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
73 lines
1.9 KiB
Plaintext
73 lines
1.9 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.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
__global__ void swap_kernel(slice<double> dst, slice<double> src)
|
|
{
|
|
size_t tid = threadIdx.x + blockIdx.x * blockDim.x;
|
|
size_t nthreads = blockDim.x * gridDim.x;
|
|
size_t n = dst.size();
|
|
|
|
for (size_t i = tid; i < n; i += nthreads)
|
|
{
|
|
double tmp = dst(i);
|
|
dst(i) = src(i);
|
|
src(i) = tmp;
|
|
}
|
|
}
|
|
|
|
int main(int argc, char** argv)
|
|
{
|
|
stream_ctx ctx;
|
|
const size_t N = 16;
|
|
double X[N], Y[N];
|
|
|
|
for (size_t i = 0; i < N; i++)
|
|
{
|
|
X[i] = 1.0;
|
|
Y[i] = 2.0;
|
|
}
|
|
|
|
auto lX = ctx.logical_data(X);
|
|
auto lY = ctx.logical_data(Y);
|
|
|
|
#ifdef NDEBUG
|
|
size_t iter_cnt = 10000000;
|
|
#else
|
|
size_t iter_cnt = 10000;
|
|
fprintf(stderr, "Warning: Running with small problem size in debug mode, should use DEBUG=0.\n");
|
|
#endif
|
|
|
|
if (argc > 1)
|
|
{
|
|
iter_cnt = atol(argv[1]);
|
|
}
|
|
|
|
std::chrono::steady_clock::time_point start, stop;
|
|
start = std::chrono::steady_clock::now();
|
|
for (size_t iter = 0; iter < iter_cnt; iter++)
|
|
{
|
|
ctx.task(lX.rw(), lY.rw())->*[&](cudaStream_t s, auto dX, auto dY) {
|
|
swap_kernel<<<4, 16, 0, s>>>(dY, dX);
|
|
};
|
|
ctx.task(lY.rw(), lX.rw())->*[&](cudaStream_t s, auto dY, auto dX) {
|
|
swap_kernel<<<4, 16, 0, s>>>(dX, dY);
|
|
};
|
|
}
|
|
stop = std::chrono::steady_clock::now();
|
|
ctx.finalize();
|
|
|
|
std::chrono::duration<double> duration = stop - start;
|
|
fprintf(stderr, "Elapsed: %.2lf us per task pair\n", duration.count() * 1000000.0 / (iter_cnt));
|
|
}
|