composable_kernel/example at 0c9a1d25b3951736bf1fdc480de5fa21208f8e56 - composable_kernel - Public git mirror

ROCm/composable_kernel

mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-11 08:50:17 +00:00

Files

History

zjing14 f5ec04f091 Grouped Gemm with Fixed K and N with SplitK (#818 )

* move all arguments into device

* add b2c_tile_map

* add examples

* add SetDeviceKernelArgs

* dedicated fixed_nk solution

* init client api

* add grouped_gemm_bias example

* add a instance

* add instances

* formatting

* fixed cmake

* Update EnableCompilerWarnings.cmake

* Update cmake-ck-dev.sh

* clean; fixed comments

* fixed comment

* add instances for fp32 output

* add instances for fp32 output

* add fp32 out client example

* fixed CI

* init commit for kbatch

* add splitk gridwise

* format

* fixed

* clean deviceop

* clean code

* finish splitk

* fixed instances

* change m_loops to tile_loops

* add setkbatch

* clean code

* add splitK+bias

* add instances

* opt mk_nk instances

* clean examples

* fixed CI

* remove zero

* finished non-zero

* clean

* clean code

* optimized global_barrier

* fixed ci

* fixed CI

* removed AddBias

* format

* fixed CI

* fixed CI

* move 20_grouped_gemm to 21_grouped_gemm

---------

Co-authored-by: Jing Zhang <jizha@amd.com>

2023-08-31 09:22:12 -05:00

..

add an example of customized type convert - bfp16_rtn (#869 )

2023-08-29 12:31:24 -05:00

02_gemm_bilinear

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

03_gemm_bias_relu

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

04_gemm_add_add_fastgelu

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

10_convnd_fwd_multiple_d_multiple_reduce

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

update copyright headers (#726 )

2023-05-31 18:46:57 -05:00

Refactor pool fwd (#815 )

2023-08-15 02:25:28 +08:00

14_gemm_quantization

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

15_grouped_gemm

Grouped Gemm with Fixed K and N with SplitK (#818 )

2023-08-31 09:22:12 -05:00

16_gemm_multi_d_multi_reduces

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

17_convnd_bwd_data

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

18_batched_gemm_reduce

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

19_binary_elementwise

update copyright headers (#726 )

2023-05-31 18:46:57 -05:00

20_grouped_conv_bwd_weight

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

21_gemm_layernorm

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

update copyright headers (#726 )

2023-05-31 18:46:57 -05:00

24_batched_gemm

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

25_gemm_bias_e_permute

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

28_grouped_gemm_bias_e_permute

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

29_batched_gemm_bias_e_permute

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

30_grouped_conv_fwd_multiple_d

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

31_batched_gemm_gemm

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

32_batched_gemm_scale_softmax_gemm

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

33_multiple_reduce

update copyright headers (#726 )

2023-05-31 18:46:57 -05:00

Batchnorm splitk single kernel (#771 )

2023-07-06 10:58:55 -05:00

use correct data types in cmake conditions for splitk gemm example (#862 )

2023-08-23 09:52:11 -07:00

36_sparse_embedding

update copyright headers (#726 )

2023-05-31 18:46:57 -05:00

37_batched_gemm_add_add_relu_gemm_add

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

38_grouped_conv_bwd_data_multiple_d

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

40_conv2d_fwd_quantization

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

41_grouped_conv_conv_fwd

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

43_splitk_gemm_bias_e_permute

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

44_elementwise_permute

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

45_elementwise_normalization

update copyright headers (#726 )

2023-05-31 18:46:57 -05:00

46_gemm_add_multiply

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

47_gemm_bias_softmax_gemm_permute

Enable gfx941 and gfx942 architectures. (#752 )

2023-06-15 08:20:59 -07:00

Refactor pool fwd (#815 )

2023-08-15 02:25:28 +08:00

49_maxpool2d_bwd

MaxPool & AvgPool bwd instances, test, ckProfiler, client example (#861 )

2023-08-31 21:01:50 +08:00

Allow building CK for specific data types and split off last remaining DL instances. (#830 )

2023-08-07 14:56:10 -07:00

51_avgpool3d_bwd

Average pool backward deviceOP and example (#797 )

2023-08-10 12:04:35 +08:00

CMakeLists.txt

Add packages for examples and profiler (#502 )

2022-11-10 13:19:33 -06:00