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
AI开发
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
Fix declaration of assembly arguments in SSYMV and DSYMV microkernels
Arguments 0 and 1 are both input and output
tags/v0.3.6^2
Martin Kroeker
GitHub
7 years ago
parent
91481a3e4e
commit
b824fa70eb
No known key found for this signature in database
GPG Key ID:
4AEE18F83AFDEB23
8 changed files
with
24 additions
and
24 deletions
Split View
Diff Options
Show Stats
Download Patch File
Download Diff File
+3
-3
kernel/x86_64/dsymv_U_microk_bulldozer-2.c
+3
-3
kernel/x86_64/dsymv_U_microk_haswell-2.c
+3
-3
kernel/x86_64/dsymv_U_microk_nehalem-2.c
+3
-3
kernel/x86_64/dsymv_U_microk_sandy-2.c
+3
-3
kernel/x86_64/ssymv_U_microk_bulldozer-2.c
+3
-3
kernel/x86_64/ssymv_U_microk_haswell-2.c
+3
-3
kernel/x86_64/ssymv_U_microk_nehalem-2.c
+3
-3
kernel/x86_64/ssymv_U_microk_sandy-2.c
+ 3
- 3
kernel/x86_64/dsymv_U_microk_bulldozer-2.c
View File
@@ -106,9 +106,9 @@ static void dsymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"vmovsd %%xmm3 ,24(%9) \n\t" // save temp2
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
+ 3
- 3
kernel/x86_64/dsymv_U_microk_haswell-2.c
View File
@@ -107,9 +107,9 @@ static void dsymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"vzeroupper \n\t"
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
+ 3
- 3
kernel/x86_64/dsymv_U_microk_nehalem-2.c
View File
@@ -101,9 +101,9 @@ static void dsymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"movsd %%xmm3 , 24(%9) \n\t" // save temp2
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
+ 3
- 3
kernel/x86_64/dsymv_U_microk_sandy-2.c
View File
@@ -116,9 +116,9 @@ static void dsymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"vzeroupper \n\t"
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
+ 3
- 3
kernel/x86_64/ssymv_U_microk_bulldozer-2.c
View File
@@ -90,9 +90,9 @@ static void ssymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"vmovss %%xmm3 ,12(%9) \n\t" // save temp2
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
+ 3
- 3
kernel/x86_64/ssymv_U_microk_haswell-2.c
View File
@@ -112,9 +112,9 @@ static void ssymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"vzeroupper \n\t"
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
+ 3
- 3
kernel/x86_64/ssymv_U_microk_nehalem-2.c
View File
@@ -106,9 +106,9 @@ static void ssymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"movss %%xmm3 , 12(%9) \n\t" // save temp2
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
+ 3
- 3
kernel/x86_64/ssymv_U_microk_sandy-2.c
View File
@@ -120,9 +120,9 @@ static void ssymv_kernel_4x4(BLASLONG n, FLOAT *a0, FLOAT *a1, FLOAT *a2, FLOAT
"vzeroupper \n\t"
:
:
"r" (i), // 0
"r" (n), // 1
"+r" (i), // 0
"+r" (n) // 1
:
"r" (x), // 2
"r" (y), // 3
"r" (a0), // 4
Write
Preview
Loading…
Cancel
Save