404 Not Found

PATH: lib64 / llvm17 / lib / clang / 17 / include

/*===---- avx512erintrin.h - AVX512ER 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 <avx512erintrin.h> directly; include <immintrin.h> instead."
#endif

#ifndef __AVX512ERINTRIN_H
#define __AVX512ERINTRIN_H

/* exp2a23 */
#define _mm512_exp2a23_round_pd(A, R) \
  ((__m512d)__builtin_ia32_exp2pd_mask((__v8df)(__m512d)(A), \
                                       (__v8df)_mm512_setzero_pd(), \
                                       (__mmask8)-1, (int)(R)))

#define _mm512_mask_exp2a23_round_pd(S, M, A, R) \
  ((__m512d)__builtin_ia32_exp2pd_mask((__v8df)(__m512d)(A), \
                                       (__v8df)(__m512d)(S), (__mmask8)(M), \
                                       (int)(R)))

#define _mm512_maskz_exp2a23_round_pd(M, A, R) \
  ((__m512d)__builtin_ia32_exp2pd_mask((__v8df)(__m512d)(A), \
                                       (__v8df)_mm512_setzero_pd(), \
                                       (__mmask8)(M), (int)(R)))

#define _mm512_exp2a23_pd(A) \
  _mm512_exp2a23_round_pd((A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_exp2a23_pd(S, M, A) \
  _mm512_mask_exp2a23_round_pd((S), (M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_exp2a23_pd(M, A) \
  _mm512_maskz_exp2a23_round_pd((M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_exp2a23_round_ps(A, R) \
  ((__m512)__builtin_ia32_exp2ps_mask((__v16sf)(__m512)(A), \
                                      (__v16sf)_mm512_setzero_ps(), \
                                      (__mmask16)-1, (int)(R)))

#define _mm512_mask_exp2a23_round_ps(S, M, A, R) \
  ((__m512)__builtin_ia32_exp2ps_mask((__v16sf)(__m512)(A), \
                                      (__v16sf)(__m512)(S), (__mmask16)(M), \
                                      (int)(R)))

#define _mm512_maskz_exp2a23_round_ps(M, A, R) \
  ((__m512)__builtin_ia32_exp2ps_mask((__v16sf)(__m512)(A), \
                                      (__v16sf)_mm512_setzero_ps(), \
                                      (__mmask16)(M), (int)(R)))

#define _mm512_exp2a23_ps(A) \
  _mm512_exp2a23_round_ps((A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_exp2a23_ps(S, M, A) \
  _mm512_mask_exp2a23_round_ps((S), (M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_exp2a23_ps(M, A) \
  _mm512_maskz_exp2a23_round_ps((M), (A), _MM_FROUND_CUR_DIRECTION)

/* rsqrt28 */
#define _mm512_rsqrt28_round_pd(A, R) \
  ((__m512d)__builtin_ia32_rsqrt28pd_mask((__v8df)(__m512d)(A), \
                                          (__v8df)_mm512_setzero_pd(), \
                                          (__mmask8)-1, (int)(R)))

#define _mm512_mask_rsqrt28_round_pd(S, M, A, R) \
  ((__m512d)__builtin_ia32_rsqrt28pd_mask((__v8df)(__m512d)(A), \
                                          (__v8df)(__m512d)(S), (__mmask8)(M), \
                                          (int)(R)))

#define _mm512_maskz_rsqrt28_round_pd(M, A, R) \
  ((__m512d)__builtin_ia32_rsqrt28pd_mask((__v8df)(__m512d)(A), \
                                          (__v8df)_mm512_setzero_pd(), \
                                          (__mmask8)(M), (int)(R)))

#define _mm512_rsqrt28_pd(A) \
  _mm512_rsqrt28_round_pd((A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rsqrt28_pd(S, M, A) \
  _mm512_mask_rsqrt28_round_pd((S), (M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rsqrt28_pd(M, A) \
  _mm512_maskz_rsqrt28_round_pd((M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_rsqrt28_round_ps(A, R) \
  ((__m512)__builtin_ia32_rsqrt28ps_mask((__v16sf)(__m512)(A), \
                                         (__v16sf)_mm512_setzero_ps(), \
                                         (__mmask16)-1, (int)(R)))

#define _mm512_mask_rsqrt28_round_ps(S, M, A, R) \
  ((__m512)__builtin_ia32_rsqrt28ps_mask((__v16sf)(__m512)(A), \
                                         (__v16sf)(__m512)(S), (__mmask16)(M), \
                                         (int)(R)))

#define _mm512_maskz_rsqrt28_round_ps(M, A, R) \
  ((__m512)__builtin_ia32_rsqrt28ps_mask((__v16sf)(__m512)(A), \
                                         (__v16sf)_mm512_setzero_ps(), \
                                         (__mmask16)(M), (int)(R)))

#define _mm512_rsqrt28_ps(A) \
  _mm512_rsqrt28_round_ps((A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rsqrt28_ps(S, M, A) \
  _mm512_mask_rsqrt28_round_ps((S), (M), A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rsqrt28_ps(M, A) \
  _mm512_maskz_rsqrt28_round_ps((M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm_rsqrt28_round_ss(A, B, R) \
  ((__m128)__builtin_ia32_rsqrt28ss_round_mask((__v4sf)(__m128)(A), \
                                               (__v4sf)(__m128)(B), \
                                               (__v4sf)_mm_setzero_ps(), \
                                               (__mmask8)-1, (int)(R)))

#define _mm_mask_rsqrt28_round_ss(S, M, A, B, R) \
  ((__m128)__builtin_ia32_rsqrt28ss_round_mask((__v4sf)(__m128)(A), \
                                               (__v4sf)(__m128)(B), \
                                               (__v4sf)(__m128)(S), \
                                               (__mmask8)(M), (int)(R)))

#define _mm_maskz_rsqrt28_round_ss(M, A, B, R) \
  ((__m128)__builtin_ia32_rsqrt28ss_round_mask((__v4sf)(__m128)(A), \
                                               (__v4sf)(__m128)(B), \
                                               (__v4sf)_mm_setzero_ps(), \
                                               (__mmask8)(M), (int)(R)))

#define _mm_rsqrt28_ss(A, B) \
  _mm_rsqrt28_round_ss((A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_mask_rsqrt28_ss(S, M, A, B) \
  _mm_mask_rsqrt28_round_ss((S), (M), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rsqrt28_ss(M, A, B) \
  _mm_maskz_rsqrt28_round_ss((M), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_rsqrt28_round_sd(A, B, R) \
  ((__m128d)__builtin_ia32_rsqrt28sd_round_mask((__v2df)(__m128d)(A), \
                                                (__v2df)(__m128d)(B), \
                                                (__v2df)_mm_setzero_pd(), \
                                                (__mmask8)-1, (int)(R)))

#define _mm_mask_rsqrt28_round_sd(S, M, A, B, R) \
  ((__m128d)__builtin_ia32_rsqrt28sd_round_mask((__v2df)(__m128d)(A), \
                                                (__v2df)(__m128d)(B), \
                                                (__v2df)(__m128d)(S), \
                                                (__mmask8)(M), (int)(R)))

#define _mm_maskz_rsqrt28_round_sd(M, A, B, R) \
  ((__m128d)__builtin_ia32_rsqrt28sd_round_mask((__v2df)(__m128d)(A), \
                                                (__v2df)(__m128d)(B), \
                                                (__v2df)_mm_setzero_pd(), \
                                                (__mmask8)(M), (int)(R)))

#define _mm_rsqrt28_sd(A, B) \
  _mm_rsqrt28_round_sd((A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_mask_rsqrt28_sd(S, M, A, B) \
  _mm_mask_rsqrt28_round_sd((S), (M), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rsqrt28_sd(M, A, B) \
  _mm_maskz_rsqrt28_round_sd((M), (A), (B), _MM_FROUND_CUR_DIRECTION)

/* rcp28 */
#define _mm512_rcp28_round_pd(A, R) \
  ((__m512d)__builtin_ia32_rcp28pd_mask((__v8df)(__m512d)(A), \
                                        (__v8df)_mm512_setzero_pd(), \
                                        (__mmask8)-1, (int)(R)))

#define _mm512_mask_rcp28_round_pd(S, M, A, R) \
  ((__m512d)__builtin_ia32_rcp28pd_mask((__v8df)(__m512d)(A), \
                                        (__v8df)(__m512d)(S), (__mmask8)(M), \
                                        (int)(R)))

#define _mm512_maskz_rcp28_round_pd(M, A, R) \
  ((__m512d)__builtin_ia32_rcp28pd_mask((__v8df)(__m512d)(A), \
                                        (__v8df)_mm512_setzero_pd(), \
                                        (__mmask8)(M), (int)(R)))

#define _mm512_rcp28_pd(A) \
  _mm512_rcp28_round_pd((A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rcp28_pd(S, M, A) \
  _mm512_mask_rcp28_round_pd((S), (M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rcp28_pd(M, A) \
  _mm512_maskz_rcp28_round_pd((M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_rcp28_round_ps(A, R) \
  ((__m512)__builtin_ia32_rcp28ps_mask((__v16sf)(__m512)(A), \
                                       (__v16sf)_mm512_setzero_ps(), \
                                       (__mmask16)-1, (int)(R)))

#define _mm512_mask_rcp28_round_ps(S, M, A, R) \
  ((__m512)__builtin_ia32_rcp28ps_mask((__v16sf)(__m512)(A), \
                                       (__v16sf)(__m512)(S), (__mmask16)(M), \
                                       (int)(R)))

#define _mm512_maskz_rcp28_round_ps(M, A, R) \
  ((__m512)__builtin_ia32_rcp28ps_mask((__v16sf)(__m512)(A), \
                                       (__v16sf)_mm512_setzero_ps(), \
                                       (__mmask16)(M), (int)(R)))

#define _mm512_rcp28_ps(A) \
  _mm512_rcp28_round_ps((A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rcp28_ps(S, M, A) \
  _mm512_mask_rcp28_round_ps((S), (M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rcp28_ps(M, A) \
  _mm512_maskz_rcp28_round_ps((M), (A), _MM_FROUND_CUR_DIRECTION)

#define _mm_rcp28_round_ss(A, B, R) \
  ((__m128)__builtin_ia32_rcp28ss_round_mask((__v4sf)(__m128)(A), \
                                             (__v4sf)(__m128)(B), \
                                             (__v4sf)_mm_setzero_ps(), \
                                             (__mmask8)-1, (int)(R)))

#define _mm_mask_rcp28_round_ss(S, M, A, B, R) \
  ((__m128)__builtin_ia32_rcp28ss_round_mask((__v4sf)(__m128)(A), \
                                             (__v4sf)(__m128)(B), \
                                             (__v4sf)(__m128)(S), \
                                             (__mmask8)(M), (int)(R)))

#define _mm_maskz_rcp28_round_ss(M, A, B, R) \
  ((__m128)__builtin_ia32_rcp28ss_round_mask((__v4sf)(__m128)(A), \
                                             (__v4sf)(__m128)(B), \
                                             (__v4sf)_mm_setzero_ps(), \
                                             (__mmask8)(M), (int)(R)))

#define _mm_rcp28_ss(A, B) \
  _mm_rcp28_round_ss((A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_mask_rcp28_ss(S, M, A, B) \
  _mm_mask_rcp28_round_ss((S), (M), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rcp28_ss(M, A, B) \
  _mm_maskz_rcp28_round_ss((M), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_rcp28_round_sd(A, B, R) \
  ((__m128d)__builtin_ia32_rcp28sd_round_mask((__v2df)(__m128d)(A), \
                                              (__v2df)(__m128d)(B), \
                                              (__v2df)_mm_setzero_pd(), \
                                              (__mmask8)-1, (int)(R)))

#define _mm_mask_rcp28_round_sd(S, M, A, B, R) \
  ((__m128d)__builtin_ia32_rcp28sd_round_mask((__v2df)(__m128d)(A), \
                                              (__v2df)(__m128d)(B), \
                                              (__v2df)(__m128d)(S), \
                                              (__mmask8)(M), (int)(R)))

#define _mm_maskz_rcp28_round_sd(M, A, B, R) \
  ((__m128d)__builtin_ia32_rcp28sd_round_mask((__v2df)(__m128d)(A), \
                                              (__v2df)(__m128d)(B), \
                                              (__v2df)_mm_setzero_pd(), \
                                              (__mmask8)(M), (int)(R)))

#define _mm_rcp28_sd(A, B) \
  _mm_rcp28_round_sd((A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_mask_rcp28_sd(S, M, A, B) \
  _mm_mask_rcp28_round_sd((S), (M), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rcp28_sd(M, A, B) \
  _mm_maskz_rcp28_round_sd((M), (A), (B), _MM_FROUND_CUR_DIRECTION)

#endif /* __AVX512ERINTRIN_H */

[+] ..
[-] riscv_ntlh.h [edit]
[-] avx512vlbitalgintrin.h [edit]
[-] avxifmaintrin.h [edit]
[-] mm_malloc.h [edit]
[-] avx512vlbf16intrin.h [edit]
[-] mwaitxintrin.h [edit]
[-] adxintrin.h [edit]
[-] arm_cmse.h [edit]
[-] __clang_cuda_intrinsics.h [edit]
[-] module.modulemap [edit]
[-] crc32intrin.h [edit]
[+] cuda_wrappers
[-] msa.h [edit]
[-] __clang_hip_stdlib.h [edit]
[-] arm_acle.h [edit]
[-] arm_neon_sve_bridge.h [edit]
[-] xsaveintrin.h [edit]
[-] velintrin_gen.h [edit]
[-] stdatomic.h [edit]
[-] hvx_hexagon_protos.h [edit]
[-] uintrintrin.h [edit]
[-] fxsrintrin.h [edit]
[-] sha512intrin.h [edit]
[-] __clang_cuda_texture_intrinsics.h [edit]
[-] iso646.h [edit]
[-] unwind.h [edit]
[-] avx512vlbwintrin.h [edit]
[-] avxvnniint8intrin.h [edit]
[-] avx512erintrin.h [edit]
[-] avxvnniintrin.h [edit]
[-] ia32intrin.h [edit]
[-] rdseedintrin.h [edit]
[-] prfchiintrin.h [edit]
[-] amxcomplexintrin.h [edit]
[-] clflushoptintrin.h [edit]
[-] htmxlintrin.h [edit]
[-] avx512fintrin.h [edit]
[-] gfniintrin.h [edit]
[-] arm_cde.h [edit]
[+] ppc_wrappers
[-] amxfp16intrin.h [edit]
[-] velintrin_approx.h [edit]
[-] avx512pfintrin.h [edit]
[-] stdarg.h [edit]
[-] cmpccxaddintrin.h [edit]
[-] avx512vlintrin.h [edit]
[-] __clang_hip_math.h [edit]
[-] vecintrin.h [edit]
[-] xtestintrin.h [edit]
[-] __wmmintrin_aes.h [edit]
[-] arm_neon.h [edit]
[-] immintrin.h [edit]
[-] ammintrin.h [edit]
[-] waitpkgintrin.h [edit]
[-] vpclmulqdqintrin.h [edit]
[-] fmaintrin.h [edit]
[-] tsxldtrkintrin.h [edit]
[-] prfchwintrin.h [edit]
[-] avx512bitalgintrin.h [edit]
[-] bmiintrin.h [edit]
[-] __wmmintrin_pclmul.h [edit]
[-] htmintrin.h [edit]
[-] mm3dnow.h [edit]
[-] __clang_cuda_builtin_vars.h [edit]
[-] __clang_hip_runtime_wrapper.h [edit]
[-] stdbool.h [edit]
[-] altivec.h [edit]
[-] wbnoinvdintrin.h [edit]
[-] keylockerintrin.h [edit]
[-] tgmath.h [edit]
[-] hexagon_circ_brev_intrinsics.h [edit]
[-] x86intrin.h [edit]
[-] pkuintrin.h [edit]
[-] avx512vbmivlintrin.h [edit]
[-] avxneconvertintrin.h [edit]
[-] __clang_hip_cmath.h [edit]
[-] sgxintrin.h [edit]
[-] f16cintrin.h [edit]
[-] opencl-c-base.h [edit]
[-] cpuid.h [edit]
[-] raointintrin.h [edit]
[-] builtins.h [edit]
[-] emmintrin.h [edit]
[-] smmintrin.h [edit]
[-] vaesintrin.h [edit]
[-] larchintrin.h [edit]
[-] avx512ifmaintrin.h [edit]
[-] intrin.h [edit]
[-] avx512vlvp2intersectintrin.h [edit]
[-] fma4intrin.h [edit]
[-] pmmintrin.h [edit]
[-] __clang_hip_libdevice_declares.h [edit]
[-] limits.h [edit]
[-] clwbintrin.h [edit]
[-] rtmintrin.h [edit]
[-] mmintrin.h [edit]
[-] stddef.h [edit]
[-] invpcidintrin.h [edit]
[-] avx512vp2intersectintrin.h [edit]
[-] cet.h [edit]
[-] xopintrin.h [edit]
[-] avx512vlvnniintrin.h [edit]
[-] avx512vlfp16intrin.h [edit]
[-] stdint.h [edit]
[-] arm64intr.h [edit]
[-] sm4intrin.h [edit]
[-] avx512vnniintrin.h [edit]
[-] avx2intrin.h [edit]
[-] movdirintrin.h [edit]
[-] tbmintrin.h [edit]
[-] arm_mve.h [edit]
[-] avx512ifmavlintrin.h [edit]
[-] amxintrin.h [edit]
[-] opencl-c.h [edit]
[-] stdalign.h [edit]
[-] __clang_cuda_device_functions.h [edit]
[-] pconfigintrin.h [edit]
[-] avx512fp16intrin.h [edit]
[-] inttypes.h [edit]
[-] arm_bf16.h [edit]
[-] __clang_cuda_math_forward_declares.h [edit]
[-] vadefs.h [edit]
[-] shaintrin.h [edit]
[-] hexagon_protos.h [edit]
[-] ptwriteintrin.h [edit]
[-] xsaveoptintrin.h [edit]
[-] enqcmdintrin.h [edit]
[-] x86gprintrin.h [edit]
[-] tmmintrin.h [edit]
[-] stdnoreturn.h [edit]
[-] avx512bf16intrin.h [edit]
[-] varargs.h [edit]
[-] s390intrin.h [edit]
[-] avx512vbmiintrin.h [edit]
[+] openmp_wrappers
[-] wmmintrin.h [edit]
[-] __clang_cuda_cmath.h [edit]
[-] clzerointrin.h [edit]
[-] xsavesintrin.h [edit]
[-] __clang_cuda_libdevice_declares.h [edit]
[-] nmmintrin.h [edit]
[-] wasm_simd128.h [edit]
[-] xsavecintrin.h [edit]
[-] avx512dqintrin.h [edit]
[-] lwpintrin.h [edit]
[-] serializeintrin.h [edit]
[-] arm_sme_draft_spec_subject_to_change.h [edit]
[-] avxintrin.h [edit]
[-] __stddef_max_align_t.h [edit]
[-] sm3intrin.h [edit]
[-] velintrin.h [edit]
[-] __clang_cuda_complex_builtins.h [edit]
[-] armintr.h [edit]
[-] avx512cdintrin.h [edit]
[-] float.h [edit]
[-] avx512vbmi2intrin.h [edit]
[-] lzcntintrin.h [edit]
[-] sifive_vector.h [edit]
[-] rdpruintrin.h [edit]
[-] arm_sve.h [edit]
[-] avx512vpopcntdqintrin.h [edit]
[-] xmmintrin.h [edit]
[-] hresetintrin.h [edit]
[-] bmi2intrin.h [edit]
[-] hexagon_types.h [edit]
[-] avx512bwintrin.h [edit]
[-] cetintrin.h [edit]
[-] __clang_cuda_math.h [edit]
[-] avx512vlvbmi2intrin.h [edit]
[-] arm_fp16.h [edit]
[-] avx512vpopcntdqvlintrin.h [edit]
[-] avxvnniint16intrin.h [edit]
[+] llvm_libc_wrappers
[-] __clang_cuda_runtime_wrapper.h [edit]
[-] cldemoteintrin.h [edit]
[-] avx512vldqintrin.h [edit]
[-] avx512vlcdintrin.h [edit]
[-] popcntintrin.h [edit]