floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #2049 from Celelibi/fix_crash_sgemm_sse_x64 

Fix crash in sgemm SSE/nano kernel on x86_64
This commit is contained in:
Martin Kroeker 2019-03-07 19:28:06 +01:00 committed by GitHub
parent db3dc9e282 b7f59da42d
commit 8d3d29e4d7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
kernel/x86_64/gemm_kernel_4x8_nano.S
View File

@ -135,7 +135,7 @@
#endif #endif
movq %rsp, %rbx # save old stack movq %rsp, %rbx # save old stack
subq $128 + LOCAL_BUFFER_SIZE, %rsp subq $256 + LOCAL_BUFFER_SIZE, %rsp
andq $-4096, %rsp # align stack andq $-4096, %rsp # align stack
STACK_TOUCHING STACK_TOUCHING

2
kernel/x86_64/gemm_kernel_8x4_sse.S
View File

@ -383,7 +383,7 @@
EMMS EMMS
movq %rsp, %rbx # save old stack movq %rsp, %rbx # save old stack
subq $128 + LOCAL_BUFFER_SIZE, %rsp subq $256 + LOCAL_BUFFER_SIZE, %rsp
andq $-4096, %rsp # align stack andq $-4096, %rsp # align stack
STACK_TOUCHING STACK_TOUCHING