Commit Graph

13501 Commits

Author SHA1 Message Date
Elwazir, Ammar d292fc4a94 Runners Update (#148)
* Update codeql.yml

* Update sync-mainline.yaml

* Update sync-staging.yaml

[ROCm/aqlprofile commit: 899d48d1ca]
2025-07-09 11:42:23 -05:00
Elwazir, Ammar 899d48d1ca Runners Update (#148)
* Update codeql.yml

* Update sync-mainline.yaml

* Update sync-staging.yaml
2025-07-09 11:42:23 -05:00
U, Srihari 7243889d6a Add perfetto support for scratch memory (#303)
* Add perfetto support for scratch memory

* Updated tests and docs.

* Update docs data

* Added underflow check

* Record all free events to 0 bytes

* Add format

* Address review comment

* updated tests for scratch memory

* update scratch-memory tests.

[ROCm/rocprofiler-sdk commit: 6f2a5a9646]
2025-07-09 21:05:45 +05:30
U, Srihari 6f2a5a9646 Add perfetto support for scratch memory (#303)
* Add perfetto support for scratch memory

* Updated tests and docs.

* Update docs data

* Added underflow check

* Record all free events to 0 bytes

* Add format

* Address review comment

* updated tests for scratch memory

* update scratch-memory tests.
2025-07-09 21:05:45 +05:30
GabrPham 7dba992ebd Update threading to use more stable threading module
Unstable threading was causing segmentation faults. Update to use more
recent threading module rather than the _thread module solved
segmentation fault issue.

multiple issues solved by this commit:
	[SWDEV-537518]
	[SWDEV-540377]
	[SWDEV-540223]

Signed-off-by: GabrPham <gabrpham_amdeng@amd.com>
2025-07-09 09:36:44 -05:00
Welton, Benjamin fbf17a42d4 [SWDEV-516561][1/2] Add MARKER_RANGE_EXTENT to capture ROCTX ranges (#363)
* [SWDEV-516561][1/2] Add MARKER_RANGE_EXTENT to capture ROCTX ranges

Range extent to capture all work between roctxpush/pop operations. Entry callback takes place during roxtxpush and exit callback takes place in roctxpop. This is primarily to allow us to keep an ancestor id on the ancestor stack such that all operations that take place within the push/pop context can be annotated as being apart of this range. With the current setup (where push and pop are two separate operations that need to be combined externally), we cannot keep an ancestor id on the stack and thus cannot tie tracing events to particular ranges.

Correlation id information is inherited from the push operation. Ancestor id needs to be added in a future commit that also outputs this ancestor to CSV.

Output:

```
[ctest] {'size': 64, 'kind': 7, 'operation': 1, 'correlation_id': {'internal': 1525, 'external': 0, 'ancestor': 1524}, 'start_timestamp': 2932551479402642, 'end_timestamp': 2932551491178449, 'thread_id': 3254861}
[ctest] {'size': 64, 'kind': 8, 'operation': 2, 'correlation_id': {'internal': 1525, 'external': 0, 'ancestor': 1524}, 'start_timestamp': 2932551479405878, 'end_timestamp': 2932551491181214, 'thread_id': 3254861}
```

Note: Kind 8 = range extent op.

* Merge fix

Revert several changes

source/lib/rocprofiler-sdk/marker/range_marker.*

- separate out range marker implementation for standard marker implementation

Update public API with marker core range

Support marker core range in sdk (source/lib/rocprofiler-sdk)

Transition rocprofiler-sdk-tool and output lib to use marker core range

Misc fixes for tests

Fix logic in lib/output/generate{CSV,Stats}.cpp

Update tests/rocprofv3/tracing-hip-in-libraries (marker validation)

Fix test_otf2_data

* Test fixes

---------

Co-authored-by: Benjamin Welton <bewelton@amd.com>

[ROCm/rocprofiler-sdk commit: 2c4e20b951]
2025-07-08 23:41:22 -07:00
Welton, Benjamin 2c4e20b951 [SWDEV-516561][1/2] Add MARKER_RANGE_EXTENT to capture ROCTX ranges (#363)
* [SWDEV-516561][1/2] Add MARKER_RANGE_EXTENT to capture ROCTX ranges

Range extent to capture all work between roctxpush/pop operations. Entry callback takes place during roxtxpush and exit callback takes place in roctxpop. This is primarily to allow us to keep an ancestor id on the ancestor stack such that all operations that take place within the push/pop context can be annotated as being apart of this range. With the current setup (where push and pop are two separate operations that need to be combined externally), we cannot keep an ancestor id on the stack and thus cannot tie tracing events to particular ranges.

Correlation id information is inherited from the push operation. Ancestor id needs to be added in a future commit that also outputs this ancestor to CSV.

Output:

```
[ctest] {'size': 64, 'kind': 7, 'operation': 1, 'correlation_id': {'internal': 1525, 'external': 0, 'ancestor': 1524}, 'start_timestamp': 2932551479402642, 'end_timestamp': 2932551491178449, 'thread_id': 3254861}
[ctest] {'size': 64, 'kind': 8, 'operation': 2, 'correlation_id': {'internal': 1525, 'external': 0, 'ancestor': 1524}, 'start_timestamp': 2932551479405878, 'end_timestamp': 2932551491181214, 'thread_id': 3254861}
```

Note: Kind 8 = range extent op.

* Merge fix

Revert several changes

source/lib/rocprofiler-sdk/marker/range_marker.*

- separate out range marker implementation for standard marker implementation

Update public API with marker core range

Support marker core range in sdk (source/lib/rocprofiler-sdk)

Transition rocprofiler-sdk-tool and output lib to use marker core range

Misc fixes for tests

Fix logic in lib/output/generate{CSV,Stats}.cpp

Update tests/rocprofv3/tracing-hip-in-libraries (marker validation)

Fix test_otf2_data

* Test fixes

---------

Co-authored-by: Benjamin Welton <bewelton@amd.com>
2025-07-08 23:41:22 -07:00
Welton, Benjamin 187bdeca54 [SDK] Added retry for signal wait (#494)
Added retry for signal wait

Co-authored-by: Benjamin Welton <bewelton@amd.com>

[ROCm/rocprofiler-sdk commit: 2fa98c4d14]
2025-07-08 23:28:02 -07:00
Welton, Benjamin 2fa98c4d14 [SDK] Added retry for signal wait (#494)
Added retry for signal wait

Co-authored-by: Benjamin Welton <bewelton@amd.com>
2025-07-08 23:28:02 -07:00
Honglei Huang 45af009c5d libhsakmt: use uint32_t for loop index variables
This patch changes the type of several loop index variables from int to
uint32_t in fmm.c. The affected functions are:
- __fmm_release
- _fmm_map_to_gpu
- _fmm_unmap_from_gpu

To fix compile warning:

warning: comparison of integer expressions of different signedness:
'int' and 'uint32_t' {aka 'unsigned int'} [-Wsign-compare]
 2009 |         for (i = 0; i < object->handle_num; i++) {

Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com>
2025-07-09 13:15:42 +08:00
vedithal-amd f730199ef7 Fix util tests (#797)
* Fix profile tests
* Update known issue for corrupted memory chart

[ROCm/rocprofiler-compute commit: c51b9d16c3]
2025-07-08 17:15:09 -04:00
vedithal-amd c51b9d16c3 Fix util tests (#797)
* Fix profile tests
* Update known issue for corrupted memory chart
2025-07-08 17:15:09 -04:00
cfallows-amd 7862701993 Update roofline bins for rocm7 changes (#755)
* Update current bins to have rocm6 suffix. Add new rocm7 bins, built on rocm7.0 latest due to hip updates.

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

* Re-add rocm version check for roof bins.

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

* Rebuild roofline binaries on top of latest rocm7 (#16379) after recent mainline promotions.
Adjusting version and distro combinations of bins following rocm6 vs rocm 7 supported OS.
*rhel8 not supported on rocm7, also not built anymore
*sles15 not supported on rocm7 but is still being built
*ubuntu stays as 22.04 and above for rocm7

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

* Minor fixes after testing.

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

* Fixed bad copy after finding it in testing ctest.

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

* Remove runpath from new bin

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

* Rework target_binary map return in detect_roofline- we should not be returning maps of different sizes or with different keys for the same method. Expected output should be consistent in case we run into bad position, or for testing purposes. Manually tested all possible roofline bin expected cases to comfirm functionality and expected user output.

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

* Update changelog with new roofline distro minimums

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

---------

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

[ROCm/rocprofiler-compute commit: 3df0d1dded]
2025-07-08 16:51:50 -04:00
cfallows-amd 3df0d1dded Update roofline bins for rocm7 changes (#755)
* Update current bins to have rocm6 suffix. Add new rocm7 bins, built on rocm7.0 latest due to hip updates.

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

* Re-add rocm version check for roof bins.

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

* Rebuild roofline binaries on top of latest rocm7 (#16379) after recent mainline promotions.
Adjusting version and distro combinations of bins following rocm6 vs rocm 7 supported OS.
*rhel8 not supported on rocm7, also not built anymore
*sles15 not supported on rocm7 but is still being built
*ubuntu stays as 22.04 and above for rocm7

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

* Minor fixes after testing.

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

* Fixed bad copy after finding it in testing ctest.

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

* Remove runpath from new bin

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

* Rework target_binary map return in detect_roofline- we should not be returning maps of different sizes or with different keys for the same method. Expected output should be consistent in case we run into bad position, or for testing purposes. Manually tested all possible roofline bin expected cases to comfirm functionality and expected user output.

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

* Update changelog with new roofline distro minimums

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

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-07-08 16:51:50 -04:00
xuchen-amd bac7fde4f4 Add tui cmake install. (#794)
[ROCm/rocprofiler-compute commit: 60a50e681b]
2025-07-08 11:18:26 -04:00
xuchen-amd 60a50e681b Add tui cmake install. (#794) 2025-07-08 11:18:26 -04:00
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 05b674651c 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

[ROCm/rocprofiler-sdk commit: 30e239d1b7]
2025-07-04 09:20:23 -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 d5ca98baed Adding OpenMP usage with rocprofv3 (#472)
* Adding openmp usage with rocprofv3

* minor changes

* Fixing missing line

[ROCm/rocprofiler-sdk commit: e7616c3aad]
2025-07-02 12:25:24 +05:30
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