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
117 lines
4.3 KiB
C
117 lines
4.3 KiB
C
/*===------------- avx512vnniintrin.h - VNNI 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 <avx512vnniintrin.h> directly; include <immintrin.h> instead."
|
|
#endif
|
|
|
|
#ifndef __AVX512VNNIINTRIN_H
|
|
#define __AVX512VNNIINTRIN_H
|
|
|
|
/* Define the default attributes for the functions in this file. */
|
|
#define __DEFAULT_FN_ATTRS \
|
|
__attribute__((__always_inline__, __nodebug__, __target__("avx512vnni"), \
|
|
__min_vector_width__(512)))
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_dpbusd_epi32(__m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_vpdpbusd512((__v16si)__S, (__v64qu)__A,
|
|
(__v64qi)__B);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_dpbusd_epi32(__m512i __S, __mmask16 __U, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpbusd_epi32(__S, __A, __B),
|
|
(__v16si)__S);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_dpbusd_epi32(__mmask16 __U, __m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpbusd_epi32(__S, __A, __B),
|
|
(__v16si)_mm512_setzero_si512());
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_dpbusds_epi32(__m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_vpdpbusds512((__v16si)__S, (__v64qu)__A,
|
|
(__v64qi)__B);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_dpbusds_epi32(__m512i __S, __mmask16 __U, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpbusds_epi32(__S, __A, __B),
|
|
(__v16si)__S);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_dpbusds_epi32(__mmask16 __U, __m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpbusds_epi32(__S, __A, __B),
|
|
(__v16si)_mm512_setzero_si512());
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_dpwssd_epi32(__m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_vpdpwssd512((__v16si)__S, (__v32hi)__A,
|
|
(__v32hi)__B);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_dpwssd_epi32(__m512i __S, __mmask16 __U, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpwssd_epi32(__S, __A, __B),
|
|
(__v16si)__S);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_dpwssd_epi32(__mmask16 __U, __m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpwssd_epi32(__S, __A, __B),
|
|
(__v16si)_mm512_setzero_si512());
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_dpwssds_epi32(__m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_vpdpwssds512((__v16si)__S, (__v32hi)__A,
|
|
(__v32hi)__B);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_dpwssds_epi32(__m512i __S, __mmask16 __U, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpwssds_epi32(__S, __A, __B),
|
|
(__v16si)__S);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_dpwssds_epi32(__mmask16 __U, __m512i __S, __m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectd_512(__U,
|
|
(__v16si)_mm512_dpwssds_epi32(__S, __A, __B),
|
|
(__v16si)_mm512_setzero_si512());
|
|
}
|
|
|
|
#undef __DEFAULT_FN_ATTRS
|
|
|
|
#endif
|