## Motivation
- Added `check_rocminfo` function that returns true if the provided regex was found, false otherwise. Can also use `GET_OUTPUT` to get the raw output filtered with or without a regex.
- Moved `rocprofiler_systems_get_gfx_archs()` to `MacroUtilities.cmake`
- Added `rocprofiler_systems_lookup_gfx()`, which detects whether a given `gfx` is from the `instinct`, `radeon` or `apu` family.
- Added `ROCPROFSYS_GFX_TARGETS` as a build argument. Used to specify the offloading architectures that GPU examples should compile for. If empty, defaults to whatever your system has.
- GPU examples now check if the given `gfx` targets (from `ROCPROFSYS_GFX_TARGETS`) are supported.
- OMPVV offload tests now only compile if `amdflang` version is `>= 20`
- Improve link time by reducing the number of GFX targets that binaries need to support.
- RCCL is now passed a `GPU_TARGETS` var specifying the architectures to build/link against.
## Motivation
<!-- Explain the purpose of this PR and the goals it aims to achieve. -->
Remove Fortran example due to Palamida scan violation.
## Technical Details
<!-- Explain the changes along with any relevant GitHub links. -->
Revert 63713f01e0.
New test to be added later.
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
* Put cached perfetto traces as default one
* Improve cached data and perfetto traces in order to be more aligned with E2E tests
* Addressing PR comments and findings
* Force early instrumentation bundle instantiation
* Sync-up insturumented containers with thread growth data
* Revert ompvv number of host threads to default 8
* Fixed counter track namings for amd-smi
* AIPROFSYST-34 [rocprof-sys] Update documentation describing newly introduced changes to default tracing mechanism
## Motivation
To solve: SWDEV-566076
FFmpeg versions >= 58.134 no longer expose read_seek and read_seek2 function pointers in AVInputFormat,
requiring alternative seek detection methods. This pull request updates the `VideoDemuxer` class to improve compatibility with newer versions of FFmpeg. The main change is how the code determines whether the input file is seekable, addressing differences in FFmpeg API versions.
## Technical Details
In `video_demuxer.h`, added a conditional check for `USE_AVCODEC_GREATER_THAN_58_134` to set `is_seekable_` to `true` for newer FFmpeg versions, since `read_seek` and `read_seek2` are no longer exposed in `AVFormatContext`. For older versions, the previous method of checking these fields remains in place. The conditional compilation
now assumes seek capability is available for newer FFmpeg versions.
* Add XGMI and PCIe metrics to the profiling data
Add support for AMD XGMI (GPU-to-GPU interconnect) and PCIe
metrics:
* XGMI link width in bits
* XGMI link speed in GT/s
* Per-link read bandwidth (KB)
* Per-link write bandwidth (KB)
- Add new categories for PCIe metrics:
* PCIe link width
* PCIe link speed in GT/s
* Accumulated bandwidth (MB)
* Instantaneous bandwidth (MB/s)
* Fix VCN/JPEG insert logic
* Modify the gpu_metrics struct to accomodate XCP structure
* Add ctest automation for gpu interconnect metrics
* Refactor to move gpu_metrics struct and serialization to another file
* Possible fix for timeout in CI
Fix redundant skip check in ctest
Add xgmi and pcie option in rocprof-sys-avail.
* Change2: Address review comments
Change ctest sampling to avoid timeout
Change variable name and code structuring
* Add option in ctest to run rocprof-sys-run without rewrite
Run transferbench with rocprof-sys-run without sampling
* Change3: Fix sample insert bug and address review comments
xgmi and pci support check
renaming variables
additional hip_api validation in rocpd
* Reduce the load from the trnasferBench sample
The CI builds were timing out when flushing a big temporary file to the
DB: (2720824.23 KB / 2720.82 MB / 2.72 GB)...
* Consolidate CTests to tests/ folder
* Remove comment
* Consolidate CTests to tests/ folder
* Remove comment
* Separate source code and test code for thread-limit into appropriate folders
* Remove sleeper.cpp and instead use linux sleep cmd
* Merge python-console tests into python-tests
This PR fixes a segmentation fault seen when running rocprof-sys-sample with multi-process OpenMP/HIP applications.
The crash was caused by missing libomptarget.so on the runtime loader path or incorrect LD_PRELOAD settings.
Fixes SWDEV-552804
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
* Added Fortran (amdflang) openmp tests using the openmp-vv project
---------
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
- Update minimum_cmake_required to match version used in CI
- We should match the minimum version that we test against
- Ensure ".S" files are treated as assembly.
- openmp-target: add runtime rpath for libomptarget and update tests
- Handle events not associated with a HIP Stream
- Kernels from OpenMP target offload are not associated with a HIP stream. Fix handling with the callback record's stream_id is 0
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: c424dac261]
* Fix: Add missing <string.h> include for C string functions in RCCL tests
* Update examples/rccl/rccl-tests/src/common.h
Yes, confirmed—<cstring> alone works in my environment. Updated the PR
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
* clang-format
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: 0ec3072e05]
- Create a local copy for ROCm/rccl-tests for our examples.
- Update argument parsing to no longer use getopt_long.
- Workaround for Dyninst instrumentation.
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: 4e5029221b]
Test is missing from rocm-7.0 stack because of a HIP version check.
In these builds, hip_version.h is still reporting 6.5.0.
This check was originally put in to skip the test on older versions
of ROCm, which should no longer be required
- For SWDEV-537718
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: 28bee27253]
- Move the MPI gotcha functionality from Timemory to the repo.
- Add the PMPI Fortran MPI functions to the existing mpi gotcha handle.
[ROCm/rocprofiler-systems commit: 4fcd8cc78d]
- Add cmake formatting rule for `rocprofiler-systems-custom-compilation`
- Resolve build failure observed with the `openmp-target` example when building in some environments
- Observed in our docker images
- Ensure `libomptarget-amdgpu-gfx*.bc` files are found
[ROCm/rocprofiler-systems commit: 96b31d92c3]
- Fix for rocjpeg sample cmake due to changes in the rocJPEG project
- Fix for rocprofiler-sdk version check - change the format
- Edits to docs for jpeg and vcn activity support - mention that these values may not be supported on all ASICs.
[ROCm/rocprofiler-systems commit: fad3a0d341]
JPEG activity recording is currently only supported on MI300 serries.
VCN activity is supported in MI100 also but there is a bug currently being fixed by FW.
- Currently only testing the Activity verification tests for MI300
- Also moves the Jpeg image copying code to after the package is found.
[ROCm/rocprofiler-systems commit: e605e5d33f]
- Add rocDecode API Tracing support using domain `rocjpeg_api` in ROCPROFSYS_ROCM_DOMAINS.
- Modify existing `videodecode` and `jpegdecode` ctests to verify API tracing
- Print Perfetto values for easy debugging in verbose mode
- Convert CMake error to a warning and skip building the "decode" examples if requirements are not found
[ROCm/rocprofiler-systems commit: 3bea1d8eac]
- Add JPEG activity track in perfetto trace
- Add JPEG decode tests to the examples
- Change existing videodecode test to include JPEG testing
- Rename videodecode test file to decode to include jpeg tests too
- Fix a bug in the test which checks for total activity of 0
- Disable rocDecode and rocJPEG samples from the github image files
[ROCm/rocprofiler-systems commit: 59d3399901]
- Copy sample videos and include in install.
- Only using the H26* videos, so the same tests can be used on MI100, which lacks AV1 decode support
- Update test parameters to videodecode test, based on feedback from the rocDecode team.
[ROCm/rocprofiler-systems commit: 5b439d80a0]
- Porting from https://github.com/ROCm/omnitrace/pull/411
- Improve OMPT support
- Add OpenMP target example to testing
- Update Timemory submodule to use ROCm/Timemory rather than NERSC/Timemory
- Update `actions/upload-artifacts` to v4
- Standardize the `cmake_minimum_required` to 3.18.4 across workflows, project, and examples
- Updated Ubuntu 20.04 workflows
[ROCm/rocprofiler-systems commit: 7dce5926a7]
The Omnitrace program is being renamed.
Full name: "ROCm Systems Profiler"
Package name: "rocprofiler-systems"
Binary / Library names: "rocprof-sys-*"
---------
Co-authored-by: Xuan Chen <xuchen@amd.com>
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: d07bf508a9]
Kian Cossettini
David Galiffi
marantic-amd
habajpai-amd
Mario Limonciello
anujshuk-amd
Sajina PK
ajanicijamd
Julian Jose
Sajina PK
Pranjal Swarup
Daniel Su
Peter Park
darren-amd