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
48 lines
1.2 KiB
Plaintext
48 lines
1.2 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) 2022-2025 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/**
|
|
* @file
|
|
* @brief Test if dot section guards are movable and if we can them as an optional value
|
|
*/
|
|
|
|
#include <cuda/experimental/stf.cuh>
|
|
|
|
#include <optional>
|
|
#include <vector>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
int main()
|
|
{
|
|
context ctx;
|
|
|
|
// Ensure the guard is movable
|
|
{
|
|
auto g = ctx.dot_section("foo");
|
|
auto g2 = mv(g);
|
|
}
|
|
|
|
// Ensure the guard can be stored as an optional
|
|
::std::vector<::std::optional<reserved::dot_section::guard>> nested_sections;
|
|
|
|
for (size_t depth = 0; depth < 3; depth++)
|
|
{
|
|
nested_sections.emplace_back(ctx.dot_section("foo"));
|
|
}
|
|
|
|
for (size_t depth = 0; depth < 3; depth++)
|
|
{
|
|
nested_sections.pop_back();
|
|
}
|
|
|
|
ctx.finalize();
|
|
}
|