1 /*===---- avx512vpopcntdqintrin.h - AVX512VPOPCNTDQ intrinsics -------------===
2 *
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a copy
5 * of this software and associated documentation files (the "Software"), to deal
6 * in the Software without restriction, including without limitation the rights
7 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
8 * copies of the Software, and to permit persons to whom the Software is
9 * furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice shall be included in
12 * all copies or substantial portions of the Software.
13 *
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
17 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
18 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
19 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
20 * THE SOFTWARE.
21 *
22 *===-----------------------------------------------------------------------===
23 */
24 #ifndef __IMMINTRIN_H
25 #error \
26 "Never use <avx512vpopcntdqvlintrin.h> directly; include <immintrin.h> instead."
27 #endif
28
29 #ifndef __AVX512VPOPCNTDQVLINTRIN_H
30 #define __AVX512VPOPCNTDQVLINTRIN_H
31
32 /* Define the default attributes for the functions in this file. */
33 #define __DEFAULT_FN_ATTRS128 \
34 __attribute__((__always_inline__, __nodebug__, __target__("avx512vpopcntdq,avx512vl"), __min_vector_width__(128)))
35 #define __DEFAULT_FN_ATTRS256 \
36 __attribute__((__always_inline__, __nodebug__, __target__("avx512vpopcntdq,avx512vl"), __min_vector_width__(256)))
37
38 static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_popcnt_epi64(__m128i __A)39 _mm_popcnt_epi64(__m128i __A) {
40 return (__m128i)__builtin_ia32_vpopcntq_128((__v2di)__A);
41 }
42
43 static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_popcnt_epi64(__m128i __W,__mmask8 __U,__m128i __A)44 _mm_mask_popcnt_epi64(__m128i __W, __mmask8 __U, __m128i __A) {
45 return (__m128i)__builtin_ia32_selectq_128(
46 (__mmask8)__U, (__v2di)_mm_popcnt_epi64(__A), (__v2di)__W);
47 }
48
49 static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_popcnt_epi64(__mmask8 __U,__m128i __A)50 _mm_maskz_popcnt_epi64(__mmask8 __U, __m128i __A) {
51 return _mm_mask_popcnt_epi64((__m128i)_mm_setzero_si128(), __U, __A);
52 }
53
54 static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_popcnt_epi32(__m128i __A)55 _mm_popcnt_epi32(__m128i __A) {
56 return (__m128i)__builtin_ia32_vpopcntd_128((__v4si)__A);
57 }
58
59 static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_popcnt_epi32(__m128i __W,__mmask8 __U,__m128i __A)60 _mm_mask_popcnt_epi32(__m128i __W, __mmask8 __U, __m128i __A) {
61 return (__m128i)__builtin_ia32_selectd_128(
62 (__mmask8)__U, (__v4si)_mm_popcnt_epi32(__A), (__v4si)__W);
63 }
64
65 static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_popcnt_epi32(__mmask8 __U,__m128i __A)66 _mm_maskz_popcnt_epi32(__mmask8 __U, __m128i __A) {
67 return _mm_mask_popcnt_epi32((__m128i)_mm_setzero_si128(), __U, __A);
68 }
69
70 static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_popcnt_epi64(__m256i __A)71 _mm256_popcnt_epi64(__m256i __A) {
72 return (__m256i)__builtin_ia32_vpopcntq_256((__v4di)__A);
73 }
74
75 static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_popcnt_epi64(__m256i __W,__mmask8 __U,__m256i __A)76 _mm256_mask_popcnt_epi64(__m256i __W, __mmask8 __U, __m256i __A) {
77 return (__m256i)__builtin_ia32_selectq_256(
78 (__mmask8)__U, (__v4di)_mm256_popcnt_epi64(__A), (__v4di)__W);
79 }
80
81 static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_popcnt_epi64(__mmask8 __U,__m256i __A)82 _mm256_maskz_popcnt_epi64(__mmask8 __U, __m256i __A) {
83 return _mm256_mask_popcnt_epi64((__m256i)_mm256_setzero_si256(), __U, __A);
84 }
85
86 static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_popcnt_epi32(__m256i __A)87 _mm256_popcnt_epi32(__m256i __A) {
88 return (__m256i)__builtin_ia32_vpopcntd_256((__v8si)__A);
89 }
90
91 static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_popcnt_epi32(__m256i __W,__mmask8 __U,__m256i __A)92 _mm256_mask_popcnt_epi32(__m256i __W, __mmask8 __U, __m256i __A) {
93 return (__m256i)__builtin_ia32_selectd_256(
94 (__mmask8)__U, (__v8si)_mm256_popcnt_epi32(__A), (__v8si)__W);
95 }
96
97 static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_popcnt_epi32(__mmask8 __U,__m256i __A)98 _mm256_maskz_popcnt_epi32(__mmask8 __U, __m256i __A) {
99 return _mm256_mask_popcnt_epi32((__m256i)_mm256_setzero_si256(), __U, __A);
100 }
101
102 #undef __DEFAULT_FN_ATTRS128
103 #undef __DEFAULT_FN_ATTRS256
104
105 #endif
106