AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
74,778 Commits 3 Branches 0 Tags
b5e4074c7883c97ea13ea2ad63fa34367906d439
Commit Graph

74778 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
gilbertlee-amd bb85692891 Enabling gdrcopy option for gfx950 (#1955) 
[ROCm/rccl commit: fedddb452c]
 2025-10-15 10:55:25 -06:00
gilbertlee-amd fedddb452c Enabling gdrcopy option for gfx950 (#1955) 2025-10-15 10:55:25 -06:00
Venkateshwar Reddy Kandula 9404178ea5 [rocprofiler-sdk][CI] rhel sles workflow fix (#1373) 
* bug fix.

* add backslash

* add export for path, bug
 2025-10-15 11:48:59 -05:00
alex-breslow-amd 455d516dc4 [gfx950] Make bypassing __threadfence the default for multinode. (#1947) 
* Gate based on ROCM version, safe for ROCm 7.0.2 and beyond.
* Updates naming to gfx9CheapFenceOff since we use this for gfx942 and gfx950.  Thanks Nilesh.
* Add info logging statement to NCCL_INIT to print whether enabled when INFO logging is enabled.

[ROCm/rccl commit: c70f5b4621]
 2025-10-15 09:15:36 -07:00
alex-breslow-amd c70f5b4621 [gfx950] Make bypassing __threadfence the default for multinode. (#1947) 
* Gate based on ROCM version, safe for ROCm 7.0.2 and beyond.
* Updates naming to gfx9CheapFenceOff since we use this for gfx942 and gfx950.  Thanks Nilesh.
* Add info logging statement to NCCL_INIT to print whether enabled when INFO logging is enabled.
 2025-10-15 09:15:36 -07:00
adapryor a64e9b4ac4 [SWDEV-560778] Update gpu metrics factory to return a new pointer every time 2025-10-15 11:00:44 -05:00
adapryor cda730140f [SWDEV-560778] Update gpu metrics factory to return a new pointer every time 
[ROCm/amdsmi commit: a64e9b4ac4]
 2025-10-15 11:00:44 -05:00
Mythreya Kuricheti ac8adbacff [CI][rocprofiler-sdk] Fix codeql jobs (#1366) 2025-10-15 10:34:29 -05:00
Saurabh Verma 946385d0ff Reverts #1379 and properly migrates the docs (#1381) 
Reverts #1379 and properly migrates the docs

---------

Co-authored-by: Matt Williams <matt.williams@amd.com>
 2025-10-15 10:48:27 -04:00
Saurabh Verma b6a187aed1 migrate aqlprofile docs 7.0.1 from standalone repo (#1379) 
This PR migrates the aqlprofile/docs folder from standalone repo to monorepo
Link to the docs branch:
https://github.com/ROCm/aqlprofile/commits/docs/7.0.1

---------

Co-authored-by: Matt Williams <matt.williams@amd.com>
Co-authored-by: pbhandar-amd <138039281+pbhandar-amd@users.noreply.github.com>
 2025-10-15 10:01:36 -04:00
Gerardo Hernandez fc5551a724 SWDEV-536360 - fix another bullet point in reduce sync operations section not being displayed on its own line (#1374) 2025-10-15 14:51:43 +01:00
Danylo Lytovchenko 59a30bb117 Add ignore revs file (#1126) 
* Add ignore revs file

* Fix rev file name
 2025-10-15 13:57:56 +02:00
ajanicijamd 259ef6348b Fixed issues with nic-performance test (#1168) 
- On some hosts the wget can finish too soon and PAPI doesn't catch even a single network event.
- On some hosts, there are multiple default NICs and the scripts didn't work in that case.
- The test script was writing the output of wget to /tmp directory, which causes a problem if another user tries to run the same test. Because the output file with the same name already exists in the same directory, but with a different owner, the test fails

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
 2025-10-14 23:45:08 -04:00
Gerardo Hernandez bfbc48bb0e SWDEV-536360 - fix bullet points in reduce sync operations section not being displayed on different lines in the browser (#1346) 2025-10-14 22:02:34 +01:00
axie_amdeng dde482d224 rocr: unitialized size variable caused huge memory/space allocation (#1232) 
Signed-off-by: Alex Xie <AlexBin.Xie@amd.com>
 2025-10-14 16:57:10 -04:00
Mythreya Kuricheti 765d9026c7 [CI][rocprofiler-sdk] Workflow improvements (#1341) 2025-10-14 15:21:55 -05:00
Ajay GunaShekar 0ac37de373 SWDEV-555665 - fix hip-tests for windows (#1028) 
* SWDEV-555665 -enable fixed windows tests
 2025-10-14 08:39:49 -07:00
isaki001 6d151d4e21 gfx950 channel tuning for ReduceScatter and AllGather (#1940) 
* add channel thresholds to override channel-count adjustments

[ROCm/rccl commit: 0f99fd84a3]
 2025-10-14 09:50:44 -05:00
isaki001 0f99fd84a3 gfx950 channel tuning for ReduceScatter and AllGather (#1940) 
* add channel thresholds to override channel-count adjustments
 2025-10-14 09:50:44 -05:00
Satyanvesh Dittakavi 9d32badcb7 SWDEV-545950 - Update indentation in hip_prof_str.h for hipStreamCopyAttributes (#1352) 2025-10-14 17:35:17 +05:30
Ioannis Assiouras 538ebc5409 SWDEV-556877 - Ensure pinned memory is released if hsa copy fails (#1137) 2025-10-14 10:08:49 +01:00
amd-srinivas1 092279449e SWDEV-546345-[catch2][dtest]-Tests for hipMemSetD2DXX Apis(Memory management) (#896) 
* SWDEV-546345-Added tests for memsetd2dxx apis

* SWDEV-546345-Optimized the code.

* SWDEV-546345-Optimized the code.

* SWDEV-546345-Addressed review comments

* SWDEV-546345-Updated code.
 2025-10-14 10:47:59 +05:30
SaleelK cc18890fe8 clr: Reset barrier_value_packet_ at init (#1162) 2025-10-13 22:01:46 -07:00
Wenkai Du 75a69211a0 Add all_reduce_bias_perf to support All Reduce with Bias (#130) 
Use dynamic symbol loading of ncclAllReduceWithBias

Co-authored-by: mberenjk <146776561+mberenjk@users.noreply.github.com>

[ROCm/rccl-tests commit: db6ea5a594]
 2025-10-13 16:09:10 -05:00
Wenkai Du db6ea5a594 Add all_reduce_bias_perf to support All Reduce with Bias (#130) 
Use dynamic symbol loading of ncclAllReduceWithBias

Co-authored-by: mberenjk <146776561+mberenjk@users.noreply.github.com>
 2025-10-13 16:09:10 -05:00
mberenjk 433251272b fixing the ar_with_bias test issue when running rccl-tests (#1912) 
* fixing the AR_With_Bias issue when running rccl-tests

[ROCm/rccl commit: e738c03e39]
 2025-10-13 13:58:21 -07:00
mberenjk e738c03e39 fixing the ar_with_bias test issue when running rccl-tests (#1912) 
* fixing the AR_With_Bias issue when running rccl-tests
 2025-10-13 13:58:21 -07:00
alex-breslow-amd d51ed2fdfd Dump compiler-determined GPU kernel resource usage (#1965) 
Adds --kernel-resource-use flag to install.sh to allow dumping per-GPU kernel resource use at compile time (e.g., VGPRs, LDS, SGPRs, scratch, etc.)


[ROCm/rccl commit: ff209e5b19]
 2025-10-13 11:24:42 -05:00
alex-breslow-amd ff209e5b19 Dump compiler-determined GPU kernel resource usage (#1965) 
Adds --kernel-resource-use flag to install.sh to allow dumping per-GPU kernel resource use at compile time (e.g., VGPRs, LDS, SGPRs, scratch, etc.)
 2025-10-13 11:24:42 -05:00
vstojilj f964f45902 SWDEV-553920 - Disable and fix failing tests (#1133) 2025-10-13 16:38:27 +02:00
vstojilj bfedf63575 SWDEV-552537 - Fix nvidia build failures (#1125) 
* SWDEV-552537 - Fix nvidia build failures

* Add string header to fix hip-tests

---------

Co-authored-by: Branislav Brzak <branislav.brzak@amd.com>
Co-authored-by: Danylo Lytovchenko <danylo.lytovchenko@amd.com>
 2025-10-13 09:20:17 +02:00
amd-srinivas1 b86b676514 SWDEV-553447-[catch2][dtest]-Add hipDeviceMallocUncached to hipMemCreate and hipMemMap flags (#857) 
* SWDEV-547367-Updated tests to work with hipMemAllocationTypeUncached

* SWDEV-553447-Updated tests of hipMemMap

* SWDEV-553447-Resolved merge conflicts

---------

Co-authored-by: jainprad <92369414+jainprad@users.noreply.github.com>
 2025-10-12 22:05:02 +05:30
Satyanvesh Dittakavi 46e683d41a SWDEV-545950 - Add hipStreamCopyAttributes API Implementation (#914) 
* SWDEV-545950 - Add hipStreamCopyAttributes API Implementation

* Add unit test for hipStreamCopyAttributes API

* Add ChangeLog and nvidia mapping for the API

* Update rocprofiler-sdk with new HIP API details

* [rocprofiler-sdk] handle hipStreamCopyAttributes in stream tracing service

- this new HIP function has multiple stream arguments and needs to be skipped because it does not have an explicit create/destroy/set functionality

* Update HIP_RUNTIME_API_TABLE_STEP_VERSION in clr and rocprofiler-sdk

* Resolve merge conflicts

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2025-10-12 19:57:05 +05:30
Geo Min 3ead4ca4a1 fixing group id (#1975) 
[ROCm/rccl commit: 97f2665da2]
 2025-10-10 16:40:44 -07:00
Geo Min 97f2665da2 fixing group id (#1975) 2025-10-10 16:40:44 -07:00
David Yat Sin 7f79d0febc rocr: Set signal memory allocations to NonPaged (#1219) 
Set memory allocation to non-paged to avoid issues caused when CP tries
to access signals after page has been migrated.
 2025-10-10 17:35:15 -04:00
Mythreya Kuricheti 24a62a2ab3 [rocprofiler-sdk] Add codeowner for api-trace.h (#1933) 
[ROCm/rccl commit: 3000f0e837]
 2025-10-10 16:29:17 -05:00
Mythreya Kuricheti 3000f0e837 [rocprofiler-sdk] Add codeowner for api-trace.h (#1933) 2025-10-10 16:29:17 -05:00
Arm Patinyasakdikul 0407f294e9 Fix unroll factor display bug. (#1969) 
[ROCm/rccl commit: ff75860d73]
 2025-10-10 15:35:06 -05:00
Arm Patinyasakdikul ff75860d73 Fix unroll factor display bug. (#1969) 2025-10-10 15:35:06 -05:00
Jason Bonnell 082e7adb81 Updated VERSION regex for tarball in Dockerfiles (#1321) 2025-10-10 15:37:13 -04:00
jamessiddeley-amd 64375c23d0 [rocprof-compute] Improve standalone roofline plot generation (#1298) 
* ruff formatting

* Update roofline.py function descriptions

* Update height calculation

* Add back cache level filtering in gui_analysis

* Update roofline_calc.py to take in ai_data for ceiling length calc

* format roofline.py

* update roof test cases

* update roofline legend plot table

* fix pdf generate cutoff

---------

Co-authored-by: cfallows-amd <Carrie.Fallows@amd.com>
 2025-10-10 14:23:23 -04:00
David Yat Sin 7f2ef6a602 rocr: Return error on signal alloc failure (#1310) 
Return HSA_STATUS_ERROR_OUT_OF_RESOURCES when signal allocation fails.
 2025-10-10 14:06:31 -04:00
amd-srinivas1 6b8a4a23ba SWDEV-546345-[catch2][dtest]- Tests for memCpyBatchAsync Apis(Memory management) (#1117) 
* SWDEV-546345-Added tests for Batch memCpy apis.

* Updated tests to use multiple data types

* SWDEV-546345-Updated tests for different data types

* SWDEV-546345-Updated clang-format

* SWDEV-546345-Updated hipMemcpy3DBatchAsync parameter

* SWDEV-546345 - Updated hipMemcpy3DBatchAsync tests with hipMemLocationTypeHost

---------

Co-authored-by: Rahul Manocha <rmanocha@amd.com>
Co-authored-by: Rambabu Swargam <rambabu.swargam@amd.com>
Co-authored-by: jainprad <92369414+jainprad@users.noreply.github.com>
 2025-10-10 22:03:06 +05:30
Istvan Kiss 51452b643f Revise the section on CU & WGP modes (#1255) 2025-10-10 09:14:03 -07:00
akolliasAMD fc73e4f858 added dl on the list of linked libraries (#275) 
[ROCm/rocshmem commit: 4ecdbc026c]
 2025-10-10 09:12:59 -06:00
akolliasAMD 4ecdbc026c added dl on the list of linked libraries (#275) 2025-10-10 09:12:59 -06:00
Giovanni Lenzi Baraldi 29f8b2c636 [aqlprofile] Bump TT2 header (#1118) 2025-10-10 13:54:38 +02:00
systems-assistant[bot] 9021b43cd1 SWDEV-546347-Added tests for Module Management APIs (#539) 
* SWDEV-546347-Added tests for hipModuleGetFunctionCount

* SWDEV-546347-Added tests for hipModuleLoadFatBinary

* SWDEV-546347-Added 3 more tests for hipModuleLoadFatBinary

* SWDEV-546347-Updated hipModuleLoadFatBinary.cc

* SWDEV-546347-Added test for hipModuleGetLoadingMode API

* SWDEV-546347-Clang-format issues

* SWDEV-546347-Removed tests of hipModuleGetLoadingMode API

* SWDEV-546347 - Updated CMake file

* SWDEV-546347-Addressed review comments

* SWDEV-546347-Updated CmakeLists

* SWDEV-546347-Addressed review comments

* SWDEV-546347-Addressed Review comments

---------

Co-authored-by: SrinivasRao Gollamandala <Srinivasarao.Gollamandala@amd.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
Co-authored-by: jainprad <92369414+jainprad@users.noreply.github.com>
Co-authored-by: Rambabu Swargam <rambabu.swargam@amd.com>
 2025-10-10 15:29:20 +05:30
Satyanvesh Dittakavi 446fbd3191 SWDEV-557093 - Add hip catch test using nested tile partition (#1180) 2025-10-10 13:16:43 +05:30