File Manager

X7ROOT File Manager

Current Path: /lib64/llvm17/lib/clang/17/include

lib64 / llvm17 / lib / clang / 17 / include /

ðŸ“ ..
ðŸ“„ __clang_cuda_builtin_vars.h(4.78 KB)
ðŸ“„ __clang_cuda_cmath.h(18.06 KB)
ðŸ“„ __clang_cuda_complex_builtins.h(9.36 KB)
ðŸ“„ __clang_cuda_device_functions.h(56.68 KB)
ðŸ“„ __clang_cuda_intrinsics.h(29.93 KB)
ðŸ“„ __clang_cuda_libdevice_declares.h(21.87 KB)
ðŸ“„ __clang_cuda_math.h(15.99 KB)
ðŸ“„ __clang_cuda_math_forward_declares.h(8.27 KB)
ðŸ“„ __clang_cuda_runtime_wrapper.h(17.61 KB)
ðŸ“„ __clang_cuda_texture_intrinsics.h(31.86 KB)
ðŸ“„ __clang_hip_cmath.h(26.34 KB)
ðŸ“„ __clang_hip_libdevice_declares.h(19.87 KB)
ðŸ“„ __clang_hip_math.h(31.96 KB)
ðŸ“„ __clang_hip_runtime_wrapper.h(4.65 KB)
ðŸ“„ __clang_hip_stdlib.h(1.19 KB)
ðŸ“„ __stddef_max_align_t.h(857 B)
ðŸ“„ __wmmintrin_aes.h(5.15 KB)
ðŸ“„ __wmmintrin_pclmul.h(1.99 KB)
ðŸ“„ adxintrin.h(7.37 KB)
ðŸ“„ altivec.h(697.32 KB)
ðŸ“„ ammintrin.h(7.54 KB)
ðŸ“„ amxcomplexintrin.h(6.81 KB)
ðŸ“„ amxfp16intrin.h(1.82 KB)
ðŸ“„ amxintrin.h(21.12 KB)
ðŸ“„ arm64intr.h(993 B)
ðŸ“„ arm_acle.h(25.66 KB)
ðŸ“„ arm_bf16.h(548 B)
ðŸ“„ arm_cde.h(32.67 KB)
ðŸ“„ arm_cmse.h(6.21 KB)
ðŸ“„ arm_fp16.h(16.92 KB)
ðŸ“„ arm_mve.h(1.48 MB)
ðŸ“„ arm_neon.h(2.45 MB)
ðŸ“„ arm_neon_sve_bridge.h(9.48 KB)
ðŸ“„ arm_sme_draft_spec_subject_to_change.h(60.2 KB)
ðŸ“„ arm_sve.h(1.51 MB)
ðŸ“„ armintr.h(843 B)
ðŸ“„ avx2intrin.h(186.96 KB)
ðŸ“„ avx512bf16intrin.h(10.51 KB)
ðŸ“„ avx512bitalgintrin.h(2.41 KB)
ðŸ“„ avx512bwintrin.h(75.33 KB)
ðŸ“„ avx512cdintrin.h(4.12 KB)
ðŸ“„ avx512dqintrin.h(58.75 KB)
ðŸ“„ avx512erintrin.h(11.83 KB)
ðŸ“„ avx512fintrin.h(382.64 KB)
ðŸ“„ avx512fp16intrin.h(156.63 KB)
ðŸ“„ avx512ifmaintrin.h(2.49 KB)
ðŸ“„ avx512ifmavlintrin.h(4.31 KB)
ðŸ“„ avx512pfintrin.h(4.53 KB)
ðŸ“„ avx512vbmi2intrin.h(13.17 KB)
ðŸ“„ avx512vbmiintrin.h(3.72 KB)
ðŸ“„ avx512vbmivlintrin.h(6.94 KB)
ðŸ“„ avx512vlbf16intrin.h(19.21 KB)
ðŸ“„ avx512vlbitalgintrin.h(4.23 KB)
ðŸ“„ avx512vlbwintrin.h(121.26 KB)
ðŸ“„ avx512vlcdintrin.h(7.66 KB)
ðŸ“„ avx512vldqintrin.h(46.41 KB)
ðŸ“„ avx512vlfp16intrin.h(85.51 KB)
ðŸ“„ avx512vlintrin.h(322.29 KB)
ðŸ“„ avx512vlvbmi2intrin.h(25.72 KB)
ðŸ“„ avx512vlvnniintrin.h(13.13 KB)
ðŸ“„ avx512vlvp2intersectintrin.h(4.44 KB)
ðŸ“„ avx512vnniintrin.h(4.21 KB)
ðŸ“„ avx512vp2intersectintrin.h(2.9 KB)
ðŸ“„ avx512vpopcntdqintrin.h(2 KB)
ðŸ“„ avx512vpopcntdqvlintrin.h(3.31 KB)
ðŸ“„ avxifmaintrin.h(5.75 KB)
ðŸ“„ avxintrin.h(195.41 KB)
ðŸ“„ avxneconvertintrin.h(14.09 KB)
ðŸ“„ avxvnniint16intrin.h(17.41 KB)
ðŸ“„ avxvnniint8intrin.h(18.67 KB)
ðŸ“„ avxvnniintrin.h(10.44 KB)
ðŸ“„ bmi2intrin.h(7.09 KB)
ðŸ“„ bmiintrin.h(14.12 KB)
ðŸ“„ builtins.h(741 B)
ðŸ“„ cet.h(1.49 KB)
ðŸ“„ cetintrin.h(3.27 KB)
ðŸ“„ cldemoteintrin.h(1.18 KB)
ðŸ“„ clflushoptintrin.h(1.17 KB)
ðŸ“„ clwbintrin.h(1.2 KB)
ðŸ“„ clzerointrin.h(1.19 KB)
ðŸ“„ cmpccxaddintrin.h(2.33 KB)
ðŸ“„ cpuid.h(11.01 KB)
ðŸ“„ crc32intrin.h(3.27 KB)
ðŸ“ cuda_wrappers
ðŸ“„ emmintrin.h(192.64 KB)
ðŸ“„ enqcmdintrin.h(2.12 KB)
ðŸ“„ f16cintrin.h(5.39 KB)
ðŸ“„ float.h(5.63 KB)
ðŸ“„ fma4intrin.h(6.82 KB)
ðŸ“„ fmaintrin.h(28.4 KB)
ðŸ“„ fxsrintrin.h(2.82 KB)
ðŸ“„ gfniintrin.h(7.57 KB)
ðŸ“„ hexagon_circ_brev_intrinsics.h(15.59 KB)
ðŸ“„ hexagon_protos.h(374.42 KB)
ðŸ“„ hexagon_types.h(130.33 KB)
ðŸ“„ hresetintrin.h(1.36 KB)
ðŸ“„ htmintrin.h(6.14 KB)
ðŸ“„ htmxlintrin.h(9.01 KB)
ðŸ“„ hvx_hexagon_protos.h(254.26 KB)
ðŸ“„ ia32intrin.h(12.72 KB)
ðŸ“„ immintrin.h(23.57 KB)
ðŸ“„ intrin.h(28.22 KB)
ðŸ“„ inttypes.h(2.26 KB)
ðŸ“„ invpcidintrin.h(764 B)
ðŸ“„ iso646.h(656 B)
ðŸ“„ keylockerintrin.h(17.98 KB)
ðŸ“„ larchintrin.h(7.8 KB)
ðŸ“„ limits.h(3.61 KB)
ðŸ“ llvm_libc_wrappers
ðŸ“„ lwpintrin.h(5 KB)
ðŸ“„ lzcntintrin.h(3.18 KB)
ðŸ“„ mm3dnow.h(4.5 KB)
ðŸ“„ mm_malloc.h(1.88 KB)
ðŸ“„ mmintrin.h(55.98 KB)
ðŸ“„ module.modulemap(3.33 KB)
ðŸ“„ movdirintrin.h(1.57 KB)
ðŸ“„ msa.h(25.01 KB)
ðŸ“„ mwaitxintrin.h(2.19 KB)
ðŸ“„ nmmintrin.h(709 B)
ðŸ“„ opencl-c-base.h(30.38 KB)
ðŸ“„ opencl-c.h(874.39 KB)
ðŸ“ openmp_wrappers
ðŸ“„ pconfigintrin.h(1.19 KB)
ðŸ“„ pkuintrin.h(934 B)
ðŸ“„ pmmintrin.h(10.5 KB)
ðŸ“„ popcntintrin.h(1.82 KB)
ðŸ“ ppc_wrappers
ðŸ“„ prfchiintrin.h(2.02 KB)
ðŸ“„ prfchwintrin.h(2.06 KB)
ðŸ“„ ptwriteintrin.h(1.05 KB)
ðŸ“„ raointintrin.h(6.59 KB)
ðŸ“„ rdpruintrin.h(1.59 KB)
ðŸ“„ rdseedintrin.h(2.85 KB)
ðŸ“„ riscv_ntlh.h(855 B)
ðŸ“„ rtmintrin.h(1.25 KB)
ðŸ“„ s390intrin.h(604 B)
ðŸ“„ serializeintrin.h(881 B)
ðŸ“„ sgxintrin.h(1.77 KB)
ðŸ“„ sha512intrin.h(5.95 KB)
ðŸ“„ shaintrin.h(7.37 KB)
ðŸ“„ sifive_vector.h(522 B)
ðŸ“„ sm3intrin.h(7.29 KB)
ðŸ“„ sm4intrin.h(8.2 KB)
ðŸ“„ smmintrin.h(99.32 KB)
ðŸ“„ stdalign.h(911 B)
ðŸ“„ stdarg.h(1.66 KB)
ðŸ“„ stdatomic.h(8.3 KB)
ðŸ“„ stdbool.h(1.04 KB)
ðŸ“„ stddef.h(4.16 KB)
ðŸ“„ stdint.h(32.49 KB)
ðŸ“„ stdnoreturn.h(1.17 KB)
ðŸ“„ tbmintrin.h(3.15 KB)
ðŸ“„ tgmath.h(29.68 KB)
ðŸ“„ tmmintrin.h(29.51 KB)
ðŸ“„ tsxldtrkintrin.h(1.97 KB)
ðŸ“„ uintrintrin.h(4.96 KB)
ðŸ“„ unwind.h(11.21 KB)
ðŸ“„ vadefs.h(1.39 KB)
ðŸ“„ vaesintrin.h(2.46 KB)
ðŸ“„ varargs.h(477 B)
ðŸ“„ vecintrin.h(360.82 KB)
ðŸ“„ velintrin.h(2.1 KB)
ðŸ“„ velintrin_approx.h(3.54 KB)
ðŸ“„ velintrin_gen.h(69.06 KB)
ðŸ“„ vpclmulqdqintrin.h(1.06 KB)
ðŸ“„ waitpkgintrin.h(1.33 KB)
ðŸ“„ wasm_simd128.h(76.25 KB)
ðŸ“„ wbnoinvdintrin.h(749 B)
ðŸ“„ wmmintrin.h(659 B)
ðŸ“„ x86gprintrin.h(2.32 KB)
ðŸ“„ x86intrin.h(1.81 KB)
ðŸ“„ xmmintrin.h(106.73 KB)
ðŸ“„ xopintrin.h(19.96 KB)
ðŸ“„ xsavecintrin.h(2.51 KB)
ðŸ“„ xsaveintrin.h(1.64 KB)
ðŸ“„ xsaveoptintrin.h(1 KB)
ðŸ“„ xsavesintrin.h(1.24 KB)
ðŸ“„ 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

X7ROOT File Manager

Editing: avx512vldqintrin.h

Upload File

Create Folder