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
53 lines
1.5 KiB
C++
53 lines
1.5 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of libcu++, the C++ Standard Library for your entire system,
|
|
// 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) 2023 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CONCURRENT_AGENTS_H
|
|
#define _CONCURRENT_AGENTS_H
|
|
|
|
#ifndef __CUDA_ARCH__
|
|
# include <thread>
|
|
#endif
|
|
|
|
#include <cuda/std/cassert>
|
|
|
|
#include "test_macros.h"
|
|
|
|
_CCCL_EXEC_CHECK_DISABLE
|
|
template <class Fun>
|
|
TEST_FUNC void execute_on_main_thread(Fun&& fun)
|
|
{
|
|
NV_IF_ELSE_TARGET(NV_IS_DEVICE, (if (threadIdx.x == 0) { fun(); } __syncthreads();), (fun();))
|
|
}
|
|
|
|
template <typename... Fs>
|
|
TEST_FUNC void concurrent_agents_launch(Fs... fs)
|
|
{
|
|
NV_IF_ELSE_TARGET(
|
|
NV_IS_DEVICE,
|
|
(assert(blockDim.x == sizeof...(Fs)); using fptr = void (*)(void*);
|
|
|
|
fptr device_threads[] = {[](void* data) {
|
|
(*reinterpret_cast<Fs*>(data))();
|
|
}...};
|
|
|
|
void* device_thread_data[] = {reinterpret_cast<void*>(&fs)...};
|
|
|
|
__syncthreads();
|
|
|
|
device_threads[threadIdx.x](device_thread_data[threadIdx.x]);
|
|
|
|
__syncthreads();),
|
|
(std::thread threads[]{std::thread{std::forward<Fs>(fs)}...};
|
|
|
|
for (auto&& thread : threads) { thread.join(); }))
|
|
}
|
|
|
|
#endif // _CONCURRENT_AGENTS_H
|