ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-05 06:01:23 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
98fd41f5977d87b939b147ec168ae964f70f0350
composable_kernel/include/ck/tensor_operation/gpu/device/impl
History
zjing14 98fd41f597 Add Gemm instances for performance improvement (#1018) 
* improve kpad

* more tuning parameters

* f16_f8_fp16

* cut test time

* add f16_f8_fp16

* add f16_f8_f16

* testing instances for skinny cases

* format

* clean

* add fp16_f8_fp16

* clang-format

* add grouped gemm instalces

* fixed profile grouped_gemm

* clean

* clean

* clean

* clean

* clean

* add missing instance func

* fixed inferface

---------

Co-authored-by: Jing Zhang <jizha@amd.com>
Co-authored-by: root <root@sh5-1e707-rc06-38.mkm.dcgpu>
2023-11-07 09:09:58 -06:00
..
device_avgpool3d_bwd_ndhwc_ndhwc.hpp
Average pool backward deviceOP and example (#797)
2023-08-10 12:04:35 +08:00
device_batched_contraction_multiple_d_wmma_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_contraction_multiple_d_xdl_cshuffle.hpp
Fp16/fp8 mixed-precision Gemm with multiply+add fusion (#865)
2023-08-28 16:27:32 -05:00
device_batched_gemm_e_permute_xdl.hpp
Fp16/fp8 mixed-precision Gemm with multiply+add fusion (#865)
2023-08-28 16:27:32 -05:00
device_batched_gemm_gemm_xdl_cshuffle.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_batched_gemm_multi_d_xdl.hpp
Fp16/fp8 mixed-precision Gemm with multiply+add fusion (#865)
2023-08-28 16:27:32 -05:00
device_batched_gemm_multiple_d_dl.hpp
Add s_nops after v_dot to avoid hazard (#808)
2023-07-27 13:29:44 -05:00
device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
[HotFix] add config and version files to pass on build info (#856)
2023-08-23 11:36:17 -07:00
device_batched_gemm_reduce_xdl_cshuffle.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_batched_gemm_xdl.hpp
added padding of K into gemm_v2r3 (#887)
2023-09-06 10:15:52 -05:00
device_batchnorm_backward_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batchnorm_forward_impl_obsolete.hpp
Batchnorm splitk single kernel (#771)
2023-07-06 10:58:55 -05:00
device_batchnorm_forward_impl.hpp
Batchnorm splitk single kernel (#771)
2023-07-06 10:58:55 -05:00
device_cgemm_4gemm_xdl_cshuffle.hpp
Enable f16/f8 mixed precision mode (#820)
2023-08-09 08:44:23 -05:00
device_column_to_image_impl.hpp
Add support for groups in Img2Col/Col2Img (#1007)
2023-10-31 10:46:32 +01:00
device_contraction_multiple_abd_xdl_cshuffle.hpp
fixed math-ci error; suspend a warning (#996)
2023-10-18 16:30:13 -07:00
device_contraction_multiple_d_xdl_cshuffle.hpp
Add support for mixed precision in contraction scale and bilinear (#973)
2023-11-02 14:26:33 -07:00
device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
Use asynchronous version of hipMemset (#850)
2023-08-18 11:14:59 +08:00
device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_elementwise_2d_impl.hpp
Using number of compute units to set gridSize (#754)
2023-06-15 10:13:59 -05:00
device_elementwise_impl.hpp
Misc fixes (#994)
2023-10-19 11:26:04 -05:00
device_elementwise_normalization_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_bias_add_reduce_xdl_cshuffle.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_gemm_dl.hpp
Fix DL GEMM instances with too large vector size (#901)
2023-09-18 14:08:23 +02:00
device_gemm_dpp.hpp
Enable DPP8 GEMM on Navi3 (#892)
2023-09-08 11:14:57 -05:00
device_gemm_multiple_abd_xdl_cshuffle.hpp
Add multiple A/B support (#906)
2023-09-26 21:16:23 -05:00
device_gemm_multiple_d_dl.hpp
Enable gfx941 and gfx942 architectures. (#752)
2023-06-15 08:20:59 -07:00
device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
[HotFix] add config and version files to pass on build info (#856)
2023-08-23 11:36:17 -07:00
device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
[HotFix] add config and version files to pass on build info (#856)
2023-08-23 11:36:17 -07:00
device_gemm_multiple_d_wmma_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_multiple_d_xdl_cshuffle.hpp
fixed fp8 issues (#894)
2023-09-12 22:17:56 -05:00
device_gemm_reduce_xdl_cshuffle.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_gemm_wmma.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_xdl_cshuffle.hpp
Add Gemm instances for performance improvement (#1018)
2023-11-07 09:09:58 -06:00
device_gemm_xdl_layernorm_cshuffle.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_gemm_xdl_skip_b_lds.hpp
Disable XDL kernels on unsupported HW Add ck::is_xdl_supported (#768)
2023-07-26 07:19:55 -07:00
device_gemm_xdl_splitk_c_shuffle.hpp
Add Gemm instances for performance improvement (#1018)
2023-11-07 09:09:58 -06:00
device_gemm_xdl_streamk.hpp
Use asynchronous version of hipMemset (#850)
2023-08-18 11:14:59 +08:00
device_gemm_xdl_waveletmodel_cshuffle.hpp
[HotFix] add config and version files to pass on build info (#856)
2023-08-23 11:36:17 -07:00
device_gemm_xdl.hpp
Enable gfx941 & gfx942 support for DeviceGemmXdl<> device op (#1017)
2023-11-01 03:17:31 +08:00
device_grouped_contraction_multiple_d_xdl_cshuffle.hpp
Fp16/fp8 mixed-precision Gemm with multiply+add fusion (#865)
2023-08-28 16:27:32 -05:00
device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
Grouped conv bwd data with fp16 input and bf8fp8 comp (#962)
2023-10-04 18:04:27 -05:00
device_grouped_conv_bwd_weight_dl.hpp
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
device_grouped_conv_bwd_weight_wmma_cshuffle.hpp
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
device_grouped_conv_bwd_weight_xdl_cshuffle.hpp
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
Revert "Grouped Gemm with looping over the tiles. (#788)" (#982)
2023-10-11 14:27:29 -05:00
device_grouped_conv_fwd_dl_nhwc_kyxc_nhwk.hpp
Revert "Grouped Gemm with looping over the tiles. (#788)" (#982)
2023-10-11 14:27:29 -05:00
device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp
[HotFix] add config and version files to pass on build info (#856)
2023-08-23 11:36:17 -07:00
device_grouped_conv_fwd_multiple_d_multiple_r.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp
Revert "Grouped Gemm with looping over the tiles. (#788)" (#982)
2023-10-11 14:27:29 -05:00
device_grouped_conv_utils.hpp
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
device_grouped_gemm_multiple_d_dl.hpp
Enable gfx941 and gfx942 architectures. (#752)
2023-06-15 08:20:59 -07:00
device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
[HotFix] add config and version files to pass on build info (#856)
2023-08-23 11:36:17 -07:00
device_grouped_gemm_xdl_fixed_nk.hpp
Add fp16/fp8 support into Grouped gemm FixedNK (#874)
2023-09-14 21:04:10 -05:00
device_grouped_gemm_xdl_splitk_cshuffle.hpp
Add Gemm instances for performance improvement (#1018)
2023-11-07 09:09:58 -06:00
device_grouped_gemm_xdl.hpp
Fp16/fp8 mixed-precision Gemm with multiply+add fusion (#865)
2023-08-28 16:27:32 -05:00
device_image_to_column_impl.hpp
Add support for groups in Img2Col/Col2Img (#1007)
2023-10-31 10:46:32 +01:00
device_max_pool_bwd_impl.hpp
MaxPool & AvgPool bwd instances, test, ckProfiler, client example (#861)
2023-08-31 21:01:50 +08:00
device_multiple_reduce_multiblock.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_multiple_reduce_threadwise.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_normalization_impl.hpp
Layernorm and groupnorm support to save mean and inverse std in forward (#929)
2023-10-19 07:36:29 +08:00
device_normalization_splitk_impl.hpp
Layernorm and groupnorm support to save mean and inverse std in forward (#929)
2023-10-19 07:36:29 +08:00
device_permute_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_pool2d_fwd_nhwc_nhwc.hpp
Refactor pool fwd (#815)
2023-08-15 02:25:28 +08:00
device_pool3d_fwd_ndhwc_ndhwc.hpp
Refactor pool fwd (#815)
2023-08-15 02:25:28 +08:00
device_put_element_impl.hpp
Maxpool bwd (#750)
2023-06-19 09:44:22 -05:00
device_reduce_common.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_reduce_multiblock.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_reduce_threadwise.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_softmax_impl.hpp
Revert "Grouped Gemm with looping over the tiles. (#788)" (#982)
2023-10-11 14:27:29 -05:00
device_sparse_embeddings_forward_layernorm.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
[HotFix] add config and version files to pass on build info (#856)
2023-08-23 11:36:17 -07:00