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
70 lines
1.6 KiB
C++
70 lines
1.6 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <cuda/std/atomic>
|
|
|
|
#include "test_macros.h"
|
|
|
|
template <class A, class T>
|
|
TEST_FUNC bool cmpxchg_weak_loop(A& atomic, T& expected, T desired)
|
|
{
|
|
for (int i = 0; i < 10; i++)
|
|
{
|
|
if (atomic.compare_exchange_weak(expected, desired) == true)
|
|
{
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
template <class A, class T>
|
|
TEST_FUNC bool
|
|
cmpxchg_weak_loop(A& atomic, T& expected, T desired, cuda::std::memory_order success, cuda::std::memory_order failure)
|
|
{
|
|
for (int i = 0; i < 10; i++)
|
|
{
|
|
if (atomic.compare_exchange_weak(expected, desired, success, failure) == true)
|
|
{
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
template <class A, class T>
|
|
TEST_FUNC bool c_cmpxchg_weak_loop(A* atomic, T* expected, T desired)
|
|
{
|
|
for (int i = 0; i < 10; i++)
|
|
{
|
|
if (cuda::std::atomic_compare_exchange_weak(atomic, expected, desired) == true)
|
|
{
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
template <class A, class T>
|
|
TEST_FUNC bool
|
|
c_cmpxchg_weak_loop(A* atomic, T* expected, T desired, cuda::std::memory_order success, cuda::std::memory_order failure)
|
|
{
|
|
for (int i = 0; i < 10; i++)
|
|
{
|
|
if (cuda::std::atomic_compare_exchange_weak_explicit(atomic, expected, desired, success, failure) == true)
|
|
{
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|