Commit Graph

13501 Commits

Author SHA1 Message Date
Kandula, Venkateshwar reddy cc18b95c7f rocprofv3-test-trace-hip-in-libraries-validate failed in PSDB (#248)
* capture streams by reference

* Fix sync_stream in tests/bin/vector-operations

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>
2025-03-07 14:43:29 -06:00
zichguan-amd 3415a500c7 Throw exception when runtime not initialized for hsa_amd_signal_wait_*
Signed-off-by: zichguan-amd <zichuan.guan@amd.com>
2025-03-07 15:17:10 -05:00
zichguan-amd e4d027191c rocr: Allow 0/NULL/invalid signal handles for wait operations to be no-op
Remove hard assertions for signal validation on hsa_amd_signal_wait_* operations, instead ignore 0/NULL/invalid signals in the dependency condition evaluation to align with HSA specs for barrier-AND and barrier-OR packets.

Signed-off-by: zichguan-amd <zichuan.guan@amd.com>
2025-03-07 15:17:10 -05:00
Sajina PK c41f69eae4 Add contributing guidelines (#119)
---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 0071fd2d81]
2025-03-07 14:47:30 -05:00
Sajina PK 0071fd2d81 Add contributing guidelines (#119)
---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-03-07 14:47:30 -05:00
Khatri, Shweta 9638da7467 Added gfx94x and gfx11xx IDs to enumerator (#5) 2025-03-07 13:56:43 -05:00
cfallows-amd 54ec17a185 FP8 roofline support (#592)
Adding FP8 datatype to roofline feature in rocprof-compute on MI300-based systems.
FP8 now shows in terminal output and roofline csv, and outputs a standalone PDF.

---------

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

[ROCm/rocprofiler-compute commit: 848fa1dc18]
2025-03-07 11:27:01 -05:00
cfallows-amd 848fa1dc18 FP8 roofline support (#592)
Adding FP8 datatype to roofline feature in rocprof-compute on MI300-based systems.
FP8 now shows in terminal output and roofline csv, and outputs a standalone PDF.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-03-07 11:27:01 -05:00
Fei Zheng 5793abe46e fix specs-correction
[ROCm/rocprofiler-compute commit: f64c83fc5e]
2025-03-07 11:27:01 -05:00
Fei Zheng f64c83fc5e fix specs-correction 2025-03-07 11:27:01 -05:00
xuchen-amd 66d538c2e0 Disable --kokkos-trace in rocprof-compute (#594)
.

[ROCm/rocprofiler-compute commit: 1b6bc89137]
2025-03-07 11:27:01 -05:00
xuchen-amd 1b6bc89137 Disable --kokkos-trace in rocprof-compute (#594)
.
2025-03-07 11:27:01 -05:00
xuchen-amd 663a41075b Fix rocprofv1 output processing. (#588)
[ROCm/rocprofiler-compute commit: b81310070e]
2025-03-07 11:27:01 -05:00
xuchen-amd b81310070e Fix rocprofv1 output processing. (#588) 2025-03-07 11:27:01 -05:00
vedithal-amd 536fb5ea26 Fix post analysis gui in standalone binary (#591)
* Fix post analysis gui in standalone binary

* Add post analysis gui assets and required server libraries for GUI
  server and web page

* Add port forwarding to docker test compose

* Update README me to use `docker compose up` instead of `docker compose run`
  to run containers with port forwarding and to leverage other
  functionalities of docker compose

[ROCm/rocprofiler-compute commit: 0b3114fa88]
2025-03-07 11:27:01 -05:00
vedithal-amd 0b3114fa88 Fix post analysis gui in standalone binary (#591)
* Fix post analysis gui in standalone binary

* Add post analysis gui assets and required server libraries for GUI
  server and web page

* Add port forwarding to docker test compose

* Update README me to use `docker compose up` instead of `docker compose run`
  to run containers with port forwarding and to leverage other
  functionalities of docker compose
2025-03-07 11:27:01 -05:00
David Galiffi 663e5b0766 Update libraries' SOVERSION to match other ROCm components (#98)
set SOVERSION to ${PROJECT_VERSION_MAJOR}

Signed-off-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 5fc495c1e7]
2025-03-07 10:18:36 -05:00
David Galiffi 5fc495c1e7 Update libraries' SOVERSION to match other ROCm components (#98)
set SOVERSION to ${PROJECT_VERSION_MAJOR}

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2025-03-07 10:18:36 -05:00
David Galiffi ab5d13b3bf Update runners to use ubuntu-latest (#131)
[ROCm/rocprofiler-systems commit: fdb6f4f6b4]
2025-03-06 18:11:19 -05:00
David Galiffi fdb6f4f6b4 Update runners to use ubuntu-latest (#131) 2025-03-06 18:11:19 -05:00
Sajina PK 527cfcafa4 Documentation update for VCN, JPEG, rocDecode and rocJPEG feature (#109)
* Documentation update for VCN, JPEG, rocDecode and rocJPEG feature

Update documents to include the new tracks for tracing VCN and JPEG
activity.
Update the rocDecode and rocJPEG tracing enabled using ROCprofiler-SDK.
Update headings to the perfetto output images.

* Add few more lines about domain values.

* Add missing words to the dictionary

[ROCm/rocprofiler-systems commit: 2222ce9b83]
2025-03-06 18:03:33 -05:00
Sajina PK 2222ce9b83 Documentation update for VCN, JPEG, rocDecode and rocJPEG feature (#109)
* Documentation update for VCN, JPEG, rocDecode and rocJPEG feature

Update documents to include the new tracks for tracing VCN and JPEG
activity.
Update the rocDecode and rocJPEG tracing enabled using ROCprofiler-SDK.
Update headings to the perfetto output images.

* Add few more lines about domain values.

* Add missing words to the dictionary
2025-03-06 18:03:33 -05:00
David Yat Sin 02b38d0614 rocr: Put back scratch_backing_memory_byte_size
The scratch_backing_memory_byte_size is not used by CP, but it is
currently used by rocgdb. Putting the field back, but we need to find a
solution for alt_scratch_backing_memory_byte_size.

Also, completely disabling alternate scratch as we need some changes to
support debugger.
2025-03-06 16:23:38 -05:00
David Galiffi 92e439627e Fix logging error (#130)
When we create profile config with rocprofiler we log the counters being registered. However, this log was being skipped in certain cases.

[ROCm/rocprofiler-systems commit: eb0a969a9c]
2025-03-06 14:30:45 -05:00
David Galiffi eb0a969a9c Fix logging error (#130)
When we create profile config with rocprofiler we log the counters being registered. However, this log was being skipped in certain cases.
2025-03-06 14:30:45 -05:00
Jonathan Kim c879fdefcf kfdtest: Add KFD SDMA queue reset testing
The KFD can per-SDMA queue reset similar to compute queue reset.
Add test.
2025-03-06 14:04:42 -05:00
Jonathan Kim ee890e7d2b kfdtest: Add KFD SDMA queue reset testing
The KFD can per-SDMA queue reset similar to compute queue reset.
Add test.
2025-03-06 14:04:42 -05:00
Jonathan Kim d047708317 kfdtest: Allow user to modify packet size for SDMA write packets
This is primarily used for debug and negative testing for SDMA queue
reset and shouldn't be used for normal run cases.
2025-03-06 14:04:42 -05:00
Jonathan Kim 9e57ce48e8 kfdtest: Add create SDMA queue by target engine
KFD supports SDMA queue creation by target engine.
Enable this for testing.
2025-03-06 14:04:42 -05:00
Jonathan Kim a957b24153 kfdtest: Add SDMA poll memory register packet support
The SDMA can wait on poll user memory.  This is being added to
support per-SDMA queue reset testing.
2025-03-06 14:04:42 -05:00
Jonathan Kim e3d09e30dc hsakmt: Expose per-SDMA queue reset capabilities
Expose new capabilities field that flags per-sdma queue reset
support.
2025-03-06 14:04:42 -05:00
Su, Daniel 11823451e6 External CI: change trigger from amd-master to amd-mainline 2025-03-06 10:29:58 -05:00
Rawat, Swati 27d0bc087c Update CHANGELOG.md: editorial review (#254)
Update CHANGELOG.md

Co-authored-by: srawat <120587655+SwRaw@users.noreply.github.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>

[ROCm/rocprofiler-sdk commit: d74ea0876f]
2025-03-06 12:32:02 +05:30
Rawat, Swati d74ea0876f Update CHANGELOG.md: editorial review (#254)
Update CHANGELOG.md

Co-authored-by: srawat <120587655+SwRaw@users.noreply.github.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>
2025-03-06 12:32:02 +05:30
Su, Daniel 70b44c576c External CI: change trigger from amd-master to amd-mainline
Signed-off-by: Su, Daniel <Daniel.Su@amd.com>
2025-03-05 16:24:29 -05:00
Sohaib Nadeem 95a07edf0b Fix hardware counter summary files not being generated after profiling (#124)
- Register a cleanup function in tim::manager instance to write out data in
counter storages

- The counter_storage::write() calls in tool_fini happen after the storage is destroyed
which is too late for the write to happen.

- Adjust traits for counter_data_tracker

- Add MIN, MAX, VAR, STDDEV columns
- Remove DEPTH, UNITS, %SELF columns

- Update "add_validation_test" to test for the existence of output file(s).
- Added step to test perfetto output for `transpose-rocprofiler-sampling`
and `transpose-rocprofiler-binary-rewrite`

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 42922ec851]
2025-03-05 16:05:18 -05:00
Sohaib Nadeem 42922ec851 Fix hardware counter summary files not being generated after profiling (#124)
- Register a cleanup function in tim::manager instance to write out data in
counter storages

- The counter_storage::write() calls in tool_fini happen after the storage is destroyed
which is too late for the write to happen.

- Adjust traits for counter_data_tracker

- Add MIN, MAX, VAR, STDDEV columns
- Remove DEPTH, UNITS, %SELF columns

- Update "add_validation_test" to test for the existence of output file(s).
- Added step to test perfetto output for `transpose-rocprofiler-sampling`
and `transpose-rocprofiler-binary-rewrite`

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-03-05 16:05:18 -05:00
Madsen, Jonathan 15c8c05f0c [rocprofv3] Fix calculation of services which collected data (#265)
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: e7c64e12f9]
2025-03-05 10:59:06 -06:00
Madsen, Jonathan e7c64e12f9 [rocprofv3] Fix calculation of services which collected data (#265)
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2025-03-05 10:59:06 -06:00
David Yat Sin 6dac90c89a rocr: Only expose ext-fine-grain pool on xgmi-hive systems
We cannot guarrantee system-scope coherency on systems with only PCIe
connections, so do not expose extended fine-grain memory pool on these
systems.
2025-03-05 10:41:38 -05:00
arvindcheru c283b69b62 Move install location of internal papi files to lib/<pkgnm> (#118)
Signed-off-by: ArvindCheru <acheruva@amd.com>

[ROCm/rocprofiler-systems commit: c3138e1962]
2025-03-05 10:23:58 -05:00
arvindcheru c3138e1962 Move install location of internal papi files to lib/<pkgnm> (#118)
Signed-off-by: ArvindCheru <acheruva@amd.com>
2025-03-05 10:23:58 -05:00
David Galiffi 8a70f4b15d Update workflow runners due to the deprecation of ubuntu-20.04 runners (#102)
* Update runners to `ubuntu-latest`.

The `ubuntu-20.04` runner is deprecated and will be removed.

* Add 'vim' and 'perfetto' to CI docker images

For convenience when using the images locally.

[ROCm/rocprofiler-systems commit: a25554359b]
2025-03-04 19:31:13 -05:00
David Galiffi a25554359b Update workflow runners due to the deprecation of ubuntu-20.04 runners (#102)
* Update runners to `ubuntu-latest`.

The `ubuntu-20.04` runner is deprecated and will be removed.

* Add 'vim' and 'perfetto' to CI docker images

For convenience when using the images locally.
2025-03-04 19:31:13 -05:00
David Galiffi 4a86630875 Move cmake files to .../lib/cmake/rocprofiler-systems (#128)
* Move cmake files to `.../lib/cmake/rocprofiler-systems`


[ROCm/rocprofiler-systems commit: a588f53d3e]
2025-03-04 19:28:59 -05:00
David Galiffi a588f53d3e Move cmake files to .../lib/cmake/rocprofiler-systems (#128)
* Move cmake files to `.../lib/cmake/rocprofiler-systems`
2025-03-04 19:28:59 -05:00
Lao, Darren 0cd46b6582 rocr: Change grid dimensions
Signed-off-by: Lao, Darren <Darren.Lao@amd.com>
2025-03-04 16:19:51 -05:00
David Yat Sin 4cb6a6d45d rocrtst: Disable RLIMIT for negative queue tests
The negative queue tests generate an exception which triggers a coredump
generation. Disable RLIMIT so that the coredumps are not generated for
these tests.
2025-03-04 10:29:34 -05:00
David Yat Sin d031af9eb5 rocr: Check RLIMIT_CORE before generating coredump
Check for RLIMIT_CORE before collecting data for coredump. If the
current limit is 0, then we can return early without spending time
collecting coredump data.
2025-03-04 10:29:34 -05:00
adapryor 9571dad23d [SWDEV-517396] Align rdc_field with rdc_bootstrap
Signed-off-by: adapryor <Adam.pryor@amd.com>
Change-Id: I5e05e25c5980a3141665ae2d13a6ae09207ccb41
2025-03-04 08:49:28 -06:00