather_pd, _mm256_i64gather_pd, _mm256_mask_i64gather_pd,
> _mm_i32gather_ps, _mm_mask_i32gather_ps, _mm256_i32gather_ps,
> _mm256_mask_i32gather_ps, _mm_i64gather_ps, _mm_mask_i64gather_ps,
> _mm256_i64gather_ps, _mm256_mask_i64gather_ps, _mm_i32gather_epi64,
> _mm_mask_i32gather_epi64, _mm256_i32gather_epi64,
> _mm256_mask_i32gather_epi64, _mm_i64gather_epi64,
> _mm_mask_i64gather_epi64, _mm256_i64gather_epi64,
> _mm256_mask_i64gather_epi64, _mm_i32gather_epi32,
> _mm_mask_i32gather_epi32, _mm256_i32gather_epi32,
> _mm256_mask_i32gather_epi32, _mm_i64gather_epi32,
> _mm_mask_i64gather_epi32, _mm256_i64gather_epi32,
> _mm256_mask_i64gather_epi32): Likewise.
> * config/i386/pmm_malloc.h (_mm_malloc, _mm_free): Likewise.
> * config/i386/ia32intrin.h (__writeeflags): Likewise.
> * config/i386/pkuintrin.h (_wrpkru): Likewise.
> * config/i386/avx512pfintrin.h (_mm512_mask_prefetch_i32gather_pd,
> _mm512_mask_prefetch_i32gather_ps, _mm512_mask_prefetch_i64gather_pd,
> _mm512_mask_prefetch_i64gather_ps, _mm512_prefetch_i32scatter_pd,
> _mm512_prefetch_i32scatter_ps, _mm512_mask_prefetch_i32scatter_pd,
> _mm512_mask_prefetch_i32scatter_ps, _mm512_prefetch_i64scatter_pd,
> _mm512_prefetch_i64scatter_ps, _mm512_mask_prefetch_i64scatter_pd,
> _mm512_mask_prefetch_i64scatter_ps): Likewise.
> * config/i386/gmm_malloc.h (_mm_malloc, _mm_free): Likewise.
> * config/i386/avx512fintrin.h (_mm512_ternarylogic_epi64,
> _mm512_mask_ternarylogic_epi64, _mm512_maskz_ternarylogic_epi64,
> _mm512_ternarylogic_epi32, _mm512_mask_ternarylogic_epi32,
> _mm512_maskz_ternarylogic_epi32, _mm512_i32gather_ps,
> _mm512_mask_i32gather_ps, _mm512_i32gather_pd, _mm512_i64gather_ps,
> _mm512_i64gather_pd, _mm512_i32gather_epi32, _mm512_i32gather_epi64,
> _mm512_i64gather_epi32, _mm512_i64gather_epi64): Likewise.
>
> --- gcc/config/i386/rdseedintrin.h.jj 2016-01-04 14:55:56.000000000 +0100
> +++ gcc/config/i386/rdseedintrin.h 2016-08-19 11:55:35.603707812 +0200
> @@ -37,24 +37,24 @@
>
> extern __inline int
> __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -_rdseed16_step (unsigned short *p)
> +_rdseed16_step (unsigned short *__p)
> {
> - return __builtin_ia32_rdseed_hi_step (p);
> + return __builtin_ia32_rdseed_hi_step (__p);
> }
>
> extern __inline int
> __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -_rdseed32_step (unsigned int *p)
> +_rdseed32_step (unsigned int *__p)
> {
> - return __builtin_ia32_rdseed_si_step (p);
> + return __builtin_ia32_rdseed_si_step (__p);
> }
>
> #ifdef __x86_64__
> extern __inline int
> __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -_rdseed64_step (unsigned long long *p)
> +_rdseed64_step (unsigned long long *__p)
> {
> - return __builtin_ia32_rdseed_di_step (p);
> + return __builtin_ia32_rdseed_di_step (__p);
> }
> #endif
>
> --- gcc/config/i386/rtmintrin.h.jj 2016-01-04 14:55:56.000000000 +0100
> +++ gcc/config/i386/rtmintrin.h 2016-08-19 11:58:16.043692136 +0200
> @@ -68,9 +68,9 @@ _xend (void)
> #ifdef __OPTIMIZE__
> extern __inline void
> __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -_xabort (const unsigned int imm)
> +_xabort (const unsigned int __imm)
> {
> - __builtin_ia32_xabort (imm);
> + __builtin_ia32_xabort (__imm);
> }
> #else
> #define _xabort(N) __builtin_ia32_xabort (N)
> --- gcc/config/i386/avx512vlintrin.h.jj 2016-08-15 17:01:04.000000000 +0200
> +++ gcc/config/i386/avx512vlintrin.h 2016-08-19 11:59:55.049448284 +0200
> @@ -9796,11 +9796,11 @@ _mm_maskz_srli_epi64 (__mmask8 __U, __m1
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_ternarylogic_epi64 (__m256i __A, __m256i __B, __m256i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m256i) __builtin_ia32_pternlogq256_mask ((__v4di) __A,
> (__v4di) __B,
> - (__v4di) __C, imm,
> + (__v4di) __C, __imm,
> (__mmask8) -1);
> }
>
> @@ -9808,11 +9808,11 @@ extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_ternarylogic_epi64 (__m256i __A, __mmask8 __U,
> __m256i __B, __m256i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m256i) __builtin_ia32_pternlogq256_mask ((__v4di) __A,
> (__v4di) __B,
> - (__v4di) __C, imm,
> + (__v4di) __C, __imm,
> (__mmask8) __U);
> }
>
> @@ -9820,23 +9820,23 @@ extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_ternarylogic_epi64 (__mmask8 __U, __m256i __A,
> __m256i __B, __m256i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m256i) __builtin_ia32_pternlogq256_maskz ((__v4di) __A,
> (__v4di) __B,
> (__v4di) __C,
> - imm,
> + __imm,
> (__mmask8) __U);
> }
>
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_ternarylogic_epi32 (__m256i __A, __m256i __B, __m256i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m256i) __builtin_ia32_pternlogd256_mask ((__v8si) __A,
> (__v8si) __B,
> - (__v8si) __C, imm,
> + (__v8si) __C, __imm,
> (__mmask8) -1);
> }
>
> @@ -9844,11 +9844,11 @@ extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_ternarylogic_epi32 (__m256i __A, __mmask8 __U,
> __m256i __B, __m256i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m256i) __builtin_ia32_pternlogd256_mask ((__v8si) __A,
> (__v8si) __B,
> - (__v8si) __C, imm,
> + (__v8si) __C, __imm,
> (__mmask8) __U);
> }
>
> @@ -9856,80 +9856,80 @@ extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_ternarylogic_epi32 (__mmask8 __U, __m256i __A,
> __m256i __B, __m256i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m256i) __builtin_ia32_pternlogd256_maskz ((__v8si) __A,
> (__v8si) __B,
> (__v8si) __C,
> - imm,
> + __imm,
> (__mmask8) __U);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ternarylogic_epi64 (__m128i __A, __m128i __B, __m128i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m128i) __builtin_ia32_pternlogq128_mask ((__v2di) __A,
> (__v2di) __B,
> - (__v2di) __C, imm,
> + (__v2di) __C, __imm,
> (__mmask8) -1);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_ternarylogic_epi64 (__m128i __A, __mmask8 __U,
> - __m128i __B, __m128i __C, const int imm)
> + __m128i __B, __m128i __C, const int __imm)
> {
> return (__m128i) __builtin_ia32_pternlogq128_mask ((__v2di) __A,
> (__v2di) __B,
> - (__v2di) __C, imm,
> + (__v2di) __C, __imm,
> (__mmask8) __U);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_ternarylogic_epi64 (__mmask8 __U, __m128i __A,
> - __m128i __B, __m128i __C, const int imm)
> + __m128i __B, __m128i __C, const int __imm)
> {
> return (__m128i) __builtin_ia32_pternlogq128_maskz ((__v2di) __A,
> (__v2di) __B,
> (__v2di) __C,
> - imm,
> + __imm,
> (__mmask8) __U);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ternarylogic_epi32 (__m128i __A, __m128i __B, __m128i __C,
> - const int imm)
> + const int __imm)
> {
> return (__m128i) __builtin_ia32_pternlogd128_mask ((__v4si) __A,
> (__v4si) __B,
> - (__v4si) __C, imm,
> + (__v4si) __C, __imm,
> (__mmask8) -1);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_ternarylogic_epi32 (__m128i __A, __mmask8 __U,
> - __m128i __B, __m128i __C, const int imm)
> + __m128i __B, __m128i __C, const int __imm)
> {
> return (__m128i) __builtin_ia32_pternlogd128_mask ((__v4si) __A,
> (__v4si) __B,
> - (__v4si) __C, imm,
> + (__v4si) __C, __imm,
> (__mmask8) __U);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_ternarylogic_epi32 (__mmask8 __U, __m128i __A,
> - __m128i __B, __m128i __C, const int imm)
> + __m128i __B, __m128i __C, const int __imm)
> {
> return (__m128i) __builtin_ia32_pternlogd128_maskz ((__v4si) __A,
> (__v4si) __B,
> (__v4si) __C,
> - imm,
> + __imm,
> (__mmask8) __U);
> }
>
> --- gcc/config/i386/lwpintrin.h.jj 2016-01-04 14:55:56.000000000 +0100
> +++ gcc/config/i386/lwpintrin.h 2016-08-19 11:57:29.951271214 +0200
> @@ -35,9 +35,9 @@
> #endif /* __LWP__ */
>
> extern __inline void __attribute__((__gnu_inline__, __always_inline__,
> __artificial__))
> -__llwpcb (void *pcbAddress)
> +__llwpcb (void *__pcbAddress)
> {
> - __builtin_ia32_llwpcb (pcbAddress);
> + __builtin_ia32_llwpcb (__pcbAddress);
> }
>
> extern __inline void * __attribute__((__gnu_inline__, __always_inline__,
> __artificial__))
> @@ -48,16 +48,17 @@ __slwpcb (void)
>
> #ifdef __OPTIMIZE__
> extern __inline void __attribute__((__gnu_inline__, __always_inline__,
> __artificial__))
> -__lwpval32 (unsigned int data2, unsigned int data1, unsigned int flags)
> +__lwpval32 (unsigned int __data2, unsigned int __data1, unsigned int __flags)
> {
> - __builtin_ia32_lwpval32 (data2, data1, flags);
> + __builtin_ia32_lwpval32 (__data2, __data1, __flags);
> }
>
> #ifdef __x86_64__
> extern __inline void __attribute__((__gnu_inline__, __always_inline__,
> __artificial__))
> -__lwpval64 (unsigned long long data2, unsigned int data1, unsigned int flags)
> +__lwpval64 (unsigned long long __data2, unsigned int __data1,
> + unsigned int __flags)
> {
> - __builtin_ia32_lwpval64 (data2, data1, flags);
> + __builtin_ia32_lwpval64 (__data2, __data1, __flags);
> }
> #endif
> #else
> @@ -74,16 +75,17 @@ __lwpval64 (unsigned long long data2, un
>
> #ifdef __OPTIMIZE__
> extern __inline unsigned char __attribute__((__gnu_inline__,
> __always_inline__, __artificial__))
> -__lwpins32 (unsigned int data2, unsigned int data1, unsigned int flags)
> +__lwpins32 (unsigned int __data2, unsigned int __data1, unsigned int __flags)
> {
> - return __builtin_ia32_lwpins32 (data2, data1, flags);
> + return __builtin_ia32_lwpins32 (__data2, __data1, __flags);
> }
>
> #ifdef __x86_64__
> extern __inline unsigned char __attribute__((__gnu_inline__,
> __always_inline__, __artificial__))
> -__lwpins64 (unsigned long long data2, unsigned int data1, unsigned int flags)
> +__lwpins64 (unsigned long long __data2, unsigned int __data1,
> + unsigned int __flags)
> {
> - return __builtin_ia32_lwpins64 (data2, data1, flags);
> + return __builtin_ia32_lwpins64 (__data2, __data1, __flags);
> }
> #endif
> #else
> --- gcc/config/i386/avx2intrin.h.jj 2016-01-04 14:55:55.000000000 +0100
> +++ gcc/config/i386/avx2intrin.h 2016-08-19 12:23:32.612588675 +0200
> @@ -1246,422 +1246,426 @@ _mm_srlv_epi64 (__m128i __X, __m128i __Y
> #ifdef __OPTIMIZE__
> extern __inline __m128d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i32gather_pd (double const *base, __m128i index, const int scale)
> +_mm_i32gather_pd (double const *__base, __m128i __index, const int __scale)
> {
> - __v2df zero = _mm_setzero_pd ();
> - __v2df mask = _mm_cmpeq_pd (zero, zero);
> + __v2df __zero = _mm_setzero_pd ();
> + __v2df __mask = _mm_cmpeq_pd (__zero, __zero);
>
> return (__m128d) __builtin_ia32_gathersiv2df (_mm_undefined_pd (),
> - base,
> - (__v4si)index,
> - mask,
> - scale);
> + __base,
> + (__v4si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i32gather_pd (__m128d src, double const *base, __m128i index,
> - __m128d mask, const int scale)
> +_mm_mask_i32gather_pd (__m128d __src, double const *__base, __m128i __index,
> + __m128d __mask, const int __scale)
> {
> - return (__m128d) __builtin_ia32_gathersiv2df ((__v2df)src,
> - base,
> - (__v4si)index,
> - (__v2df)mask,
> - scale);
> + return (__m128d) __builtin_ia32_gathersiv2df ((__v2df)__src,
> + __base,
> + (__v4si)__index,
> + (__v2df)__mask,
> + __scale);
> }
>
> extern __inline __m256d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i32gather_pd (double const *base, __m128i index, const int scale)
> +_mm256_i32gather_pd (double const *__base, __m128i __index, const int
> __scale)
> {
> - __v4df zero = _mm256_setzero_pd ();
> - __v4df mask = _mm256_cmp_pd (zero, zero, _CMP_EQ_OQ);
> + __v4df __zero = _mm256_setzero_pd ();
> + __v4df __mask = _mm256_cmp_pd (__zero, __zero, _CMP_EQ_OQ);
>
> return (__m256d) __builtin_ia32_gathersiv4df (_mm256_undefined_pd (),
> - base,
> - (__v4si)index,
> - mask,
> - scale);
> + __base,
> + (__v4si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m256d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i32gather_pd (__m256d src, double const *base,
> - __m128i index, __m256d mask, const int scale)
> +_mm256_mask_i32gather_pd (__m256d __src, double const *__base,
> + __m128i __index, __m256d __mask, const int __scale)
> {
> - return (__m256d) __builtin_ia32_gathersiv4df ((__v4df)src,
> - base,
> - (__v4si)index,
> - (__v4df)mask,
> - scale);
> + return (__m256d) __builtin_ia32_gathersiv4df ((__v4df)__src,
> + __base,
> + (__v4si)__index,
> + (__v4df)__mask,
> + __scale);
> }
>
> extern __inline __m128d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i64gather_pd (double const *base, __m128i index, const int scale)
> +_mm_i64gather_pd (double const *__base, __m128i __index, const int __scale)
> {
> - __v2df src = _mm_setzero_pd ();
> - __v2df mask = _mm_cmpeq_pd (src, src);
> + __v2df __src = _mm_setzero_pd ();
> + __v2df __mask = _mm_cmpeq_pd (__src, __src);
>
> - return (__m128d) __builtin_ia32_gatherdiv2df (src,
> - base,
> - (__v2di)index,
> - mask,
> - scale);
> + return (__m128d) __builtin_ia32_gatherdiv2df (__src,
> + __base,
> + (__v2di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i64gather_pd (__m128d src, double const *base, __m128i index,
> - __m128d mask, const int scale)
> +_mm_mask_i64gather_pd (__m128d __src, double const *__base, __m128i __index,
> + __m128d __mask, const int __scale)
> {
> - return (__m128d) __builtin_ia32_gatherdiv2df ((__v2df)src,
> - base,
> - (__v2di)index,
> - (__v2df)mask,
> - scale);
> + return (__m128d) __builtin_ia32_gatherdiv2df ((__v2df)__src,
> + __base,
> + (__v2di)__index,
> + (__v2df)__mask,
> + __scale);
> }
>
> extern __inline __m256d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i64gather_pd (double const *base, __m256i index, const int scale)
> +_mm256_i64gather_pd (double const *__base, __m256i __index, const int
> __scale)
> {
> - __v4df src = _mm256_setzero_pd ();
> - __v4df mask = _mm256_cmp_pd (src, src, _CMP_EQ_OQ);
> + __v4df __src = _mm256_setzero_pd ();
> + __v4df __mask = _mm256_cmp_pd (__src, __src, _CMP_EQ_OQ);
>
> - return (__m256d) __builtin_ia32_gatherdiv4df (src,
> - base,
> - (__v4di)index,
> - mask,
> - scale);
> + return (__m256d) __builtin_ia32_gatherdiv4df (__src,
> + __base,
> + (__v4di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m256d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i64gather_pd (__m256d src, double const *base,
> - __m256i index, __m256d mask, const int scale)
> +_mm256_mask_i64gather_pd (__m256d __src, double const *__base,
> + __m256i __index, __m256d __mask, const int __scale)
> {
> - return (__m256d) __builtin_ia32_gatherdiv4df ((__v4df)src,
> - base,
> - (__v4di)index,
> - (__v4df)mask,
> - scale);
> + return (__m256d) __builtin_ia32_gatherdiv4df ((__v4df)__src,
> + __base,
> + (__v4di)__index,
> + (__v4df)__mask,
> + __scale);
> }
>
> extern __inline __m128
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i32gather_ps (float const *base, __m128i index, const int scale)
> +_mm_i32gather_ps (float const *__base, __m128i __index, const int __scale)
> {
> - __v4sf src = _mm_setzero_ps ();
> - __v4sf mask = _mm_cmpeq_ps (src, src);
> + __v4sf __src = _mm_setzero_ps ();
> + __v4sf __mask = _mm_cmpeq_ps (__src, __src);
>
> - return (__m128) __builtin_ia32_gathersiv4sf (src,
> - base,
> - (__v4si)index,
> - mask,
> - scale);
> + return (__m128) __builtin_ia32_gathersiv4sf (__src,
> + __base,
> + (__v4si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i32gather_ps (__m128 src, float const *base, __m128i index,
> - __m128 mask, const int scale)
> +_mm_mask_i32gather_ps (__m128 __src, float const *__base, __m128i __index,
> + __m128 __mask, const int __scale)
> {
> - return (__m128) __builtin_ia32_gathersiv4sf ((__v4sf)src,
> - base,
> - (__v4si)index,
> - (__v4sf)mask,
> - scale);
> + return (__m128) __builtin_ia32_gathersiv4sf ((__v4sf)__src,
> + __base,
> + (__v4si)__index,
> + (__v4sf)__mask,
> + __scale);
> }
>
> extern __inline __m256
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i32gather_ps (float const *base, __m256i index, const int scale)
> +_mm256_i32gather_ps (float const *__base, __m256i __index, const int __scale)
> {
> - __v8sf src = _mm256_setzero_ps ();
> - __v8sf mask = _mm256_cmp_ps (src, src, _CMP_EQ_OQ);
> + __v8sf __src = _mm256_setzero_ps ();
> + __v8sf __mask = _mm256_cmp_ps (__src, __src, _CMP_EQ_OQ);
>
> - return (__m256) __builtin_ia32_gathersiv8sf (src,
> - base,
> - (__v8si)index,
> - mask,
> - scale);
> + return (__m256) __builtin_ia32_gathersiv8sf (__src,
> + __base,
> + (__v8si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m256
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i32gather_ps (__m256 src, float const *base,
> - __m256i index, __m256 mask, const int scale)
> +_mm256_mask_i32gather_ps (__m256 __src, float const *__base,
> + __m256i __index, __m256 __mask, const int __scale)
> {
> - return (__m256) __builtin_ia32_gathersiv8sf ((__v8sf)src,
> - base,
> - (__v8si)index,
> - (__v8sf)mask,
> - scale);
> + return (__m256) __builtin_ia32_gathersiv8sf ((__v8sf)__src,
> + __base,
> + (__v8si)__index,
> + (__v8sf)__mask,
> + __scale);
> }
>
> extern __inline __m128
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i64gather_ps (float const *base, __m128i index, const int scale)
> +_mm_i64gather_ps (float const *__base, __m128i __index, const int __scale)
> {
> - __v4sf src = _mm_setzero_ps ();
> - __v4sf mask = _mm_cmpeq_ps (src, src);
> + __v4sf __src = _mm_setzero_ps ();
> + __v4sf __mask = _mm_cmpeq_ps (__src, __src);
>
> - return (__m128) __builtin_ia32_gatherdiv4sf (src,
> - base,
> - (__v2di)index,
> - mask,
> - scale);
> + return (__m128) __builtin_ia32_gatherdiv4sf (__src,
> + __base,
> + (__v2di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i64gather_ps (__m128 src, float const *base, __m128i index,
> - __m128 mask, const int scale)
> +_mm_mask_i64gather_ps (__m128 __src, float const *__base, __m128i __index,
> + __m128 __mask, const int __scale)
> {
> - return (__m128) __builtin_ia32_gatherdiv4sf ((__v4sf)src,
> - base,
> - (__v2di)index,
> - (__v4sf)mask,
> - scale);
> + return (__m128) __builtin_ia32_gatherdiv4sf ((__v4sf)__src,
> + __base,
> + (__v2di)__index,
> + (__v4sf)__mask,
> + __scale);
> }
>
> extern __inline __m128
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i64gather_ps (float const *base, __m256i index, const int scale)
> +_mm256_i64gather_ps (float const *__base, __m256i __index, const int __scale)
> {
> - __v4sf src = _mm_setzero_ps ();
> - __v4sf mask = _mm_cmpeq_ps (src, src);
> + __v4sf __src = _mm_setzero_ps ();
> + __v4sf __mask = _mm_cmpeq_ps (__src, __src);
>
> - return (__m128) __builtin_ia32_gatherdiv4sf256 (src,
> - base,
> - (__v4di)index,
> - mask,
> - scale);
> + return (__m128) __builtin_ia32_gatherdiv4sf256 (__src,
> + __base,
> + (__v4di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i64gather_ps (__m128 src, float const *base,
> - __m256i index, __m128 mask, const int scale)
> +_mm256_mask_i64gather_ps (__m128 __src, float const *__base,
> + __m256i __index, __m128 __mask, const int __scale)
> {
> - return (__m128) __builtin_ia32_gatherdiv4sf256 ((__v4sf)src,
> - base,
> - (__v4di)index,
> - (__v4sf)mask,
> - scale);
> + return (__m128) __builtin_ia32_gatherdiv4sf256 ((__v4sf)__src,
> + __base,
> + (__v4di)__index,
> + (__v4sf)__mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i32gather_epi64 (long long int const *base,
> - __m128i index, const int scale)
> +_mm_i32gather_epi64 (long long int const *__base,
> + __m128i __index, const int __scale)
> {
> - __v2di src = __extension__ (__v2di){ 0, 0 };
> - __v2di mask = __extension__ (__v2di){ ~0, ~0 };
> + __v2di __src = __extension__ (__v2di){ 0, 0 };
> + __v2di __mask = __extension__ (__v2di){ ~0, ~0 };
>
> - return (__m128i) __builtin_ia32_gathersiv2di (src,
> - base,
> - (__v4si)index,
> - mask,
> - scale);
> + return (__m128i) __builtin_ia32_gathersiv2di (__src,
> + __base,
> + (__v4si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i32gather_epi64 (__m128i src, long long int const *base,
> - __m128i index, __m128i mask, const int scale)
> +_mm_mask_i32gather_epi64 (__m128i __src, long long int const *__base,
> + __m128i __index, __m128i __mask, const int __scale)
> {
> - return (__m128i) __builtin_ia32_gathersiv2di ((__v2di)src,
> - base,
> - (__v4si)index,
> - (__v2di)mask,
> - scale);
> + return (__m128i) __builtin_ia32_gathersiv2di ((__v2di)__src,
> + __base,
> + (__v4si)__index,
> + (__v2di)__mask,
> + __scale);
> }
>
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i32gather_epi64 (long long int const *base,
> - __m128i index, const int scale)
> +_mm256_i32gather_epi64 (long long int const *__base,
> + __m128i __index, const int __scale)
> {
> - __v4di src = __extension__ (__v4di){ 0, 0, 0, 0 };
> - __v4di mask = __extension__ (__v4di){ ~0, ~0, ~0, ~0 };
> + __v4di __src = __extension__ (__v4di){ 0, 0, 0, 0 };
> + __v4di __mask = __extension__ (__v4di){ ~0, ~0, ~0, ~0 };
>
> - return (__m256i) __builtin_ia32_gathersiv4di (src,
> - base,
> - (__v4si)index,
> - mask,
> - scale);
> + return (__m256i) __builtin_ia32_gathersiv4di (__src,
> + __base,
> + (__v4si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i32gather_epi64 (__m256i src, long long int const *base,
> - __m128i index, __m256i mask, const int scale)
> -{
> - return (__m256i) __builtin_ia32_gathersiv4di ((__v4di)src,
> - base,
> - (__v4si)index,
> - (__v4di)mask,
> - scale);
> +_mm256_mask_i32gather_epi64 (__m256i __src, long long int const *__base,
> + __m128i __index, __m256i __mask,
> + const int __scale)
> +{
> + return (__m256i) __builtin_ia32_gathersiv4di ((__v4di)__src,
> + __base,
> + (__v4si)__index,
> + (__v4di)__mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i64gather_epi64 (long long int const *base,
> - __m128i index, const int scale)
> +_mm_i64gather_epi64 (long long int const *__base,
> + __m128i __index, const int __scale)
> {
> - __v2di src = __extension__ (__v2di){ 0, 0 };
> - __v2di mask = __extension__ (__v2di){ ~0, ~0 };
> + __v2di __src = __extension__ (__v2di){ 0, 0 };
> + __v2di __mask = __extension__ (__v2di){ ~0, ~0 };
>
> - return (__m128i) __builtin_ia32_gatherdiv2di (src,
> - base,
> - (__v2di)index,
> - mask,
> - scale);
> + return (__m128i) __builtin_ia32_gatherdiv2di (__src,
> + __base,
> + (__v2di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i64gather_epi64 (__m128i src, long long int const *base, __m128i
> index,
> - __m128i mask, const int scale)
> +_mm_mask_i64gather_epi64 (__m128i __src, long long int const *__base,
> + __m128i __index, __m128i __mask, const int __scale)
> {
> - return (__m128i) __builtin_ia32_gatherdiv2di ((__v2di)src,
> - base,
> - (__v2di)index,
> - (__v2di)mask,
> - scale);
> + return (__m128i) __builtin_ia32_gatherdiv2di ((__v2di)__src,
> + __base,
> + (__v2di)__index,
> + (__v2di)__mask,
> + __scale);
> }
>
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i64gather_epi64 (long long int const *base,
> - __m256i index, const int scale)
> +_mm256_i64gather_epi64 (long long int const *__base,
> + __m256i __index, const int __scale)
> {
> - __v4di src = __extension__ (__v4di){ 0, 0, 0, 0 };
> - __v4di mask = __extension__ (__v4di){ ~0, ~0, ~0, ~0 };
> + __v4di __src = __extension__ (__v4di){ 0, 0, 0, 0 };
> + __v4di __mask = __extension__ (__v4di){ ~0, ~0, ~0, ~0 };
>
> - return (__m256i) __builtin_ia32_gatherdiv4di (src,
> - base,
> - (__v4di)index,
> - mask,
> - scale);
> + return (__m256i) __builtin_ia32_gatherdiv4di (__src,
> + __base,
> + (__v4di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i64gather_epi64 (__m256i src, long long int const *base,
> - __m256i index, __m256i mask, const int scale)
> -{
> - return (__m256i) __builtin_ia32_gatherdiv4di ((__v4di)src,
> - base,
> - (__v4di)index,
> - (__v4di)mask,
> - scale);
> +_mm256_mask_i64gather_epi64 (__m256i __src, long long int const *__base,
> + __m256i __index, __m256i __mask,
> + const int __scale)
> +{
> + return (__m256i) __builtin_ia32_gatherdiv4di ((__v4di)__src,
> + __base,
> + (__v4di)__index,
> + (__v4di)__mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i32gather_epi32 (int const *base, __m128i index, const int scale)
> +_mm_i32gather_epi32 (int const *__base, __m128i __index, const int __scale)
> {
> - __v4si src = __extension__ (__v4si){ 0, 0, 0, 0 };
> - __v4si mask = __extension__ (__v4si){ ~0, ~0, ~0, ~0 };
> + __v4si __src = __extension__ (__v4si){ 0, 0, 0, 0 };
> + __v4si __mask = __extension__ (__v4si){ ~0, ~0, ~0, ~0 };
>
> - return (__m128i) __builtin_ia32_gathersiv4si (src,
> - base,
> - (__v4si)index,
> - mask,
> - scale);
> + return (__m128i) __builtin_ia32_gathersiv4si (__src,
> + __base,
> + (__v4si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i32gather_epi32 (__m128i src, int const *base, __m128i index,
> - __m128i mask, const int scale)
> +_mm_mask_i32gather_epi32 (__m128i __src, int const *__base, __m128i __index,
> + __m128i __mask, const int __scale)
> {
> - return (__m128i) __builtin_ia32_gathersiv4si ((__v4si)src,
> - base,
> - (__v4si)index,
> - (__v4si)mask,
> - scale);
> + return (__m128i) __builtin_ia32_gathersiv4si ((__v4si)__src,
> + __base,
> + (__v4si)__index,
> + (__v4si)__mask,
> + __scale);
> }
>
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i32gather_epi32 (int const *base, __m256i index, const int scale)
> +_mm256_i32gather_epi32 (int const *__base, __m256i __index, const int
> __scale)
> {
> - __v8si src = __extension__ (__v8si){ 0, 0, 0, 0, 0, 0, 0, 0 };
> - __v8si mask = __extension__ (__v8si){ ~0, ~0, ~0, ~0, ~0, ~0, ~0, ~0 };
> + __v8si __src = __extension__ (__v8si){ 0, 0, 0, 0, 0, 0, 0, 0 };
> + __v8si __mask = __extension__ (__v8si){ ~0, ~0, ~0, ~0, ~0, ~0, ~0, ~0 };
>
> - return (__m256i) __builtin_ia32_gathersiv8si (src,
> - base,
> - (__v8si)index,
> - mask,
> - scale);
> + return (__m256i) __builtin_ia32_gathersiv8si (__src,
> + __base,
> + (__v8si)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i32gather_epi32 (__m256i src, int const *base,
> - __m256i index, __m256i mask, const int scale)
> -{
> - return (__m256i) __builtin_ia32_gathersiv8si ((__v8si)src,
> - base,
> - (__v8si)index,
> - (__v8si)mask,
> - scale);
> +_mm256_mask_i32gather_epi32 (__m256i __src, int const *__base,
> + __m256i __index, __m256i __mask,
> + const int __scale)
> +{
> + return (__m256i) __builtin_ia32_gathersiv8si ((__v8si)__src,
> + __base,
> + (__v8si)__index,
> + (__v8si)__mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_i64gather_epi32 (int const *base, __m128i index, const int scale)
> +_mm_i64gather_epi32 (int const *__base, __m128i __index, const int __scale)
> {
> - __v4si src = __extension__ (__v4si){ 0, 0, 0, 0 };
> - __v4si mask = __extension__ (__v4si){ ~0, ~0, ~0, ~0 };
> + __v4si __src = __extension__ (__v4si){ 0, 0, 0, 0 };
> + __v4si __mask = __extension__ (__v4si){ ~0, ~0, ~0, ~0 };
>
> - return (__m128i) __builtin_ia32_gatherdiv4si (src,
> - base,
> - (__v2di)index,
> - mask,
> - scale);
> + return (__m128i) __builtin_ia32_gatherdiv4si (__src,
> + __base,
> + (__v2di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_i64gather_epi32 (__m128i src, int const *base, __m128i index,
> - __m128i mask, const int scale)
> +_mm_mask_i64gather_epi32 (__m128i __src, int const *__base, __m128i __index,
> + __m128i __mask, const int __scale)
> {
> - return (__m128i) __builtin_ia32_gatherdiv4si ((__v4si)src,
> - base,
> - (__v2di)index,
> - (__v4si)mask,
> - scale);
> + return (__m128i) __builtin_ia32_gatherdiv4si ((__v4si)__src,
> + __base,
> + (__v2di)__index,
> + (__v4si)__mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_i64gather_epi32 (int const *base, __m256i index, const int scale)
> +_mm256_i64gather_epi32 (int const *__base, __m256i __index, const int
> __scale)
> {
> - __v4si src = __extension__ (__v4si){ 0, 0, 0, 0 };
> - __v4si mask = __extension__ (__v4si){ ~0, ~0, ~0, ~0 };
> + __v4si __src = __extension__ (__v4si){ 0, 0, 0, 0 };
> + __v4si __mask = __extension__ (__v4si){ ~0, ~0, ~0, ~0 };
>
> - return (__m128i) __builtin_ia32_gatherdiv4si256 (src,
> - base,
> - (__v4di)index,
> - mask,
> - scale);
> + return (__m128i) __builtin_ia32_gatherdiv4si256 (__src,
> + __base,
> + (__v4di)__index,
> + __mask,
> + __scale);
> }
>
> extern __inline __m128i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm256_mask_i64gather_epi32 (__m128i src, int const *base,
> - __m256i index, __m128i mask, const int scale)
> -{
> - return (__m128i) __builtin_ia32_gatherdiv4si256 ((__v4si)src,
> - base,
> - (__v4di)index,
> - (__v4si)mask,
> - scale);
> +_mm256_mask_i64gather_epi32 (__m128i __src, int const *__base,
> + __m256i __index, __m128i __mask,
> + const int __scale)
> +{
> + return (__m128i) __builtin_ia32_gatherdiv4si256 ((__v4si)__src,
> + __base,
> + (__v4di)__index,
> + (__v4si)__mask,
> + __scale);
> }
> #else /* __OPTIMIZE__ */
> #define _mm_i32gather_pd(BASE, INDEX, SCALE) \
> --- gcc/config/i386/pmm_malloc.h.jj 2016-01-04 14:55:56.000000000 +0100
> +++ gcc/config/i386/pmm_malloc.h 2016-08-19 12:37:07.701297173 +0200
> @@ -35,23 +35,23 @@ extern "C" int posix_memalign (void **,
> #endif
>
> static __inline void *
> -_mm_malloc (size_t size, size_t alignment)
> +_mm_malloc (size_t __size, size_t __alignment)
> {
> - void *ptr;
> - if (alignment == 1)
> - return malloc (size);
> - if (alignment == 2 || (sizeof (void *) == 8 && alignment == 4))
> - alignment = sizeof (void *);
> - if (posix_memalign (&ptr, alignment, size) == 0)
> - return ptr;
> + void *__ptr;
> + if (__alignment == 1)
> + return malloc (__size);
> + if (__alignment == 2 || (sizeof (void *) == 8 && __alignment == 4))
> + __alignment = sizeof (void *);
> + if (posix_memalign (&__ptr, __alignment, __size) == 0)
> + return __ptr;
> else
> return NULL;
> }
>
> static __inline void
> -_mm_free (void * ptr)
> +_mm_free (void *__ptr)
> {
> - free (ptr);
> + free (__ptr);
> }
>
> #endif /* _MM_MALLOC_H_INCLUDED */
> --- gcc/config/i386/ia32intrin.h.jj 2016-01-04 14:55:55.000000000 +0100
> +++ gcc/config/i386/ia32intrin.h 2016-08-19 12:24:15.836042925 +0200
> @@ -261,9 +261,9 @@ __readeflags (void)
> /* Write flags register */
> extern __inline void
> __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -__writeeflags (unsigned long long X)
> +__writeeflags (unsigned long long __X)
> {
> - __builtin_ia32_writeeflags_u64 (X);
> + __builtin_ia32_writeeflags_u64 (__X);
> }
>
> #define _bswap64(a) __bswapq(a)
> @@ -281,9 +281,9 @@ __readeflags (void)
> /* Write flags register */
> extern __inline void
> __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -__writeeflags (unsigned int X)
> +__writeeflags (unsigned int __X)
> {
> - __builtin_ia32_writeeflags_u32 (X);
> + __builtin_ia32_writeeflags_u32 (__X);
> }
>
> #endif
> --- gcc/config/i386/pkuintrin.h.jj 2016-08-19 11:37:50.000000000 +0200
> +++ gcc/config/i386/pkuintrin.h 2016-08-19 11:55:00.695146383 +0200
> @@ -43,9 +43,9 @@ _rdpkru_u32 (void)
>
> extern __inline void
> __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -_wrpkru (unsigned int key)
> +_wrpkru (unsigned int __key)
> {
> - __builtin_ia32_wrpkru (key);
> + __builtin_ia32_wrpkru (__key);
> }
>
> #ifdef __DISABLE_PKU__
> --- gcc/config/i386/avx512pfintrin.h.jj 2016-08-15 17:01:04.000000000 +0200
> +++ gcc/config/i386/avx512pfintrin.h 2016-08-19 12:04:56.039666815 +0200
> @@ -48,110 +48,110 @@ typedef unsigned short __mmask16;
> #ifdef __OPTIMIZE__
> extern __inline void
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_mask_prefetch_i32gather_pd (__m256i index, __mmask8 mask,
> - void *addr, int scale, int hint)
> +_mm512_mask_prefetch_i32gather_pd (__m256i __index, __mmask8 __mask,
> + void *__addr, int __scale, int __hint)
> {
> - __builtin_ia32_gatherpfdpd (mask, (__v8si) index, (long long const *) 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)
> +_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);
> + __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)
> +_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);
> + __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,
> - void *addr, int scale, int hint)
> +_mm512_mask_prefetch_i64gather_ps (__m512i __index, __mmask8 __mask,
> + void *__addr, int __scale, int __hint)
> {
> - __builtin_ia32_gatherpfqps (mask, (__v8di) index, (int const *) 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_pd (void *addr, __m256i index, int scale,
> - int hint)
> +_mm512_prefetch_i32scatter_pd (void *__addr, __m256i __index, int __scale,
> + int __hint)
> {
> - __builtin_ia32_scatterpfdpd ((__mmask8) 0xFF, (__v8si) index,
> - (long long const *)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_prefetch_i32scatter_ps (void *addr, __m512i index, int scale,
> - int hint)
> +_mm512_prefetch_i32scatter_ps (void *__addr, __m512i __index, int __scale,
> + int __hint)
> {
> - __builtin_ia32_scatterpfdps ((__mmask16) 0xFFFF, (__v16si) index, (int
> const *) 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_i32scatter_pd (void *addr, __mmask8 mask,
> - __m256i index, int scale, int hint)
> +_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);
> + __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)
> +_mm512_mask_prefetch_i32scatter_ps (void *__addr, __mmask16 __mask,
> + __m512i __index, int __scale, int __hint)
> {
> - __builtin_ia32_scatterpfdps (mask, (__v16si) index, (int const *) 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)
> +_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);
> + __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)
> +_mm512_prefetch_i64scatter_ps (void *__addr, __m512i __index, int __scale,
> + int __hint)
> {
> - __builtin_ia32_scatterpfqps ((__mmask8) 0xFF, (__v8di) index, (int const
> *) addr,
> - scale, 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)
> +_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);
> + __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)
> +_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);
> + __builtin_ia32_scatterpfqps (__mask, (__v8di) __index, (int const *)
> __addr,
> + __scale, __hint);
> }
>
> #else
> --- gcc/config/i386/gmm_malloc.h.jj 2016-01-04 14:55:55.000000000 +0100
> +++ gcc/config/i386/gmm_malloc.h 2016-08-19 12:38:26.653300307 +0200
> @@ -27,48 +27,48 @@
> #include <stdlib.h>
> #include <errno.h>
>
> -static __inline__ void*
> -_mm_malloc (size_t size, size_t align)
> +static __inline__ void *
> +_mm_malloc (size_t __size, size_t __align)
> {
> - void * malloc_ptr;
> - void * aligned_ptr;
> + void * __malloc_ptr;
> + void * __aligned_ptr;
>
> /* Error if align is not a power of two. */
> - if (align & (align - 1))
> + if (__align & (__align - 1))
> {
> errno = EINVAL;
> - return ((void*) 0);
> + return ((void *) 0);
> }
>
> - if (size == 0)
> + if (__size == 0)
> return ((void *) 0);
>
> /* Assume malloc'd pointer is aligned at least to sizeof (void*).
> If necessary, add another sizeof (void*) to store the value
> returned by malloc. Effectively this enforces a minimum alignment
> of sizeof double. */
> - if (align < 2 * sizeof (void *))
> - align = 2 * sizeof (void *);
> + if (__align < 2 * sizeof (void *))
> + __align = 2 * sizeof (void *);
>
> - malloc_ptr = malloc (size + align);
> - if (!malloc_ptr)
> + __malloc_ptr = malloc (__size + __align);
> + if (!__malloc_ptr)
> return ((void *) 0);
>
> /* Align We have at least sizeof (void *) space below malloc'd ptr. */
> - aligned_ptr = (void *) (((size_t) malloc_ptr + align)
> - & ~((size_t) (align) - 1));
> + __aligned_ptr = (void *) (((size_t) __malloc_ptr + __align)
> + & ~((size_t) (__align) - 1));
>
> /* Store the original pointer just before p. */
> - ((void **) aligned_ptr) [-1] = malloc_ptr;
> + ((void **) __aligned_ptr)[-1] = __malloc_ptr;
>
> - return aligned_ptr;
> + return __aligned_ptr;
> }
>
> static __inline__ void
> -_mm_free (void * aligned_ptr)
> +_mm_free (void *__aligned_ptr)
> {
> - if (aligned_ptr)
> - free (((void **) aligned_ptr) [-1]);
> + if (__aligned_ptr)
> + free (((void **) __aligned_ptr)[-1]);
> }
>
> #endif /* _MM_MALLOC_H_INCLUDED */
> --- gcc/config/i386/avx512fintrin.h.jj 2016-08-15 17:01:04.000000000 +0200
> +++ gcc/config/i386/avx512fintrin.h 2016-08-19 12:25:13.683312532 +0200
> @@ -1438,66 +1438,68 @@ _mm_sub_round_ss (__m128 __A, __m128 __B
> #ifdef __OPTIMIZE__
> extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_ternarylogic_epi64 (__m512i __A, __m512i __B, __m512i __C, const int
> imm)
> +_mm512_ternarylogic_epi64 (__m512i __A, __m512i __B, __m512i __C,
> + const int __imm)
> {
> return (__m512i) __builtin_ia32_pternlogq512_mask ((__v8di) __A,
> (__v8di) __B,
> - (__v8di) __C, imm,
> + (__v8di) __C, __imm,
> (__mmask8) -1);
> }
>
> extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_ternarylogic_epi64 (__m512i __A, __mmask8 __U, __m512i __B,
> - __m512i __C, const int imm)
> + __m512i __C, const int __imm)
> {
> return (__m512i) __builtin_ia32_pternlogq512_mask ((__v8di) __A,
> (__v8di) __B,
> - (__v8di) __C, imm,
> + (__v8di) __C, __imm,
> (__mmask8) __U);
> }
>
> extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_ternarylogic_epi64 (__mmask8 __U, __m512i __A, __m512i __B,
> - __m512i __C, const int imm)
> + __m512i __C, const int __imm)
> {
> return (__m512i) __builtin_ia32_pternlogq512_maskz ((__v8di) __A,
> (__v8di) __B,
> (__v8di) __C,
> - imm, (__mmask8) __U);
> + __imm, (__mmask8) __U);
> }
>
> extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_ternarylogic_epi32 (__m512i __A, __m512i __B, __m512i __C, const int
> imm)
> +_mm512_ternarylogic_epi32 (__m512i __A, __m512i __B, __m512i __C,
> + const int __imm)
> {
> return (__m512i) __builtin_ia32_pternlogd512_mask ((__v16si) __A,
> (__v16si) __B,
> (__v16si) __C,
> - imm, (__mmask16) -1);
> + __imm, (__mmask16) -1);
> }
>
> extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_ternarylogic_epi32 (__m512i __A, __mmask16 __U, __m512i __B,
> - __m512i __C, const int imm)
> + __m512i __C, const int __imm)
> {
> return (__m512i) __builtin_ia32_pternlogd512_mask ((__v16si) __A,
> (__v16si) __B,
> (__v16si) __C,
> - imm, (__mmask16) __U);
> + __imm, (__mmask16) __U);
> }
>
> extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_ternarylogic_epi32 (__mmask16 __U, __m512i __A, __m512i __B,
> - __m512i __C, const int imm)
> + __m512i __C, const int __imm)
> {
> return (__m512i) __builtin_ia32_pternlogd512_maskz ((__v16si) __A,
> (__v16si) __B,
> (__v16si) __C,
> - imm, (__mmask16) __U);
> + __imm, (__mmask16) __U);
> }
> #else
> #define _mm512_ternarylogic_epi64(A, B, C, I) \
> @@ -9211,21 +9213,21 @@ extern __inline __m512
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i32gather_ps (__m512i __index, float const *__addr, int __scale)
> {
> - __m512 v1_old = _mm512_undefined_ps ();
> - __mmask16 mask = 0xFFFF;
> + __m512 __v1_old = _mm512_undefined_ps ();
> + __mmask16 __mask = 0xFFFF;
>
> - return (__m512) __builtin_ia32_gathersiv16sf ((__v16sf) v1_old,
> + return (__m512) __builtin_ia32_gathersiv16sf ((__v16sf) __v1_old,
> __addr,
> (__v16si) __index,
> - mask, __scale);
> + __mask, __scale);
> }
>
> extern __inline __m512
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_mask_i32gather_ps (__m512 v1_old, __mmask16 __mask,
> +_mm512_mask_i32gather_ps (__m512 __v1_old, __mmask16 __mask,
> __m512i __index, float const *__addr, int __scale)
> {
> - return (__m512) __builtin_ia32_gathersiv16sf ((__v16sf) v1_old,
> + return (__m512) __builtin_ia32_gathersiv16sf ((__v16sf) __v1_old,
> __addr,
> (__v16si) __index,
> __mask, __scale);
> @@ -9235,12 +9237,12 @@ extern __inline __m512d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i32gather_pd (__m256i __index, double const *__addr, int __scale)
> {
> - __m512d v1_old = _mm512_undefined_pd ();
> - __mmask8 mask = 0xFF;
> + __m512d __v1_old = _mm512_undefined_pd ();
> + __mmask8 __mask = 0xFF;
>
> - return (__m512d) __builtin_ia32_gathersiv8df ((__v8df) v1_old,
> + return (__m512d) __builtin_ia32_gathersiv8df ((__v8df) __v1_old,
> __addr,
> - (__v8si) __index, mask,
> + (__v8si) __index, __mask,
> __scale);
> }
>
> @@ -9259,12 +9261,12 @@ extern __inline __m256
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i64gather_ps (__m512i __index, float const *__addr, int __scale)
> {
> - __m256 v1_old = _mm256_undefined_ps ();
> - __mmask8 mask = 0xFF;
> + __m256 __v1_old = _mm256_undefined_ps ();
> + __mmask8 __mask = 0xFF;
>
> - return (__m256) __builtin_ia32_gatherdiv16sf ((__v8sf) v1_old,
> + return (__m256) __builtin_ia32_gatherdiv16sf ((__v8sf) __v1_old,
> __addr,
> - (__v8di) __index, mask,
> + (__v8di) __index, __mask,
> __scale);
> }
>
> @@ -9283,12 +9285,12 @@ extern __inline __m512d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i64gather_pd (__m512i __index, double const *__addr, int __scale)
> {
> - __m512d v1_old = _mm512_undefined_pd ();
> - __mmask8 mask = 0xFF;
> + __m512d __v1_old = _mm512_undefined_pd ();
> + __mmask8 __mask = 0xFF;
>
> - return (__m512d) __builtin_ia32_gatherdiv8df ((__v8df) v1_old,
> + return (__m512d) __builtin_ia32_gatherdiv8df ((__v8df) __v1_old,
> __addr,
> - (__v8di) __index, mask,
> + (__v8di) __index, __mask,
> __scale);
> }
>
> @@ -9307,13 +9309,13 @@ extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i32gather_epi32 (__m512i __index, int const *__addr, int __scale)
> {
> - __m512i v1_old = _mm512_undefined_epi32 ();
> - __mmask16 mask = 0xFFFF;
> + __m512i __v1_old = _mm512_undefined_epi32 ();
> + __mmask16 __mask = 0xFFFF;
>
> - return (__m512i) __builtin_ia32_gathersiv16si ((__v16si) v1_old,
> + return (__m512i) __builtin_ia32_gathersiv16si ((__v16si) __v1_old,
> __addr,
> (__v16si) __index,
> - mask, __scale);
> + __mask, __scale);
> }
>
> extern __inline __m512i
> @@ -9331,12 +9333,12 @@ extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i32gather_epi64 (__m256i __index, long long const *__addr, int
> __scale)
> {
> - __m512i v1_old = _mm512_undefined_epi32 ();
> - __mmask8 mask = 0xFF;
> + __m512i __v1_old = _mm512_undefined_epi32 ();
> + __mmask8 __mask = 0xFF;
>
> - return (__m512i) __builtin_ia32_gathersiv8di ((__v8di) v1_old,
> + return (__m512i) __builtin_ia32_gathersiv8di ((__v8di) __v1_old,
> __addr,
> - (__v8si) __index, mask,
> + (__v8si) __index, __mask,
> __scale);
> }
>
> @@ -9356,13 +9358,13 @@ extern __inline __m256i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i64gather_epi32 (__m512i __index, int const *__addr, int __scale)
> {
> - __m256i v1_old = _mm256_undefined_si256 ();
> - __mmask8 mask = 0xFF;
> + __m256i __v1_old = _mm256_undefined_si256 ();
> + __mmask8 __mask = 0xFF;
>
> - return (__m256i) __builtin_ia32_gatherdiv16si ((__v8si) v1_old,
> + return (__m256i) __builtin_ia32_gatherdiv16si ((__v8si) __v1_old,
> __addr,
> (__v8di) __index,
> - mask, __scale);
> + __mask, __scale);
> }
>
> extern __inline __m256i
> @@ -9380,12 +9382,12 @@ extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_i64gather_epi64 (__m512i __index, long long const *__addr, int
> __scale)
> {
> - __m512i v1_old = _mm512_undefined_epi32 ();
> - __mmask8 mask = 0xFF;
> + __m512i __v1_old = _mm512_undefined_epi32 ();
> + __mmask8 __mask = 0xFF;
>
> - return (__m512i) __builtin_ia32_gatherdiv8di ((__v8di) v1_old,
> + return (__m512i) __builtin_ia32_gatherdiv8di ((__v8di) __v1_old,
> __addr,
> - (__v8di) __index, mask,
> + (__v8di) __index, __mask,
> __scale);
> }
>
>
>
> Jakub
