xuchen-amd f0fad19e8b Add chip specs (#681) ...

* Add perfmon config spec, enhance memory partition info.

* Add gfx950 perfmon config.

* Add High Freq variants in gfx942.

* Add backup detection methods for gpu model.

* Improve get_num_xcds logic by adding detection of 1to1 arch-to-compute_partition logic.

* Add default compute partition settings spx:8 for when gpu_model=None.

* Update gpu spec tests.

* Add backup compute partition detection.

---------

Signed-off-by: xuchen-amd <xuchen@amd.com>

2025-05-29 16:35:34 -04:00

..

workloads

Support MI 350 profiling (#632)

2025-04-03 02:21:18 -04:00

__init__.py

Initial commit

2022-11-04 14:49:36 -05:00

4gpus.json

Rename Omniperf to ROCm Compute Profiler (#428)

2024-11-01 12:20:21 -04:00

CMakeLists.txt

Add mi300 TCP counter tests (#644)

2025-04-02 20:32:13 -04:00

conftest.py

Implement interface to rocprofiler sdk (#695)

2025-05-13 10:48:21 -04:00

generate_test_analyze_workloads.py

Sync staging with mainline (#524)

2025-01-02 15:29:47 -06:00

generate_workloads.sh

Sync staging with mainline (#524)

2025-01-02 15:29:47 -06:00

test_analyze_commands.py

Support MI 350 profiling (#632)

2025-04-03 02:21:18 -04:00

test_analyze_workloads.py

Support MI 350 profiling (#632)

2025-04-03 02:21:18 -04:00

test_gpu_specs.py

Add chip specs (#681)

2025-05-29 16:35:34 -04:00

test_import_workloads.py

Sync staging with mainline (#524)

2025-01-02 15:29:47 -06:00

test_profile_general.py

Fix MI350 tests (#706)

2025-05-15 13:37:55 -04:00

test_TCP_counters.py

Use gpu model series instead of gpu model name for testing (#696)

2025-05-06 18:23:08 -04:00

test_utils.py

Analysis report block based filtering for profiling (#566)

2025-03-10 14:42:56 -04:00