Add single kernel filtering to roofline plots (#757)

* Add single kernel filtering for roofline
* Add --kernel to documentation
* Add kernel labels to roofline pdfs

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

* Add test cases

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

* Add autodetect for mode (profile or analyze) during roof validate and filter
Prevent --kernel from affecting roofline in gui mode- although this may be broken in develop branch anyways

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

* Add note about roof-only usage checking for existing profiling files in the dir. If roof-only is not provided, rocprof-compute currently assumes it has to profile in full regardless. Will look into this another day.

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

* Update CHANGELOG.md

Add line in resolved issues section to highlight that kernel filtering is now working for roofline plots

* Apply changes suggested by docs team

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

* Update projects/rocprofiler-compute/CHANGELOG.md

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>
This commit is contained in:
cfallows-amd
2025-08-27 13:41:07 -04:00
کامیت شده توسط GitHub
والد 2e50d88fe6
کامیت c68ba44e72
5فایلهای تغییر یافته به همراه129 افزوده شده و 8 حذف شده
@@ -895,9 +895,48 @@ def test_roofline_empty_kernel_names_handling(binary_handler_profile_rocprof_com
]
workload_dir = test_utils.get_output_dir()
returncode = binary_handler_profile_rocprof_compute( # noqa: F841
config, workload_dir, options, check_success=True, roof=True
)
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@pytest.mark.misc
def test_roofline_kernel_filter(binary_handler_profile_rocprof_compute):
"""
Test roofline multi-attempt profiling with `--kernel`
Expect to be able to re-profile from same workload if kernels are valid.
(Validity of --kernels tested in test_roofline_kernel_filter_error_handling already)
"""
if soc in ("MI100"):
pytest.skip("Skipping roofline test for MI100")
return
options = [
"--device",
"0",
"--roof-only",
"--kernel-names",
]
workload_dir = test_utils.get_output_dir()
returncode = binary_handler_profile_rocprof_compute( # noqa: F841
config, workload_dir, options, check_success=True, roof=True
)
# Don't clean output dir, use same workload
options.extend(["--kernel", config["kernel_name_1"]])
returncode = binary_handler_profile_rocprof_compute( # noqa: F841
config, workload_dir, options, check_success=True, roof=True
)
# Test nonexistent kernel on roof profile using existing profiling data
# Since already profiled, throw error if non-existent kernel requested for roofline
options.append("nonexistent_kernel_name_that_should_not_match_anything")
returncode = binary_handler_profile_rocprof_compute( # noqa: F841
config, workload_dir, options, check_success=False, roof=True
)
assert returncode == 1
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@@ -934,6 +973,10 @@ def test_roof_plot_modes(binary_handler_profile_rocprof_compute):
assert True
return
# Test `--kernel` filtering outputs are present and labelled correctly
filter_kernelName = "kernelName_legend_" + config["kernel_name_1"]
filter_empirRoof = "empirRoof_gpu-0_" + config["kernel_name_1"]
plot_configurations = [
{
"options": ["--device", "0", "--roof-only", "--roofline-data-type", "FP32"],
@@ -944,8 +987,15 @@ def test_roof_plot_modes(binary_handler_profile_rocprof_compute):
"expected_files": ["empirRoof_gpu-0_FP16.pdf"],
},
{
"options": ["--device", "0", "--roof-only", "--kernel-names"],
"expected_files": ["kernelName_legend.pdf"],
"options": [
"--device",
"0",
"--roof-only",
"--kernel-names",
"--kernel",
config["kernel_name_1"],
],
"expected_files": [filter_kernelName, filter_empirRoof],
},
]