# NVIDIA/thrust

[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl

Repository: https://github.com/NVIDIA/thrust
Canonical: https://ross.abutalabs.com/products/thrust
Language: C++
License: NOASSERTION
License Family: other
Topics: cuda, nvidia-hpc-sdk, thrust, gpu, cpp, cpp11, cpp14, cpp17, cpp20, cxx, cxx11, cxx14, cxx17, cxx20, algorithms, nvidia, gpu-computing
Archived: true
Last push: 2024-02-08T15:54:40+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 5294, "days_push": 937, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5002, forks 760 (observed 2026-08-28T04:09:04.497235+00:00)

## What it is
Thrust is a C++ parallel algorithms library providing an STL-like high-level interface for GPU and multicore CPU computing, built on CUDA, TBB, and OpenMP backends. This repository is archived; development has moved to the unified NVIDIA/cccl repository.

## Use cases
- sort large arrays on the GPU with C++
- parallel reductions and scans in CUDA
- write performance-portable parallel C++ code
- replace hand-written CUDA kernels with high-level algorithms
- transfer data between host and device vectors
- generate random numbers in parallel

## When to choose
- you want STL-style parallel algorithms on NVIDIA GPUs
- you need productivity over fine-grained kernel control
- you are already using the CUDA Toolkit or NVIDIA HPC SDK

## When to avoid
- you need the latest updates - use NVIDIA/cccl instead
- you require fine-grained control over CUDA kernels and memory
- you target non-NVIDIA GPUs exclusively

## Facets
- artifact type: library
- maturity: maintenance
- function: gpu-computing, concurrency, math
- domain: gpu-computing, developer-tools, performance
- platform: cpp, cross-platform
- tags: parallel-algorithms, cuda, stl-like, archived, nvidia, hpc, algorithms, gpu

## Member repositories
- NVIDIA/thrust (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:04.497235+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 2026-08-29T18:17:35.344741+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/thrust (fetched 2026-08-28T04:09:04.497235+00:00, sha b7ef3b6f7244)
- Data as of 2026-08-30T08:39:29.467469+00:00.