ggottipa-amd
77f7541755
* Adding --torch-operator option in rocprof-compute. Creates csv file for each operator that has gpu activity, showing operator to counter values mapping. * --torch-operators flag added to rocprofiler-sdk * Adding ctest for --torch-operators. * Adding pytest markers. * Corrections in ctest and message logging. * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Adding a check for pytorch installation only when --torch-operators is passed. * moving inject_roctx.py into src/utils. * rebase * Updating docs and changelog. * Update projects/rocprofiler-compute/src/argparser.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update projects/rocprofiler-compute/src/utils/inject_roctx.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Removing special characters. * Minor corrections. * Setting default value for torch_operators_enabled. * Updating the number of files according to the number of passes. * Adding rocpd support. * Adding a warning message to be shown when profiling a non-python workload. * copilot suggestions, rocpd+native tool fix * Fixed the incorrect usage of dispatch_id as event_id in the function update_rocpd_pmc_events() * ruff format fix * ruff formating * Deleting torch_trace.csvs after consolidating the operator data. * Removing checks since *torch_trace.csv files are deleted. * Fixing file deletion. * Update projects/rocprofiler-compute/src/utils/inject_roctx.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_base.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update projects/rocprofiler-compute/src/utils/utils.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update projects/rocprofiler-compute/tests/test_profile_general.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Using default options in the testcase. * Adding test for overhead measurement. * Corrections in docs. * doc updates. * Update projects/rocprofiler-compute/src/utils/inject_roctx.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Handling potential empty frames. * Corrected the test cases. * Changing the flag to --torch-trace * Fixed helper_app path issues * Path issues * process_torch_trace_output() now takes csv file paths as input + allows default usage. * Replaced pandas with sqlite3 * Adding marker_trace extraction to rocpd_data.py * Allowing all workloads to use --torch-trace option. Assuming the workload is user verified. * Modified help section for the flag. * Added difference in runtimes for longest running kernels in each profiling runs to overhead measurements. * Update projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_base.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_base.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Removed the accesses to the tables. * Ruff fixes. * ruff * Ruff Fixes * Adding getattr for args.torch_trace to handle mock args. * Fix for 'Missing guid in counter collection data - in csv mode' * Sending output_format to process_torch_trace_output * Warning for self contained binaries. * Ruff * Ruff * Measuring longest_running_kernel_baseline instead of worst_kernel_increase, very small kernel runtimes are blowing up the worst_kernel_increase metric. * Minor fixes in input arguments * Ruff * Loging PyTorch version * Fix ruff formatting for PyTorch version logging --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
116 wiersze
2.6 KiB
TOML
116 wiersze
2.6 KiB
TOML
[project]
|
|
name = "rocprof_compute"
|
|
requires-python = ">=3.9"
|
|
|
|
[project.optional-dependencies]
|
|
developer = [
|
|
"ruff>=0.12.7",
|
|
"pre-commit",
|
|
]
|
|
|
|
[tool.ruff]
|
|
line-length = 88
|
|
|
|
# Ruff's default excludes cover: .bzr, .direnv, .eggs, .git, .git-rewrite, .hg, .ipynb_checkpoints,
|
|
# .mypy_cache, .nox, .pants.d, .pyenv, .pytest_cache, .pytype, .ruff_cache, .svn,
|
|
# .tox, .venv, .vscode, __pypackages__, _build, buck-out, build, dist, node_modules,
|
|
# site-packages, venv
|
|
|
|
extend-exclude = [
|
|
".github",
|
|
".misc",
|
|
"external",
|
|
"build-rocprof_compute",
|
|
"src/rocprof_compute_analyze/analysis_db.py",
|
|
"src/rocprof_compute_tui/widgets/splitter.py"
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
# Enable Pyflakes (F), pycodestyle (E, W for PEP8), aisort (I),
|
|
# type annotation (ANN), and f-string (UP) rules.
|
|
select = ["E", "W", "F", "I", "ANN", "UP", "PTH"]
|
|
ignore = ["E713", "E711", "UP045", "PTH123", "PTH207"]
|
|
fixable = ["ALL"]
|
|
unfixable = []
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
# Ignore ANN and UP rules for all files except those in src/
|
|
"!src/**" = ["ANN", "UP", "PTH"]
|
|
|
|
[tool.ruff.lint.flake8-annotations]
|
|
allow-star-arg-any = true #allow Any for *args
|
|
ignore-fully-untyped = false #require type annotations
|
|
suppress-dummy-args = true #don't require annotation for "_" arguments
|
|
suppress-none-returning = false #require explicit None return types
|
|
|
|
[tool.ruff.format]
|
|
preview = true
|
|
|
|
# Like Black, use double quotes for strings.
|
|
quote-style = "double"
|
|
|
|
# Like Black, indent with spaces, rather than tabs.
|
|
indent-style = "space"
|
|
|
|
# Like Black, respect magic trailing commas.
|
|
skip-magic-trailing-comma = false
|
|
|
|
# Like Black, automatically detect the appropriate line ending.
|
|
line-ending = "auto"
|
|
|
|
docstring-code-format = true
|
|
docstring-code-line-length = "dynamic"
|
|
|
|
|
|
[tool.pytest.ini_options]
|
|
addopts = [
|
|
"--import-mode=importlib",
|
|
]
|
|
|
|
pythonpath = [
|
|
".",
|
|
"src",
|
|
"src/rocprof_compute_soc",
|
|
"src/utils",
|
|
"src/rocprof_compute_analyze/utils",
|
|
"tests"
|
|
]
|
|
|
|
markers = [
|
|
"section",
|
|
"kernel_execution",
|
|
"misc",
|
|
"mem",
|
|
"sort",
|
|
"join",
|
|
"verbosity",
|
|
"dispatch",
|
|
"list_metrics",
|
|
"filter_block",
|
|
"filter_kernel",
|
|
"dispatch",
|
|
"normal_unit",
|
|
"max_stat",
|
|
"time_unit",
|
|
"decimal",
|
|
"col",
|
|
"kernel_verbose",
|
|
"serial",
|
|
"L1_cache",
|
|
"num_xcds_spec_class",
|
|
"num_xcds_cli_output",
|
|
"sets_func",
|
|
"sets_perf",
|
|
"pc_sampling",
|
|
"live_attach_detach",
|
|
"roofline_1",
|
|
"roofline_2",
|
|
"path",
|
|
"sci_notion",
|
|
"iteration_multiplexing_1",
|
|
"iteration_multiplexing_2",
|
|
"iteration_multiplexing_stochastic",
|
|
"noise_clamp",
|
|
"torch_ops",
|
|
]
|