Skip to content

R
riscv-gcc-1
Commit 78cef090 by Jakub Jelinek
Options

x86: Fix -O0 intrinsic *gather*/*scatter* macros [PR94832] 

As reported in the PR, while most intrinsic -O0 macro argument uses
are properly wrapped in ()s or used in context where having a complex
expression passed as the argument doesn't pose a problem (e.g. when
macro argument use is in between commas, or between ( and comma, or
between comma and ) etc.), especially the gather/scatter macros don't do
this and if one passes to some macro e.g. x + y as argument, the
corresponding inline function would do cast on the argument, but
the macro does (int) ARG, then it is (int) x + y rather than (int) (x + y).

The following patch fixes those issues in *gather/*scatter*; additionally,
the AVX2 macros were passing incorrect mask of e.g.
(__v2df)_mm_set1_pd((double)(long long int) -1)
which is IMHO equivalent to
(__v2df){-1.0, -1.0}
when it really wants to pass __v2df vector with all bits set.
I've used what the inline functions use for those cases.

2020-04-29  Jakub Jelinek  <jakub@redhat.com>

	PR target/94832
	* config/i386/avx2intrin.h (_mm_mask_i32gather_pd,
	_mm256_mask_i32gather_pd, _mm_mask_i64gather_pd,
	_mm256_mask_i64gather_pd, _mm_mask_i32gather_ps,
	_mm256_mask_i32gather_ps, _mm_mask_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): Surround macro parameter uses with
	parens.
	(_mm_i32gather_pd, _mm256_i32gather_pd, _mm_i64gather_pd,
	_mm256_i64gather_pd, _mm_i32gather_ps, _mm256_i32gather_ps,
	_mm_i64gather_ps, _mm256_i64gather_ps): Likewise.  Don't use
	as mask vector containing -1.0 or -1.0f elts, but instead vector
	with all bits set using _mm*_cmpeq_p? with zero operands.
	* config/i386/avx512fintrin.h (_mm512_i32gather_ps,
	_mm512_mask_i32gather_ps, _mm512_i32gather_pd,
	_mm512_mask_i32gather_pd, _mm512_i64gather_ps,
	_mm512_mask_i64gather_ps, _mm512_i64gather_pd,
	_mm512_mask_i64gather_pd, _mm512_i32gather_epi32,
	_mm512_mask_i32gather_epi32, _mm512_i32gather_epi64,
	_mm512_mask_i32gather_epi64, _mm512_i64gather_epi32,
	_mm512_mask_i64gather_epi32, _mm512_i64gather_epi64,
	_mm512_mask_i64gather_epi64, _mm512_i32scatter_ps,
	_mm512_mask_i32scatter_ps, _mm512_i32scatter_pd,
	_mm512_mask_i32scatter_pd, _mm512_i64scatter_ps,
	_mm512_mask_i64scatter_ps, _mm512_i64scatter_pd,
	_mm512_mask_i64scatter_pd, _mm512_i32scatter_epi32,
	_mm512_mask_i32scatter_epi32, _mm512_i32scatter_epi64,
	_mm512_mask_i32scatter_epi64, _mm512_i64scatter_epi32,
	_mm512_mask_i64scatter_epi32, _mm512_i64scatter_epi64,
	_mm512_mask_i64scatter_epi64): Surround macro parameter uses with
	parens.
	* config/i386/avx512pfintrin.h (_mm512_prefetch_i32gather_pd,
	_mm512_prefetch_i32gather_ps, _mm512_mask_prefetch_i32gather_pd,
	_mm512_mask_prefetch_i32gather_ps, _mm512_prefetch_i64gather_pd,
	_mm512_prefetch_i64gather_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/avx512vlintrin.h (_mm256_mmask_i32gather_ps,
	_mm_mmask_i32gather_ps, _mm256_mmask_i32gather_pd,
	_mm_mmask_i32gather_pd, _mm256_mmask_i64gather_ps,
	_mm_mmask_i64gather_ps, _mm256_mmask_i64gather_pd,
	_mm_mmask_i64gather_pd, _mm256_mmask_i32gather_epi32,
	_mm_mmask_i32gather_epi32, _mm256_mmask_i32gather_epi64,
	_mm_mmask_i32gather_epi64, _mm256_mmask_i64gather_epi32,
	_mm_mmask_i64gather_epi32, _mm256_mmask_i64gather_epi64,
	_mm_mmask_i64gather_epi64, _mm256_i32scatter_ps,
	_mm256_mask_i32scatter_ps, _mm_i32scatter_ps, _mm_mask_i32scatter_ps,
	_mm256_i32scatter_pd, _mm256_mask_i32scatter_pd, _mm_i32scatter_pd,
	_mm_mask_i32scatter_pd, _mm256_i64scatter_ps,
	_mm256_mask_i64scatter_ps, _mm_i64scatter_ps, _mm_mask_i64scatter_ps,
	_mm256_i64scatter_pd, _mm256_mask_i64scatter_pd, _mm_i64scatter_pd,
	_mm_mask_i64scatter_pd, _mm256_i32scatter_epi32,
	_mm256_mask_i32scatter_epi32, _mm_i32scatter_epi32,
	_mm_mask_i32scatter_epi32, _mm256_i32scatter_epi64,
	_mm256_mask_i32scatter_epi64, _mm_i32scatter_epi64,
	_mm_mask_i32scatter_epi64, _mm256_i64scatter_epi32,
	_mm256_mask_i64scatter_epi32, _mm_i64scatter_epi32,
	_mm_mask_i64scatter_epi32, _mm256_i64scatter_epi64,
	_mm256_mask_i64scatter_epi64, _mm_i64scatter_epi64,
	_mm_mask_i64scatter_epi64): Likewise.
parent 27594524
Showing with 110 additions and 32 deletions
gcc/ChangeLog
2020-04-29 Jakub Jelinek <jakub@redhat.com>
PR target/94832
* config/i386/avx2intrin.h (_mm_mask_i32gather_pd,
_mm256_mask_i32gather_pd, _mm_mask_i64gather_pd,
_mm256_mask_i64gather_pd, _mm_mask_i32gather_ps,
_mm256_mask_i32gather_ps, _mm_mask_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): Surround macro parameter uses with
parens.
(_mm_i32gather_pd, _mm256_i32gather_pd, _mm_i64gather_pd,
_mm256_i64gather_pd, _mm_i32gather_ps, _mm256_i32gather_ps,
_mm_i64gather_ps, _mm256_i64gather_ps): Likewise. Don't use
as mask vector containing -1.0 or -1.0f elts, but instead vector
with all bits set using _mm*_cmpeq_p? with zero operands.
* config/i386/avx512fintrin.h (_mm512_i32gather_ps,
_mm512_mask_i32gather_ps, _mm512_i32gather_pd,
_mm512_mask_i32gather_pd, _mm512_i64gather_ps,
_mm512_mask_i64gather_ps, _mm512_i64gather_pd,
_mm512_mask_i64gather_pd, _mm512_i32gather_epi32,
_mm512_mask_i32gather_epi32, _mm512_i32gather_epi64,
_mm512_mask_i32gather_epi64, _mm512_i64gather_epi32,
_mm512_mask_i64gather_epi32, _mm512_i64gather_epi64,
_mm512_mask_i64gather_epi64, _mm512_i32scatter_ps,
_mm512_mask_i32scatter_ps, _mm512_i32scatter_pd,
_mm512_mask_i32scatter_pd, _mm512_i64scatter_ps,
_mm512_mask_i64scatter_ps, _mm512_i64scatter_pd,
_mm512_mask_i64scatter_pd, _mm512_i32scatter_epi32,
_mm512_mask_i32scatter_epi32, _mm512_i32scatter_epi64,
_mm512_mask_i32scatter_epi64, _mm512_i64scatter_epi32,
_mm512_mask_i64scatter_epi32, _mm512_i64scatter_epi64,
_mm512_mask_i64scatter_epi64): Surround macro parameter uses with
parens.
* config/i386/avx512pfintrin.h (_mm512_prefetch_i32gather_pd,
_mm512_prefetch_i32gather_ps, _mm512_mask_prefetch_i32gather_pd,
_mm512_mask_prefetch_i32gather_ps, _mm512_prefetch_i64gather_pd,
_mm512_prefetch_i64gather_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/avx512vlintrin.h (_mm256_mmask_i32gather_ps,
_mm_mmask_i32gather_ps, _mm256_mmask_i32gather_pd,
_mm_mmask_i32gather_pd, _mm256_mmask_i64gather_ps,
_mm_mmask_i64gather_ps, _mm256_mmask_i64gather_pd,
_mm_mmask_i64gather_pd, _mm256_mmask_i32gather_epi32,
_mm_mmask_i32gather_epi32, _mm256_mmask_i32gather_epi64,
_mm_mmask_i32gather_epi64, _mm256_mmask_i64gather_epi32,
_mm_mmask_i64gather_epi32, _mm256_mmask_i64gather_epi64,
_mm_mmask_i64gather_epi64, _mm256_i32scatter_ps,
_mm256_mask_i32scatter_ps, _mm_i32scatter_ps, _mm_mask_i32scatter_ps,
_mm256_i32scatter_pd, _mm256_mask_i32scatter_pd, _mm_i32scatter_pd,
_mm_mask_i32scatter_pd, _mm256_i64scatter_ps,
_mm256_mask_i64scatter_ps, _mm_i64scatter_ps, _mm_mask_i64scatter_ps,
_mm256_i64scatter_pd, _mm256_mask_i64scatter_pd, _mm_i64scatter_pd,
_mm_mask_i64scatter_pd, _mm256_i32scatter_epi32,
_mm256_mask_i32scatter_epi32, _mm_i32scatter_epi32,
_mm_mask_i32scatter_epi32, _mm256_i32scatter_epi64,
_mm256_mask_i32scatter_epi64, _mm_i32scatter_epi64,
_mm_mask_i32scatter_epi64, _mm256_i64scatter_epi32,
_mm256_mask_i64scatter_epi32, _mm_i64scatter_epi32,
_mm_mask_i64scatter_epi32, _mm256_i64scatter_epi64,
_mm256_mask_i64scatter_epi64, _mm_i64scatter_epi64,
_mm_mask_i64scatter_epi64): Likewise.
2020-04-29 Jeff Law <law@redhat.com>
* config/h8300/h8300.md (H8/SX div patterns): All H8/SX specific
......
gcc/config/i386/avx512pfintrin.h
......@@ -192,68 +192,73 @@ _mm512_mask_prefetch_i64scatter_ps (void *__addr, __mmask8 __mask,
#else
#define _mm512_prefetch_i32gather_pd(INDEX, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfdpd ((__mmask8)0xFF, (__v8si)(__m256i)INDEX, \
(void const *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfdpd ((__mmask8)0xFF, (__v8si)(__m256i) (INDEX), \
(void const *) (ADDR), (int) (SCALE), \
(int) (HINT))
#define _mm512_prefetch_i32gather_ps(INDEX, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfdps ((__mmask16)0xFFFF, (__v16si)(__m512i)INDEX, \
(void const *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfdps ((__mmask16)0xFFFF, (__v16si)(__m512i) (INDEX), \
(void const *) (ADDR), (int) (SCALE), \
(int) (HINT))
#define _mm512_mask_prefetch_i32gather_pd(INDEX, MASK, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfdpd ((__mmask8)MASK, (__v8si)(__m256i)INDEX, \
(void const *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfdpd ((__mmask8) (MASK), (__v8si)(__m256i) (INDEX), \
(void 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, \
(void const *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfdps ((__mmask16) (MASK), (__v16si)(__m512i) (INDEX),\
(void const *) (ADDR), (int) (SCALE), \
(int) (HINT))
#define _mm512_prefetch_i64gather_pd(INDEX, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfqpd ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfqpd ((__mmask8)0xFF, (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_prefetch_i64gather_ps(INDEX, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfqps ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfqps ((__mmask8)0xFF, (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_mask_prefetch_i64gather_pd(INDEX, MASK, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfqpd ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfqpd ((__mmask8) (MASK), (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_mask_prefetch_i64gather_ps(INDEX, MASK, ADDR, SCALE, HINT) \
__builtin_ia32_gatherpfqps ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_gatherpfqps ((__mmask8) (MASK), (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_prefetch_i32scatter_pd(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdpd ((__mmask8)0xFF, (__v8si)(__m256i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfdpd ((__mmask8)0xFF, (__v8si)(__m256i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_prefetch_i32scatter_ps(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdps ((__mmask16)0xFFFF, (__v16si)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfdps ((__mmask16)0xFFFF, (__v16si)(__m512i) (INDEX),\
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_mask_prefetch_i32scatter_pd(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdpd ((__mmask8)MASK, (__v8si)(__m256i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfdpd ((__mmask8) (MASK), (__v8si)(__m256i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_mask_prefetch_i32scatter_ps(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfdps ((__mmask16) (MASK), \
(__v16si)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_prefetch_i64scatter_pd(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqpd ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfqpd ((__mmask8)0xFF, (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_prefetch_i64scatter_ps(ADDR, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqps ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfqps ((__mmask8)0xFF, (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_mask_prefetch_i64scatter_pd(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqpd ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfqpd ((__mmask8) (MASK), (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#define _mm512_mask_prefetch_i64scatter_ps(ADDR, MASK, INDEX, SCALE, HINT) \
__builtin_ia32_scatterpfqps ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
(void *)ADDR, (int)SCALE, (int)HINT)
__builtin_ia32_scatterpfqps ((__mmask8) (MASK), (__v8di)(__m512i) (INDEX), \
(void *) (ADDR), (int) (SCALE), (int) (HINT))
#endif
#ifdef __DISABLE_AVX512PF__
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment