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
75 lines
1.6 KiB
Plaintext
75 lines
1.6 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 Ensure a graph_ctx can be used concurrently
|
|
*
|
|
*/
|
|
|
|
#include <cuda/experimental/stf.cuh>
|
|
|
|
#include <mutex>
|
|
#include <thread>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
void mytask(graph_ctx ctx, int /*id*/)
|
|
{
|
|
const size_t N = 16;
|
|
|
|
int alpha = 3;
|
|
|
|
auto lX = ctx.logical_data<int>(N);
|
|
auto lY = ctx.logical_data<int>(N);
|
|
|
|
ctx.parallel_for(lX.shape(), lX.write(), lY.write())->*[] __device__(size_t i, auto x, auto y) {
|
|
x(i) = (1 + i);
|
|
y(i) = (2 + i * i);
|
|
};
|
|
|
|
/* Compute Y = Y + alpha X */
|
|
for (size_t i = 0; i < 200; i++)
|
|
{
|
|
ctx.parallel_for(lY.shape(), lY.rw(), lX.read())->*[alpha] __device__(size_t i, auto dY, auto dX) {
|
|
dY(i) += alpha * dX(i);
|
|
};
|
|
}
|
|
|
|
ctx.host_launch(lX.read(), lY.read())->*[alpha](auto x, auto y) {
|
|
for (size_t i = 0; i < N; i++)
|
|
{
|
|
EXPECT(x(i) == 1 + i);
|
|
EXPECT(y(i) == 2 + i * i + 200 * alpha * x(i));
|
|
}
|
|
};
|
|
}
|
|
|
|
int main()
|
|
{
|
|
graph_ctx ctx;
|
|
|
|
::std::vector<::std::thread> threads;
|
|
// Launch threads
|
|
for (int i = 0; i < 10; ++i)
|
|
{
|
|
threads.emplace_back(mytask, ctx, i);
|
|
}
|
|
|
|
// Wait for all threads to complete.
|
|
for (auto& th : threads)
|
|
{
|
|
th.join();
|
|
}
|
|
|
|
ctx.finalize();
|
|
}
|