AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
76,333 Commits 3 Branches 0 Tags
develop
Commit Graph

76333 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ammar ELWazir e6a4ad787a SWDEV-466390: Adding License for roctx, docs, tests packages (#1174) 
* Adding License for roctx, docs, tests packages

* Fixing Docs/ROCTx packages

* Fixing roctx path

[ROCm/rocprofiler-sdk commit: d269c845ae]
 2024-11-05 13:38:55 -06:00
Ammar ELWazir d269c845ae SWDEV-466390: Adding License for roctx, docs, tests packages (#1174) 
* Adding License for roctx, docs, tests packages

* Fixing Docs/ROCTx packages

* Fixing roctx path
 2024-11-05 13:38:55 -06:00
David Galiffi 42d64232af Merge pull request #466 from ROCm/dgaliffi/sync-main-with-stg 
Omniperf v3.0.0 in prep for ROCm 6.3.0

[ROCm/rocprofiler-compute commit: 71bc463921]
 2024-11-05 13:53:20 -05:00
David Galiffi 71bc463921 Merge pull request #466 from ROCm/dgaliffi/sync-main-with-stg 
Omniperf v3.0.0 in prep for ROCm 6.3.0
 2024-11-05 13:53:20 -05:00
meserve-amd 4467e50453 SWDEV-470692: Fix parsing of unknown API records 
- A valid trace is now given even if an individual entry in an API trace
  does not contain a parameter list
- Previously an "unknown" record in an API trace would cause the entire
  output to be discarded

Change-Id: I29bf6df2cf58a231d836aafb37fbde9c5d85512f
 2024-11-05 12:48:35 -05:00
meserve-amd f3aaad1687 SWDEV-470692: Fix parsing of unknown API records 
- A valid trace is now given even if an individual entry in an API trace
  does not contain a parameter list
- Previously an "unknown" record in an API trace would cause the entire
  output to be discarded

Change-Id: I29bf6df2cf58a231d836aafb37fbde9c5d85512f


[ROCm/rocprofiler commit: 4467e50453]
 2024-11-05 12:48:35 -05:00
David Galiffi 38da6b266a Merge branch 'amd-staging' into dgaliffi/sync-main-with-stg 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>


[ROCm/rocprofiler-compute commit: f0ccace29b]
 2024-11-05 11:21:47 -05:00
David Galiffi f0ccace29b Merge branch 'amd-staging' into dgaliffi/sync-main-with-stg 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2024-11-05 11:21:47 -05:00
Fei Zheng 03ffa7a756 Merge pull request #460 from feizheng10/doc_warp_efficency 
Fix PoP of VALU Active Threads with wave_size

[ROCm/rocprofiler-compute commit: b4f9b38e99]
 2024-11-05 09:00:59 -07:00
Fei Zheng b4f9b38e99 Merge pull request #460 from feizheng10/doc_warp_efficency 
Fix PoP of VALU Active Threads with wave_size
 2024-11-05 09:00:59 -07:00
David Galiffi 7eaaa83024 Fix for proto files not being viewable in Perfetto UI (#16) 
- Fix for proto files not being viewable in Perfetto UI
  - Ported from https://github.com/ROCm/omnitrace/pull/411

- Update Workflows

- Use V47 trace_processor_shell for certain OS releases.
  - RedHat 8, SUSE 15.5, and Ubuntu 20.04 are no longer compatible with the latest trace_processor_shell.
  - Incompatible version of GLIBC.

- Remove notes about Perfetto workaround in documentation.

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 21d9ab79fd]
 2024-11-05 10:14:25 -05:00
David Galiffi 21d9ab79fd Fix for proto files not being viewable in Perfetto UI (#16) 
- Fix for proto files not being viewable in Perfetto UI
  - Ported from https://github.com/ROCm/omnitrace/pull/411

- Update Workflows

- Use V47 trace_processor_shell for certain OS releases.
  - RedHat 8, SUSE 15.5, and Ubuntu 20.04 are no longer compatible with the latest trace_processor_shell.
  - Incompatible version of GLIBC.

- Remove notes about Perfetto workaround in documentation.

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2024-11-05 10:14:25 -05:00
gilbertlee-amd 71809e8bc0 Updating RCCL Replayer README (#1408) 
[ROCm/rccl commit: cb1027de97]
 2024-11-05 08:06:11 -07:00
gilbertlee-amd cb1027de97 Updating RCCL Replayer README (#1408) 2024-11-05 08:06:11 -07:00
Benjamin Welton 0568f772ab Kernel Serialization Documentation (#1167) 
* Kernel Serialization Documentation

Added docs for kernel serialization.

* Update counter_collection_services.md

* correcting counter collection mode names

* correcting counter collection modes naming

---------

Co-authored-by: Gopesh Bhardwaj <gopesh.bhardwaj@amd.com>

[ROCm/rocprofiler-sdk commit: dc6a568ec5]
 2024-11-05 09:00:11 -06:00
Benjamin Welton dc6a568ec5 Kernel Serialization Documentation (#1167) 
* Kernel Serialization Documentation

Added docs for kernel serialization.

* Update counter_collection_services.md

* correcting counter collection mode names

* correcting counter collection modes naming

---------

Co-authored-by: Gopesh Bhardwaj <gopesh.bhardwaj@amd.com>
 2024-11-05 09:00:11 -06:00
Peter Park 5a30a05800 Fix changelog heading 
Signed-off-by: Peter Park <peter.park@amd.com>


[ROCm/rocprofiler-compute commit: 6a381d8966]
 2024-11-05 09:07:57 -05:00
Peter Park 6a381d8966 Fix changelog heading 
Signed-off-by: Peter Park <peter.park@amd.com>
 2024-11-05 09:07:57 -05:00
srawat 162fb23187 Update CHANGELOG.md (#1181) 
[ROCm/rocprofiler-sdk commit: 216f724e9a]
 2024-11-05 18:11:57 +05:30
srawat 216f724e9a Update CHANGELOG.md (#1181) 2024-11-05 18:11:57 +05:30
Vladana Stojiljkovic 353bb4ac4d SWDEV-479312 - Implement tests for hipMemcpy2DArrayToArray 
Change-Id: Id42557aefa0a887799402503c8905ee4cd322629


[ROCm/hip-tests commit: 558cbfd829]
 2024-11-05 04:06:26 -05:00
Vladana Stojiljkovic 558cbfd829 SWDEV-479312 - Implement tests for hipMemcpy2DArrayToArray 
Change-Id: Id42557aefa0a887799402503c8905ee4cd322629
 2024-11-05 04:06:26 -05:00
Vladana Stojiljkovic f6f7b7cf9c SWDEV-478205 - Implement tests for hipTexRefSetMaxAnisotropy 
Change-Id: I0ef580ea9be685ab83c9ee29193eae4aa0813d3a


[ROCm/hip-tests commit: e53b31db23]
 2024-11-05 02:47:37 -05:00
Vladana Stojiljkovic e53b31db23 SWDEV-478205 - Implement tests for hipTexRefSetMaxAnisotropy 
Change-Id: I0ef580ea9be685ab83c9ee29193eae4aa0813d3a
 2024-11-05 02:47:37 -05:00
Marko Arandjelovic 712ee64a1a SWDEV-478801 - Add unit test for hipMemcpyDtoA 
Change-Id: Ia0f606294574c43b5e84438a33eda4c43bd0acbc


[ROCm/hip-tests commit: 04ad40156c]
 2024-11-05 02:40:33 -05:00
Marko Arandjelovic 04ad40156c SWDEV-478801 - Add unit test for hipMemcpyDtoA 
Change-Id: Ia0f606294574c43b5e84438a33eda4c43bd0acbc
 2024-11-05 02:40:33 -05:00
Ajay 2bca736134 SWDEV-495842 - use find_program clang, llvm-mc instead of hip_package 
Helps in needing minimum files to build hip runtime on windows

Change-Id: I1d27b72d3b0551b9261524606f08361d00463394


[ROCm/clr commit: aa4f27c29b]
 2024-11-04 23:09:11 -05:00
Ajay aa4f27c29b SWDEV-495842 - use find_program clang, llvm-mc instead of hip_package 
Helps in needing minimum files to build hip runtime on windows

Change-Id: I1d27b72d3b0551b9261524606f08361d00463394
 2024-11-04 23:09:11 -05:00
Brandon Potter 17f9e07ecc Add tiled fine-grained unit tests 
[ROCm/rocshmem commit: d241015e0f]
 2024-11-04 17:16:07 -06:00
Brandon Potter d241015e0f Add tiled fine-grained unit tests 2024-11-04 17:16:07 -06:00
fei.zheng f1c9c686ff fix PoP of VALU Active Threads with wave_size 
Signed-off-by: fei.zheng <fei.zheng@amd.com>


[ROCm/rocprofiler-compute commit: 1b37572b4a]
 2024-11-04 14:31:52 -07:00
fei.zheng 1b37572b4a fix PoP of VALU Active Threads with wave_size 
Signed-off-by: fei.zheng <fei.zheng@amd.com>
 2024-11-04 14:31:52 -07:00
darren-amd 61258b9a9f remove undefined computeColl declaration 
[ROCm/rccl commit: ebf0417e90]
 2024-11-04 13:42:01 -05:00
darren-amd ebf0417e90 remove undefined computeColl declaration 2024-11-04 13:42:01 -05:00
Marko Arandjelovic a02d7f921d SWDEV-479213 - Add unit test for hipMemcpyHtoAAsync 
Change-Id: I698eb2f7b73db439c1082ef79e2e5b5462e8fd1e


[ROCm/hip-tests commit: 003707116b]
 2024-11-04 12:43:54 -05:00
Marko Arandjelovic 003707116b SWDEV-479213 - Add unit test for hipMemcpyHtoAAsync 
Change-Id: I698eb2f7b73db439c1082ef79e2e5b5462e8fd1e
 2024-11-04 12:43:54 -05:00
Jaydeep Patel 83b098f3e0 SWDEV-482400 - Use correct way to add delay/wait on GPU. 
Change-Id: Id1610227c97cc43d289f8c3a04c0c53707ccef48


[ROCm/hip-tests commit: 23eead4e7b]
 2024-11-04 12:07:52 -05:00
Jaydeep Patel 23eead4e7b SWDEV-482400 - Use correct way to add delay/wait on GPU. 
Change-Id: Id1610227c97cc43d289f8c3a04c0c53707ccef48
 2024-11-04 12:07:52 -05:00
saurabhAMD 69d976532b GPU allocation for CPX Unit Tests using PCI bus id (#1403) 
* mapping devices wrt pci

* Gpu allocation by using pci mapping

* Passing gpuPriorityOrder in as an argument rather than making the functions non-static.

* Removing redundant testBed instance calling

[ROCm/rccl commit: 69b2b712ab]
 2024-11-04 10:51:00 -06:00
saurabhAMD 69b2b712ab GPU allocation for CPX Unit Tests using PCI bus id (#1403) 
* mapping devices wrt pci

* Gpu allocation by using pci mapping

* Passing gpuPriorityOrder in as an argument rather than making the functions non-static.

* Removing redundant testBed instance calling
 2024-11-04 10:51:00 -06:00
Marko Arandjelovic a8b1c12007 SWDEV-452308 - Enable Unit_hipVoteSync_All 
Change-Id: If989e2d1cf609f3f644b8adfb6d31100a8a5ed7a


[ROCm/hip-tests commit: 862b8d6d1f]
 2024-11-04 11:47:23 -05:00
Marko Arandjelovic 862b8d6d1f SWDEV-452308 - Enable Unit_hipVoteSync_All 
Change-Id: If989e2d1cf609f3f644b8adfb6d31100a8a5ed7a
 2024-11-04 11:47:23 -05:00
Brandon Potter 74dec9374d Convert simple fine tests into parameterized tests 
[ROCm/rocshmem commit: 749d9f0781]
 2024-11-04 10:46:50 -06:00
Brandon Potter 749d9f0781 Convert simple fine tests into parameterized tests 2024-11-04 10:46:50 -06:00
corey-derochie-amd ad1384bea1 Hide or fix all build warnings (#1331) 
* Changing C-strings to be const.

* Changed variable-length arrays to std::vector to avoid warnings. VLA is a compiler extension.

* Changed `#define` inside functions into `constexpr int` to preserve scoping and avoid macro redefinition warnings.

* Disabled warnings for modifying `CMAKE_CXX_FLAGS` caused by `check_symbol_exists`, which temporarily modifies the flag to do a compile check.

* Fixed VLA in rccl UT.

[ROCm/rccl commit: 1c45962273]
 2024-11-04 09:46:42 -07:00
corey-derochie-amd 1c45962273 Hide or fix all build warnings (#1331) 
* Changing C-strings to be const.

* Changed variable-length arrays to std::vector to avoid warnings. VLA is a compiler extension.

* Changed `#define` inside functions into `constexpr int` to preserve scoping and avoid macro redefinition warnings.

* Disabled warnings for modifying `CMAKE_CXX_FLAGS` caused by `check_symbol_exists`, which temporarily modifies the flag to do a compile check.

* Fixed VLA in rccl UT.
 2024-11-04 09:46:42 -07:00
Vladana Stojiljkovic 5e41c48966 SWDEV-478472 - Fix tests to return hipErrorInvalidChannelDescriptor instead of hipErrorUnknown 
Change-Id: I1dc3af072aed813173cc12e9976a34ddf8c7d6a8


[ROCm/hip-tests commit: 5fa9900949]
 2024-11-04 11:25:54 -05:00
Vladana Stojiljkovic 5fa9900949 SWDEV-478472 - Fix tests to return hipErrorInvalidChannelDescriptor instead of hipErrorUnknown 
Change-Id: I1dc3af072aed813173cc12e9976a34ddf8c7d6a8
 2024-11-04 11:25:54 -05:00
Jaydeep Patel 9e080a303c SWDEV-483355 - hipDrvMemcpy2DUnaligned is not supported for inter GPU copy without p2p access. 
Change-Id: Ie484efc5779b139e5ca2d504342fb49edfb6b30c


[ROCm/hip-tests commit: 7aff6567b7]
 2024-11-04 11:23:39 -05:00
Jaydeep Patel 7aff6567b7 SWDEV-483355 - hipDrvMemcpy2DUnaligned is not supported for inter GPU copy without p2p access. 
Change-Id: Ie484efc5779b139e5ca2d504342fb49edfb6b30c
 2024-11-04 11:23:39 -05:00