mirror of
https://github.com/opencv/opencv.git
synced 2026-09-11 04:43:22 -05:00
37c9ab1815
Fix MLAS 32-bit x86 build by integrating missing upstream assembly files #29226 ### Pull Request Readiness Checklist This resolves the 32-bit x86 build failure for MLAS. Related to: https://github.com/opencv/opencv/pull/29218 * Added the required `x86` assembly files and headers from upstream. * Added `__x86_64__` guards around the AMX `syscall` and the FMA3/AVX512F kernel assignments to prevent 32-bit compilation crashes. 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
80 lines
1.3 KiB
C
80 lines
1.3 KiB
C
/*++
|
|
|
|
Copyright (c) Microsoft Corporation. All rights reserved.
|
|
|
|
Licensed under the MIT License.
|
|
|
|
Module Name:
|
|
|
|
asmmacro.h
|
|
|
|
Abstract:
|
|
|
|
This module implements common macros for the assembly modules.
|
|
|
|
--*/
|
|
|
|
#if defined(__APPLE__)
|
|
#define C_UNDERSCORE(symbol) _##symbol
|
|
#else
|
|
#define C_UNDERSCORE(symbol) symbol
|
|
#endif
|
|
|
|
/*++
|
|
|
|
Macro Description:
|
|
|
|
This macro emits the assembler directives to annotate a new function.
|
|
|
|
Arguments:
|
|
|
|
FunctionName - Supplies the name of the function.
|
|
|
|
--*/
|
|
|
|
.macro FUNCTION_ENTRY FunctionName
|
|
|
|
.p2align 4
|
|
#if defined(__APPLE__)
|
|
.globl _\FunctionName\()
|
|
_\FunctionName\():
|
|
#else
|
|
.globl \FunctionName\()
|
|
.type \FunctionName\(),@function
|
|
\FunctionName\():
|
|
#endif
|
|
|
|
.endm
|
|
|
|
/*++
|
|
|
|
Macro Description:
|
|
|
|
This macro emits the code to load the global offset table address into the
|
|
supplied register.
|
|
|
|
Arguments:
|
|
|
|
TargetReg - Specifies the target register.
|
|
|
|
--*/
|
|
|
|
.macro LoadGlobalOffsetTable, TargetReg
|
|
|
|
//
|
|
// The LLVM integrated assembler doesn't support the Intel syntax for OFFSET:
|
|
//
|
|
// add ebx,OFFSET _GLOBAL_OFFSET_TABLE_
|
|
//
|
|
// Workaround this by temporarily switching to AT&T syntax.
|
|
//
|
|
|
|
.att_syntax
|
|
|
|
calll __x86.get_pc_thunk.\TargetReg\()
|
|
addl $_GLOBAL_OFFSET_TABLE_,%e\TargetReg\()
|
|
|
|
.intel_syntax noprefix
|
|
|
|
.endm
|