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

Refs #154. Fixed gemv_t bug about overflow 16MB buffer on x86.

This commit is contained in:
Zhang Xianyi 2013-01-20 21:22:12 +08:00
parent 200e4acf15
commit 0b08f7479e
2 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
kernel/x86/gemv_t_sse.S
View File

@ -142,7 +142,9 @@
.L0t: .L0t:
xorl J,J xorl J,J
addl $1,J addl $1,J
sall $21,J # J=2^22 sall $22,J # J=2^24*sizeof(float)=buffer size(16MB)
subl $8, J # Don't use last 8 float in the buffer.
# Now, split M by block J
subl J,MMM # MMM=MMM-J subl J,MMM # MMM=MMM-J
movl J,M movl J,M
jge .L00t jge .L00t

4
kernel/x86/gemv_t_sse2.S
View File

@ -128,7 +128,9 @@
.L0t: .L0t:
xorl J,J xorl J,J
addl $1,J addl $1,J
sall $22,J # J=2^22 sall $21,J # J=2^21*sizeof(double)=buffer size(16MB)
subl $4, J # Don't use last 4 double in the buffer.
# Now, split M by block J
subl J,MMM # MMM=MMM-J subl J,MMM # MMM=MMM-J
movl J,M movl J,M
jge .L00t jge .L00t