# pytorch/cpuinfo

CPU INFOrmation library (x86/x86-64/ARM/ARM64, Linux/Windows/Android/macOS/iOS)

Repository: https://github.com/pytorch/cpuinfo
Canonical: https://ross.abutalabs.com/products/cpuinfo
Language: C
License: BSD-2-Clause
License Family: permissive
Topics: cpu, cpu-model, instruction-set, cpu-cache, cpu-topology, cpuid
Last push: 2026-07-30T17:32:33+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 100
- inputs: {"age_days": 3470, "days_push": 34, "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 1187, forks 411 (observed 2026-08-28T04:03:55.301290+00:00)

## What it is
A C/C++ library that detects CPU information essential for performance optimization, including supported instruction sets, cache details, core microarchitectures, and topology. It works across x86/x86-64/ARM/ARM64 architectures on Linux, Windows, macOS, Android, iOS, and FreeBSD.

## Use cases
- detect which SIMD instruction sets the host CPU supports
- get CPU cache sizes and topology for performance tuning
- identify CPU microarchitecture at runtime to dispatch optimized code paths
- query processor name and vendor on mobile and desktop platforms
- handle heterogeneous cores like big.LITTLE in thread scheduling
- check if ARM NEON or x86 AVX is available before running optimized kernels

## When to choose
- you need reliable, production-quality CPU feature and topology detection across multiple OSes and architectures
- you are writing performance-critical C/C++ code that dispatches based on CPU capabilities
- you target heterogeneous mobile SoCs and need per-core microarchitecture or cache info

## When to avoid
- you only need basic CPU counts or simple feature flags available via OS APIs or std::thread::hardware_concurrency
- you work in a language ecosystem with its own CPU detection (e.g., Python's cpuinfo package)
- you need GPU or other hardware information, not CPU details

## Facets
- artifact type: library
- maturity: stable
- function: developer-tools, sdk
- domain: developer-tools, hardware, performance, cross-platform
- platform: windows, cross-platform, cpp, c
- tags: cpu-detection, cpu-topology, instruction-set, cpu-cache, cpuid, big-little, hardware-info, linux, macos, android, ios

## Member repositories
- pytorch/cpuinfo (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.301290+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 2026-08-30T06:23:43.605095+00:00, confidence not recorded.
  - readme: https://github.com/pytorch/cpuinfo (fetched 2026-08-28T04:03:55.301290+00:00, sha 4a7aa434a652)
- Data as of 2026-08-30T08:39:29.467469+00:00.