メニュー
Run C++ and Python tests for amd-smi. Use when: running tests, verifying test results, checking test coverage, pre-review test validation.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/ROCm/rocm-systems --skill amdsmi-test-runnerコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
| name | amdsmi-test-runner |
| description | Run C++ and Python tests for amd-smi. Use when: running tests, verifying test results, checking test coverage, pre-review test validation. |
How to build and run all test suites for amd-smi. Assumes the amdsmi-build-install skill has already been executed (build exists and is installed).
amdsmi-build-install skill first)build/ directory exists with compiled test binariesIf not already built (the build skill builds with -DBUILD_TESTS=ON):
cd build && make -j$(nproc) amdsmitst
cd build/tests
source ../../tests/amd_smi_test/amdsmitst.exclude
source ../../tests/amd_smi_test/detect_asic_filter.sh
./amdsmitst --gtest_filter="-${GTEST_EXCLUDE}"
| Output | Meaning | Severity |
|---|---|---|
[ PASSED ] | Test passed | — |
[ FAILED ] | Test failed | ❌ BLOCKING |
[ SKIPPED ] | Test skipped (blacklisted) | — |
| Binary not found | Build didn't produce test binary | ⚠️ IMPORTANT |
Run the suite files directly (each sys.exit(0/1)):
cd tests/python
python3 unit_tests.py -v
python3 integration_test.py -v
python3 cli_unit_test.py -v
# System install
python3 -c "import amdsmi; print(amdsmi.__version__)"
# Verify CLI works
amd-smi version
amd-smi static
Tests must work in both install contexts:
| Context | How to Verify |
|---|---|
| System install (RPM/DEB) | Default after amdsmi-build-install |
run-all-tests.sh (this skill's directory) runs the C++ GTest, Python unit,
integration, and CLI suites, tees each to a timestamped log dir, and prints a
pass/fail summary. It derives the project root, so run it from anywhere in the tree:
.claude/skills/amdsmi-test-runner/run-all-tests.sh # logs under $TMPDIR/amdsmi-tests-<stamp>/
.claude/skills/amdsmi-test-runner/run-all-tests.sh -o ./ci-logs
Each suite's full output is in <logdir>/<suite>.log; the exit code is non-zero
if any suite failed.
On success, report:
On failure:
Decode and triage HRR capture archives with full GPU replay by default (Linux). Builds hrr-playback when missing. On Windows: full native GPU replay via triage_archive.ps1 + ensure_playback.ps1 (PowerShell); Docker replay requires Linux or WSL2. Never edits source. Print finding summary in the chat reply.
Profiles a target application using rocprofv3 with program counter sampling enabled and then analyzes the results. Use when the user has a program that runs on an AMD GPU and asks to perform PC sampling, to determine the runtime performance characteristics of their application, to determine stall reasons, or to determine hotspots in the code.
Use when writing, planning, or improving unit tests for low-level transport or systems code — especially when reasoning about branch coverage, test gaps, identifying which uncovered paths are worth pursuing, or deciding when a feature's test suite is ready to merge.