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
56 lines
1.4 KiB
Plaintext
56 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 Implementation of the DOT kernel using a reduce access mode
|
|
*
|
|
*/
|
|
|
|
#include <cuda/experimental/stf.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
int main()
|
|
{
|
|
const size_t N = 16;
|
|
double X[N], Y[N];
|
|
|
|
double ref_res = 0.0;
|
|
|
|
for (size_t i = 0; i < N; i++)
|
|
{
|
|
X[i] = cos(double(i));
|
|
Y[i] = sin(double(i));
|
|
|
|
// Compute the reference result of the DOT product of X and Y
|
|
ref_res += X[i] * Y[i];
|
|
}
|
|
|
|
context ctx;
|
|
auto lX = ctx.logical_data(X);
|
|
auto lY = ctx.logical_data(Y);
|
|
|
|
auto lsum = ctx.logical_data(shape_of<scalar_view<double>>());
|
|
|
|
/* Compute sum(x_i * y_i)*/
|
|
ctx.parallel_for(lY.shape(), lX.read(), lY.read(), lsum.reduce(reducer::sum<double>{}))
|
|
->*[] __device__(size_t i, auto dX, auto dY, double& sum) {
|
|
sum += dX(i) * dY(i);
|
|
};
|
|
|
|
double res = ctx.wait(lsum);
|
|
|
|
ctx.finalize();
|
|
|
|
_CCCL_ASSERT(fabs(res - ref_res) < 0.0001, "Invalid result");
|
|
}
|