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
530 B
530 B
Once Thrust has been installed, these example programs can be compiled
directly with nvcc. For example, the following command will compile the
norm example.
$ nvcc norm.cu -o norm
These examples are also available online: https://github.com/NVIDIA/cccl/tree/main/thrust/examples
For any serious experimentation, we recommend using CMake and CCCL from GitHub. We also provide consistent and convenient development environments as devcontainers.