# NVIDIA/cccl

CUDA Core Compute Libraries

Repository: https://github.com/NVIDIA/cccl
Canonical: https://ross.abutalabs.com/products/cccl
Homepage: https://nvidia.github.io/cccl/
Language: C++
License: NOASSERTION
License Family: other
Topics: accelerated-computing, cpp, cpp-programming, cuda, cuda-cpp, cuda-kernels, cuda-library, cuda-programming, gpu, gpu-acceleration, gpu-computing, gpu-programming, hpc, nvidia, nvidia-gpu, parallel-algorithm, parallel-computing, parallel-programming, modern-cpp
Last push: 2026-08-26T21:52:38+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 100
- inputs: {"age_days": 2176, "days_push": 7, "days_rel": 28, "gap_med": 6.5, "n_releases_24m": 47}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2488, forks 476 (observed 2026-08-28T04:06:55.625497+00:00)

## What it is
CUDA Core Compute Libraries (CCCL) is NVIDIA's unified repository for Thrust, CUB, and libcudacxx, providing high-performance C++ abstractions for CUDA GPU programming. It serves as the standard library for CUDA C++, offering parallel algorithms, cooperative kernel building blocks, and host/device-compatible standard library implementations.

## Use cases
- write parallel algorithms on GPUs with a high-level C++ API
- build custom CUDA kernels with block-wide and warp-wide cooperative primitives
- use the C++ standard library in both host and device code
- achieve performance portability across GPUs and multicore CPUs
- reduce, scan, sort, and transform large arrays on NVIDIA GPUs
- write safe and efficient CUDA C++ without hand-tuning every kernel

## When to avoid
- you are targeting non-NVIDIA GPUs or CPU-only parallelism without a supported backend
- you need a runtime or driver-level API rather than C++ header libraries
- your project does not use C++ or CUDA

## Facets
- artifact type: library
- maturity: active
- function: gpu-computing, concurrency, math, developer-tools
- domain: gpu-computing, developer-tools, performance, programming-languages
- platform: cpp, cross-platform
- tags: cuda, thrust, cub, libcudacxx, parallel-algorithms, hpc, nvidia, algorithms, gpu

## Member repositories
- NVIDIA/cccl (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:55.625497+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 2026-08-30T02:27:51.799472+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/cccl (fetched 2026-08-28T04:06:55.625497+00:00, sha 05c15ac8bedb)
  - homepage: https://nvidia.github.io/cccl/ (fetched 2026-08-29T10:09:40.821899+00:00, sha f52048a5b8eb)
- Data as of 2026-08-30T08:39:29.467469+00:00.