Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
f4bf0c3b3 Update overview.md <> Fri Dec 6 17:27:21 2024 +0100 <> Philipp Samfass <[email protected]> 00f72f6a4 war/fea(cuda compat.): create include/cuda symlink <> Fri Dec 6 01:56:32 2024 -0800 <> Philipp Samfass <[email protected]> Symlink `include/cuda` to `include/hip` This ensures that packages that depend on libhipcxx without installing libhipcxx can still include the libhipcxx headers from the "cuda" folder to minimize code changes. e1c03527b Revert "Check if fixes the issue with FIND_CUDF variable" <> Fri Nov 29 15:47:43 2024 +0000 <> domcharrier <[email protected]> This reverts commit 0593a67. 55cb910bc Revert "Choose installation location considering if libhipcxx is installed stanalone or via another project." <> Fri Nov 29 15:45:20 2024 +0000 <> domcharrier <[email protected]> This reverts commit 49675d0. c036af706 add ISSUE_TEMPLATES WIP <> Thu Oct 17 11:17:08 2024 +0200 <> Philipp Samfass <[email protected]> 19d7f7d57 fix/feat(*test/config.py): add gfx1100 to possible HIP archs <> Fri Oct 18 09:10:08 2024 +0200 <> Philipp Samfass <[email protected]> bd8dac851 fixi/feat(*utils/amd/linux/perform_tests.bash): add gfx1100 to known architectures <> Thu Oct 17 18:36:24 2024 +0200 <> Philipp Samfass <[email protected]> 7bddf81b8 doc(README, overview.md): add gfx1100 as supported GPU <> Wed Oct 2 11:59:46 2024 +0200 <> Philipp Samfass <[email protected]> 9d1eb6fbf feat(chrono): add support for gfx1100 which has a 100 Mhz realtime TSC <> Mon Sep 30 17:15:43 2024 +0200 <> Philipp Samfass <[email protected]> 22c122096 Fixed memory_resource tests to use hip instead of cuda in their include path <> Tue Oct 1 07:13:39 2024 +0000 <> monoatamd <[email protected]> 69ce859c3 Merge pull request #35 from AMD-AI/feat/fix_raft_duplicate_symbol <> Fri Sep 27 11:24:21 2024 +0200 <> Mohammad Norouzi <[email protected]> Fix duplicate symbol error that started to happen in RAFT 0f1e849f3 Fix license note <> Fri Sep 27 11:13:02 2024 +0200 <> Mohammad Norouzi <[email protected]> 3d38efbf8 Fix duplicate symbol error that started to happen in RAFT <> Fri Sep 27 08:13:38 2024 +0000 <> monoatamd <[email protected]> 37ce80e Merge pull request #34 from AMD-AI/feat/revert_license_note_changes <> Tue Sep 24 13:47:38 2024 +0200 <> Mohammad Norouzi <[email protected]> Feat/revert license note changes dd73a5e Minor typo <> Tue Sep 24 11:36:11 2024 +0000 <> monoatamd <[email protected]> 4001376 Fix more license issues <> Tue Sep 24 11:35:46 2024 +0000 <> monoatamd <[email protected]> b937204 Change more files with license changes (libhip++ to libcu++) <> Tue Sep 24 11:28:45 2024 +0000 <> monoatamd <[email protected]> b1d4b4e Revert libhip++ to libcu++ in some license notes <> Tue Sep 24 11:21:04 2024 +0000 <> monoatamd <[email protected]> a4d7f4f Merge pull request #33 from AMD-AI/feat/add_missing_license <> Mon Sep 23 19:01:15 2024 +0200 <> Mohammad Norouzi <[email protected]> Added missing AMD mod license note to some headers cb066df remove gitignore file <> Mon Sep 23 17:00:47 2024 +0000 <> monoatamd <[email protected]> 399c81a Added missing AMD mod license note to some headers <> Mon Sep 23 16:58:56 2024 +0000 <> monoatamd <[email protected]> 95e52e7 Merge pull request #32 from AMD-AI/feat/rmm_missing_headers <> Mon Sep 23 18:33:28 2024 +0200 <> Mohammad Norouzi <[email protected]> Feat/rmm missing headers 49675d0 Choose installation location considering if libhipcxx is installed stanalone or via another project. <> Thu Sep 19 11:57:32 2024 +0000 <> monoatamd <[email protected]> 0593a67 Check if fixes the issue with FIND_CUDF variable <> Thu Sep 19 11:50:26 2024 +0200 <> Mohammad Norouzi <[email protected]> 4341747 fix/partial upgrade: fix definition of _LIBCUDACXX_CPO_ACCESSIBILITY, as it would otherwise cause linker errors due to multiple definitions in dependent projects <> Thu Jun 6 04:25:41 2024 -0700 <> Philipp Samfass <[email protected]> dc82c67 Avoid warning "return value of hipGetLastError is ignored" <> Thu May 23 11:05:26 2024 +0000 <> monoatamd <[email protected]> 3029dca include missing macro <> Fri May 17 09:46:55 2024 +0000 <> monoatamd <[email protected]> 8969dff hipify memory_resource header <> Fri May 17 09:29:47 2024 +0000 <> monoatamd <[email protected]> 242226a hipify stream_ref header <> Fri May 17 09:11:27 2024 +0000 <> monoatamd <[email protected]> e712bd2 Add missing headers include/hip/memory_resource and include/hip/stream_ref which are required for RMM 24.06 <> Thu May 16 10:12:36 2024 +0000 <> monoatamd <[email protected]> f088e14 Merge pull request #31 from AMD-AI/fix_cmake_install_new <> Thu Aug 29 10:00:42 2024 +0200 <> Philipp Samfass <[email protected]> Support custom CMAKE_INSTALL_LIBDIR values of 1+ directory c124c3f Merge pull request #29 from AMD-AI/palamida <> Wed Aug 28 09:09:14 2024 +0200 <> Philipp Samfass <[email protected]> Sync internal dev branch with publicly released libhipcxx 53a17a7 Support custom CMAKE_INSTALL_LIBDIR values of 1+ directory When `CMAKE_INSTALL_LIBDIR` is set to something like `lib/aarch64/` the hard-coded logic in `libhipcxx-header-search.cmake.in` fails. <> Wed Jul 17 06:19:44 2024 -0700 <> Philipp Samfass <[email protected]> f525aca Corrected license disclaimer <> Fri May 3 07:00:43 2024 -0700 <> Philipp Samfass <[email protected]> 91c1928 Merge branch 'refactor_doc' into palamida <> Fri May 3 06:57:09 2024 -0700 <> Philipp Samfass <[email protected]> baf6f7c docu: beta release of libhipcxx documentation (ported existing libcudacxx documentation) <> Fri May 3 06:53:49 2024 -0700 <> Philipp Samfass <[email protected]> dbaad20 remove modifications copyright for file which has not been modified <> Fri May 3 06:42:09 2024 -0700 <> Philipp Samfass <[email protected]> ed8e1cd refactor: rename _LIBCUDACXX_CUDA_ABI_VERSION to _LIBHIPCXX_HIP_ABI_VERSION <> Fri May 3 06:33:40 2024 -0700 <> Philipp Samfass <[email protected]> e54658d added modifications copyright license to further files where it was missing <> Fri May 3 06:28:52 2024 -0700 <> Philipp Samfass <[email protected]> 57abc6d doc/cleanup: clean-up documentation for unsupported APIs/features <> Fri May 3 06:04:39 2024 -0700 <> Philipp Samfass <[email protected]> 3d93906 Update perform_tests.bash <> Fri May 3 13:46:25 2024 +0200 <> Philipp Samfass <[email protected]> 5bd8419 doc: revised documentation (overview + setup instructions) <> Thu May 2 09:09:17 2024 -0700 <> Philipp Samfass <[email protected]> fff2495 doc: add files needed to generate ROCm docs documentation <> Thu May 2 09:05:25 2024 -0700 <> Philipp Samfass <[email protected]> 76b10af refactor/doc: renamed _LIBCUDACXX_CUDA_API_VERSION to _LIBHIPCXX_HIP_API_VERSION <> Thu May 2 08:34:13 2024 -0700 <> Philipp Samfass <[email protected]> b97b300 doc: clean-up not needed files <> Thu May 2 08:10:17 2024 -0700 <> Philipp Samfass <[email protected]> 3aa9ad9 Update README.md <> Thu May 2 16:33:25 2024 +0200 <> Philipp Samfass <[email protected]> d2c356c Update README.md <> Thu May 2 13:50:56 2024 +0200 <> Philipp Samfass <[email protected]> 3bdfc63 restructured README.md <> Thu May 2 02:56:51 2024 -0700 <> Philipp Samfass <[email protected]> 778b39f further improvements for README.md <> Thu May 2 02:50:00 2024 -0700 <> Philipp Samfass <[email protected]> a91bde8 modifications to LICENSE in README <> Thu May 2 02:32:24 2024 -0700 <> Philipp Samfass <[email protected]> fffb51f cleanup README <> Thu May 2 02:17:32 2024 -0700 <> Philipp Samfass <[email protected]> c8e56dc remove links to internal SWDEV tickets <> Thu May 2 01:55:04 2024 -0700 <> Philipp Samfass <[email protected]> 827621b modifications license for libhipcxx-config.cmake <> Thu May 2 01:46:53 2024 -0700 <> Philipp Samfass <[email protected]> 1b4c393 added modifications license to further files in cmake/* <> Thu May 2 01:43:30 2024 -0700 <> Philipp Samfass <[email protected]> 606fada modifications license for benchmarks/* <> Thu May 2 01:40:26 2024 -0700 <> Philipp Samfass <[email protected]> ccdc6bc further adding of modifications license (CMakeLists.txt, lit.cfg*,...) <> Thu May 2 01:35:16 2024 -0700 <> Philipp Samfass <[email protected]> acbbc54 Add missing modifications license to further files <> Thu May 2 01:19:43 2024 -0700 <> Philipp Samfass <[email protected]> 5073cf8 added modifications license to further *.cpp files in .upstream-tests/* <> Thu May 2 01:14:23 2024 -0700 <> Philipp Samfass <[email protected]> d213dc0 .upstream-tests: added further missing copyright modifications license comments <> Thu May 2 00:18:07 2024 -0700 <> Philipp Samfass <[email protected]> cade8b9 added license modifications to further *.h files in .upstream-tests/* <> Tue Apr 30 09:47:03 2024 -0700 <> Philipp Samfass <[email protected]> 957255a add modifications license to several header files in .upstream-tests/* <> Tue Apr 30 08:44:37 2024 -0700 <> Philipp Samfass <[email protected]> 24b47fb add modifications license to further *.cpp files in .upstream-tests <> Tue Apr 30 08:25:57 2024 -0700 <> Philipp Samfass <[email protected]> 8d2e919 add modifications license for further *.cpp files in .upstream-tests/* <> Tue Apr 30 07:10:54 2024 -0700 <> Philipp Samfass <[email protected]> 40ce60d Added further missing modifications license to .upstream-tests/* <> Tue Apr 30 06:28:06 2024 -0700 <> Philipp Samfass <[email protected]> 167346e add missing license for examples <> Tue Apr 30 06:20:18 2024 -0700 <> Philipp Samfass <[email protected]> fba5d59 Add modifications license comment for .upstream-tests/* that use "Part of libcu++ Project" header without NVIDIA copyright notice. <> Tue Apr 30 05:38:39 2024 -0700 <> Philipp Samfass <[email protected]> 517c0d0 add modification license to *cpp upstream tests that have NVIDIA FileCopyrightText notice (without files containing file type in first line) <> Tue Apr 30 05:02:35 2024 -0700 <> Philipp Samfass <[email protected]> 0e74ae2 upstream tests: add modifications license for C++ files that do not contain file type comment and that do not contain NVIDIA copyright, dual license <> Tue Apr 30 04:19:56 2024 -0700 <> Philipp Samfass <[email protected]> 693420f fix: remove symlink from cuda->hip again, as it breaks the build of dependees such as hipDF which create a Python wheel. Instead, copy/duplicate the header files into <include_dir>/cuda directory during installation. <> Tue Apr 30 02:01:11 2024 -0700 <> Philipp Samfass <[email protected]> 6a0854f Add modification license/new license to several files <> Tue Apr 30 01:12:34 2024 -0700 <> Philipp Samfass <[email protected]> 876f077 re-add example that shows how to use chrono_sysclock workaround (missing UNIX timestamp on the device for C++20) <> Tue Apr 30 01:10:51 2024 -0700 <> Philipp Samfass <[email protected]> 8ce656e tmpfix: revert change which causes re-definition conflicts <> Mon Apr 29 08:16:43 2024 -0700 <> Philipp Samfass <[email protected]> 371c1b3 feat: add HIP example for concurrent_hash_table cleanup: remove CUDA examples <> Mon Apr 29 08:06:45 2024 -0700 <> Philipp Samfass <[email protected]> 5765d5c further cleanup <> Mon Apr 29 07:54:36 2024 -0700 <> Philipp Samfass <[email protected]> dd2cbb2 tmpfix: disable further unsupported tests with hipcc <> Mon Apr 29 06:14:01 2024 -0700 <> Philipp Samfass <[email protected]> a6c0af0 further cleanup of CUDA-/NVIDIA-specific files <> Mon Apr 29 05:57:21 2024 -0700 <> Philipp Samfass <[email protected]> 68e2a66 cleanup further CUDA/NVIDIA-specific files <> Mon Apr 29 05:01:25 2024 -0700 <> Philipp Samfass <[email protected]> cded55d cleanup: docker files that are currently CUDA-specific and that have not been ported <> Mon Apr 29 05:00:18 2024 -0700 <> Philipp Samfass <[email protected]> 49ca96a feat: add namespace alias cuda == hip to facilitate porting of applications/libraries that depend on libhipcxx <> Mon Apr 29 04:57:44 2024 -0700 <> Philipp Samfass <[email protected]> 273222c revise README.md <> Mon Apr 29 04:36:35 2024 -0700 <> Philipp Samfass <[email protected]> 132a816 CMakeLists.txt: Abort with error if CUDA language/backend is used, as it is currently not supported in libhipcxx. <> Mon Apr 29 04:21:52 2024 -0700 <> Philipp Samfass <[email protected]> b2ce469 Add symlink from cuda -> hip, so that includes with prefix "cuda" (e.g. #include <cuda/std/atomic>) work without source code changes on HIP/AMD. <> Mon Apr 29 04:17:49 2024 -0700 <> Philipp Samfass <[email protected]> 9fda01e delete NVIDIA-licensed source code files <> Mon Apr 29 02:05:21 2024 -0700 <> Philipp Samfass <[email protected]> c381718 LICENSE.txt: add MIT license, remove NVIDIA license <> Mon Apr 29 02:04:48 2024 -0700 <> Philipp Samfass <[email protected]> fb46b59 remove HIP examples <> Thu Apr 4 05:40:22 2024 -0700 <> Philipp Samfass <[email protected]> bf68096 restore original .gitignore <> Thu Apr 4 05:37:28 2024 -0700 <> Philipp Samfass <[email protected]> 9645d7a remove no longer supported CI actions <> Thu Apr 4 05:34:29 2024 -0700 <> Philipp Samfass <[email protected]> fb91d45 remove HIP benchmarks <> Thu Apr 4 05:12:49 2024 -0700 <> Philipp Samfass <[email protected]> 70a3632 add license to README.md <> Thu Apr 4 05:03:04 2024 -0700 <> Philipp Samfass <[email protected]> d28972a re-add original libcudacxx LICENSE.TXT <> Thu Apr 4 04:51:58 2024 -0700 <> Philipp Samfass <[email protected]> 24bfdcc Merge pull request #26 from AMD-AI/add_cdna3_support <> Mon Mar 25 12:05:09 2024 +0100 <> Philipp Samfass <[email protected]> CDNA3 support for libhipcxx 618ae65 Update alloc_convert_copy.fail.cpp <> Mon Mar 25 12:03:56 2024 +0100 <> Philipp Samfass <[email protected]> 133757d war/tmpfix: disable currently unsupported test with hipcc <> Tue Mar 12 08:33:30 2024 -0500 <> Philipp Samfass <[email protected]> 32dabf7 fix: syntax warning <> Tue Mar 12 08:24:34 2024 -0500 <> Philipp Samfass <[email protected]> 36eb72f war/fix: -stdc++20 seems presently not supported for HIP as a device function can't use new at the moment, see https://<redacted>libhipcxx/issues/25 <> Tue Mar 12 07:41:15 2024 -0500 <> Philipp Samfass <[email protected]> a3bf846 doc(README): add MI300 arch <> Tue Mar 12 04:23:42 2024 -0500 <> Philipp Samfass <[email protected]> 789d6a1 maint/feat: Add necessary TSC clockrate definitions for MI300 <> Tue Mar 12 04:22:54 2024 -0500 <> Philipp Samfass <[email protected]> a35b57b feat(maintenance): add architectures gfx940 gfx941 gfx942 to build system <> Mon Mar 11 09:11:49 2024 -0700 <> Philipp Samfass <[email protected]> b5c23eb doc (README): make user aware that more recent lit versions are currently not supported (requires maintenance) <> Mon Mar 11 09:11:19 2024 -0700 <> Philipp Samfass <[email protected]> 0297d2b Merge pull request #24 from AMD-AI/rocm-6.0 <> Wed Jan 10 14:19:53 2024 +0100 <> Philipp Samfass <[email protected]> fix/war for ROCm 6.0: Resolve header guard conflict between libhipcxx and rocthrust 90fe908 fix/war: ROCm 6.0 includes nv/target as part of rocthrust which causes a conflict with the libhipcxx nv/target and nv/detail/__target__macros header guards (same guard name). We therefore rename the header guards in libhipcxx. <> Tue Dec 19 06:20:24 2023 -0800 <> Philipp Samfass <[email protected]> 12b2c75 Merge pull request #23 from AMD-AI/war_missing_typedefs_hiprtc <> Sun Sep 17 00:33:48 2023 +0200 <> ADiL <[email protected]> Fix: WAR for missing typedefs with HIPRTC 2f25fe9 Added a workaround for missing typedefs when libhipcxx headers are JIT-compiled with HIPRTC. See SWDEV-421819 <> Wed Sep 13 10:35:11 2023 +0000 <> Philipp Samfass <[email protected]> 81c8aac Merge pull request #22 from AMD-AI/fix_compiler_macros <> Mon Sep 11 19:48:40 2023 +0200 <> ADiL <[email protected]> Fix: compiler macros 6876082 fix: fixed compiler macros for selecting compilation path w/o HIP_RTC; this fixes several compiler errors when building the headers <> Mon Sep 11 13:13:35 2023 +0000 <> Philipp Samfass <[email protected]> 77ed3be Merge pull request #20 from AMD-AI/hiprtc <> Wed Aug 30 10:15:08 2023 +0200 <> ADiL <[email protected]> Hiprtc b3472da Add hiprtc compilation path <> Fri Aug 18 10:04:26 2023 +0000 <> mnorouzi <[email protected]> 619f29b Merge pull request #19 from AMD-AI/fixes_for_rocm_5_6 <> Wed Jul 26 11:05:07 2023 +0200 <> ADiL <[email protected]> Fixes for rocm 5 6 509499e Merge pull request #18 from AMD-AI/fixes_for_rocm_5_6 <> Tue Jul 25 16:43:42 2023 +0200 <> ADiL <[email protected]> Fixes for ROCm 5.6 1ab5888 1) deleted duplicate header files 2) Fixed failing test std/utilities/meta/meta.unary/meta.unary.prop/is_constructible.pass.cpp: Here, a fallback implementation for is_constructible is tested which is not needed for hip. Some change between ROCm 5.5 and 5.6 makes this fallback implementation fail. Since we do not need the fallback implementation, we will disable this test for now, just like it has been done for MVCC. <> Tue Jul 25 12:20:07 2023 +0000 <> Philipp Samfass <[email protected]> 29ed3e1 Merge pull request #17 from AMD-AI/dev <> Tue Jul 11 16:32:06 2023 +0200 <> ADiL <[email protected]> Merge dev and main for first beta release 7a5ee88 Merge pull request #16 from AMD-AI/refactoring <> Tue Jul 11 14:33:06 2023 +0200 <> ADiL <[email protected]> Remove deprecated todos fc92066 Merge pull request #15 from AMD-AI/readme <> Tue Jul 11 14:32:17 2023 +0200 <> ADiL <[email protected]> Add README 801876d Update README.md <> Tue Jul 11 09:47:20 2023 +0200 <> Philipp Samfass <[email protected]> 3cb8270 Update README.md <> Tue Jul 11 09:37:11 2023 +0200 <> Philipp Samfass <[email protected]> Minor edits + fix formatting a98dc96 Update readme to include limitations, tickets, atomics usage, etc. <> Mon Jul 10 16:44:10 2023 +0000 <> monoatamd <[email protected]> 561316b Merge branch 'dev' of github.com:AMD-AI/libhipcxx into readme <> Mon Jul 10 14:04:39 2023 +0000 <> monoatamd <[email protected]> 1aebbd9 Remove deprecated todos <> Mon Jul 10 07:28:07 2023 +0000 <> monoatamd <[email protected]> 7fb2c0c Merge pull request #14 from AMD-AI/fixes_for_rocm_5_5 <> Thu Jun 22 12:29:25 2023 +0200 <> ADiL <[email protected]> Fix build and tests for ROCm 5.5 6c52029 Update README.md <> Thu Jun 22 10:08:41 2023 +0200 <> Philipp Samfass <[email protected]> 979c5ef fix compiler errors with ROCm 5.5: The new clang compiler has additional features that would break the functionality of LIBCUDACXX, use LIBCUDACXX implementations instead. <> Thu Jun 15 13:18:53 2023 +0200 <> Philipp Samfass <[email protected]> ad1781b fix: missing semicolon <> Thu Jun 15 13:16:16 2023 +0200 <> Philipp Samfass <[email protected]> 6b4f8cd Merge pull request #13 from AMD-AI/revise_nanosleep <> Thu May 11 18:24:45 2023 +0200 <> ADiL <[email protected]> Revise nanosleep 88c8dbd fixed test that was failing for wrong reason <> Thu May 11 15:32:34 2023 +0200 <> Philipp Samfass <[email protected]> b4e0f4a Merge branch 'dev' into revise_nanosleep <> Wed May 10 18:16:40 2023 +0200 <> Philipp Samfass <[email protected]> 39184f3 Merge pull request #12 from AMD-AI/refactoring <> Tue May 9 18:00:36 2023 +0200 <> ADiL <[email protected]> Major Refactoring b4a84f0 fixed variable name <> Mon May 8 10:23:07 2023 +0200 <> Philipp Samfass <[email protected]> bad0c56 Update README.md <> Mon May 8 10:11:41 2023 +0200 <> Philipp Samfass <[email protected]> ad7340b started to revise readme <> Mon May 8 09:29:50 2023 +0200 <> Philipp Samfass <[email protected]> e8f8345 added an improved implementation of nanosleep for AMD GPUs, which is less fine-granular but uses S_SLEEP to block the waves for some cycles <> Mon May 8 08:30:24 2023 +0200 <> Philipp Samfass <[email protected]> 0e86c48 bug: replace cuda with hip in some tests <> Tue May 2 13:56:34 2023 +0000 <> monoatamd <[email protected]> 2e4db76 Merge branch 'dev' into refactoring <> Tue May 2 14:50:55 2023 +0200 <> Mohammad Norouzi <[email protected]> abca790 change from LIBHIPCXX_CUDA_COMPILER to more generic name LIBHIPCXX_GPU_COMPILER <> Tue May 2 13:31:52 2023 +0200 <> Philipp Samfass <[email protected]> ece320b Merge pull request #11 from AMD-AI/feature/tuple_implementation <> Tue May 2 11:28:28 2023 +0200 <> ADiL <[email protected]> Feature/tuple implementation d22152c Update alloc_convert_copy.fail.cpp <> Tue May 2 09:10:56 2023 +0200 <> Philipp Samfass <[email protected]> 1a961df feat: Support more tests and comments for unsprtd <> Fri Apr 28 16:16:32 2023 +0000 <> monoatamd <[email protected]> b0e12e9 refactored naming in lit testing helper script <> Fri Apr 28 12:16:19 2023 +0200 <> Philipp Samfass <[email protected]> a82cb0a further refactoring of lit test configuration naming + renamed generated Makefile target from check-cudacxx to check-hipcxx <> Fri Apr 28 11:48:04 2023 +0200 <> Philipp Samfass <[email protected]> 6c1bad3 renamed user facing CMake configuration options <> Thu Apr 27 16:52:45 2023 +0200 <> Philipp Samfass <[email protected]> 1f3b597 fix CMake issues and change from cuda to hip in examples <> Thu Apr 27 12:39:02 2023 +0200 <> Philipp Samfass <[email protected]> a4c5242 Merge branch 'dev' into refactoring <> Thu Apr 27 12:01:20 2023 +0200 <> Philipp Samfass <[email protected]> ab16059 change namespace name from cuda to hip <> Thu Apr 27 11:58:00 2023 +0200 <> Philipp Samfass <[email protected]> ca306bd bug: Rewind changes in alloc_convert_copy.fail.cpp <> Thu Apr 27 08:36:47 2023 +0000 <> monoatamd <[email protected]> 33f1be9 feat: Support more tests <> Thu Apr 27 08:29:28 2023 +0000 <> monoatamd <[email protected]> d76c328 renamed include paths to "#include <hip/*>", adapted CMake header-only tests <> Thu Apr 27 09:52:00 2023 +0200 <> Philipp Samfass <[email protected]> 35c52c9 Merge pull request #10 from AMD-AI/feature/hip_examples <> Thu Apr 27 04:02:46 2023 +0200 <> ADiL <[email protected]> Feature/hip examples 2afcb70 renamed CMake target from libcudacxx to libhipcxx <> Wed Apr 26 10:40:14 2023 +0200 <> Philipp Samfass <[email protected]> 47af8d6 feat: Add benchmarking for more atomics <> Tue Apr 25 14:12:12 2023 +0000 <> monoatamd <[email protected]> 0d04123 added house age computation and filtering based on chrono to demonstrator scenario + some cosmetic adjustments <> Tue Apr 25 12:47:27 2023 +0200 <> Philipp Samfass <[email protected]> 77a63dc feat: Add example for sprint 3 demo <> Mon Apr 24 16:28:06 2023 +0000 <> monoatamd <[email protected]> 80e7367 Merge branch 'dev' of github.com:AMD-AI/libhipcxx into feature/hip_examples <> Mon Apr 24 09:00:03 2023 +0000 <> monoatamd <[email protected]> cc683e0 Merge pull request #8 from AMD-AI/feature/numerics <> Fri Apr 21 22:48:57 2023 +0200 <> ADiL <[email protected]> Feature/numerics 8ec6ab0 Merge branch 'dev' into feature/numerics <> Fri Apr 21 14:50:06 2023 +0200 <> Mohammad Norouzi <[email protected]> 492a531 removed thread fence examples <> Fri Apr 21 14:16:12 2023 +0200 <> Philipp Samfass <[email protected]> 4eb9b60 added example app for demonstrating safe arithmetic operations to hip examples <> Fri Apr 21 14:14:45 2023 +0200 <> Philipp Samfass <[email protected]> abf447b added demonstration example for system_clock workaround (C++20, HIP) to CMakeLists.txt <> Fri Apr 21 14:09:03 2023 +0200 <> Philipp Samfass <[email protected]> 460aca1 fix: Restructure directories in benchmarks <> Fri Apr 21 09:07:28 2023 +0000 <> monoatamd <[email protected]> 41b451e Merge branch 'dev' of github.com:AMD-AI/libhipcxx into feature/hip_examples <> Fri Apr 21 08:45:36 2023 +0000 <> monoatamd <[email protected]> e898359 Merge pull request #7 from AMD-AI/feature/chrono <> Fri Apr 21 09:34:19 2023 +0200 <> Philipp Samfass <[email protected]> HIP support for chrono time library c146f3b Merge branch 'dev' into feature/chrono <> Fri Apr 21 09:16:12 2023 +0200 <> Philipp Samfass <[email protected]> 2d417a1 feat: Add benchmarks for performance on reals <> Thu Apr 20 17:03:05 2023 +0000 <> monoatamd <[email protected]> 8dd78a1 Merge pull request #9 from AMD-AI/feature/type_traits_implementation <> Thu Apr 20 15:17:31 2023 +0200 <> Philipp Samfass <[email protected]> feat: Fix unsupported tests 8993108 feat: Fix unsupported tests <> Thu Apr 20 12:12:03 2023 +0000 <> monoatamd <[email protected]> 1b15682 enabled further passing tests <> Thu Apr 20 12:49:38 2023 +0200 <> Philipp Samfass <[email protected]> 9499db9 enabled an additional test that is now supported <> Thu Apr 20 12:19:49 2023 +0200 <> Philipp Samfass <[email protected]> 2e5e486 Merge pull request #6 from AMD-AI/chrono_device_sysclock_unix_timestamp_cpp20 <> Wed Apr 19 21:06:42 2023 +0200 <> ADiL <[email protected]> Add workaround for missing UNIX timestamp counter on device for chrono::system_clock 762b377 removed obsolete file <> Wed Apr 19 14:28:42 2023 +0200 <> Philipp Samfass <[email protected]> 2ffba17 improved output of demonstrator for safe arithmetic operations using libhipcxx <> Wed Apr 19 12:30:22 2023 +0200 <> Philipp Samfass <[email protected]> 852d4c7 re-added justification on unsupported test case that got lost previously <> Wed Apr 19 11:56:02 2023 +0200 <> Philipp Samfass <[email protected]> 072af6f Refactored code and initialized sysclock state in constant memory for HIP implementation <> Wed Apr 19 11:05:44 2023 +0200 <> Philipp Samfass <[email protected]> d67e660 Merge pull request #5 from AMD-AI/feature/atomic_implementation <> Tue Apr 18 18:28:44 2023 +0200 <> ADiL <[email protected]> Feature/atomic implementation f0b4144 fixed a macro that was causing a compiler error for one test <> Tue Apr 18 17:26:11 2023 +0200 <> Philipp Samfass <[email protected]> 9fa587a Added HIP example to demonstrate the workaround for enabling a system_clock with UNIX time epoch on AMD devices. <> Tue Apr 18 13:26:38 2023 +0200 <> Philipp Samfass <[email protected]> 3d1866b fixed conversion of host time period to device time period <> Tue Apr 18 13:20:45 2023 +0200 <> Philipp Samfass <[email protected]> adcd125 Merge branch 'feature/chrono' into chrono_device_sysclock_unix_timestamp_cpp20 <> Tue Apr 18 12:51:42 2023 +0200 <> Philipp Samfass <[email protected]> 9586351 switch to more portable wall_clock64 from s_memrealtime <> Tue Apr 18 10:54:22 2023 +0200 <> Philipp Samfass <[email protected]> 717f7bf Switch to wall_clock64 as s_memrealtime is not available on all devices. Added comment that HIP nanosleep implementation is only supported for gfx90a and gfx908 up to now. <> Tue Apr 18 10:02:53 2023 +0200 <> Philipp Samfass <[email protected]> 1396e56 added demonstration example for safe arithmetic operations that uses cuda::std::numeric_limits <> Mon Apr 17 15:13:17 2023 +0200 <> Philipp Samfass <[email protected]> 7197a26 reenable test functor for double <> Mon Apr 17 14:54:45 2023 +0200 <> Philipp Samfass <[email protected]> f6d5adf Comment regarding the review <> Mon Apr 17 14:25:53 2023 +0200 <> Mohammad Norouzi <[email protected]> 3d196b3 feat: Add benchmarking for atomics on ints <> Fri Apr 14 16:10:25 2023 +0000 <> monoatamd <[email protected]> 7a5aa52 added justification on why a numerics-related test case is unsupported for HIP <> Fri Apr 14 14:55:08 2023 +0200 <> Philipp Samfass <[email protected]> 36941d6 added another now supported test for atomics <> Fri Apr 14 14:10:59 2023 +0200 <> Philipp Samfass <[email protected]> b632c42 1) renamed cuda_thread_count and hip_thread_count to gpu_thread_count 2) disabled two atomics tests which are not supported due to not having implemented cuda::std::chrono::system_clock for HIP <> Fri Apr 14 12:32:28 2023 +0200 <> Philipp Samfass <[email protected]> 7813d4e Merge branch 'dev' into feature/atomic_implementation <> Fri Apr 14 11:38:08 2023 +0200 <> Mohammad Norouzi <[email protected]> 0471a3b made failing chrono-related test unsupported as it has not been implemented yet <> Fri Apr 14 10:36:41 2023 +0200 <> Philipp Samfass <[email protected]> ab9de07 added JIRA ticket that documents missing support for __nanosleep <> Fri Apr 14 10:33:43 2023 +0200 <> Philipp Samfass <[email protected]> 46d895f added HIP example for chrono timestamp processing <> Thu Apr 13 16:15:12 2023 +0200 <> Philipp Samfass <[email protected]> 09d0bcb bug: Add comment for underaligned types <> Thu Apr 13 13:20:36 2023 +0000 <> monoatamd <[email protected]> d1f1675 renamed atomics_thread_fence and included it as a target into CMakeLists.txt <> Wed Apr 12 15:35:10 2023 +0200 <> Philipp Samfass <[email protected]> 5a110da Merge branch 'feature/hip_examples' of github.com:AMD-AI/libhipcxx into feature/hip_examples <> Wed Apr 12 15:31:31 2023 +0200 <> Philipp Samfass <[email protected]> 3e227df Added hipified concurrent_hash_table example + basic CMakeLists.txt <> Wed Apr 12 15:30:51 2023 +0200 <> Philipp Samfass <[email protected]> 5389297 feat: Import Dominic's atomics benchmarking <> Wed Apr 12 12:24:43 2023 +0000 <> monoatamd <[email protected]> e70ea02 feat: test thread_fence <> Wed Apr 12 11:29:57 2023 +0000 <> monoatamd <[email protected]> a0337c9 Created new directory for HIP examples, moved CUDA examples into separate folder and added HIP example for reductions of housing prices (libhipcxx atomics). <> Wed Apr 12 13:18:46 2023 +0200 <> Philipp Samfass <[email protected]> 0289625 fixed documentation of system_clock workaround for C++20 and HIP <> Wed Apr 12 12:05:06 2023 +0200 <> Philipp Samfass <[email protected]> feff1b2 revised documentation for chrono system_clock workaround that provides UNIX timestamps on the device <> Tue Apr 11 15:23:07 2023 +0200 <> Philipp Samfass <[email protected]> 63eadc5 fixed failing chrono test by making the expected-error-re regular expression match the actual error message <> Tue Apr 11 13:28:24 2023 +0200 <> Philipp Samfass <[email protected]> 0200ba5 Disabled static assert in one chrono-related test for ctime for HIP. It fails because of a mismatch in the signatures (return type) of the function definition of clock() in the amd_device_functions.h header file and the declaration of that function in the time.h system header. <> Tue Apr 11 12:43:12 2023 +0200 <> Philipp Samfass <[email protected]> d8618bf Made experimental workaround implementation of system_clock for HIP and C++20 non-default, added documentation and improved error handling. <> Thu Apr 6 16:31:09 2023 +0200 <> Philipp Samfass <[email protected]> f4793e6 Merge pull request #4 from AMD-AI/feature/ci_for_c++20 <> Wed Apr 5 17:25:38 2023 +0200 <> ADiL <[email protected]> Load more recent compiler for CI to enable support for c++20 839c1f2 Load more recent compiler for CI to enable support for c++20 <> Wed Apr 5 14:37:03 2023 +0200 <> Philipp Samfass <[email protected]> 9af273f minor fix of TSC-related macro name in __threading_support <> Wed Apr 5 14:32:05 2023 +0200 <> Philipp Samfass <[email protected]> ee20a76 First implementation of system_clock based on s_memrealtime clock (25 MHz on gfx908,gfx90a). This is WIP. It has the limitation that s_memrealtime does not return a UNIX timestamp. Therefore, the implementation is not conforming to the C++20 standard. <> Wed Apr 5 14:26:51 2023 +0200 <> Philipp Samfass <[email protected]> 9b7bdd2 activated chrono-related tests (chrono implementation is WIP) <> Wed Apr 5 14:24:54 2023 +0200 <> Philipp Samfass <[email protected]> 597732a Starting with C++20, system_clock needs to return an UNIX timestamp. This POC implementation of chrono:system_clock relies on obtaining an initial UNIX timestamp from the host to implement a system_clock that uses UNIX timestamps on the device. It is a prototype that can be extended in the future in case UNIX timestamps are needed on the device. <> Wed Apr 5 09:18:59 2023 +0200 <> Philipp Samfass <[email protected]> 3a4b61c Merge pull request #3 from AMD-AI/feature/pretty_test_output <> Tue Mar 28 14:58:08 2023 +0200 <> Mohammad Norouzi <[email protected]> Pretty testing output 9f7ff9a removed no longer needed echo statement <> Tue Mar 28 12:03:11 2023 +0200 <> Philipp Samfass <[email protected]> 0ab7bdd This commit adds a --pretty option to the bash testing script for the libhipcxx tests. It is helpful for instance for demonstration purposes. <> Tue Mar 28 11:58:08 2023 +0200 <> Philipp Samfass <[email protected]> 646271a bug: Fix macro definition in atomic tests <> Tue Mar 28 08:54:38 2023 +0000 <> monoatamd <[email protected]> ba5faa6 Update macros to select local memory <> Mon Mar 27 13:10:24 2023 +0000 <> monoatamd <[email protected]> 56ad293 Merge branch 'feature/atomic_implementation' of github.com:AMD-AI/libhipcxx into feature/atomic_implementation <> Fri Mar 24 15:21:51 2023 +0100 <> Philipp Samfass <[email protected]> 073fcee feat: activated additional atomics-related tests <> Fri Mar 24 15:21:24 2023 +0100 <> Philipp Samfass <[email protected]> 63046ce Update cuda_space_selector.h <> Fri Mar 24 13:33:21 2023 +0100 <> Philipp Samfass <[email protected]> Added JIRA ticket number to comment on workaround for the issue of atomics not working in local memory for 8-byte datatypes. 8f944be Select strong or weak CAS based on boolean argument passed to function. Note: this may be further optimized using templates. <> Fri Mar 24 12:47:11 2023 +0100 <> Philipp Samfass <[email protected]> 744874c Added ticket ID for failing __hip_atomic_fetch_(min/max/or/xor/and) with hipMallocManaged. <> Fri Mar 24 11:04:28 2023 +0100 <> Philipp Samfass <[email protected]> a83e327 Feat: added support for heterogeneous atomic tests. FIXME: The __hip_atomic_fetch_(max,min,or,xor,and) builtins are not returning the correct value if the atomic is allocated in managed memory with hipMallocManaged. The corresponding tests have been deactivated until a fix for this issue becomes available. <> Thu Mar 23 18:01:39 2023 +0100 <> Philipp Samfass <[email protected]> f2dc2d9 Added a workaround nanosleep implementation as a nanosleep PTX equivalent is missing on AMD CDNA: FIXME: In lack of a clock rate independent nanosleep ISA instruction on gfx90a and gfx908, we use s_memrealtime that runs at a fixed clock rate of 25 MHz to simulate a nanosleep. Each cycle of the 25 MHz clock has a duration of 40 ns, which is the granularity of this method. <> Tue Mar 21 17:22:53 2023 +0100 <> Philipp Samfass <[email protected]> 146db46 fixed compilation macros in two atomics tests <> Tue Mar 21 16:25:40 2023 +0100 <> Philipp Samfass <[email protected]> a00e271 Merge pull request #2 from AMD-AI/feature/tests_with_hip <> Tue Mar 21 14:41:06 2023 +0100 <> ADiL <[email protected]> Feature/tests with hip 31d545e bugfix: alloc device shared mem for 8-byte types <> Thu Mar 16 08:15:08 2023 +0000 <> monoatamd <[email protected]> ec7e300 disabled two unsupported tests <> Wed Mar 15 17:57:24 2023 +0100 <> Philipp Samfass <[email protected]> e3810ce minor bug: made two failing chrono-related tests unsupported <> Wed Mar 15 16:12:31 2023 +0100 <> Philipp Samfass <[email protected]> c25caf9 minor cleanup/cosmetics <> Wed Mar 15 15:14:28 2023 +0100 <> Philipp Samfass <[email protected]> ad81c64 cosmetics: replace CUDA by HIP in force_include_hip.h header <> Wed Mar 15 14:49:32 2023 +0100 <> Philipp Samfass <[email protected]> 0461037 revert accidental commit of commented tests <> Wed Mar 15 13:38:19 2023 +0100 <> Philipp Samfass <[email protected]> ce48336 enabled more atomic tests <> Wed Mar 15 13:21:00 2023 +0100 <> Philipp Samfass <[email protected]> 52ff7f8 bug: use shred mem for 8-byte types allctd locally <> Wed Mar 15 12:16:55 2023 +0000 <> monoatamd <[email protected]> 98d79d7 cmake: set CUDA compiler ID for hipcc <> Wed Mar 15 09:13:04 2023 +0100 <> Philipp Samfass <[email protected]> c277d46 minor bug: fixed filename for CI <> Wed Mar 15 09:08:57 2023 +0100 <> Philipp Samfass <[email protected]> 1142f0e minor bug: fixed compiler warnings CI: enable atomic tests for CI <> Wed Mar 15 08:55:47 2023 +0100 <> Philipp Samfass <[email protected]> 01b6848 minor bug: made chrono sysclock test unsupported <> Mon Mar 13 18:17:54 2023 +0100 <> Philipp Samfass <[email protected]> d4c54a5 feat: add atomics, except local_memory_selector <> Mon Mar 13 17:14:56 2023 +0000 <> monoatamd <[email protected]> 38ab7d3 fixed missing cuda:: in error message <> Mon Mar 13 17:50:00 2023 +0100 <> Philipp Samfass <[email protected]> 3661a36 Merge branch 'feature/tests_with_hip' into feature/atomic_implementation <> Mon Mar 13 16:25:09 2023 +0000 <> monoatamd <[email protected]> e3b7dfb remove nvcc-lit-note and fixed 5 more tests (low-hanging fruits), made two tests that require more investigation unsupported for now <> Mon Mar 13 17:10:20 2023 +0100 <> Philipp Samfass <[email protected]> 9a862a3 fixed regex in iterator_traits test for clang-verify <> Mon Mar 13 12:50:12 2023 +0100 <> Philipp Samfass <[email protected]> 9d0a7b1 Change back to expected-error from nvcc-lit-error for clang-verify tests, but ignore additional unexpected errors emitted by hipcc for the clang-verify pass. This change fixes .fail.cpp tests that would just fail because of additional unexpected errors (although the expected errors are printed) with HIP. Yet, some tests are still failing because they do *not* return the expected compiler errors. We need to fix them individually. <> Fri Mar 10 18:47:27 2023 +0100 <> Philipp Samfass <[email protected]> 873c755 Disabled a deprecation test for hipcc which fails due to cuda::std::experimental not being declared. This test is not critical for functionality but may have to be revisited at a later point. <> Fri Mar 10 15:02:46 2023 +0100 <> Philipp Samfass <[email protected]> 2737373 disabled further unsupported tests (latch & atomics) <> Fri Mar 10 14:23:52 2023 +0100 <> Philipp Samfass <[email protected]> 1fd80b2 minor bug: fixed nullptr_t test <> Fri Mar 10 11:06:52 2023 +0000 <> monoatamd <[email protected]> 02f51ba revert accidentally commited change on failing experimental test <> Fri Mar 10 12:00:24 2023 +0100 <> Philipp Samfass <[email protected]> be6b9e7 made atomics-related tests unsupported as support for atomics hasn't been implemented <> Fri Mar 10 11:55:57 2023 +0100 <> Philipp Samfass <[email protected]> 3771d6c feat: add cuda path for tuple, span, array <> Wed Mar 8 13:21:45 2023 +0000 <> monoatamd <[email protected]> b7c2e64 feat: add cuda path for pairs & heter. tests <> Mon Mar 6 15:42:57 2023 +0000 <> monoatamd <[email protected]> 6ed8978 made types.fail.cpp test unsupported as it tests for CUDA-specific compiler behavior <> Thu Mar 2 18:14:07 2023 +0100 <> Philipp Samfass <[email protected]> 03846c7 fixed warnings and fixed issues with two tests <> Thu Mar 2 16:46:56 2023 +0100 <> Philipp Samfass <[email protected]> ac6705a feat: impl. fetch_add and load for int and float <> Thu Mar 2 09:47:07 2023 +0000 <> monoatamd <[email protected]> 167909c feat: fix host calls in host device [cmplx number] <> Thu Mar 2 09:19:21 2023 +0000 <> monoatamd <[email protected]> c91cafc CI: fix path <> Wed Mar 1 17:19:43 2023 +0100 <> Philipp Samfass <[email protected]> 08ee221 CI: attempt to fix path to test script <> Wed Mar 1 17:15:17 2023 +0100 <> Philipp Samfass <[email protected]> 66c2994 CI: fix workflow yaml file <> Wed Mar 1 17:05:52 2023 +0100 <> Philipp Samfass <[email protected]> a1d6dc3 added testing of supported tests to CI <> Wed Mar 1 17:02:43 2023 +0100 <> Philipp Samfass <[email protected]> ed1a212 This commit renders several LIT tests unsupported which use APIs that are not yet ported to HIP. We will step-by-step enable those tests again as we add the HIP-support for different APIs to libhipcxx. <> Tue Feb 28 13:39:21 2023 +0100 <> Philipp Samfass <[email protected]> ba04212 feat: complete adding cuda path to build system <> Mon Feb 27 17:39:21 2023 +0000 <> monoatamd <[email protected]> 411c5e4 feat: include CUDA compilation path by default <> Fri Feb 24 14:31:35 2023 +0000 <> monoatamd <[email protected]> 51db828 added feature flags for gfx architecture, set feature flags with hipcc for lit testing correctly <> Fri Feb 24 14:58:54 2023 +0100 <> Philipp Samfass <[email protected]> 3d2a0e0 added CDNA architecture detection to LIT building and testing <> Fri Feb 24 14:07:15 2023 +0100 <> Philipp Samfass <[email protected]> e5dc0e5 set default libstdc++ for stdlib_under_test when using hipcc (https://github.com/RadeonOpenCompute/ROCm_Documentation/blob/master/Programming_Guides/HIP-porting-guide.rst#libc-and-libstdc) <> Fri Feb 24 09:37:24 2023 +0100 <> Philipp Samfass <[email protected]> 392717e chore: add gitignore <> Thu Feb 23 15:03:46 2023 +0000 <> monoatamd <[email protected]> 5c9b196 make CMake abort when trying to enable both CUDA and HIP support <> Thu Feb 23 15:13:28 2023 +0100 <> Philipp Samfass <[email protected]> 37a6840 apply workaround for HIPCC issue, so that all "fake main" functions are compiled for both host and device <> Thu Feb 23 14:53:11 2023 +0100 <> Philipp Samfass <[email protected]> 1543da8 merging CI functionality into this branch <> Thu Feb 23 13:14:09 2023 +0100 <> Philipp Samfass <[email protected]> Merge branch 'dev' into feature/tests_with_hip 2889a0c Merge pull request #1 from AMD-AI/feature/github-ci <> Thu Feb 23 12:50:01 2023 +0100 <> ADiL <[email protected]> Feature/GitHub CI 3e42b97 1) found workaround for hipcc compilation error where __host__ __device__ declaration is ignored and main function is only compiled for host 2) added workaround to some test files 3) removed libc++ from linking command when compiling with hipcc <> Thu Feb 23 12:11:39 2023 +0100 <> Philipp Samfass <[email protected]> 862f5ee changed name of workflow build run for github CI <> Wed Feb 22 16:56:43 2023 +0100 <> Philipp Samfass <[email protected]> fec8683 added build workflow (WIP) <> Wed Feb 22 16:54:41 2023 +0100 <> Philipp Samfass <[email protected]> eedddd8 Initial modifications to CMake build and lit testing infrastructure (WIP) Lit tests are being built with hipcc, but there are yet compiler errors to fix. <> Wed Feb 22 14:03:37 2023 +0100 <> Philipp Samfass <[email protected]> da591af Update github-actions-demo.yml <> Tue Feb 21 16:50:49 2023 +0100 <> Philipp Samfass <[email protected]> Test self-hosted runner 484dac0 Added GitHub Actions example <> Tue Feb 21 09:07:33 2023 +0100 <> Philipp Samfass <[email protected]> 2e9ba13 Delete LICENSE.TXT <> Fri Feb 17 19:31:26 2023 +0100 <> ADiL <[email protected]> 013a759 Update README.md <> Tue Feb 14 17:30:34 2023 +0100 <> ADiL <[email protected]> Co-authored-by: psamfass <[email protected]> Co-authored-by: domcharrier <[email protected]> Co-authored-by: monoatamd <[email protected]> Co-authored-by: reger-men <[email protected]>
- Loading branch information
4 people
committed
Dec 9, 2024
0 parents
commit 6710086