mirror of
https://github.com/opencv/opencv.git
synced 2026-07-31 08:13:04 +04:00
Abhishek Gola
bdf348c13a
Added MLAS third party module and integrated into GeMM path #28934 ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [x] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
35 lines
564 B
ArmAsm
35 lines
564 B
ArmAsm
/*++
|
|
|
|
Copyright (c) Microsoft Corporation. All rights reserved.
|
|
|
|
Licensed under the MIT License.
|
|
|
|
Module Name:
|
|
|
|
SgemmKernelFma3.s
|
|
|
|
Abstract:
|
|
|
|
This module implements the kernels for the single precision matrix/matrix
|
|
multiply operation (SGEMM).
|
|
|
|
This implementation uses AVX fused multiply/add instructions.
|
|
|
|
--*/
|
|
|
|
#include "asmmacro.h"
|
|
#include "SgemmKernelCommon.h"
|
|
#include "FgemmKernelFma3Common.h"
|
|
|
|
.intel_syntax noprefix
|
|
|
|
.text
|
|
|
|
//
|
|
// Generate the GEMM kernel.
|
|
//
|
|
|
|
FgemmKernelFma3Function MlasGemmFloatKernelFma3
|
|
|
|
.end
|