File Manager

003 File Manager

Current Path: /usr/lib/clang/11.0.1/include

📁 ..
📄 __clang_cuda_builtin_vars.h(4.56 KB)
📄 __clang_cuda_cmath.h(16.37 KB)
📄 __clang_cuda_complex_builtins.h(8.5 KB)
📄 __clang_cuda_device_functions.h(55.59 KB)
📄 __clang_cuda_intrinsics.h(21.59 KB)
📄 __clang_cuda_libdevice_declares.h(21.73 KB)
📄 __clang_cuda_math.h(15.91 KB)
📄 __clang_cuda_math_forward_declares.h(8.21 KB)
📄 __clang_cuda_runtime_wrapper.h(14.85 KB)
📄 __clang_hip_libdevice_declares.h(19.19 KB)
📄 __clang_hip_math.h(35.41 KB)
📄 __clang_hip_runtime_wrapper.h(1.79 KB)
📄 __stddef_max_align_t.h(857 B)
📄 __wmmintrin_aes.h(5.14 KB)
📄 __wmmintrin_pclmul.h(2.01 KB)
📄 adxintrin.h(2.32 KB)
📄 altivec.h(609.12 KB)
📄 ammintrin.h(7.42 KB)
📄 amxintrin.h(8.24 KB)
📄 arm64intr.h(993 B)
📄 arm_acle.h(21.87 KB)
📄 arm_bf16.h(548 B)
📄 arm_cde.h(32.67 KB)
📄 arm_cmse.h(6.21 KB)
📄 arm_fp16.h(16.97 KB)
📄 arm_mve.h(1.48 MB)
📄 arm_neon.h(2.31 MB)
📄 arm_sve.h(1.14 MB)
📄 armintr.h(843 B)
📄 avx2intrin.h(38.11 KB)
📄 avx512bf16intrin.h(10.45 KB)
📄 avx512bitalgintrin.h(2.41 KB)
📄 avx512bwintrin.h(75.17 KB)
📄 avx512cdintrin.h(4.12 KB)
📄 avx512dqintrin.h(58.3 KB)
📄 avx512erintrin.h(11.7 KB)
📄 avx512fintrin.h(377.18 KB)
📄 avx512ifmaintrin.h(2.49 KB)
📄 avx512ifmavlintrin.h(4.44 KB)
📄 avx512pfintrin.h(4.53 KB)
📄 avx512vbmi2intrin.h(13.1 KB)
📄 avx512vbmiintrin.h(3.72 KB)
📄 avx512vbmivlintrin.h(6.94 KB)
📄 avx512vlbf16intrin.h(17.88 KB)
📄 avx512vlbitalgintrin.h(4.23 KB)
📄 avx512vlbwintrin.h(110.39 KB)
📄 avx512vlcdintrin.h(7.66 KB)
📄 avx512vldqintrin.h(46.24 KB)
📄 avx512vlintrin.h(322.04 KB)
📄 avx512vlvbmi2intrin.h(25.59 KB)
📄 avx512vlvnniintrin.h(7.87 KB)
📄 avx512vlvp2intersectintrin.h(4.44 KB)
📄 avx512vnniintrin.h(4.21 KB)
📄 avx512vp2intersectintrin.h(2.9 KB)
📄 avx512vpopcntdqintrin.h(2 KB)
📄 avx512vpopcntdqvlintrin.h(3.31 KB)
📄 avxintrin.h(193.62 KB)
📄 bmi2intrin.h(2.25 KB)
📄 bmiintrin.h(14.02 KB)
📄 cet.h(1.49 KB)
📄 cetintrin.h(2.78 KB)
📄 cldemoteintrin.h(1.18 KB)
📄 clflushoptintrin.h(861 B)
📄 clwbintrin.h(1.2 KB)
📄 clzerointrin.h(1.13 KB)
📄 cpuid.h(10.42 KB)
📁 cuda_wrappers
📄 emmintrin.h(180.78 KB)
📄 enqcmdintrin.h(2.12 KB)
📄 f16cintrin.h(5.37 KB)
📄 fma4intrin.h(6.82 KB)
📄 fmaintrin.h(6.83 KB)
📁 fuzzer
📄 fxsrintrin.h(2.82 KB)
📄 gfniintrin.h(7.66 KB)
📄 htmintrin.h(6.14 KB)
📄 htmxlintrin.h(9.01 KB)
📄 ia32intrin.h(12.65 KB)
📄 immintrin.h(18.38 KB)
📄 invpcidintrin.h(764 B)
📄 lwpintrin.h(5 KB)
📄 lzcntintrin.h(3.18 KB)
📄 mm3dnow.h(4.5 KB)
📄 mm_malloc.h(1.7 KB)
📄 mmintrin.h(55.85 KB)
📄 module.modulemap(3.33 KB)
📄 movdirintrin.h(1.57 KB)
📄 msa.h(25.01 KB)
📄 mwaitxintrin.h(1.07 KB)
📄 nmmintrin.h(580 B)
📄 opencl-c-base.h(20.83 KB)
📄 opencl-c.h(835.47 KB)
📁 openmp_wrappers
📄 pconfigintrin.h(1.19 KB)
📄 pkuintrin.h(934 B)
📄 pmmintrin.h(10.09 KB)
📄 popcntintrin.h(1.58 KB)
📁 ppc_wrappers
📄 prfchwintrin.h(1.93 KB)
📁 profile
📄 ptwriteintrin.h(1.05 KB)
📄 rdseedintrin.h(1.16 KB)
📄 rtmintrin.h(1.24 KB)
📄 s390intrin.h(604 B)
📁 sanitizer
📄 serializeintrin.h(881 B)
📄 sgxintrin.h(1.77 KB)
📄 shaintrin.h(1.87 KB)
📄 smmintrin.h(98.76 KB)
📄 tbmintrin.h(3.15 KB)
📄 tmmintrin.h(29.37 KB)
📄 tsxldtrkintrin.h(1.97 KB)
📄 vadefs.h(1.39 KB)
📄 vaesintrin.h(2.39 KB)
📄 vecintrin.h(356.66 KB)
📄 vpclmulqdqintrin.h(1 KB)
📄 waitpkgintrin.h(1.33 KB)
📄 wasm_simd128.h(45.99 KB)
📄 wbnoinvdintrin.h(749 B)
📄 wmmintrin.h(530 B)
📄 x86intrin.h(1.67 KB)
📄 xmmintrin.h(106.24 KB)
📄 xopintrin.h(19.91 KB)
📁 xray
📄 xsavecintrin.h(1010 B)
📄 xsaveintrin.h(1.64 KB)
📄 xsaveoptintrin.h(1 KB)
📄 xsavesintrin.h(1.24 KB)
📄 xtestintrin.h(873 B)

Editing: avx512vldqintrin.h

/*===---- avx512vldqintrin.h - AVX512VL and AVX512DQ intrinsics ------------===
 *
 * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 * See https://llvm.org/LICENSE.txt for license information.
 * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */

#ifndef __IMMINTRIN_H
#error "Never use <avx512vldqintrin.h> directly; include <immintrin.h> instead."
#endif

#ifndef __AVX512VLDQINTRIN_H
#define __AVX512VLDQINTRIN_H

/* Define the default attributes for the functions in this file. */
#define __DEFAULT_FN_ATTRS128 __attribute__((__always_inline__, __nodebug__, __target__("avx512vl,avx512dq"), __min_vector_width__(128)))
#define __DEFAULT_FN_ATTRS256 __attribute__((__always_inline__, __nodebug__, __target__("avx512vl,avx512dq"), __min_vector_width__(256)))

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mullo_epi64 (__m256i __A, __m256i __B) {
  return (__m256i) ((__v4du) __A * (__v4du) __B);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_mullo_epi64(__m256i __W, __mmask8 __U, __m256i __A, __m256i __B) {
  return (__m256i)__builtin_ia32_selectq_256((__mmask8)__U,
                                             (__v4di)_mm256_mullo_epi64(__A, __B),
                                             (__v4di)__W);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_mullo_epi64(__mmask8 __U, __m256i __A, __m256i __B) {
  return (__m256i)__builtin_ia32_selectq_256((__mmask8)__U,
                                             (__v4di)_mm256_mullo_epi64(__A, __B),
                                             (__v4di)_mm256_setzero_si256());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mullo_epi64 (__m128i __A, __m128i __B) {
  return (__m128i) ((__v2du) __A * (__v2du) __B);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_mullo_epi64(__m128i __W, __mmask8 __U, __m128i __A, __m128i __B) {
  return (__m128i)__builtin_ia32_selectq_128((__mmask8)__U,
                                             (__v2di)_mm_mullo_epi64(__A, __B),
                                             (__v2di)__W);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_mullo_epi64(__mmask8 __U, __m128i __A, __m128i __B) {
  return (__m128i)__builtin_ia32_selectq_128((__mmask8)__U,
                                             (__v2di)_mm_mullo_epi64(__A, __B),
                                             (__v2di)_mm_setzero_si128());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_mask_andnot_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_andnot_pd(__A, __B),
                                              (__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_maskz_andnot_pd(__mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_andnot_pd(__A, __B),
                                              (__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_mask_andnot_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_andnot_pd(__A, __B),
                                              (__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_maskz_andnot_pd(__mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_andnot_pd(__A, __B),
                                              (__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_mask_andnot_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_andnot_ps(__A, __B),
                                             (__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_maskz_andnot_ps(__mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_andnot_ps(__A, __B),
                                             (__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_mask_andnot_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_andnot_ps(__A, __B),
                                             (__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_maskz_andnot_ps(__mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_andnot_ps(__A, __B),
                                             (__v4sf)_mm_setzero_ps());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_mask_and_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_and_pd(__A, __B),
                                              (__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_maskz_and_pd(__mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_and_pd(__A, __B),
                                              (__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_mask_and_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_and_pd(__A, __B),
                                              (__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_maskz_and_pd(__mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_and_pd(__A, __B),
                                              (__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_mask_and_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_and_ps(__A, __B),
                                             (__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_maskz_and_ps(__mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_and_ps(__A, __B),
                                             (__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_mask_and_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_and_ps(__A, __B),
                                             (__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_maskz_and_ps(__mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_and_ps(__A, __B),
                                             (__v4sf)_mm_setzero_ps());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_mask_xor_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_xor_pd(__A, __B),
                                              (__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_maskz_xor_pd(__mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_xor_pd(__A, __B),
                                              (__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_mask_xor_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_xor_pd(__A, __B),
                                              (__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_maskz_xor_pd (__mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_xor_pd(__A, __B),
                                              (__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_mask_xor_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_xor_ps(__A, __B),
                                             (__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_maskz_xor_ps(__mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_xor_ps(__A, __B),
                                             (__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_mask_xor_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_xor_ps(__A, __B),
                                             (__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_maskz_xor_ps(__mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_xor_ps(__A, __B),
                                             (__v4sf)_mm_setzero_ps());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_mask_or_pd(__m256d __W, __mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_or_pd(__A, __B),
                                              (__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_maskz_or_pd(__mmask8 __U, __m256d __A, __m256d __B) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_or_pd(__A, __B),
                                              (__v4df)_mm256_setzero_pd());
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_mask_or_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_or_pd(__A, __B),
                                              (__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_maskz_or_pd(__mmask8 __U, __m128d __A, __m128d __B) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_or_pd(__A, __B),
                                              (__v2df)_mm_setzero_pd());
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_mask_or_ps(__m256 __W, __mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_or_ps(__A, __B),
                                             (__v8sf)__W);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_maskz_or_ps(__mmask8 __U, __m256 __A, __m256 __B) {
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
                                             (__v8sf)_mm256_or_ps(__A, __B),
                                             (__v8sf)_mm256_setzero_ps());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_mask_or_ps(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_or_ps(__A, __B),
                                             (__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_maskz_or_ps(__mmask8 __U, __m128 __A, __m128 __B) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm_or_ps(__A, __B),
                                             (__v4sf)_mm_setzero_ps());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvtpd_epi64 (__m128d __A) {
  return (__m128i) __builtin_ia32_cvtpd2qq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvtpd_epi64 (__m128i __W, __mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvtpd2qq128_mask ((__v2df) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvtpd_epi64 (__mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvtpd2qq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtpd_epi64 (__m256d __A) {
  return (__m256i) __builtin_ia32_cvtpd2qq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtpd_epi64 (__m256i __W, __mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvtpd2qq256_mask ((__v4df) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtpd_epi64 (__mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvtpd2qq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvtpd_epu64 (__m128d __A) {
  return (__m128i) __builtin_ia32_cvtpd2uqq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvtpd_epu64 (__m128i __W, __mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvtpd2uqq128_mask ((__v2df) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvtpd_epu64 (__mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvtpd2uqq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtpd_epu64 (__m256d __A) {
  return (__m256i) __builtin_ia32_cvtpd2uqq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtpd_epu64 (__m256i __W, __mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvtpd2uqq256_mask ((__v4df) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtpd_epu64 (__mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvtpd2uqq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvtps_epi64 (__m128 __A) {
  return (__m128i) __builtin_ia32_cvtps2qq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvtps_epi64 (__m128i __W, __mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvtps2qq128_mask ((__v4sf) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvtps_epi64 (__mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvtps2qq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtps_epi64 (__m128 __A) {
  return (__m256i) __builtin_ia32_cvtps2qq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtps_epi64 (__m256i __W, __mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvtps2qq256_mask ((__v4sf) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtps_epi64 (__mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvtps2qq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvtps_epu64 (__m128 __A) {
  return (__m128i) __builtin_ia32_cvtps2uqq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvtps_epu64 (__m128i __W, __mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvtps2uqq128_mask ((__v4sf) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvtps_epu64 (__mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvtps2uqq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvtps_epu64 (__m128 __A) {
  return (__m256i) __builtin_ia32_cvtps2uqq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvtps_epu64 (__m256i __W, __mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvtps2uqq256_mask ((__v4sf) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtps_epu64 (__mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvtps2uqq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_cvtepi64_pd (__m128i __A) {
  return (__m128d)__builtin_convertvector((__v2di)__A, __v2df);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_mask_cvtepi64_pd (__m128d __W, __mmask8 __U, __m128i __A) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_cvtepi64_pd(__A),
                                              (__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_maskz_cvtepi64_pd (__mmask8 __U, __m128i __A) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_cvtepi64_pd(__A),
                                              (__v2df)_mm_setzero_pd());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_cvtepi64_pd (__m256i __A) {
  return (__m256d)__builtin_convertvector((__v4di)__A, __v4df);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_mask_cvtepi64_pd (__m256d __W, __mmask8 __U, __m256i __A) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_cvtepi64_pd(__A),
                                              (__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtepi64_pd (__mmask8 __U, __m256i __A) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_cvtepi64_pd(__A),
                                              (__v4df)_mm256_setzero_pd());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_cvtepi64_ps (__m128i __A) {
  return (__m128) __builtin_ia32_cvtqq2ps128_mask ((__v2di) __A,
                (__v4sf) _mm_setzero_ps(),
                (__mmask8) -1);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_mask_cvtepi64_ps (__m128 __W, __mmask8 __U, __m128i __A) {
  return (__m128) __builtin_ia32_cvtqq2ps128_mask ((__v2di) __A,
                (__v4sf) __W,
                (__mmask8) __U);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_maskz_cvtepi64_ps (__mmask8 __U, __m128i __A) {
  return (__m128) __builtin_ia32_cvtqq2ps128_mask ((__v2di) __A,
                (__v4sf) _mm_setzero_ps(),
                (__mmask8) __U);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS256
_mm256_cvtepi64_ps (__m256i __A) {
  return (__m128)__builtin_convertvector((__v4di)__A, __v4sf);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS256
_mm256_mask_cvtepi64_ps (__m128 __W, __mmask8 __U, __m256i __A) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm256_cvtepi64_ps(__A),
                                             (__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtepi64_ps (__mmask8 __U, __m256i __A) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm256_cvtepi64_ps(__A),
                                             (__v4sf)_mm_setzero_ps());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvttpd_epi64 (__m128d __A) {
  return (__m128i) __builtin_ia32_cvttpd2qq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvttpd_epi64 (__m128i __W, __mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvttpd2qq128_mask ((__v2df) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvttpd_epi64 (__mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvttpd2qq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvttpd_epi64 (__m256d __A) {
  return (__m256i) __builtin_ia32_cvttpd2qq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvttpd_epi64 (__m256i __W, __mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvttpd2qq256_mask ((__v4df) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvttpd_epi64 (__mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvttpd2qq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvttpd_epu64 (__m128d __A) {
  return (__m128i) __builtin_ia32_cvttpd2uqq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvttpd_epu64 (__m128i __W, __mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvttpd2uqq128_mask ((__v2df) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvttpd_epu64 (__mmask8 __U, __m128d __A) {
  return (__m128i) __builtin_ia32_cvttpd2uqq128_mask ((__v2df) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvttpd_epu64 (__m256d __A) {
  return (__m256i) __builtin_ia32_cvttpd2uqq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvttpd_epu64 (__m256i __W, __mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvttpd2uqq256_mask ((__v4df) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvttpd_epu64 (__mmask8 __U, __m256d __A) {
  return (__m256i) __builtin_ia32_cvttpd2uqq256_mask ((__v4df) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvttps_epi64 (__m128 __A) {
  return (__m128i) __builtin_ia32_cvttps2qq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvttps_epi64 (__m128i __W, __mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvttps2qq128_mask ((__v4sf) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvttps_epi64 (__mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvttps2qq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvttps_epi64 (__m128 __A) {
  return (__m256i) __builtin_ia32_cvttps2qq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvttps_epi64 (__m256i __W, __mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvttps2qq256_mask ((__v4sf) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvttps_epi64 (__mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvttps2qq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_cvttps_epu64 (__m128 __A) {
  return (__m128i) __builtin_ia32_cvttps2uqq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) -1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_cvttps_epu64 (__m128i __W, __mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvttps2uqq128_mask ((__v4sf) __A,
                (__v2di) __W,
                (__mmask8) __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_cvttps_epu64 (__mmask8 __U, __m128 __A) {
  return (__m128i) __builtin_ia32_cvttps2uqq128_mask ((__v4sf) __A,
                (__v2di) _mm_setzero_si128(),
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_cvttps_epu64 (__m128 __A) {
  return (__m256i) __builtin_ia32_cvttps2uqq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) -1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_cvttps_epu64 (__m256i __W, __mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvttps2uqq256_mask ((__v4sf) __A,
                (__v4di) __W,
                (__mmask8) __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_cvttps_epu64 (__mmask8 __U, __m128 __A) {
  return (__m256i) __builtin_ia32_cvttps2uqq256_mask ((__v4sf) __A,
                (__v4di) _mm256_setzero_si256(),
                (__mmask8) __U);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_cvtepu64_pd (__m128i __A) {
  return (__m128d)__builtin_convertvector((__v2du)__A, __v2df);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_mask_cvtepu64_pd (__m128d __W, __mmask8 __U, __m128i __A) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_cvtepu64_pd(__A),
                                              (__v2df)__W);
}

static __inline__ __m128d __DEFAULT_FN_ATTRS128
_mm_maskz_cvtepu64_pd (__mmask8 __U, __m128i __A) {
  return (__m128d)__builtin_ia32_selectpd_128((__mmask8)__U,
                                              (__v2df)_mm_cvtepu64_pd(__A),
                                              (__v2df)_mm_setzero_pd());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_cvtepu64_pd (__m256i __A) {
  return (__m256d)__builtin_convertvector((__v4du)__A, __v4df);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_mask_cvtepu64_pd (__m256d __W, __mmask8 __U, __m256i __A) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_cvtepu64_pd(__A),
                                              (__v4df)__W);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtepu64_pd (__mmask8 __U, __m256i __A) {
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__U,
                                              (__v4df)_mm256_cvtepu64_pd(__A),
                                              (__v4df)_mm256_setzero_pd());
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_cvtepu64_ps (__m128i __A) {
  return (__m128) __builtin_ia32_cvtuqq2ps128_mask ((__v2di) __A,
                (__v4sf) _mm_setzero_ps(),
                (__mmask8) -1);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_mask_cvtepu64_ps (__m128 __W, __mmask8 __U, __m128i __A) {
  return (__m128) __builtin_ia32_cvtuqq2ps128_mask ((__v2di) __A,
                (__v4sf) __W,
                (__mmask8) __U);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS128
_mm_maskz_cvtepu64_ps (__mmask8 __U, __m128i __A) {
  return (__m128) __builtin_ia32_cvtuqq2ps128_mask ((__v2di) __A,
                (__v4sf) _mm_setzero_ps(),
                (__mmask8) __U);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS256
_mm256_cvtepu64_ps (__m256i __A) {
  return (__m128)__builtin_convertvector((__v4du)__A, __v4sf);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS256
_mm256_mask_cvtepu64_ps (__m128 __W, __mmask8 __U, __m256i __A) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm256_cvtepu64_ps(__A),
                                             (__v4sf)__W);
}

static __inline__ __m128 __DEFAULT_FN_ATTRS256
_mm256_maskz_cvtepu64_ps (__mmask8 __U, __m256i __A) {
  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
                                             (__v4sf)_mm256_cvtepu64_ps(__A),
                                             (__v4sf)_mm_setzero_ps());
}

#define _mm_range_pd(A, B, C) \
  (__m128d)__builtin_ia32_rangepd128_mask((__v2df)(__m128d)(A), \
                                          (__v2df)(__m128d)(B), (int)(C), \
                                          (__v2df)_mm_setzero_pd(), \
                                          (__mmask8)-1)

#define _mm_mask_range_pd(W, U, A, B, C) \
  (__m128d)__builtin_ia32_rangepd128_mask((__v2df)(__m128d)(A), \
                                          (__v2df)(__m128d)(B), (int)(C), \
                                          (__v2df)(__m128d)(W), \
                                          (__mmask8)(U))

#define _mm_maskz_range_pd(U, A, B, C) \
  (__m128d)__builtin_ia32_rangepd128_mask((__v2df)(__m128d)(A), \
                                          (__v2df)(__m128d)(B), (int)(C), \
                                          (__v2df)_mm_setzero_pd(), \
                                          (__mmask8)(U))

#define _mm256_range_pd(A, B, C) \
  (__m256d)__builtin_ia32_rangepd256_mask((__v4df)(__m256d)(A), \
                                          (__v4df)(__m256d)(B), (int)(C), \
                                          (__v4df)_mm256_setzero_pd(), \
                                          (__mmask8)-1)

#define _mm256_mask_range_pd(W, U, A, B, C) \
  (__m256d)__builtin_ia32_rangepd256_mask((__v4df)(__m256d)(A), \
                                          (__v4df)(__m256d)(B), (int)(C), \
                                          (__v4df)(__m256d)(W), \
                                          (__mmask8)(U))

#define _mm256_maskz_range_pd(U, A, B, C) \
  (__m256d)__builtin_ia32_rangepd256_mask((__v4df)(__m256d)(A), \
                                          (__v4df)(__m256d)(B), (int)(C), \
                                          (__v4df)_mm256_setzero_pd(), \
                                          (__mmask8)(U))

#define _mm_range_ps(A, B, C) \
  (__m128)__builtin_ia32_rangeps128_mask((__v4sf)(__m128)(A), \
                                         (__v4sf)(__m128)(B), (int)(C), \
                                         (__v4sf)_mm_setzero_ps(), \
                                         (__mmask8)-1)

#define _mm_mask_range_ps(W, U, A, B, C) \
  (__m128)__builtin_ia32_rangeps128_mask((__v4sf)(__m128)(A), \
                                         (__v4sf)(__m128)(B), (int)(C), \
                                         (__v4sf)(__m128)(W), (__mmask8)(U))

#define _mm_maskz_range_ps(U, A, B, C) \
  (__m128)__builtin_ia32_rangeps128_mask((__v4sf)(__m128)(A), \
                                         (__v4sf)(__m128)(B), (int)(C), \
                                         (__v4sf)_mm_setzero_ps(), \
                                         (__mmask8)(U))

#define _mm256_range_ps(A, B, C) \
  (__m256)__builtin_ia32_rangeps256_mask((__v8sf)(__m256)(A), \
                                         (__v8sf)(__m256)(B), (int)(C), \
                                         (__v8sf)_mm256_setzero_ps(), \
                                         (__mmask8)-1)

#define _mm256_mask_range_ps(W, U, A, B, C) \
  (__m256)__builtin_ia32_rangeps256_mask((__v8sf)(__m256)(A), \
                                         (__v8sf)(__m256)(B), (int)(C), \
                                         (__v8sf)(__m256)(W), (__mmask8)(U))

#define _mm256_maskz_range_ps(U, A, B, C) \
  (__m256)__builtin_ia32_rangeps256_mask((__v8sf)(__m256)(A), \
                                         (__v8sf)(__m256)(B), (int)(C), \
                                         (__v8sf)_mm256_setzero_ps(), \
                                         (__mmask8)(U))

#define _mm_reduce_pd(A, B) \
  (__m128d)__builtin_ia32_reducepd128_mask((__v2df)(__m128d)(A), (int)(B), \
                                           (__v2df)_mm_setzero_pd(), \
                                           (__mmask8)-1)

#define _mm_mask_reduce_pd(W, U, A, B) \
  (__m128d)__builtin_ia32_reducepd128_mask((__v2df)(__m128d)(A), (int)(B), \
                                           (__v2df)(__m128d)(W), \
                                           (__mmask8)(U))

#define _mm_maskz_reduce_pd(U, A, B) \
  (__m128d)__builtin_ia32_reducepd128_mask((__v2df)(__m128d)(A), (int)(B), \
                                           (__v2df)_mm_setzero_pd(), \
                                           (__mmask8)(U))

#define _mm256_reduce_pd(A, B) \
  (__m256d)__builtin_ia32_reducepd256_mask((__v4df)(__m256d)(A), (int)(B), \
                                           (__v4df)_mm256_setzero_pd(), \
                                           (__mmask8)-1)

#define _mm256_mask_reduce_pd(W, U, A, B) \
  (__m256d)__builtin_ia32_reducepd256_mask((__v4df)(__m256d)(A), (int)(B), \
                                           (__v4df)(__m256d)(W), \
                                           (__mmask8)(U))

#define _mm256_maskz_reduce_pd(U, A, B) \
  (__m256d)__builtin_ia32_reducepd256_mask((__v4df)(__m256d)(A), (int)(B), \
                                           (__v4df)_mm256_setzero_pd(), \
                                           (__mmask8)(U))

#define _mm_reduce_ps(A, B) \
  (__m128)__builtin_ia32_reduceps128_mask((__v4sf)(__m128)(A), (int)(B), \
                                          (__v4sf)_mm_setzero_ps(), \
                                          (__mmask8)-1)

#define _mm_mask_reduce_ps(W, U, A, B) \
  (__m128)__builtin_ia32_reduceps128_mask((__v4sf)(__m128)(A), (int)(B), \
                                          (__v4sf)(__m128)(W), \
                                          (__mmask8)(U))

#define _mm_maskz_reduce_ps(U, A, B) \
  (__m128)__builtin_ia32_reduceps128_mask((__v4sf)(__m128)(A), (int)(B), \
                                          (__v4sf)_mm_setzero_ps(), \
                                          (__mmask8)(U))

#define _mm256_reduce_ps(A, B) \
  (__m256)__builtin_ia32_reduceps256_mask((__v8sf)(__m256)(A), (int)(B), \
                                          (__v8sf)_mm256_setzero_ps(), \
                                          (__mmask8)-1)

#define _mm256_mask_reduce_ps(W, U, A, B) \
  (__m256)__builtin_ia32_reduceps256_mask((__v8sf)(__m256)(A), (int)(B), \
                                          (__v8sf)(__m256)(W), \
                                          (__mmask8)(U))

#define _mm256_maskz_reduce_ps(U, A, B) \
  (__m256)__builtin_ia32_reduceps256_mask((__v8sf)(__m256)(A), (int)(B), \
                                          (__v8sf)_mm256_setzero_ps(), \
                                          (__mmask8)(U))

static __inline__ __mmask8 __DEFAULT_FN_ATTRS128
_mm_movepi32_mask (__m128i __A)
{
  return (__mmask8) __builtin_ia32_cvtd2mask128 ((__v4si) __A);
}

static __inline__ __mmask8 __DEFAULT_FN_ATTRS256
_mm256_movepi32_mask (__m256i __A)
{
  return (__mmask8) __builtin_ia32_cvtd2mask256 ((__v8si) __A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_movm_epi32 (__mmask8 __A)
{
  return (__m128i) __builtin_ia32_cvtmask2d128 (__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_movm_epi32 (__mmask8 __A)
{
  return (__m256i) __builtin_ia32_cvtmask2d256 (__A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_movm_epi64 (__mmask8 __A)
{
  return (__m128i) __builtin_ia32_cvtmask2q128 (__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_movm_epi64 (__mmask8 __A)
{
  return (__m256i) __builtin_ia32_cvtmask2q256 (__A);
}

static __inline__ __mmask8 __DEFAULT_FN_ATTRS128
_mm_movepi64_mask (__m128i __A)
{
  return (__mmask8) __builtin_ia32_cvtq2mask128 ((__v2di) __A);
}

static __inline__ __mmask8 __DEFAULT_FN_ATTRS256
_mm256_movepi64_mask (__m256i __A)
{
  return (__mmask8) __builtin_ia32_cvtq2mask256 ((__v4di) __A);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_broadcast_f32x2 (__m128 __A)
{
  return (__m256)__builtin_shufflevector((__v4sf)__A, (__v4sf)__A,
                                         0, 1, 0, 1, 0, 1, 0, 1);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_mask_broadcast_f32x2 (__m256 __O, __mmask8 __M, __m128 __A)
{
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__M,
                                             (__v8sf)_mm256_broadcast_f32x2(__A),
                                             (__v8sf)__O);
}

static __inline__ __m256 __DEFAULT_FN_ATTRS256
_mm256_maskz_broadcast_f32x2 (__mmask8 __M, __m128 __A)
{
  return (__m256)__builtin_ia32_selectps_256((__mmask8)__M,
                                             (__v8sf)_mm256_broadcast_f32x2(__A),
                                             (__v8sf)_mm256_setzero_ps());
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_broadcast_f64x2(__m128d __A)
{
  return (__m256d)__builtin_shufflevector((__v2df)__A, (__v2df)__A,
                                          0, 1, 0, 1);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_mask_broadcast_f64x2(__m256d __O, __mmask8 __M, __m128d __A)
{
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__M,
                                            (__v4df)_mm256_broadcast_f64x2(__A),
                                            (__v4df)__O);
}

static __inline__ __m256d __DEFAULT_FN_ATTRS256
_mm256_maskz_broadcast_f64x2 (__mmask8 __M, __m128d __A)
{
  return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__M,
                                            (__v4df)_mm256_broadcast_f64x2(__A),
                                            (__v4df)_mm256_setzero_pd());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_broadcast_i32x2 (__m128i __A)
{
  return (__m128i)__builtin_shufflevector((__v4si)__A, (__v4si)__A,
                                          0, 1, 0, 1);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_broadcast_i32x2 (__m128i __O, __mmask8 __M, __m128i __A)
{
  return (__m128i)__builtin_ia32_selectd_128((__mmask8)__M,
                                             (__v4si)_mm_broadcast_i32x2(__A),
                                             (__v4si)__O);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_broadcast_i32x2 (__mmask8 __M, __m128i __A)
{
  return (__m128i)__builtin_ia32_selectd_128((__mmask8)__M,
                                             (__v4si)_mm_broadcast_i32x2(__A),
                                             (__v4si)_mm_setzero_si128());
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_broadcast_i32x2 (__m128i __A)
{
  return (__m256i)__builtin_shufflevector((__v4si)__A, (__v4si)__A,
                                          0, 1, 0, 1, 0, 1, 0, 1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_broadcast_i32x2 (__m256i __O, __mmask8 __M, __m128i __A)
{
  return (__m256i)__builtin_ia32_selectd_256((__mmask8)__M,
                                             (__v8si)_mm256_broadcast_i32x2(__A),
                                             (__v8si)__O);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_broadcast_i32x2 (__mmask8 __M, __m128i __A)
{
  return (__m256i)__builtin_ia32_selectd_256((__mmask8)__M,
                                             (__v8si)_mm256_broadcast_i32x2(__A),
                                             (__v8si)_mm256_setzero_si256());
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_broadcast_i64x2(__m128i __A)
{
  return (__m256i)__builtin_shufflevector((__v2di)__A, (__v2di)__A,
                                          0, 1, 0, 1);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_broadcast_i64x2(__m256i __O, __mmask8 __M, __m128i __A)
{
  return (__m256i)__builtin_ia32_selectq_256((__mmask8)__M,
                                            (__v4di)_mm256_broadcast_i64x2(__A),
                                            (__v4di)__O);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_broadcast_i64x2 (__mmask8 __M, __m128i __A)
{
  return (__m256i)__builtin_ia32_selectq_256((__mmask8)__M,
                                            (__v4di)_mm256_broadcast_i64x2(__A),
                                            (__v4di)_mm256_setzero_si256());
}

#define _mm256_extractf64x2_pd(A, imm) \
  (__m128d)__builtin_ia32_extractf64x2_256_mask((__v4df)(__m256d)(A), \
                                                (int)(imm), \
                                                (__v2df)_mm_undefined_pd(), \
                                                (__mmask8)-1)

#define _mm256_mask_extractf64x2_pd(W, U, A, imm) \
  (__m128d)__builtin_ia32_extractf64x2_256_mask((__v4df)(__m256d)(A), \
                                                (int)(imm), \
                                                (__v2df)(__m128d)(W), \
                                                (__mmask8)(U))

#define _mm256_maskz_extractf64x2_pd(U, A, imm) \
  (__m128d)__builtin_ia32_extractf64x2_256_mask((__v4df)(__m256d)(A), \
                                                (int)(imm), \
                                                (__v2df)_mm_setzero_pd(), \
                                                (__mmask8)(U))

#define _mm256_extracti64x2_epi64(A, imm) \
  (__m128i)__builtin_ia32_extracti64x2_256_mask((__v4di)(__m256i)(A), \
                                                (int)(imm), \
                                                (__v2di)_mm_undefined_si128(), \
                                                (__mmask8)-1)

#define _mm256_mask_extracti64x2_epi64(W, U, A, imm) \
  (__m128i)__builtin_ia32_extracti64x2_256_mask((__v4di)(__m256i)(A), \
                                                (int)(imm), \
                                                (__v2di)(__m128i)(W), \
                                                (__mmask8)(U))

#define _mm256_maskz_extracti64x2_epi64(U, A, imm) \
  (__m128i)__builtin_ia32_extracti64x2_256_mask((__v4di)(__m256i)(A), \
                                                (int)(imm), \
                                                (__v2di)_mm_setzero_si128(), \
                                                (__mmask8)(U))

#define _mm256_insertf64x2(A, B, imm) \
  (__m256d)__builtin_ia32_insertf64x2_256((__v4df)(__m256d)(A), \
                                          (__v2df)(__m128d)(B), (int)(imm))

#define _mm256_mask_insertf64x2(W, U, A, B, imm) \
  (__m256d)__builtin_ia32_selectpd_256((__mmask8)(U), \
                                  (__v4df)_mm256_insertf64x2((A), (B), (imm)), \
                                  (__v4df)(__m256d)(W))

#define _mm256_maskz_insertf64x2(U, A, B, imm) \
  (__m256d)__builtin_ia32_selectpd_256((__mmask8)(U), \
                                  (__v4df)_mm256_insertf64x2((A), (B), (imm)), \
                                  (__v4df)_mm256_setzero_pd())

#define _mm256_inserti64x2(A, B, imm) \
  (__m256i)__builtin_ia32_inserti64x2_256((__v4di)(__m256i)(A), \
                                          (__v2di)(__m128i)(B), (int)(imm))

#define _mm256_mask_inserti64x2(W, U, A, B, imm) \
  (__m256i)__builtin_ia32_selectq_256((__mmask8)(U), \
                                  (__v4di)_mm256_inserti64x2((A), (B), (imm)), \
                                  (__v4di)(__m256i)(W))

#define _mm256_maskz_inserti64x2(U, A, B, imm) \
  (__m256i)__builtin_ia32_selectq_256((__mmask8)(U), \
                                  (__v4di)_mm256_inserti64x2((A), (B), (imm)), \
                                  (__v4di)_mm256_setzero_si256())

#define _mm_mask_fpclass_pd_mask(U, A, imm) \
  (__mmask8)__builtin_ia32_fpclasspd128_mask((__v2df)(__m128d)(A), (int)(imm), \
                                             (__mmask8)(U))

#define _mm_fpclass_pd_mask(A, imm) \
  (__mmask8)__builtin_ia32_fpclasspd128_mask((__v2df)(__m128d)(A), (int)(imm), \
                                             (__mmask8)-1)

#define _mm256_mask_fpclass_pd_mask(U, A, imm) \
  (__mmask8)__builtin_ia32_fpclasspd256_mask((__v4df)(__m256d)(A), (int)(imm), \
                                             (__mmask8)(U))

#define _mm256_fpclass_pd_mask(A, imm) \
  (__mmask8)__builtin_ia32_fpclasspd256_mask((__v4df)(__m256d)(A), (int)(imm), \
                                             (__mmask8)-1)

#define _mm_mask_fpclass_ps_mask(U, A, imm) \
  (__mmask8)__builtin_ia32_fpclassps128_mask((__v4sf)(__m128)(A), (int)(imm), \
                                             (__mmask8)(U))

#define _mm_fpclass_ps_mask(A, imm) \
  (__mmask8)__builtin_ia32_fpclassps128_mask((__v4sf)(__m128)(A), (int)(imm), \
                                             (__mmask8)-1)

#define _mm256_mask_fpclass_ps_mask(U, A, imm) \
  (__mmask8)__builtin_ia32_fpclassps256_mask((__v8sf)(__m256)(A), (int)(imm), \
                                             (__mmask8)(U))

#define _mm256_fpclass_ps_mask(A, imm) \
  (__mmask8)__builtin_ia32_fpclassps256_mask((__v8sf)(__m256)(A), (int)(imm), \
                                             (__mmask8)-1)

#undef __DEFAULT_FN_ATTRS128
#undef __DEFAULT_FN_ATTRS256

#endif

003 File Manager

Editing: avx512vldqintrin.h

Upload File

Create Folder