Files
TheRock/compiler/amd-llvm/clang/lib/Headers/avx10_2_512minmaxintrin.h
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

128 lines
7.3 KiB
C

/*===---- avx10_2_512minmaxintrin.h - AVX10_2_512MINMAX 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 <avx10_2_512minmaxintrin.h> directly; include <immintrin.h> instead."
#endif // __IMMINTRIN_H
#ifndef __AVX10_2_512MINMAXINTRIN_H
#define __AVX10_2_512MINMAXINTRIN_H
#define _mm512_minmax_pbh(A, B, C) \
((__m512bh)__builtin_ia32_vminmaxbf16512((__v32bf)(__m512bh)(A), \
(__v32bf)(__m512bh)(A), (int)(C)))
#define _mm512_mask_minmax_pbh(W, U, A, B, C) \
((__m512bh)__builtin_ia32_selectpbf_512( \
(__mmask32)(U), \
(__v32bf)_mm512_minmax_pbh((__v32bf)(__m512bh)(A), \
(__v32bf)(__m512bh)(B), (int)(C)), \
(__v32bf)(__m512bh)(W)))
#define _mm512_maskz_minmax_pbh(U, A, B, C) \
((__m512bh)__builtin_ia32_selectpbf_512( \
(__mmask32)(U), \
(__v32bf)_mm512_minmax_pbh((__v32bf)(__m512bh)(A), \
(__v32bf)(__m512bh)(B), (int)(C)), \
(__v32bf) __builtin_bit_cast(__m512bh, _mm512_setzero_ps())))
#define _mm512_minmax_pd(A, B, C) \
((__m512d)__builtin_ia32_vminmaxpd512_round_mask( \
(__v8df)(__m512d)(A), (__v8df)(__m512d)(B), (int)(C), \
(__v8df)_mm512_undefined_pd(), (__mmask8)-1, \
_MM_FROUND_CUR_DIRECTION))
#define _mm512_mask_minmax_pd(W, U, A, B, C) \
((__m512d)__builtin_ia32_vminmaxpd512_round_mask( \
(__v8df)(__m512d)(A), (__v8df)(__m512d)(B), (int)(C), \
(__v8df)(__m512d)(W), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
#define _mm512_maskz_minmax_pd(U, A, B, C) \
((__m512d)__builtin_ia32_vminmaxpd512_round_mask( \
(__v8df)(__m512d)(A), (__v8df)(__m512d)(B), (int)(C), \
(__v8df)_mm512_setzero_pd(), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
#define _mm512_minmax_round_pd(A, B, C, R) \
((__m512d)__builtin_ia32_vminmaxpd512_round_mask( \
(__v8df)(__m512d)(A), (__v8df)(__m512d)(B), (int)(C), \
(__v8df)_mm512_undefined_pd(), (__mmask8)-1, (int)(R)))
#define _mm512_mask_minmax_round_pd(W, U, A, B, C, R) \
((__m512d)__builtin_ia32_vminmaxpd512_round_mask( \
(__v8df)(__m512d)(A), (__v8df)(__m512d)(B), (int)(C), \
(__v8df)(__m512d)(W), (__mmask8)(U), (int)(R)))
#define _mm512_maskz_minmax_round_pd(U, A, B, C, R) \
((__m512d)__builtin_ia32_vminmaxpd512_round_mask( \
(__v8df)(__m512d)(A), (__v8df)(__m512d)(B), (int)(C), \
(__v8df)_mm512_setzero_pd(), (__mmask8)(U), (int)(R)))
#define _mm512_minmax_ph(A, B, C) \
((__m512h)__builtin_ia32_vminmaxph512_round_mask( \
(__v32hf)(__m512h)(A), (__v32hf)(__m512h)(B), (int)(C), \
(__v32hf)_mm512_undefined_ph(), (__mmask32)-1, \
_MM_FROUND_CUR_DIRECTION))
#define _mm512_mask_minmax_ph(W, U, A, B, C) \
((__m512h)__builtin_ia32_vminmaxph512_round_mask( \
(__v32hf)(__m512h)(A), (__v32hf)(__m512h)(B), (int)(C), \
(__v32hf)(__m512h)(W), (__mmask32)(U), _MM_FROUND_CUR_DIRECTION))
#define _mm512_maskz_minmax_ph(U, A, B, C) \
((__m512h)__builtin_ia32_vminmaxph512_round_mask( \
(__v32hf)(__m512h)(A), (__v32hf)(__m512h)(B), (int)(C), \
(__v32hf)_mm512_setzero_ph(), (__mmask32)(U), _MM_FROUND_CUR_DIRECTION))
#define _mm512_minmax_round_ph(A, B, C, R) \
((__m512h)__builtin_ia32_vminmaxph512_round_mask( \
(__v32hf)(__m512h)(A), (__v32hf)(__m512h)(B), (int)(C), \
(__v32hf)_mm512_undefined_ph(), (__mmask32)-1, (int)(R)))
#define _mm512_mask_minmax_round_ph(W, U, A, B, C, R) \
((__m512h)__builtin_ia32_vminmaxph512_round_mask( \
(__v32hf)(__m512h)(A), (__v32hf)(__m512h)(B), (int)(C), \
(__v32hf)(__m512h)(W), (__mmask32)(U), (int)(R)))
#define _mm512_maskz_minmax_round_ph(U, A, B, C, R) \
((__m512h)__builtin_ia32_vminmaxph512_round_mask( \
(__v32hf)(__m512h)(A), (__v32hf)(__m512h)(B), (int)(C), \
(__v32hf)_mm512_setzero_ph(), (__mmask32)(U), (int)(R)))
#define _mm512_minmax_ps(A, B, C) \
((__m512)__builtin_ia32_vminmaxps512_round_mask( \
(__v16sf)(__m512)(A), (__v16sf)(__m512)(B), (int)(C), \
(__v16sf)_mm512_undefined_ps(), (__mmask16)-1, \
_MM_FROUND_CUR_DIRECTION))
#define _mm512_mask_minmax_ps(W, U, A, B, C) \
((__m512)__builtin_ia32_vminmaxps512_round_mask( \
(__v16sf)(__m512)(A), (__v16sf)(__m512)(B), (int)(C), (__v16sf)(W), \
(__mmask16)(U), _MM_FROUND_CUR_DIRECTION))
#define _mm512_maskz_minmax_ps(U, A, B, C) \
((__m512)__builtin_ia32_vminmaxps512_round_mask( \
(__v16sf)(__m512)(A), (__v16sf)(__m512)(B), (int)(C), \
(__v16sf)_mm512_setzero_ps(), (__mmask16)(U), _MM_FROUND_CUR_DIRECTION))
#define _mm512_minmax_round_ps(A, B, C, R) \
((__m512)__builtin_ia32_vminmaxps512_round_mask( \
(__v16sf)(__m512)(A), (__v16sf)(__m512)(B), (int)(C), \
(__v16sf)_mm512_undefined_ps(), (__mmask16)-1, (int)(R)))
#define _mm512_mask_minmax_round_ps(W, U, A, B, C, R) \
((__m512)__builtin_ia32_vminmaxps512_round_mask( \
(__v16sf)(__m512)(A), (__v16sf)(__m512)(B), (int)(C), (__v16sf)(W), \
(__mmask16)(U), (int)(R)))
#define _mm512_maskz_minmax_round_ps(U, A, B, C, R) \
((__m512)__builtin_ia32_vminmaxps512_round_mask( \
(__v16sf)(__m512)(A), (__v16sf)(__m512)(B), (int)(C), \
(__v16sf)_mm512_setzero_ps(), (__mmask16)(U), (int)(R)))
#endif // __AVX10_2_512MINMAXINTRIN_H