Chao Liu cd167e492a Compile for gfx908 and gfx90a (#130) ...

* adding compilation for multiple targets

* fix build

* clean

* update Jekinsfile

* update readme

* update Jenkins

* use ck::half_t instead of ushort for bf16

* rename enum classes

* clean

* rename

* clean

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

..

clang-format-overwrite.sh

Add gemm_shuffle host api (#71)

2022-01-21 00:31:17 -06:00

cmake-rocm.sh

Compile for gfx908 and gfx90a (#130)

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

conv2d_fwd.sh

GEMM+Bias+ReLU+Add (#76)

2022-02-06 22:32:47 -06:00

conv_driver.sh

ckProfiler and device-level XDL GEMM operator (#48)

2021-11-14 11:28:32 -06:00

count_vgpr.sh

revise count_vgpr script to capture all possible syntaxes (#124)

2022-03-11 13:30:50 -06:00

docker-rocm4.1.sh

xdlops_v4r4_fwd fp32/fp16 (#34)

2021-07-01 14:33:00 -05:00

docker-rocm4.3.1.sh

Tweak GEMM kernel (#38)

2021-10-06 11:12:36 -05:00

example_gemm_xdl.sh

ckProfiler and device-level XDL GEMM operator (#48)

2021-11-14 11:28:32 -06:00

gemm_driver.sh

ckProfiler and device-level XDL GEMM operator (#48)

2021-11-14 11:28:32 -06:00

gemm.sh

GEMM+Bias+ReLU+Add (#76)

2022-02-06 22:32:47 -06:00

hipclang_opt.sh

Dynamic tensor descriptor (#24)

2021-03-25 13:51:11 -05:00

pool2d_fwd.sh

GEMM+Bias+ReLU+Add (#76)

2022-02-06 22:32:47 -06:00

profile_conv.sh

GEMM+Bias+ReLU+Add (#76)

2022-02-06 22:32:47 -06:00

profile_gemm.sh

add args for packed gemm (#54)

2021-11-24 12:33:55 -06:00

profile_reduce_no_index.sh

Reduction for int8 and bfloat16 (#125)

2022-03-22 14:35:14 -05:00

profile_reduce_with_index.sh

Reduction for int8 and bfloat16 (#125)

2022-03-22 14:35:14 -05:00

test_convnd_fwd.sh

Unified conv3D API + support for all data types. (#133)

2022-03-23 10:23:13 -05:00

test_reduce_no_index.sh

Reduction for int8 and bfloat16 (#125)

2022-03-22 14:35:14 -05:00

test_reduce_with_index.sh

Reduction for int8 and bfloat16 (#125)

2022-03-22 14:35:14 -05:00