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
57 lines
1.3 KiB
Plaintext
57 lines
1.3 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 Test explicit uses of the API to change stage and create a sequence
|
|
* of CUDA graphs
|
|
*/
|
|
|
|
#include <cuda/experimental/__stf/graph/graph_ctx.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
int main()
|
|
{
|
|
graph_ctx ctx;
|
|
|
|
const size_t N = 8;
|
|
const size_t NITER = 2;
|
|
|
|
double A[N];
|
|
for (size_t i = 0; i < N; i++)
|
|
{
|
|
A[i] = 1.0 * i;
|
|
}
|
|
|
|
auto lA = ctx.logical_data(A);
|
|
|
|
for (size_t k = 0; k < NITER; k++)
|
|
{
|
|
ctx.parallel_for(blocked_partition(), exec_place::current_device(), lA.shape(), lA.rw())
|
|
->*[] __host__ __device__(size_t i, slice<double> A) { A(i) = cos(A(i)); };
|
|
|
|
ctx.change_stage();
|
|
}
|
|
|
|
ctx.finalize();
|
|
|
|
for (size_t i = 0; i < N; i++)
|
|
{
|
|
double Ai_ref = 1.0 * i;
|
|
for (size_t k = 0; k < NITER; k++)
|
|
{
|
|
Ai_ref = cos(Ai_ref);
|
|
}
|
|
|
|
EXPECT(fabs(A[i] - Ai_ref) < 0.01);
|
|
}
|
|
}
|