Merge remote-tracking branch 'origin/develop' into migx_merge

docs/Contributors_Guide.rst

@@ -2,7 +2,101 @@
 Contributor's Guide
 ===================
 
-Pull-request guidelines
-=======================
+This chapter explains how to get started contributing to the Composable Kernel project and what are
+the contributing rules.
 
-[TODO]
+Getting started
+===============
+
+#. **Documentation:** Before contributing to the library, familiarize yourself with the
+   `Composable Kernel User Guide <https://rocm.docs.amd.com/projects/composable_kernel/en/latest/>`_.
+   It provides insight into the core concepts, environment configuration, and steps to obtain or
+   build the library. You can also find some of this information in the
+   `README file <https://github.com/ROCmSoftwarePlatform/composable_kernel/blob/develop/README.md>`_
+   on the project's GitHub page.
+#. **Additional reading:** We also recommend reading a `blog post
+   <https://community.amd.com/t5/instinct-accelerators/amd-composable-kernel-library-efficient-fused-kernels-for-ai/ba-p/553224>`_
+   from the AMD Community portal. It offers a deeper understanding of the library's objectives and
+   showcases its performance capabilities.
+#. **General information:** For broader information about AMD products, consider exploring the
+   `AMD Developer Central portal <https://www.amd.com/en/developer.html>`_.
+
+How do I contribute
+===================
+
+We deeply value contributions from our users. You can make an impact by reporting issues or
+proposing code enhancements through pull requests.
+
+Reporting issues
+----------------
+
+We use `Github issues <https://github.com/ROCmSoftwarePlatform/composable_kernel/issues>`_
+to track public bugs and enhancement requests.
+
+If you encounter an issue with the library, please check if the problem has already been
+reported by searching existing issues on GitHub. If your issue seems unique, please submit a new
+issue. All reported issues must include:
+
+* A comprehensive description of the problem, including:
+
+  * What did you observe?
+  * Why do you think it is a bug (if it seems like one)?
+  * What did you expect to happen? What would indicate the resolution of the problem?
+  * Are there any known workarounds?
+
+* Your configuration details, including:
+
+  * Which GPU are you using?
+  * Which OS version are you on?
+  * Which ROCm version are you using?
+  * Are you using a Docker image? If so, which one?
+
+* Steps to reproduce the issue, including:
+
+  * What actions trigger the issue? What are the reproduction steps?
+
+    * If you build the library from scratch, what CMake command did you use?
+
+  * How frequently does this issue happen? Does it reproduce every time? Or is it a sporadic issue?
+
+Before sumbitting any issue, ensure you have addressed all relevant questions from the checklist.
+
+Creating Pull Requests
+----------------------
+
+You can submit `Pull Requests (PR) on GitHub
+<https://github.com/ROCmSoftwarePlatform/composable_kernel/pulls>`_.
+
+All contributors are required to develop their changes on a separate branch and then create a
+pull requrest to merge their changes into the `develop` branch, which is the default
+development branch in the Composable Kernel project. All external contributors must use their own
+forks of the project to develop their changes.
+
+When submitting a Pull Request you should:
+
+* Describe the change providing information about the motivation for the change and a general
+  description of all code modifications.
+
+* Verify and test the change:
+
+  * Run any relevant existing tests.
+  * Write new tests if added functionality is not covered by current tests.
+
+* Ensure your changes align with the coding style defined in the ``.clang-format`` file located in
+  the project's root directory. We leverage `pre-commit` to run `clang-format` automatically. We
+  highly recommend contributors utilize this method to maintain consistent code formatting.
+  Instructions on setting up `pre-commit` can be found in the project's
+  `README file <https://github.com/ROCmSoftwarePlatform/composable_kernel/blob/develop/README.md>`_
+
+* Link your PR to any related issues:
+
+  * If there is an issue that is resolved by your change, please provide a link to the issue in
+    the description of your pull request.
+
+* For larger contributions, structure your change into a sequence of smaller, focused commits, each
+  addressing a particular aspect or fix.
+
+Following the above guidelines ensures a seamless review process and faster assistance from our
+end.
+
+Thank you for your commitment to enhancing the Composable Kernel project! We look forward to collaborating with you.

docs/sphinx/requirements.in

 rocm-docs-core>=0.20.0
-sphinxcontrib-bibtex==2.5.0
+sphinxcontrib-bibtex==2.6.1

docs/sphinx/requirements.txt

@@ -42,12 +42,18 @@ fastjsonschema==2.18.0
     # via rocm-docs-core
 gitdb==4.0.10
     # via gitpython
-gitpython==3.1.31
+gitpython==3.1.35
     # via rocm-docs-core
 idna==3.4
     # via requests
 imagesize==1.4.1
     # via sphinx
+importlib-metadata==6.8.0
+    # via
+    #   sphinx
+    #   sphinxcontrib-bibtex
+importlib-resources==6.1.0
+    # via rocm-docs-core
 jinja2==3.1.2
     # via
     #   myst-parser
@@ -90,9 +96,13 @@ pygments==2.14.0
     #   pydata-sphinx-theme
     #   sphinx
 pyjwt[crypto]==2.6.0
-    # via pygithub
+    # via
+    #   pygithub
+    #   pyjwt
 pynacl==1.5.0
     # via pygithub
+pytz==2023.3.post1
+    # via babel
 pyyaml==6.0
     # via
     #   myst-parser
@@ -103,7 +113,7 @@ requests==2.28.2
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core>=0.20.0
+rocm-docs-core==0.27.0
     # via -r requirements.in
 six==1.16.0
     # via
@@ -139,7 +149,7 @@ sphinx-notfound-page==0.8.3
     # via rocm-docs-core
 sphinxcontrib-applehelp==1.0.4
     # via sphinx
-sphinxcontrib-bibtex==2.5.0
+sphinxcontrib-bibtex==2.6.1
     # via -r requirements.in
 sphinxcontrib-devhelp==1.0.2
     # via sphinx
@@ -157,3 +167,7 @@ urllib3==1.26.15
     # via requests
 wrapt==1.15.0
     # via deprecated
+zipp==3.17.0
+    # via
+    #   importlib-metadata
+    #   importlib-resources

example/01_gemm/CMakeLists.txt

-if(DL_KERNELS)
-  add_custom_target(example_gemm_dl)
-
-  add_example_executable(example_gemm_dl_fp32 gemm_dl_fp32.cpp)
-  add_dependencies(example_gemm_dl example_gemm_dl_fp32)
-  if(DTYPES MATCHES "fp16" OR NOT DEFINED DTYPES)
-    add_example_executable(example_gemm_dl_fp16 gemm_dl_fp16.cpp)
-    add_dependencies(example_gemm_dl example_gemm_dl_fp16)
-    add_example_executable(example_gemm_dl_dpp8_fp16 gemm_dl_dpp8_fp16.cpp)
-    add_dependencies(example_gemm_dl example_gemm_dl_dpp8_fp16)
-  endif()
-  if(DTYPES MATCHES "int8" OR NOT DEFINED DTYPES)
-    add_example_executable(example_gemm_dl_int8 gemm_dl_int8.cpp)
-    add_dependencies(example_gemm_dl example_gemm_dl_int8)
-  endif()
-
-  if(USE_BITINT_EXTENSION_INT4)
+add_custom_target(example_gemm_dl)
+
+add_example_executable(example_gemm_dl_fp32 gemm_dl_fp32.cpp)
+add_example_dependencies(example_gemm_dl example_gemm_dl_fp32)
+
+add_example_executable(example_gemm_dl_fp16 gemm_dl_fp16.cpp)
+add_example_dependencies(example_gemm_dl example_gemm_dl_fp16)
+
+add_example_executable(example_gemm_dpp_fp16 gemm_dpp_fp16.cpp)
+
+add_example_executable(example_gemm_dl_int8 gemm_dl_int8.cpp)
+add_example_dependencies(example_gemm_dl example_gemm_dl_int8)
+if(USE_BITINT_EXTENSION_INT4)
     add_example_executable(example_gemm_dl_int4 gemm_dl_int4.cpp)
-    add_dependencies(example_gemm_dl example_gemm_dl_int4)
-  endif(USE_BITINT_EXTENSION_INT4)
-endif()
+    add_example_dependencies(example_gemm_dl example_gemm_dl_int4)
+endif(USE_BITINT_EXTENSION_INT4)
 
 add_custom_target(example_gemm_xdl)
-if(DTYPES MATCHES "fp16" OR NOT DEFINED DTYPES)
-  add_example_executable(example_gemm_xdl_fp16 gemm_xdl_fp16.cpp)
-  add_example_executable(example_gemm_xdl_wavelet_fp16 gemm_xdl_wavelet_fp16.cpp)
-  add_dependencies(example_gemm_xdl example_gemm_xdl_fp16)
-  add_dependencies(example_gemm_xdl example_gemm_xdl_wavelet_fp16)
-  add_example_executable(example_gemm_xdl_skip_b_lds_fp16 gemm_xdl_skip_b_lds_fp16.cpp)
-  add_dependencies(example_gemm_xdl example_gemm_xdl_skip_b_lds_fp16)
-
-  if(GPU_TARGETS MATCHES "gfx1100" OR GPU_TARGETS MATCHES "gfx1101" OR GPU_TARGETS MATCHES "gfx1102")
+add_example_executable(example_gemm_xdl_fp16 gemm_xdl_fp16.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16)
+
+add_example_executable(example_gemm_xdl_wavelet_fp16 gemm_xdl_wavelet_fp16.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_wavelet_fp16)
+
+add_example_executable(example_gemm_xdl_skip_b_lds_fp16 gemm_xdl_skip_b_lds_fp16.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_skip_b_lds_fp16)
+if(GPU_TARGETS MATCHES "gfx1100" OR GPU_TARGETS MATCHES "gfx1101" OR GPU_TARGETS MATCHES "gfx1102")
     add_custom_target(example_gemm_wmma)
     add_example_executable(example_gemm_wmma_fp16 gemm_wmma_fp16.cpp)
-    add_dependencies(example_gemm_wmma example_gemm_wmma_fp16)
-  endif()
-
+    add_example_dependencies(example_gemm_wmma example_gemm_wmma_fp16)
 endif()
 
-if(DTYPES MATCHES "bf16" OR NOT DEFINED DTYPES)
-  add_example_executable(example_gemm_xdl_bf16 gemm_xdl_bf16.cpp)
-  add_dependencies(example_gemm_xdl example_gemm_xdl_bf16)
-endif()
+add_example_executable(example_gemm_xdl_bf16 gemm_xdl_bf16.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_bf16)
 
-if(DTYPES MATCHES "int8" OR NOT DEFINED DTYPES)
-  add_example_executable(example_gemm_xdl_int8 gemm_xdl_int8.cpp)
-  add_dependencies(example_gemm_xdl example_gemm_xdl_int8)
-endif()
+add_example_executable(example_gemm_xdl_bf16_rtn gemm_xdl_bf16_rtn.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_bf16_rtn)
+
+add_example_executable(example_gemm_xdl_int8 gemm_xdl_int8.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_int8)
 
 if(USE_BITINT_EXTENSION_INT4)
     add_example_executable(example_gemm_xdl_int4 gemm_xdl_int4.cpp)
-  add_dependencies(example_gemm_xdl example_gemm_xdl_int4)
+    add_example_dependencies(example_gemm_xdl example_gemm_xdl_int4)
 endif(USE_BITINT_EXTENSION_INT4)
 
-if(DTYPES MATCHES "fp64" OR NOT DEFINED DTYPES)
-  # FIXME: re-enable this exampe as test when SWDEV-335738 is fixed
-  add_example_executable_no_testing(example_gemm_xdl_fp64 gemm_xdl_fp64.cpp)
-  add_dependencies(example_gemm_xdl example_gemm_xdl_fp64)
-endif()
+# FIXME: re-enable this exampe as test when SWDEV-335738 is fixed
+add_example_executable_no_testing(example_gemm_xdl_fp64 gemm_xdl_fp64.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp64)
 
 add_example_executable(example_gemm_xdl_streamk gemm_xdl_streamk.cpp)
 
-if(DTYPES MATCHES "fp8" OR NOT DEFINED DTYPES)
-  if(GPU_TARGETS MATCHES "gfx940" OR GPU_TARGETS MATCHES "gfx941" OR GPU_TARGETS MATCHES "gfx942")
-    add_example_executable(example_gemm_xdl_f8 gemm_xdl_f8.cpp)
-    add_dependencies(example_gemm_xdl example_gemm_xdl_f8)
-  endif()
-endif()
+add_example_executable(example_gemm_xdl_fp8 gemm_xdl_fp8.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp8)
+
+add_example_executable(example_gemm_xdl_fp8_bf8 gemm_xdl_fp8_bf8.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp8_bf8)
 
-add_example_executable(example_gemm_xdl_fp16_f8 gemm_xdl_fp16_f8.cpp)
-add_dependencies(example_gemm_xdl example_gemm_xdl_fp16_f8)
+add_example_executable(example_gemm_xdl_fp16_fp8 gemm_xdl_fp16_fp8.cpp)
+add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16_fp8)

example/03_gemm_bias_relu/CMakeLists.txt

-if(DTYPES MATCHES "fp16" OR NOT DEFINED DTYPES)
 list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942)
 set(target 0)
 foreach(gpu IN LISTS GPU_TARGETS)
@@ -7,4 +6,3 @@ foreach(gpu IN LISTS GPU_TARGETS)
    set(target 1)
  endif()
 endforeach()
-endif()