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
19 lines
545 B
Plaintext
19 lines
545 B
Plaintext
#define _CCCL_BEFORE_NVTX_RANGE_SCOPE(name) static_assert(false);
|
|
#define CCCL_DISABLE_NVTX
|
|
|
|
#include <cub/device/device_for.cuh>
|
|
|
|
#include <cuda/iterator>
|
|
#include <cuda/std/functional>
|
|
|
|
#if defined(CCCL_DISABLE_NVTX) && defined(NVTX_VERSION)
|
|
# error "NVTX was included somewhere even though it is turned off via CCCL_DISABLE_NVTX"
|
|
#endif // defined(CCCL_DISABLE_NVTX) && defined(NVTX_VERSION)
|
|
|
|
int main()
|
|
{
|
|
cuda::counting_iterator<int> it{0};
|
|
cub::DeviceFor::ForEach(it, it + 16, ::cuda::std::negate<int>{});
|
|
cudaDeviceSynchronize();
|
|
}
|