AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13,501 Commits 3 Branches 0 Tags
e56ff3716d7b8d04ee60e42d2ebb6ebf5d0d58db
Commit Graph

13501 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Nagaraj, Sriraksha 4282aa31d9 Adding att v3 support (#84) 
* Adding att v3 support

* misc fix

* bug fix

* Python linting workflow and rules

* fix regex

* Adding temporary args

* fix temporary args

* fix format

* remove att_perfcounters from test input

* Review comments (#163)

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>

* Revert "Review comments (#163)"

This reverts commit 9ef0f8e5a4489d5581255e1b70ced2aef5c1c1d0.

* Address review comments 2

* review changes

* review comments

* review

* cmake alias

* review

* review

* review

* review

* Enabling percounter in v3 script

* review

* formatting

* formatting

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Baraldi, Giovanni <Giovanni.Baraldi@amd.com>
Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>

[ROCm/rocprofiler-sdk commit: d4a51e4102]
 2025-02-04 04:05:38 -06:00
Nagaraj, Sriraksha d4a51e4102 Adding att v3 support (#84) 
* Adding att v3 support

* misc fix

* bug fix

* Python linting workflow and rules

* fix regex

* Adding temporary args

* fix temporary args

* fix format

* remove att_perfcounters from test input

* Review comments (#163)

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>

* Revert "Review comments (#163)"

This reverts commit 9ef0f8e5a4489d5581255e1b70ced2aef5c1c1d0.

* Address review comments 2

* review changes

* review comments

* review

* cmake alias

* review

* review

* review

* review

* Enabling percounter in v3 script

* review

* formatting

* formatting

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Baraldi, Giovanni <Giovanni.Baraldi@amd.com>
Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
 2025-02-04 04:05:38 -06:00
Madsen, Jonathan 6c773a7616 Fix HSA_AMD_MEMORY_POOL_EXECUTABLE_FLAG for ROCm < 6.3 (#178) 
Fix HSA_AMD_MEMORY_POOL_EXECUTABLE_FLAG for ROCm < 6.4

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 72a27feb04]
 2025-02-04 04:05:19 -06:00
Madsen, Jonathan 72a27feb04 Fix HSA_AMD_MEMORY_POOL_EXECUTABLE_FLAG for ROCm < 6.3 (#178) 
Fix HSA_AMD_MEMORY_POOL_EXECUTABLE_FLAG for ROCm < 6.4

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2025-02-04 04:05:19 -06:00
Madsen, Jonathan 6cb0dda8ba Fix async memory copy validation tests (#182) 
* Fix async copy validation test

- make the async copy tracing test work regardless of however many HSA memory copies the HIP memory copy decomposes into

* Fix rocprofv3 memory copy tests

* Fix compilation support for hipGraphBatchMemOpNodeGetParams

* Fix rocprofv3-test-summary-*-validate

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 7fcd80f744]
 2025-02-04 02:41:19 -06:00
Madsen, Jonathan 7fcd80f744 Fix async memory copy validation tests (#182) 
* Fix async copy validation test

- make the async copy tracing test work regardless of however many HSA memory copies the HIP memory copy decomposes into

* Fix rocprofv3 memory copy tests

* Fix compilation support for hipGraphBatchMemOpNodeGetParams

* Fix rocprofv3-test-summary-*-validate

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2025-02-04 02:41:19 -06:00
ajanicijamd aab094f1db Added libamd_comgr.so to internal modules and fix argument parsing module in Timemory (#96) 
Updates Timemory submodule

[ROCm/rocprofiler-systems commit: fc5b325979]
 2025-02-03 14:43:14 -05:00
ajanicijamd fc5b325979 Added libamd_comgr.so to internal modules and fix argument parsing module in Timemory (#96) 
Updates Timemory submodule
 2025-02-03 14:43:14 -05:00
Vignesh Edithal e68c297cb2 Use github app for develop to amd-staging sync 
* Use the token for rocprofiler-compute-runner github app to perform
  auth to bypass amd-staging branch protection


[ROCm/rocprofiler-compute commit: 25b6bbbb3c]
 2025-02-03 13:41:14 -05:00
Vignesh Edithal 25b6bbbb3c Use github app for develop to amd-staging sync 
* Use the token for rocprofiler-compute-runner github app to perform
  auth to bypass amd-staging branch protection
 2025-02-03 13:41:14 -05:00
David Galiffi 78f1c9e179 Disable the weekly sync 
Disable the weekly sync from staging to mainline. We'll do this manually with CQE approval.

[ROCm/rocprofiler-systems commit: 80dc2efc50]
 2025-02-03 13:13:22 -05:00
David Galiffi 80dc2efc50 Disable the weekly sync 
Disable the weekly sync from staging to mainline. We'll do this manually with CQE approval.
 2025-02-03 13:13:22 -05:00
Choudhary, Rahul d70d3fb59f Create kws_caller.yml and rocm_ci_caller.yml (#1) 
Enabling per PR based KWS check and PSDB check
 2025-02-03 09:43:35 -08:00
Choudhary, Rahul fad2fcda9f Merge pull request #1 from AMD-ROCm-Internal/rahchoud_amdeng-patch-1 
Create kws_caller.yml and rocm_ci_caller.yml
 2025-02-03 09:35:08 -08:00
Young Hui - AMD 5c27ece3ff DOCs: update index and TOC to better organize how-to docs (#78) 
[ROCm/rocprofiler-systems commit: 10ba4b76de]
 2025-01-31 21:03:18 -05:00
Young Hui - AMD 10ba4b76de DOCs: update index and TOC to better organize how-to docs (#78) 2025-01-31 21:03:18 -05:00
Choudhary, Rahul 7c03610905 Update rocm_ci_caller.yml added amd-npi pull request trigger 2025-01-31 16:10:41 -08:00
Choudhary, Rahul 33ac653411 Delete .github/rocm_ci_caller.yml 2025-01-31 16:06:10 -08:00
Choudhary, Rahul 6bd1718fd1 Create rocm_ci_caller.yml 2025-01-31 16:05:53 -08:00
Choudhary, Rahul 0e1d6396cc Create rocm_ci_caller.yml 2025-01-31 15:43:24 -08:00
Choudhary, Rahul 0f7c9495f4 Create kws_caller.yml and rocm_ci_caller.yml 
Enabling ROCM CI workflow
 2025-01-31 15:42:44 -08:00
Choudhary, Rahul c603d7164c Create rocm_ci_caller.yml 2025-01-31 14:25:18 -08:00
Choudhary, Rahul 460a28ed03 Create kws_caller.yml 2025-01-31 14:22:03 -08:00
Justin Williams f106364fc7 Make README.md pretty 
Change-Id: I7c3341deaf3621ebbc9e495b023b1dd4971a5f1d
 2025-01-31 12:22:45 -06:00
Galantsev, Dmitrii bee9991c4a Revert "Dgalants/add auth script location (#108)" 
This reverts commit a70aa81cfd.
 2025-01-31 12:22:45 -06:00
Madsen, Jonathan 8c9185d725 Update HIP string formatting for ROCm 6.4.0 (#144) 
Fix HIP data type stringify

- when ROCPROFILER_CI is not defined, provide default for case statements
- Add support for hipGraphNodeTypeBatchMemOp when HIP version is >= 6.4.0

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: f3752faa0a]
 2025-01-30 20:51:52 -06:00
Madsen, Jonathan f3752faa0a Update HIP string formatting for ROCm 6.4.0 (#144) 
Fix HIP data type stringify

- when ROCPROFILER_CI is not defined, provide default for case statements
- Add support for hipGraphNodeTypeBatchMemOp when HIP version is >= 6.4.0

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2025-01-30 20:51:52 -06:00
cfallows-amd 8c5db3f1d8 Upgrade ROCm-SMI to AMD SMI (#86) 
* Integrating amd-smi into rocprofiler-systems due to rocm-smi deprecation.
* No functionality changes to users other than naming conventions.
* New tracks available in perfetto- gpu busy percentage metrics now splits gfx busy into separate gfx, umc, and mm engine measurements.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 0c32dfd6bc]
 2025-01-30 21:32:07 -05:00
cfallows-amd 0c32dfd6bc Upgrade ROCm-SMI to AMD SMI (#86) 
* Integrating amd-smi into rocprofiler-systems due to rocm-smi deprecation.
* No functionality changes to users other than naming conventions.
* New tracks available in perfetto- gpu busy percentage metrics now splits gfx busy into separate gfx, umc, and mm engine measurements.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
 2025-01-30 21:32:07 -05:00
dependabot[bot] bdd0bd0955 Bump rocm-docs-core from 1.14.1 to 1.15.0 in /docs/sphinx (#547) 
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.14.1 to 1.15.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.14.1...v1.15.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

[ROCm/rocprofiler-compute commit: 95b600ea58]
 2025-01-30 17:25:46 -07:00
dependabot[bot] 95b600ea58 Bump rocm-docs-core from 1.14.1 to 1.15.0 in /docs/sphinx (#547) 
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.14.1 to 1.15.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.14.1...v1.15.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-01-30 17:25:46 -07:00
Kandula, Venkateshwar reddy aaad37dec1 add gfx12 for counter collection tests (#108) 
* add gfx12 for counter def.

* Update continuous_integration.yml

* Update counter_defs.yaml

* commenting logging.

* Update ioctl.cpp

* add gfx12 to tests

* Update ioctl.cpp

* Add description to GFX12 GL2C_EA_RDREQ counter

* Updates from editor

---------

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>
Co-authored-by: Kuricheti, Mythreya <Mythreya.Kuricheti@amd.com>

[ROCm/rocprofiler-sdk commit: 121901c321]
 2025-01-30 15:16:48 -06:00
Kandula, Venkateshwar reddy 121901c321 add gfx12 for counter collection tests (#108) 
* add gfx12 for counter def.

* Update continuous_integration.yml

* Update counter_defs.yaml

* commenting logging.

* Update ioctl.cpp

* add gfx12 to tests

* Update ioctl.cpp

* Add description to GFX12 GL2C_EA_RDREQ counter

* Updates from editor

---------

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>
Co-authored-by: Kuricheti, Mythreya <Mythreya.Kuricheti@amd.com>
 2025-01-30 15:16:48 -06:00
Madsen, Jonathan 0a735d1684 Partial fix of legacy rocprofiler project name (#110) 
* Partial fix of legacy rocprofiler project name

* Formatting fix

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 1f49d6c57b]
 2025-01-30 13:43:35 -06:00
Madsen, Jonathan 1f49d6c57b Partial fix of legacy rocprofiler project name (#110) 
* Partial fix of legacy rocprofiler project name

* Formatting fix

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2025-01-30 13:43:35 -06:00
Kuricheti, Mythreya 5dbb3b2f80 Fix navi48 counter event IDs (#158) 
* Initial fix for navi48 counters

* Add GL2C navi4x gfx12 counters

[ROCm/rocprofiler-sdk commit: d43070bf08]
 2025-01-30 13:40:25 -06:00
Kuricheti, Mythreya d43070bf08 Fix navi48 counter event IDs (#158) 
* Initial fix for navi48 counters

* Add GL2C navi4x gfx12 counters
 2025-01-30 13:40:25 -06:00
sonadeem ff01f62777 cmake: Fix BUILD_SHARED_LIBS option and README for it 
BUILD_SHARED_LIBS is a global flag so we don't need to set a default
option for it in both libhsakmt and hsa-runtime, only the top level
CMakeLists file. Also updated README to reflect that libhsakmt is
always built statically and gets linked to libhsa-runtime.

Change-Id: I1511f68a268032bec9758bc731d8074f33ec980f
 2025-01-30 14:17:27 -05:00
Elwazir, Ammar c5b75976c6 SLES Git Safe Directory (#177) 
* Update continuous_integration.yml

* Updates from editor

[ROCm/rocprofiler-sdk commit: acab62706b]
 2025-01-30 12:32:58 -06:00
Elwazir, Ammar acab62706b SLES Git Safe Directory (#177) 
* Update continuous_integration.yml

* Updates from editor
 2025-01-30 12:32:58 -06:00
Pryor, Adam a70aa81cfd Dgalants/add auth script location (#108) 
* DOCS: Add authentication scripts location

Change-Id: Ie285d80ea6d9bb8f710998208d0aa7c6db661d02
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>

* Make README.md pretty (#44)

Change-Id: I7c3341deaf3621ebbc9e495b023b1dd4971a5f1d

---------

Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Co-authored-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Co-authored-by: Williams, Justin <Justin.Williams@amd.com>
 2025-01-30 12:08:11 -06:00
Galantsev, Dmitrii 4da277a64e DOCS: Add authentication scripts location (#96) 
Change-Id: Ie285d80ea6d9bb8f710998208d0aa7c6db661d02

Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2025-01-30 12:06:18 -06:00
Kuricheti, Mythreya 33a480d38e Generate code coverage comment as collapsible summary (#169) 
* Generate codecoverage comment as collapsible summary

* Tweak markdown formatting

[ROCm/rocprofiler-sdk commit: 58ecbd83a9]
 2025-01-30 12:04:07 -06:00
Kuricheti, Mythreya 58ecbd83a9 Generate code coverage comment as collapsible summary (#169) 
* Generate codecoverage comment as collapsible summary

* Tweak markdown formatting
 2025-01-30 12:04:07 -06:00
dependabot[bot] ba360d552c Bump rocm-docs-core[api_reference] from 1.14.1 to 1.15.0 in /docs/sphinx (#94) 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.14.1 to 1.15.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.14.1...v1.15.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

[ROCm/rocprofiler-systems commit: af3a8f695f]
 2025-01-30 11:59:56 -05:00
dependabot[bot] af3a8f695f Bump rocm-docs-core[api_reference] from 1.14.1 to 1.15.0 in /docs/sphinx (#94) 
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.14.1 to 1.15.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.14.1...v1.15.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-01-30 11:59:56 -05:00
David Belanger f24d789dee kfdtest: Convert ExtendedCuMask test to multi-GPU framework 
Convert test to use multi-GPU framework.

Add mutex to fix intermixed log issue and annotate logging with
gpu node number.

Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: Ic2beeadb1eb4b5a9a0710ac1dbd60b9bf1d84c33
 2025-01-30 11:41:00 -05:00
Galantsev, Dmitrii a8d479c147 CMAKE - Fix ABSL in clang18+ (#106) 
Please see:
- https://github.com/abseil/abseil-cpp/issues/1747
- https://github.com/llvm/llvm-project/issues/102443

When GRPC is compiled with different compiler from RDC - ABI broke.
Possibly because some templates were not instantiated.
Setting '-fclang-abi-compat=17' fixes the issue.

Change-Id: Ic6409cf413c87b135f334e5b03145cb1c63356d4

Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2025-01-30 10:33:58 -06:00
Pryor, Adam af56e460c4 SWDEV-500382 fix energy consumed (#105) 
Change-Id: I3f180f34abed763db1287bf01581753534f32828

Signed-off-by: adapryor <Adam.pryor@amd.com>
 2025-01-30 09:38:00 -06:00
David Galiffi 06f81ac26d Update CODEOWNERS (#91) 
Use GitHub Org Teams

[ROCm/rocprofiler-systems commit: 8deebb607b]
 2025-01-29 16:55:39 -05:00