procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

rs6000: Add support for SSE4.1 "test" intrinsics

Browse source 
2021-07-13  Paul A. Clarke  <pc@us.ibm.com>

gcc
	* config/rs6000/smmintrin.h (_mm_testz_si128, _mm_testc_si128,
	_mm_testnzc_si128, _mm_test_all_ones, _mm_test_all_zeros,
	_mm_test_mix_ones_zeros): New.
This commit is contained in:
Paul A. Clarke 2021-06-29 09:18:55 -05:00
parent 4d3eaeb4f5
commit acd4b9103c
1 changed files with 56 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

56
gcc/config/rs6000/smmintrin.h
View file

@ -116,4 +116,60 @@ _mm_blendv_epi8 (__m128i __A, __m128i __B, __m128i __mask)
return (__m128i) vec_sel ((__v16qu) __A, (__v16qu) __B, __lmask);
}
__inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_testz_si128 (__m128i __A, __m128i __B)
{
/* Note: This implementation does NOT set "zero" or "carry" flags. */
const __v16qu __zero = {0};
return vec_all_eq (vec_and ((__v16qu) __A, (__v16qu) __B), __zero);
}
__inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_testc_si128 (__m128i __A, __m128i __B)
{
/* Note: This implementation does NOT set "zero" or "carry" flags. */
const __v16qu __zero = {0};
const __v16qu __notA = vec_nor ((__v16qu) __A, (__v16qu) __A);
return vec_all_eq (vec_and ((__v16qu) __notA, (__v16qu) __B), __zero);
}
__inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_testnzc_si128 (__m128i __A, __m128i __B)
{
/* Note: This implementation does NOT set "zero" or "carry" flags. */
return _mm_testz_si128 (__A, __B) == 0 && _mm_testc_si128 (__A, __B) == 0;
}
__inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_test_all_zeros (__m128i __A, __m128i __mask)
{
const __v16qu __zero = {0};
return vec_all_eq (vec_and ((__v16qu) __A, (__v16qu) __mask), __zero);
}
__inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_test_all_ones (__m128i __A)
{
const __v16qu __ones = vec_splats ((unsigned char) 0xff);
return vec_all_eq ((__v16qu) __A, __ones);
}
__inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_test_mix_ones_zeros (__m128i __A, __m128i __mask)
{
const __v16qu __zero = {0};
const __v16qu __Amasked = vec_and ((__v16qu) __A, (__v16qu) __mask);
const int any_ones = vec_any_ne (__Amasked, __zero);
const __v16qu __notA = vec_nor ((__v16qu) __A, (__v16qu) __A);
const __v16qu __notAmasked = vec_and ((__v16qu) __notA, (__v16qu) __mask);
const int any_zeros = vec_any_ne (__notAmasked, __zero);
return any_ones * any_zeros;
}
#endif