Commit grafiek

12613 Commits

Auteur SHA1 Bericht Datum
Kian Cossettini ec683aefa7 Added compatibility matrix for docker-build script (#268)
- matrix -m argument for build-docker.sh that lists compatible OS + ROCm combinations.
- ${DISTRO} is now case-insensitive.
- Added note to README.md to mention this flag.
- Removed --build-arg AMDGPU_RPM=${ROCM_RPM}, which is no longer used

[ROCm/rocprofiler-systems commit: 67bc147780]
2025-07-08 11:05:14 -04:00
Kian Cossettini 67bc147780 Added compatibility matrix for docker-build script (#268)
- matrix -m argument for build-docker.sh that lists compatible OS + ROCm combinations.
- ${DISTRO} is now case-insensitive.
- Added note to README.md to mention this flag.
- Removed --build-arg AMDGPU_RPM=${ROCM_RPM}, which is no longer used
2025-07-08 11:05:14 -04:00
Fei Zheng 09ec955554 PC Sampling: fix potential_end_offset (#792)
* fix potential_end_offset

* format code: unrelated

[ROCm/rocprofiler-compute commit: 1b7445faa4]
2025-07-08 08:52:01 -04:00
Fei Zheng 1b7445faa4 PC Sampling: fix potential_end_offset (#792)
* fix potential_end_offset

* format code: unrelated
2025-07-08 08:52:01 -04:00
Fei Zheng c867eaa9cd format with isort (#793)
[ROCm/rocprofiler-compute commit: 239e6550f4]
2025-07-08 08:51:20 -04:00
Fei Zheng 239e6550f4 format with isort (#793) 2025-07-08 08:51:20 -04:00
fxmarty-amd a91e3f74f3 fix normalization (#789)
[ROCm/rocprofiler-compute commit: c58ee9e73b]
2025-07-08 08:50:41 -04:00
fxmarty-amd c58ee9e73b fix normalization (#789) 2025-07-08 08:50:41 -04:00
Pryor, Adam ca9d8c4bae Adam/bill cleanup (#209)
Co-authored-by: Bill(Shuzhou) Liu <shuzhou.liu@amd.com>
2025-07-07 15:41:22 -05:00
Sajina PK 329183b112 Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity (#272)
* Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity

Modify ROCPROFSYS_THROW to only include backtraces when:
  debug mode is enabled, OR
  verbose level is >= 2, OR
  running in CI environment

* Fix formatting errors

[ROCm/rocprofiler-systems commit: b0ff07b4fe]
2025-07-07 14:14:02 -04:00
Sajina PK b0ff07b4fe Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity (#272)
* Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity

Modify ROCPROFSYS_THROW to only include backtraces when:
  debug mode is enabled, OR
  verbose level is >= 2, OR
  running in CI environment

* Fix formatting errors
2025-07-07 14:14:02 -04:00
Bhardwaj, Gopesh 99a7fe5ff0 Ignoring aligned attribute warning (#70)
ignoring aligned attribute warning

[ROCm/roctracer commit: dd745ed9c7]
2025-07-07 09:34:39 -05:00
Bhardwaj, Gopesh dd745ed9c7 Ignoring aligned attribute warning (#70)
ignoring aligned attribute warning
2025-07-07 09:34:39 -05:00
Apurv Mishra 3115384874 kfdtest: Temporarily blacklist KFDEvictTest suite
blacklist the KFDEvictTest suite until the defects
SWDEV 535386 and 537002, where these test cases fail
inconsistently, are fixed

Signed-off-by: Apurv Mishra <Apurv.Mishra@amd.com>
2025-07-04 11:47:20 -04:00
Roy, Rakesh 30e239d1b7 Fix find_if build error for RHEL10 (#499)
overriding Jonathan's final approval ( as it is a long weekend in US/NA)
adding algorithm header to recognize stdlib's find_if looks fine
2025-07-04 09:20:23 -04:00
Castillo, Juan bab82d98b7 [SWDEV-539845] Add support for board voltage (#92)
* Add the API and CLI to show the board voltage.

---------

Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Co-authored-by: Liu, Shuzhou (Bill) <Shuzhou.Liu@amd.com>
2025-07-03 01:58:50 -05:00
Cheruvally, Aravindan 55ab9b2bda SWDEV-530465 Update share/doc/<pkgnm> License folder (#86)
Update share/doc/ folder for license/docs to reflect correct package name.
Signed-off-by: Cheruvally, Aravindan <Aravindan.Cheruvally@amd.com>
2025-07-03 01:56:50 -05:00
cfallows-amd 30466f6bfa Adjust csv output list for test_block_SPI for MI350 (#785)
Adjusting expected output list for test_block_SPI for MI350 series products.
Run formatter.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

[ROCm/rocprofiler-compute commit: 61a9381edf]
2025-07-03 01:58:11 -04:00
cfallows-amd 61a9381edf Adjust csv output list for test_block_SPI for MI350 (#785)
Adjusting expected output list for test_block_SPI for MI350 series products.
Run formatter.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-07-03 01:58:11 -04:00
jamessiddeley-amd 94ea0fbf2f additional-code-coverage-compute (#763)
* added additional functions to test_utils.py

* added code coverage for db_connector.py

* Update test_profile_general.py

Added additional roofline test cases

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

* updated coverage mi_gpu_spec.py 73% -> 94%

* added parser.py coverage

* removed redundant comments

* added test_utils and test_db_connector

---------

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

[ROCm/rocprofiler-compute commit: a6463f5e98]
2025-07-02 13:29:10 -04:00
jamessiddeley-amd a6463f5e98 additional-code-coverage-compute (#763)
* added additional functions to test_utils.py

* added code coverage for db_connector.py

* Update test_profile_general.py

Added additional roofline test cases

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

* updated coverage mi_gpu_spec.py 73% -> 94%

* added parser.py coverage

* removed redundant comments

* added test_utils and test_db_connector

---------

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>
2025-07-02 13:29:10 -04:00
Galantsev, Dmitrii 6c32364d19 Exposed the energy count and current socket power metrics to profilers like PAPI (#225) 2025-07-02 09:50:09 -05:00
Adam McDaniel f688c9938d Exposed the energy count and current socket power metrics to profilers like PAPI 2025-07-02 09:47:17 -05:00
Galantsev, Dmitrii 731be3f743 Revert "rsmi_init: Do not complain loudly when no driver is found"
This reverts commit 8ca4207d5c.
2025-07-02 09:45:41 -05:00
cfallows-amd e085f3cc54 Fix method return for python version compatibility (#784)
Support for python3.8 and above means union defined in one of the methods was throwing errors for anything less than python3.10. Swapping out | operand for Optional[] resolves errors on systems using <3.10. No functional changes.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

[ROCm/rocprofiler-compute commit: a59b1ea6e6]
2025-07-02 10:36:37 -04:00
cfallows-amd a59b1ea6e6 Fix method return for python version compatibility (#784)
Support for python3.8 and above means union defined in one of the methods was throwing errors for anything less than python3.10. Swapping out | operand for Optional[] resolves errors on systems using <3.10. No functional changes.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-07-02 10:36:37 -04:00
vedithal-amd 740fe492c2 Fix rocprofiler sdk list counters (#765)
[ROCm/rocprofiler-compute commit: 894046f283]
2025-07-02 09:41:51 -04:00
vedithal-amd 894046f283 Fix rocprofiler sdk list counters (#765) 2025-07-02 09:41:51 -04:00
Chris Freehill 12430fe25a rocr: Fix isa entries for gfx906/sramecc
Some of the entries for gfx906 in the ISA table in isa.cpp
had "any" for "sramecc-" instead of "disabled". This fixes
that.
2025-07-02 08:40:30 -05:00
Bhardwaj, Gopesh e7616c3aad Adding OpenMP usage with rocprofv3 (#472)
* Adding openmp usage with rocprofv3

* minor changes

* Fixing missing line
2025-07-02 12:25:24 +05:30
Su, Daniel 3a66cd7998 External CI: change amd-master trigger to amd-mainline (#10)
[ROCm/roctracer commit: 9cca903417]
2025-07-01 18:22:05 -05:00
Su, Daniel 9cca903417 External CI: change amd-master trigger to amd-mainline (#10) 2025-07-01 18:22:05 -05:00
Yang, Chun 5e99084425 Enabled RPB for Navi48 (#115)
* Enabled RPB for Navi48

* Fixing RPB addresses

* Removing non-Navi files

* Removing RPB enum not needed
2025-07-01 22:05:28 +00:00
Baraldi, Giovanni c0c08b2f08 [rocprofv3] Fix ATT library path (#476)
* Fix library path

* Update docs

* Review comments

* Update source/bin/rocprofv3.py

---------

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
2025-07-01 22:08:29 +02:00
Ma, Bing 7710e8bca3 [pmc_builder] Centralize the programming for GFX_INDEX and PERFMON_CNTL (#133)
Prepare multiple GC instances with different programming sequence for GFX_INDEX and PERFMON_CNTL.
2025-07-01 09:22:46 -07:00
Nagaraj, Sriraksha 1524ceb84d [SDK] Internal event id for AQL packet increased to 64-bit unsigned int (#380)
* event id to 64 bit size

* review comments

* review comments

* review comments

* fix

* handle exception

* fix formatting issue

* fix tests
2025-06-30 17:54:37 -05:00
Madsen, Jonathan 3590ecc10e [SDK] Fix buffer tracing stringify of stack-allocated char* buffer (#429)
* [SDK] Fix buffer tracing stringify of stack-allocated char* buffer

* Formatting

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2025-06-30 17:51:26 -05:00
Madsen, Jonathan 730b4e0a54 [CI] Use rocprof-azure-gpuless-emu-runner-set for build-docs-from-source job (#493) 2025-06-30 17:50:43 -05:00
Trowbridge, Ian 0904b6e34d [rocprofv3] Add check for Stream Stack Pointer before use (#465)
* Added null check for stream_stack before get_stream_id is called

* Rename function and add check for stream strack before pop

* Removed empty check for stream stack and adding error log for get_stream_id in stream.cpp
2025-06-30 17:49:48 -05:00
Jonathan Luu 463d6b60d5 SWDEV-531400 Remove file reorganization backwards compatibility (rdc) 2025-06-30 15:20:26 -07:00
Madsen, Jonathan 99e262ca4a [CI] Disable conversion script validation (#492)
- pytest fails when you selectively disable all the tests in the suite
2025-06-30 17:02:53 -05:00
Kuricheti, Mythreya 7842dfe839 [SDK] Filter agents that are not CPU or GPU (#374)
* Filter HSA agents

* Review comments
2025-06-30 15:54:48 -05:00
Madsen, Jonathan f0fe04b95e [CI] Disable other unstable tests (#491)
Disable other unstable tests

- validation test_validate_counter_collection_pmc1 for conversion script
- increase timeout for tests/rocprofv3/pc-sampling execution phase
2025-06-30 15:53:30 -05:00
Madsen, Jonathan 69f71b8097 [CI] Disable other unstable tests (#490)
* Disable other unstable tests

* Disable validating test_total_runtime in kernel-tracing

* The disabled tests will be stabilized and re-enabled by ROCm 7.0.1 or ROCm 7.1
2025-06-30 15:42:38 -05:00
Elwazir, Ammar 747763eadd Update sync-mainline.yaml
[ROCm/rocprofiler-register commit: 80fcffeb5a]
2025-06-30 15:24:35 -05:00
Elwazir, Ammar 80fcffeb5a Update sync-mainline.yaml 2025-06-30 15:24:35 -05:00
Elwazir, Ammar 3c986be896 Update sync-staging.yaml
[ROCm/rocprofiler-register commit: 57143911c3]
2025-06-30 15:24:13 -05:00
Elwazir, Ammar 57143911c3 Update sync-staging.yaml 2025-06-30 15:24:13 -05:00
Madsen, Jonathan 640ca55ac0 [CI] Testing stability (#486)
* [CI] Testing Stability

- CMake option ROCPROFILER_DISABLE_UNSTABLE_CTESTS
  - used for tests which periodically fail around 1 out of every 10 runs
  - set to ON while instability remains, this needs to set to OFF in ROCm 7.1 or, ideally, ROCm 7.0.1
- Use FIXTURES_SETUP and FIXTURES_REQUIRED for some tests
- replace "threw an exception" with "${ROCPROFILER_DEFAULT_FAIL_REGEX}" for misc FAIL_REGULAR_EXPRESSIONS

* Remove contents of all EXCLUDE_{TESTS,LABEL}_REGEX from CI workflow

* Disable patch git step in code-coverage run

* Tweak spin time of reproducible runtime

* Removed patch git step in code-coverage run

* Update ROCPROFILER_DEFAULT_FAIL_REGEX

* Mark test-counter-collection tests as unstable

- add fixtures setup/required

* Remove ATTACHED_FILES_ON_FAIL

- CDash doesn't store enable downloading these properly anyway

* Relax collection-period fuzzing window

* Disable unstable collection-period test

- too unstable

* formatting

* Disable unstable device_counting_service_test.async_counters

* Suppress perfetto internal data race errors

* Switch code-coverage CI jobs to mi300 runner

* Timeout increases

* rocprofv3-test-rocpd updates

- add fixtures
- switch executable
- redefine input/output paths

* Revert code-coverage job to mi300a runner

* Update rocprofv3-test-rocpd-execute-multiproc

- reduce problem size

* disable multiproc rocpd

* Split code-coverage into separate workflow

- network issues cause this job to fail frequently
- when in a separate workflow, it can be restarted easily

* Fixtures for rocprofv3-test-trace-hip-in-libraries

* Disable unstable device_counting_service_test.sync_counters

* Potential fix for code scanning alert no. 171: Workflow does not contain permissions

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* Switch code-coverage to run on rocprof-azure

- mi300a EMU runner set is unstable (network issues)

* tests/rocprofv3/pc-sampling SKIP_REGULAR_EXPRESSION

* Update rocprofv3-test-list-avail-trace-execute

- reduce log level and increase timeout

* rocprofv3: Prevent recursive call to rocprofv3_error_signal_handler + log chaining

* rocprofv3: Use ROCP_ERROR + std::exit instead of ROCP_FATAL

- should help with SKIP_REGULAR_EXPRESSION

---------

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-06-30 15:07:37 -05:00
Chris Freehill f1bd89bd0d rocr/rocrtst: Update to c++17 2025-06-30 14:02:24 -05:00