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
52 lines
1.3 KiB
Plaintext
52 lines
1.3 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of CUDASTF in CUDA C++ Core Libraries,
|
|
// under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
// SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <cuda/experimental/__stf/graph/graph_ctx.cuh>
|
|
#include <cuda/experimental/__stf/stream/stream_ctx.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
template <typename S>
|
|
__global__ void inc_kernel(S sA)
|
|
{
|
|
sA(threadIdx.x)++;
|
|
}
|
|
|
|
template <typename Ctx>
|
|
void run()
|
|
{
|
|
int A[10] = {0};
|
|
stream_ctx ctx;
|
|
|
|
auto l = ctx.logical_data(A);
|
|
|
|
for (size_t k = 0; k < 10; k++)
|
|
{
|
|
// size_t h = l.hash();
|
|
// fprintf(stderr, "iter %zu : logical data hash %zu ctx.hash %zu\n", k, h, ctx.hash());
|
|
|
|
ctx.task(l.rw())->*[](cudaStream_t stream, auto sA) {
|
|
inc_kernel<<<1, 10, 0, stream>>>(sA);
|
|
};
|
|
}
|
|
|
|
ctx.host_launch(l.read())->*[&](auto /*unused*/) {
|
|
// fprintf(stderr, "HOST end : logical data hash %zu ctx.hash %zu\n", l.hash(), ctx.hash());
|
|
};
|
|
|
|
ctx.finalize();
|
|
}
|
|
|
|
int main()
|
|
{
|
|
run<stream_ctx>();
|
|
run<graph_ctx>();
|
|
}
|