56fd68e7dd
CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
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);
|
|
}
|
|
}
|