Commit Graph

7 Commits

Author SHA1 Message Date
Chao Liu
7569eeaf55 refactor direct
[ROCm/composable_kernel commit: 24d2f034fa]
2018-11-25 01:10:11 -06:00
Chao Liu
779a90edb3 faster: output skip LDS
[ROCm/composable_kernel commit: c587726190]
2018-11-16 06:08:11 -06:00
Chao Liu
3e4752bf7e refactor
[ROCm/composable_kernel commit: 73480fee36]
2018-11-15 23:53:23 -06:00
Chao Liu
cd469dcd63 clean up
[ROCm/composable_kernel commit: 29496c95d3]
2018-11-15 20:16:58 -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
9f6a585b84 add 2nd version of blockwise_tensor_op
[ROCm/composable_kernel commit: 08c7f74391]
2018-11-07 18:35:54 -06:00