diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index de17acb9cd..1809abebba 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -1,8 +1,8 @@ * @junliume @illsilin @carlushuang @aosewski @poyenc # Documentation files -docs/* @ROCm/rocm-documentation @junliume @illsilin @carlushuang @aosewski @poyenc +docs/ @ROCm/rocm-documentation @junliume @illsilin @carlushuang @aosewski @poyenc *.md @ROCm/rocm-documentation @junliume @illsilin @carlushuang @aosewski @poyenc *.rst @ROCm/rocm-documentation @junliume @illsilin @carlushuang @aosewski @poyenc .readthedocs.yaml @ROCm/rocm-documentation @junliume @illsilin @carlushuang @aosewski @poyenc # Header directory for Doxygen documentation -library/include/* @ROCm/rocm-documentation @junliume @illsilin @carlushuang @aosewski @poyenc +library/include/ @ROCm/rocm-documentation @junliume @illsilin @carlushuang @aosewski @poyenc diff --git a/CHANGELOG.md b/CHANGELOG.md index fb2ba1975f..dec6334cf5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,38 +1,46 @@ # Changelog for Composable Kernel -Full documentation for Composable Kernel is not yet available. +Documentation for Composable Kernel available at [https://rocm.docs.amd.com/projects/composable_kernel/en/latest/](https://rocm.docs.amd.com/projects/composable_kernel/en/latest/). -## CK for ROCm 6.1.0 +## Composable Kernel 1.1.0 for ROCm 6.1.0 ### Additions + * Added generic instances for GEMM XDL operations (#1161) * Added gamma and beta parameters for the layernorm and groupnorm bwd operations (#1133) * Introduced wrapper sublibrary (limited functionality). (#1071, #1098, #1108, #1126) * Added an option to vary the number of warm-up cycles and iterations for ckProfiler (#1124) ### Optimizations + * New performance optimizations for GEMM operations on MI200 and MI300 architectures (#1135) ### Fixes + * Reduced the build time for most GPU architectures (#1084) * Fixed some conversion issues for fp8 data type (#1099) ### Changes + None ### Known issues + None -## CK for ROCm 6.0.0 +## Composable Kernel 1.1.0 for ROCm 6.0.0 ### Fixes - * Fixed a hazard associated with inline v_dot (#808) - * Fixed two bugs in grouped convolution backward data without K padding (#848 #876) + +* Fixed a hazard associated with inline v_dot (#808) +* Fixed two bugs in grouped convolution backward data without K padding (#848 #876) ### Optimizations + None ### Additions + * Added an image to a column kernel (#867) * Added a column to an image kernel (#930) * Support for 3D grouped convolution on RDNA 3 GPUs (#935, #950, #985) @@ -42,18 +50,22 @@ None * Support for Batched GEMM DL (#732) ### Changes - * Changed the grouped convolution API to maintain consistency with other convolution kernels (#817) -## CK 0.2.0 for ROCm 5.7.0 +* Changed the grouped convolution API to maintain consistency with other convolution kernels (#817) + +## Composable Kernel 0.2.0 for ROCm 5.7.0 ### Fixes + * Fixed a bug in 6-dimensional kernels (#555) * Fixed a test case failure with grouped convolution backward weight (#524) ### Optimizations + * Improved the performance of the normalization kernel ### Additions + * New CMake flags: * "DL_KERNELS"-* Must be set to "ON" in order to build the GEMM DL and batched_gemm_multi_d_dl instances * "DTYPES" -- Can be set to any subset of "fp64;fp32;fp16;fp8;bf16;int8" to build an instance of the specified data types @@ -71,4 +83,5 @@ None * MaxPool and AvgPool forward (#815); MaxPool backward (#750) ### Changes + None