0406493ae0
Merge commit 'b5e1645a1476ea48ceeb601076ccb0714cc2948b' into develop
2025-08-06 01:30:06 +00:00
b5e1645a14
Fix hsa_code_object_app test deadlock with profiler serialization ( #577 )
...
Problem with original test:
- Created circular dependencies between queues:
* Queue1: Kernel A → Barrier(waits for signal_2) → Kernel C
* Queue2: Barrier(waits for signal_1) → Kernel B → sets signal_2
- With strict "one kernel at a time" serialization, this created deadlock:
* Queue1 executed Kernel A, then blocked on barrier waiting for signal_2
* Serializer switched to Queue2, but Queue2 was blocked waiting for signal_1
* Neither queue could proceed: Queue1 needed Queue2's Kernel B to complete,
but Queue2 couldn't start until Queue1 finished completely
- Test would hang indefinitely at hsa_signal_wait_relaxed() for signal_2
Solution implemented:
- Reordered packet submission to eliminate circular dependencies
- Ensured signal producers execute before consumers need them:
* Kernel A produces signal_1 before Queue2's barrier needs it
* Kernel B produces signal_2 before Queue1's continuation needs it
- Dependencies now flow forward without cycles, allowing serializer progress
Refactoring changes:
- Extract common functionality into helper functions:
* create_completion_signal() for signal creation
* create_queue() for queue creation
* submit_kernel_packet() for kernel dispatch packets
* submit_barrier_packet() for barrier packets
- Add comprehensive documentation explaining expected execution pattern
- Simplify main() function making the dependency flow more readable
Co-authored-by: Benjamin Welton <bewelton@amd.com >
2025-08-05 17:29:07 -07:00
cdacbdc758
Merge commit '6918af0dd60df64fa445256480dd27be33979c07' into develop
2025-08-05 23:01:31 +00:00
00a09fbf21
Aug 5 Migration Updates
2025-08-05 17:42:06 -04:00
ad660b7bd8
Source of truth updates for Aug 5
2025-08-05 17:10:23 -04:00
792cf209a7
Updating migration status from Aug 5th
2025-08-05 17:06:50 -04:00
edf4735b3e
Preserve file-path commit histories
2025-08-05 16:59:19 -04:00
0892fc31c7
Preserve file-path commit histories
2025-08-05 16:57:37 -04:00
6918af0dd6
[CI] fix RHEL requirements issue ( #563 )
...
* use gcc/g++ from /opt/rh/
2025-08-05 15:47:47 -05:00
7bc75a21da
Preserving file-path commit histories
2025-08-05 15:56:47 -04:00
aad122c939
Merge commit '5f422c1993e4d920b388cc4fc9c52983d507c763' into develop
2025-08-05 17:05:53 +00:00
5f422c1993
Fix missing include file in rocJPEG test app ( #525 )
...
- Fixes compilation error for rocJPEG test app
- SWDEV-544094
2025-08-05 11:50:01 -05:00
44df81c7fd
GitHub Actions: Don't run sync jobs on forks
2025-08-05 12:12:30 -04:00
54161f54fe
Update readme for aqlprofile ( #570 )
...
* Update readme for aqlprofile
* Apply suggestions from code review
Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com >
---------
Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com >
Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com >
2025-08-05 11:11:40 -05:00
fc3eb4211d
[SDK] Fix data race by syncing emplace and flush operations. ( #529 )
...
* Fix data race by syncing reader and writer
* Address review comments
2025-08-05 11:07:00 -05:00
f2eb9e07cc
Merge commit 'e3206c8a29d286c448b533d51b318c3f80b7158c' into develop
2025-08-05 16:06:35 +00:00
1c3af22585
Merge commit 'a84c455a9de4569e589dc22d254ef3162a2de12a' into develop
2025-08-05 16:06:34 +00:00
e3206c8a29
Include installation sql header in rocpd library ( #576 )
...
Include installation of rocpd sql header
2025-08-05 11:04:09 -05:00
ca9905d6bb
Update CHANGELOG.md ( #557 )
...
* Update CHANGELOG.md
* some more updates
---------
Co-authored-by: srawat <120587655+SwRaw@users.noreply.github.com >
2025-08-05 10:29:42 -05:00
cb816c1c21
Update sync-mainline.yaml
...
[ROCm/rocprofiler commit: a84c455a9d
2025-08-05 10:28:30 -05:00
a84c455a9d
Update sync-mainline.yaml
2025-08-05 10:28:30 -05:00
909f551889
Update sync-staging.yaml
...
[ROCm/rocprofiler commit: 008ee0a6f5
2025-08-05 10:27:18 -05:00
008ee0a6f5
Update sync-staging.yaml
2025-08-05 10:27:18 -05:00
2cf4ef5ea0
Update sync-staging.yaml
...
[ROCm/rocprofiler commit: 07a55ae99c
2025-08-05 10:22:54 -05:00
07a55ae99c
Update sync-staging.yaml
2025-08-05 10:22:54 -05:00
3b008fae9c
Merge commit 'e8675243442b2fb1044235af47affad11f2ca54c' into develop
2025-08-05 15:07:38 +00:00
e867524344
Fix autogen config test ( #856 )
...
* Only check file content hash consistency
* Do not check file modification timestamps since that can be updated by
git commands
2025-08-05 10:50:32 -04:00
14b0b2a7d7
Merge commit 'fd6f96ffb54054b405a6f05f800c64394126672d' into develop
2025-08-04 22:06:08 +00:00
fd6f96ffb5
Adding GPU index as a parameter for ATT ( #547 )
...
* Adding GPU index as a parameter for ATT
* Tidy fix
* Using tokenize
* Update tests/rocprofv3/advanced-thread-trace/CMakeLists.txt
Co-authored-by: Indic, Vladimir <Vladimir.Indic@amd.com >
* Update tests/rocprofv3/advanced-thread-trace/CMakeLists.txt
* Adding error logging. Using idx instead of id.
---------
Co-authored-by: Giovanni <gbaraldi@amd.com >
Co-authored-by: Indic, Vladimir <Vladimir.Indic@amd.com >
2025-08-04 23:15:50 +02:00
e7f8c9e278
Merge commit '533a8329d8f38b66b6c3577f141396a99d3fabbc' into develop
2025-08-04 19:07:14 +00:00
533a8329d8
Revert memory allocation CSV output file header and update tests ( #532 )
...
* Reverted header and field location for csv memory allocation and updated tests
* Updated example csv file and made small update
2025-08-04 13:22:27 -05:00
a2a355236a
Merge commit 'ea0a3e8da4d0b7e18654f85a92b2428197683459' into develop
2025-08-03 03:38:45 +00:00
0c7d3048e6
Merge commit 'c424dac2617be1af60115802b0b094a60d91646c' into develop
2025-08-03 03:38:44 +00:00
38b30a4a6f
Merge commit '7251cea0bc9e90217aea53bd8870a5be728814c2' into develop
2025-08-03 03:38:43 +00:00
86a5e6b8a0
Merge commit 'b349e406eddbd7c4a1663823c7318fd54a4507de' into develop
2025-08-03 03:38:41 +00:00
807784b3a3
Merge commit '31dfc0fccedbd50a93dad3ff514e74ed252ec239' into develop
2025-08-03 03:38:38 +00:00
870dc948b1
Terminology change: monorepo -> super-repo
2025-08-02 22:23:24 -04:00
153f71fb0d
Append, instead of prepend, breadcrumb for patch backs to old repos
2025-08-02 22:13:43 -04:00
c2d62973d4
Copying updates from rocm-libraries
2025-08-02 22:08:24 -04:00
d5000f623e
Update CODEOWNERS
2025-08-02 19:37:03 -04:00
b349e406ed
Fix L2 cache bandwidth metrics for MI350 ( #843 )
...
* Fix L2 cache bandwidth metrics for MI350
* Address review comments
2025-08-01 14:00:46 -04:00
6902b12e65
Fix metrics description ( #853 )
...
* Fix ordering of metrics description
2025-08-01 13:56:29 -04:00
d84863b7af
Remove duplicate metric descriptions from documentation ( #852 )
2025-08-01 13:33:58 -04:00
0d6e172679
update license files ( #849 )
2025-08-01 10:14:39 -06:00
9ddee8de2e
TUI: Kernel Selection ( #769 )
2025-08-01 11:31:43 -04:00
81daaaecc7
Fix pc sampling unit test ( #847 )
2025-08-01 09:28:43 -06:00
7251cea0bc
Fix rocpd kernel traces csv output ( #497 )
...
* Fix rocpd kernel traces csv
* Updated CHANGELOG.md
* Add guid header
* address comment.
* Fix test failures
---------
Co-authored-by: Srihari Uttanur <srihariu@amd.com >
2025-08-01 08:31:21 +05:30
ea0a3e8da4
libhsakmt: Use numa_node_size64 with long long
2025-07-31 18:17:52 -05:00
70ebb4a299
Backport CHANGELOG changes from 7.0 release ( #845 )
...
* Backport CHANGELOG changes from 7.0 release
* Backport CHANGELOG changes from https://github.com/ROCm/rocprofiler-compute/pull/815
2025-07-31 19:02:50 -04:00
6df6f3ec6e
Rocprofiler-Compute Formatting Workflow ( #18 )
...
* Added Formatting Workflow for Compute
* Update rocprofiler-compute-formatting.yml
* Removed use of action for black and isort in compute formatting
---------
Co-authored-by: Sivasuntharampillai, Haresh <Haresh.Sivasuntharampillai+amdeng@amd.com >
2025-07-31 17:47:18 -04:00
systems-assistant[bot]
Welton, Benjamin
Joseph Macaranas
Joseph Macaranas
Kandula, Venkateshwar reddy
Bhardwaj, Gopesh
Baraldi, Giovanni
U, Srihari
Radosavljevic, Milan
Rawat, Swati
Elwazir, Ammar
vedithal-amd
Trowbridge, Ian
Fei Zheng
xuchen-amd
Yiannis Papadopoulos
amd-hsivasun