OSchip
/
OpenBLAS
Not watched
1
0
Fork 0
Code
Releases 66 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
Browse Source

Fix crash in sgemm SSE/nano kernel on x86_64 

Fix bug #2047.

Signed-off-by: Celelibi <celelibi@gmail.com>
tags/v0.3.6^2
Celelibi 7 years ago
parent
db3dc9e282
commit
b7f59da42d
2 changed files with 2 additions and 2 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +1
    -1
      kernel/x86_64/gemm_kernel_4x8_nano.S
  2. +1
    -1
      kernel/x86_64/gemm_kernel_8x4_sse.S

+ 1
- 1
kernel/x86_64/gemm_kernel_4x8_nano.S View File

@@ -135,7 +135,7 @@
#endif

movq %rsp, %rbx # save old stack
subq $128 + LOCAL_BUFFER_SIZE, %rsp
subq $256 + LOCAL_BUFFER_SIZE, %rsp
andq $-4096, %rsp # align stack

STACK_TOUCHING


+ 1
- 1
kernel/x86_64/gemm_kernel_8x4_sse.S View File

@@ -383,7 +383,7 @@
EMMS

movq %rsp, %rbx # save old stack
subq $128 + LOCAL_BUFFER_SIZE, %rsp
subq $256 + LOCAL_BUFFER_SIZE, %rsp
andq $-4096, %rsp # align stack

STACK_TOUCHING


Write Preview
Loading…
Cancel
Save