Philippe Tillet
|
a26582d34b
|
More cleaning
|
2016-10-02 20:21:38 -04:00 |
|
Philippe Tillet
|
77178d7017
|
GEMM: Better handling of AT=1 and BT=0
|
2016-10-02 17:37:49 -04:00 |
|
Philippe Tillet
|
e1baf85707
|
Code quality: removed obsolete/dead code
|
2016-10-01 19:27:42 -04:00 |
|
Philippe Tillet
|
284fb5e109
|
Database: Updated Pascal profile
|
2016-09-30 01:21:24 -04:00 |
|
Philippe Tillet
|
5d0e29db1f
|
Bench: Fixed CUDA synchronization issue
|
2016-09-30 01:21:24 -04:00 |
|
Philippe Tillet
|
7210098e1a
|
Profiles: Now reverting to default for unprovided operations in .json
|
2016-09-29 23:37:37 -04:00 |
|
Philippe Tillet
|
adf2dc7ea5
|
Runtime: Added Pascal profile (default to Maxwell)
|
2016-09-29 14:53:33 -04:00 |
|
Philippe Tillet
|
fa4cb6866d
|
Bench: Now displaying results in a table
|
2016-09-29 14:50:42 -04:00 |
|
Philippe Tillet
|
1e178dab22
|
Code quality: shortened parameter names in JIT code generator
|
2016-07-02 21:47:41 -07:00 |
|
Philippe Tillet
|
1e439ad5bc
|
JIT: No longer using fallbacks for stride[0] > 1
It was pretty messy.
|
2016-04-10 16:31:29 -04:00 |
|
Philippe Tillet
|
97a0d65a4d
|
Code quality: reorganized files structure
|
2016-04-10 13:13:16 -04:00 |
|