# andikleen/pmu-tools

Intel PMU profiling tools

Repository: https://github.com/andikleen/pmu-tools
Canonical: https://ross.abutalabs.com/products/pmu-tools
Language: Python
License: GPL-2.0
License Family: copyleft
Last push: 2026-07-24T05:02:11+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 35, longevity 100
- inputs: {"age_days": 4863, "days_push": 40, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2245, forks 360 (observed 2026-08-28T04:06:30.064747+00:00)

## What it is
pmu-tools is a collection of Python tools and C libraries for profile collection and performance analysis on Intel CPUs, built on top of Linux perf and CPU performance counters. Its main tools, toplev and ocperf, provide top-down bottleneck analysis and access to Intel event lists.

## Use cases
- profile a program on Intel CPUs using performance counters
- find CPU bottlenecks with top-down analysis
- run Intel perf events not supported by stock perf
- measure whole-system performance during a workload
- sample the location of bottlenecks in a workload

## When to choose
- you need deep hardware-level performance analysis on Intel CPUs on Linux
- you want automated bottleneck identification without manual counter setup
- you need access to the full Intel perfmon event lists

## When to avoid
- you are profiling on AMD or ARM CPUs
- you need a GUI-based profiler
- you are on a non-Linux platform

## Facets
- artifact type: cli-tool
- maturity: active
- function: benchmarking, monitoring, developer-tools, cli
- domain: performance, developer-tools
- platform: python, cli
- tags: intel-pmu, perf, profiling, performance-counters, top-down-analysis, hardware-profiling, command-line, linux

## Member repositories
- andikleen/pmu-tools (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:30.064747+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:43:59.771807+00:00, confidence not recorded.
  - readme: https://github.com/andikleen/pmu-tools (fetched 2026-08-28T04:06:30.064747+00:00, sha 586d7b905199)
  - registry_pypi: https://pypi.org/pypi/pmu-tools/json (fetched 2026-08-29T10:24:20.603303+00:00, sha fd637a2170a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.