# RRZE-HPC/likwid

Performance monitoring and benchmarking suite

Repository: https://github.com/RRZE-HPC/likwid
Canonical: https://ross.abutalabs.com/products/likwid
Homepage: https://hpc.fau.de/research/tools/likwid/
Language: C
License: GPL-3.0
License Family: copyleft
Topics: likwid, hardware-performance-counters, threading, x86, c, lua, hwloc, linux, pin, assembly, benchmarking, instrumentation, profiling, performance-engineering, performance-analysis, armv8, power9, nvidia-gpu, amd-gpu
Last push: 2026-08-19T14:16:28+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 74, longevity 100
- inputs: {"age_days": 4139, "days_push": 14, "days_rel": 14, "gap_med": 138.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1934, forks 272 (observed 2026-08-28T04:05:56.392186+00:00)

## What it is
LIKWID is a command-line tool suite and library for performance-oriented programmers on Linux, supporting Intel, AMD, ARMv8, and POWER9 CPUs plus Nvidia and AMD GPUs. It provides hardware performance counter measurement, CPU pinning, topology inspection, energy monitoring, and micro-benchmarking.

## Use cases
- measure hardware performance counters for my application
- pin threads of an OpenMP program to specific cores
- print CPU cache and NUMA topology
- read RAPL energy consumption of a workload
- run micro-benchmarks for CPU architectures
- control CPU and uncore frequencies
- profile HPC application performance on a cluster

## When to choose
- you need low-level hardware counter profiling on Linux x86, ARM, or POWER
- you are doing HPC performance engineering or teaching
- you want thread pinning and NUMA memory management tools

## When to avoid
- you need profiling on Windows or macOS
- you want a GUI-based profiler
- your workload is GPU-only without supported Nvidia/AMD GPUs

## Facets
- artifact type: cli-tool
- maturity: active
- function: benchmarking, monitoring, developer-tools
- domain: performance, developer-tools
- platform: cli
- tags: hardware-performance-counters, profiling, hpc, numa, cpu-pinning, rapl, openmp, mpi, microbenchmarking, command-line, linux

## Member repositories
- RRZE-HPC/likwid (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:56.392186+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 2026-08-30T03:08:28.801641+00:00, confidence not recorded.
  - readme: https://github.com/RRZE-HPC/likwid (fetched 2026-08-28T04:05:56.392186+00:00, sha 9d7246095639)
  - homepage: https://hpc.fau.de/research/tools/likwid/ (fetched 2026-08-29T10:48:24.798632+00:00, sha c1be60a0f976)
  - site_page: https://hpc.fau.de/about-us/funding (fetched 2026-08-29T10:48:24.806667+00:00, sha 84f89e39af27)
  - site_page: https://hpc.fau.de/about-us/people/liaison-scientists (fetched 2026-08-29T10:48:24.808932+00:00, sha 06b13d45245e)
  - site_page: https://hpc.fau.de/about-us/people/nhr-graduate-school (fetched 2026-08-29T10:48:24.811507+00:00, sha 694fbc3402d9)
  - site_page: https://hpc.fau.de/about-us/nhr-compute-time-projects/list-of-well-known-codes (fetched 2026-08-29T10:48:24.813865+00:00, sha 8f291748d6c7)
  - site_page: https://hpc.fau.de/about-us/hpc-usage-reports/biology-life-sciences-pharmacy/hpc-user-report-from-a-bochicchio-professorship-of-computational-biology (fetched 2026-08-29T10:48:24.815830+00:00, sha c02d53315cf2)
  - site_page: https://hpc.fau.de/about-us/hpc-usage-reports/biology-life-sciences-pharmacy/hpc-user-report-from-a-horn-bioinformatics (fetched 2026-08-29T10:48:24.818072+00:00, sha c0dc5337fd6b)
  - site_page: https://doc.nhr.fau.de/faq (fetched 2026-08-29T10:48:24.801638+00:00, sha 8498b6395041)
  - site_page: https://doc.nhr.fau.de/clusters/overview (fetched 2026-08-29T10:48:24.804759+00:00, sha ec77649b4cf2)
- Data as of 2026-08-30T08:39:29.467469+00:00.