ltqin 781cacd2e6 NHWC Conv2d Bwd weight fp16 ckprofiler and test (#166) ...

* change backward weight name

* start add bwd weight lib and profiler

* change tuning paramter

* change output info

* add bwd weight test

* change test info

* using conv_util

* change wgt to weight

* add }

* add fp32

2022-04-04 20:32:00 -05:00

..

block

Improve Reduction kernel api (#152)

2022-04-04 20:31:44 -05:00

device

NHWC Conv2d Bwd weight fp16 ckprofiler and test (#166)

2022-04-04 20:32:00 -05:00

element

Gemm+Reduce Fusion (#128)

2022-03-23 22:18:42 -05:00

grid

Improve Reduction kernel api (#152)

2022-04-04 20:31:44 -05:00

thread

Improve Reduction kernel api (#152)

2022-04-04 20:31:44 -05:00

warp

Compile for gfx908 and gfx90a (#130)

2022-03-31 12:33:34 -05:00