dedf08166a
Added 863 files from NVIDIA/cccl sparse checkout: - c2h/ (27 files): Catch2 test helpers — generators, validators, runner - nvbench_helper/ (10 files): Benchmark harness utilities - cmake/ (29 files): CMake presets and build helpers - cudax/ (794 files): Experimental CUDA extensions - AGENTS.md: NVIDIA's official AI agent instructions for CCCL - CMakePresets.json: Standardized build configurations - cccl-version.json: Version tracking Also added CCCL_ASSET_MAP.md mapping all 4295 CCCL files to competition value and PRD items. cccl_upstream now covers 100% of competition-critical assets: - 27 tuning headers (SM80/90/100 benchmark data) - 32 dispatch headers (algorithm implementations) - 60 Thrust examples (correctness verification) - 217 CUB Catch2 tests (regression matrix) - 153 CUB benchmarks (parameter space search) - 18 CUB examples (API verification) - 27 test helpers + benchmark harness - 794 cudax experimental extensions
58 lines
1.5 KiB
Plaintext
58 lines
1.5 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) 2022-2025 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//! @file
|
|
//! @brief Add tasks to a user-provided graph
|
|
|
|
#include <cuda/experimental/__stf/graph/graph_ctx.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
__global__ void dummy() {}
|
|
|
|
int main()
|
|
{
|
|
cudaGraph_t graph;
|
|
cudaGraphExec_t graphExec = NULL;
|
|
cudaStream_t stream;
|
|
|
|
cuda_safe_call(cudaStreamCreateWithFlags(&stream, cudaStreamNonBlocking));
|
|
|
|
cuda_safe_call(cudaGraphCreate(&graph, 0));
|
|
|
|
graph_ctx ctx(graph);
|
|
|
|
auto lX = ctx.token();
|
|
auto lY = ctx.token();
|
|
auto lZ = ctx.token();
|
|
|
|
ctx.task(lX.write())->*[](cudaStream_t s) {
|
|
dummy<<<1, 1, 0, s>>>();
|
|
};
|
|
|
|
ctx.task(lX.read(), lY.write())->*[](cudaStream_t s) {
|
|
dummy<<<1, 1, 0, s>>>();
|
|
};
|
|
|
|
ctx.task(lX.read(), lZ.write())->*[](cudaStream_t s) {
|
|
dummy<<<1, 1, 0, s>>>();
|
|
};
|
|
|
|
ctx.task(lY.rw(), lZ.rw())->*[](cudaStream_t s) {
|
|
dummy<<<1, 1, 0, s>>>();
|
|
};
|
|
|
|
ctx.finalize_as_graph();
|
|
|
|
cuda_safe_call(cudaGraphInstantiate(&graphExec, graph, NULL, NULL, 0));
|
|
cuda_safe_call(cudaGraphLaunch(graphExec, stream));
|
|
cuda_safe_call(cudaStreamSynchronize(stream));
|
|
}
|