# boostorg/compute

A C++ GPU Computing Library for OpenCL

Repository: https://github.com/boostorg/compute
Canonical: https://ross.abutalabs.com/products/compute
Homepage: http://boostorg.github.io/compute/
Language: C++
License: BSL-1.0
License Family: other
Topics: opencl, boost, c-plus-plus, cpp, compute, gpu, gpgpu, performance, hpc
Last push: 2026-08-12T11:35:26+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 100
- inputs: {"age_days": 4932, "days_push": 21, "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 1660, forks 339 (observed 2026-08-28T04:05:18.340158+00:00)

## What it is
Boost.Compute is a C++ GPU/parallel-computing library built on OpenCL, providing a thin C++ wrapper over the OpenCL API plus an STL-like interface with containers, algorithms, and fancy iterators. It is header-only and lets developers run computations like sorting and reductions on GPUs and multi-core CPUs.

## Use cases
- sort large arrays of floats on the GPU
- run parallel reductions and scans on OpenCL devices
- copy data between host and GPU device memory
- use STL-style algorithms like transform and accumulate on the GPU
- write portable GPGPU code in C++ without raw OpenCL boilerplate
- interoperate with the OpenCL and OpenGL APIs

## When to choose
- you want an STL-like C++ interface for OpenCL GPU computing
- you need portable GPGPU code across OpenCL implementations
- you prefer a header-only library with no linking step
- you want common parallel algorithms and containers out of the box

## When to avoid
- you need CUDA-specific features or NVIDIA-only optimizations
- you want actively developed cutting-edge GPU compute features
- you target platforms without OpenCL support
- you need a modern C++ GPU library like SYCL instead

## Facets
- artifact type: library
- maturity: maintenance
- function: gpu-computing, math, concurrency
- domain: gpu-computing, performance, developer-tools
- platform: cpp, cross-platform
- tags: opencl, gpgpu, stl-like, header-only, parallel-computing, boost, algorithms, gpu

## Member repositories
- boostorg/compute (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:18.340158+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 2026-08-30T03:44:40.015060+00:00, confidence not recorded.
  - readme: https://github.com/boostorg/compute (fetched 2026-08-28T04:05:18.340158+00:00, sha 479e600218cd)
  - homepage: http://boostorg.github.io/compute/ (fetched 2026-08-29T11:17:00.992921+00:00, sha 12348e288e39)
- Data as of 2026-08-30T08:39:29.467469+00:00.