[rocprof-compute] Generalize Roofline (#325)

* per kernel analysis Roofline

* added per-kernel eval_metric calculation with display

* fixed typo

* updated tty.py show_all()

* formatting

* fixed ctest failures and updated equations

* formatting

* updated metric descriptoins

* review tweaks

* update docs

* added roofline gui analysis

* updated GUI docs

* updated print statement

* comment tweaks and ran ruff formatting
This commit is contained in:
jamessiddeley-amd
2025-08-20 09:58:08 -04:00
committed by GitHub
parent 71b725f307
commit 5840940caa
26 changed files with 2612 additions and 158 deletions
@@ -1676,9 +1676,9 @@ class TestSetsIntegration:
memory_metrics = ["16.1.2", "17.1.0"]
for metric_id in memory_metrics:
assert (
metric_id in open(Path(workload_dir) / "log.txt", "r").read()
), f"Expected memory metric {metric_id} not found"
assert metric_id in open(Path(workload_dir) / "log.txt", "r").read(), (
f"Expected memory metric {metric_id} not found"
)
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@@ -1745,7 +1745,9 @@ class TestSetsIntegration:
assert returncode == 1
test_utils.clean_output_dir(config["cleanup"], workload_dir)
def test_set_and_block_mutual_exclusion(self, binary_handler_profile_rocprof_compute):
def test_set_and_block_mutual_exclusion(
self, binary_handler_profile_rocprof_compute
):
options = ["--set", "compute_thruput_util", "--block", "12"]
workload_dir = test_utils.get_output_dir()
@@ -30,18 +30,17 @@ import json
import locale
import logging
import os
import tempfile
import pathlib
import re
import shutil
import subprocess
import tempfile
from pathlib import Path
from types import SimpleNamespace
from unittest import mock
import pandas as pd
import pytest
import yaml
import utils.utils as utils