This website works better with JavaScript.
Home
Issues
Pull Requests
Milestones
AI流水线
Repositories
Datasets
Forum
实训
竞赛
大数据
Register
Sign In
OSchip
/
OpenBLAS
Not watched
Unwatch
Watch all
Watch but not notify
1
Star
0
Fork
0
Code
Releases
66
Wiki
evaluate
Activity
Issues
0
Pull Requests
0
Datasets
Model
Cloudbrain
HPC
Browse Source
Refs
#171
. Prevent loading the dirty number from the buffer in sgemv_t x86 kernel.
tags/v0.2.6
Zhang Xianyi
12 years ago
parent
fd3046b32a
commit
91ed4e4450
1 changed files
with
14 additions
and
0 deletions
Split View
Diff Options
Show Stats
Download Patch File
Download Diff File
+14
-0
kernel/x86/gemv_t_sse.S
+ 14
- 0
kernel/x86/gemv_t_sse.S
View File
@@ -236,6 +236,20 @@
jg .L06
ALIGN_4
//Padding zero to prevent loading the dirty number from buffer.
movl M, I
movl $8, J
andl $7, I
xorps %xmm0, %xmm0
subl I, J
ALIGN_2
.L07:
movss %xmm0, 0 * SIZE(Y1)
addl $SIZE, Y1
decl J
jg .L07
ALIGN_4
.L10:
movl Y, Y1
Write
Preview
Loading…
Cancel
Save