56fd68e7dd
CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
CUDA CCCL Python Package
cuda.cccl
provides a Pythonic interface to the
CUDA Core Compute Libraries.
It provides the following modules:
cuda.compute- Device-level parallel algorithms (reduce, scan, sort, etc.) and iteratorscuda.cccl.headers- Programmatic access to CCCL headers
Installation
Install from PyPI:
pip install cuda-cccl[cu13] # For CUDA 13.x (pip-installed cuda-toolkit)
pip install cuda-cccl[cu12] # For CUDA 12.x (pip-installed cuda-toolkit)
If you already have a CUDA toolkit on your system and do not want pip to
install it, use the sysctk variants:
pip install cuda-cccl[sysctk13] # For CUDA 13.x (system CUDA toolkit)
pip install cuda-cccl[sysctk12] # For CUDA 12.x (system CUDA toolkit)
For a minimal install without Numba (useful when supplying pre-compiled operators):
pip install cuda-cccl[minimal-cu13] # pip-installed cuda-toolkit
pip install cuda-cccl[minimal-sysctk13] # system CUDA toolkit
Install from conda-forge:
conda install -c conda-forge cccl-python
Requirements: Python 3.10+, CUDA Toolkit 12.x or 13.x, NVIDIA GPU with Compute Capability 7.5+
Documentation
For complete documentation, examples, and API reference, visit:
- Full Documentation: nvidia.github.io/cccl/python
- Repository: github.com/NVIDIA/cccl
- Examples: github.com/NVIDIA/cccl/tree/main/python/cuda_cccl/tests/compute/examples