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
1.4 KiB
Plaintext
58 lines
1.4 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.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/**
|
|
* @file
|
|
*
|
|
* @brief Illustrate how to use the void data interface
|
|
*
|
|
*/
|
|
|
|
#include <cuda/experimental/stf.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
__global__ void dummy_kernel() {}
|
|
|
|
int main()
|
|
{
|
|
context ctx;
|
|
|
|
auto token = ctx.token();
|
|
ctx.task(token.write())->*[](cudaStream_t) {
|
|
|
|
};
|
|
|
|
void_interface sync;
|
|
auto token2 = ctx.logical_data(sync);
|
|
|
|
auto token3 = ctx.token();
|
|
ctx.task(token2.write(), token.read())->*[](cudaStream_t) {
|
|
|
|
};
|
|
|
|
// Do not pass useless arguments by removing void_interface arguments
|
|
// Note that the rw() access is possible even if there was no prior write()
|
|
// or actual underlying data.
|
|
ctx.task(token3.rw(), token.read())->*[](cudaStream_t) {
|
|
|
|
};
|
|
|
|
ctx.cuda_kernel(token3.rw())->*[]() {
|
|
return cuda_kernel_desc{dummy_kernel, 16, 128, 0};
|
|
};
|
|
|
|
EXPECT(token.is_void_interface());
|
|
EXPECT(token2.is_void_interface());
|
|
EXPECT(token3.is_void_interface());
|
|
|
|
ctx.finalize();
|
|
}
|