Chao Liu
|
f2523a771e
|
adding implicit gemm v4r2
[ROCm/composable_kernel commit: 923578a389]
|
2019-07-05 15:35:11 -05:00 |
|
Chao Liu
|
98db3224e6
|
some benchmark on vega 7
[ROCm/composable_kernel commit: f0716f5b10]
|
2019-06-28 16:13:54 -05:00 |
|
Chao Liu
|
99fc474d24
|
tested on P100
[ROCm/composable_kernel commit: dab2938937]
|
2019-06-27 15:46:09 -05:00 |
|
Chao Liu
|
c37a237f00
|
do more benchmark
[ROCm/composable_kernel commit: 85ae70d3d3]
|
2019-06-26 21:43:26 -05:00 |
|
Chao Liu
|
f9dd497fc9
|
add more test
[ROCm/composable_kernel commit: 35269cf77a]
|
2019-06-26 15:51:22 -05:00 |
|
Chao Liu
|
8826080382
|
debugging vector load for generic tensor copy
[ROCm/composable_kernel commit: e55cfe1536]
|
2019-06-24 11:49:13 -05:00 |
|
Chao Liu
|
5b938e815e
|
enabling vector load on merged dim
[ROCm/composable_kernel commit: df29a7e097]
|
2019-06-24 11:20:19 -05:00 |
|
Chao Liu
|
8f649c000c
|
added strides and dilations suppport to implicit gemm v4
[ROCm/composable_kernel commit: b1cb48a04d]
|
2019-06-13 16:20:10 -05:00 |
|
Chao Liu
|
5f217ebda5
|
reorginzed files
[ROCm/composable_kernel commit: 1566b31736]
|
2019-06-13 15:12:12 -05:00 |
|