ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 10:09:41 +00:00
Code Issues Packages Projects Releases Wiki Activity
31 Commits 742 Branches 38 Tags
e70223c1c4bc8f7920c19ad30dd2bcaa654e34d8
Commit Graph

23 Commits

Author SHA1 Message Date
Chao Liu
e70223c1c4 add host winograd 3x3 conv 
[ROCm/composable_kernel commit: dbffe05a98]
 2018-11-21 13:21:34 -06:00
Chao Liu
69a23647d8 refactor 
[ROCm/composable_kernel commit: a21b0d27a5]
 2018-11-20 10:51:28 -06:00
Chao Liu
cb8367c0eb rename 
[ROCm/composable_kernel commit: 6790b8f3cc]
 2018-11-20 10:43:37 -06:00
Chao Liu
3ac454af51 hand tuned params 
[ROCm/composable_kernel commit: d2a488ddec]
 2018-11-20 10:34:16 -06:00
Chao Liu
779a90edb3 faster: output skip LDS 
[ROCm/composable_kernel commit: c587726190]
 2018-11-16 06:08:11 -06:00
Chao Liu
c220b9878a refactor 
[ROCm/composable_kernel commit: 5096a157da]
 2018-11-16 01:45:24 -06:00
Chao Liu
3e4752bf7e refactor 
[ROCm/composable_kernel commit: 73480fee36]
 2018-11-15 23:53:23 -06:00
Chao Liu
d33b269f6d refactor 
[ROCm/composable_kernel commit: adf4b173b3]
 2018-11-15 23:22:06 -06:00
Chao Liu
ae630b42a0 refactor 
[ROCm/composable_kernel commit: 99d05ba77f]
 2018-11-15 22:41:01 -06:00
Chao Liu
fbc1d7b252 faster 
[ROCm/composable_kernel commit: c8d0356a34]
 2018-11-15 18:54:57 -06:00
Chao Liu
e807d7ff6c improved blockwise_tensor_op 
[ROCm/composable_kernel commit: 1812666a47]
 2018-11-14 08:55:45 -06:00
Chao Liu
0103b03b7e refactor 
[ROCm/composable_kernel commit: ff31af2227]
 2018-11-13 15:46:19 -06:00
Chao Liu
d6d74f711d refactor 
[ROCm/composable_kernel commit: 0404f777b4]
 2018-11-13 15:22:41 -06:00
Chao Liu
9f6a585b84 add 2nd version of blockwise_tensor_op 
[ROCm/composable_kernel commit: 08c7f74391]
 2018-11-07 18:35:54 -06:00
Chao Liu
bfc1a1108d clean up 
[ROCm/composable_kernel commit: 5d2cafcb24]
 2018-11-07 11:26:13 -06:00
Chao Liu
709e67b2a7 sucess cuda run 
[ROCm/composable_kernel commit: 84b36bc18d]
 2018-11-04 14:55:55 -06:00
Chao Liu
1545a3f6f9 conv: update tensorDesc calculation 
[ROCm/composable_kernel commit: 6a45afba95]
 2018-11-04 04:55:37 -06:00
Chao Liu
621850a671 use constant tensor descriptor 
[ROCm/composable_kernel commit: 1b648f2f42]
 2018-11-04 04:08:51 -06:00
Chao Liu
a80cde213d initial direct conv correct run 
[ROCm/composable_kernel commit: 9657baec32]
 2018-11-02 00:25:21 -05:00
Chao Liu
9c02482e6d convolution: init cuda run 
[ROCm/composable_kernel commit: dfa0213942]
 2018-10-30 11:12:21 -05:00
Chao Liu
6a5c465ad9 initial cuda build 
[ROCm/composable_kernel commit: 2f2cf35bf4]
 2018-10-22 11:51:10 -05:00
Chao Liu
6521ccba67 cpu direct conv 
[ROCm/composable_kernel commit: d51b81588f]
 2018-10-19 01:26:21 -05:00
Chao Liu
8bfafec554 start adding convolution 
[ROCm/composable_kernel commit: fc98757acd]
 2018-10-08 22:49:58 -05:00