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
54 lines
1.9 KiB
Plaintext
54 lines
1.9 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of CUDA Experimental 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) 2025 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Example of using `cub::DeviceReduce::Reduce` with cudax environment.
|
|
|
|
#include <cub/device/device_reduce.cuh>
|
|
|
|
#include <cuda/experimental/container.cuh>
|
|
#include <cuda/experimental/memory_resource.cuh>
|
|
#include <cuda/experimental/stream.cuh>
|
|
|
|
#include <iostream>
|
|
|
|
namespace cudax = cuda::experimental;
|
|
|
|
int main()
|
|
{
|
|
constexpr int num_items = 50000;
|
|
|
|
// A CUDA stream on which to execute the reduction
|
|
cuda::stream stream{cuda::devices[0]};
|
|
cuda::device_memory_pool_ref mr = cuda::device_default_memory_pool(cuda::devices[0]);
|
|
|
|
// Allocate input and output, but do not zero initialize output (`cuda::no_init`)
|
|
auto d_in = cuda::make_buffer<int>(stream, mr, num_items, 1);
|
|
auto d_out = cuda::make_buffer<float>(stream, mr, 1, cuda::no_init);
|
|
|
|
// An environment we use to pass all necessary information to CUB
|
|
cudax::env_t<cuda::mr::device_accessible> env{mr, stream};
|
|
auto error = cub::DeviceReduce::Reduce(d_in.begin(), d_out.begin(), num_items, cuda::std::plus{}, 0, env);
|
|
if (error != cudaSuccess)
|
|
{
|
|
std::cerr << "cub::DeviceReduce::Reduce failed: " << cudaGetErrorString(error) << "\n";
|
|
exit(EXIT_FAILURE);
|
|
}
|
|
|
|
auto h_out = cuda::make_buffer<float>(stream, cuda::pinned_default_memory_pool(), d_out);
|
|
|
|
stream.sync();
|
|
|
|
if (h_out.get_unsynchronized(0) != num_items)
|
|
{
|
|
std::cerr << "Result verification failed: " << h_out.get_unsynchronized(0) << " != " << num_items << "\n";
|
|
exit(EXIT_FAILURE);
|
|
}
|
|
}
|