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
49 lines
1.3 KiB
Plaintext
49 lines
1.3 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of CUDA Experimental 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) 2025 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Include this first
|
|
#include <cuda/experimental/execution.cuh>
|
|
|
|
// Then include the test helpers
|
|
#include <nv/target>
|
|
|
|
#include "common/checked_receiver.cuh"
|
|
#include "common/utility.cuh"
|
|
#include "testing.cuh"
|
|
|
|
namespace ex = cuda::experimental::execution;
|
|
|
|
namespace
|
|
{
|
|
C2H_TEST("simple use of sequence executes both child operations", "[adaptors][sequence]")
|
|
{
|
|
bool flag1{false};
|
|
bool flag2{false};
|
|
|
|
auto sndr1 = ex::sequence(
|
|
ex::just() | ex::then([&] {
|
|
flag1 = true;
|
|
}),
|
|
ex::just() | ex::then([&] {
|
|
flag2 = true;
|
|
}));
|
|
|
|
check_value_types<types<>>(sndr1);
|
|
check_sends_stopped<false>(sndr1);
|
|
check_error_types<ex::exception_ptr>(sndr1);
|
|
|
|
auto op = ex::connect(std::move(sndr1), checked_value_receiver<>{});
|
|
ex::start(op);
|
|
|
|
CHECK(flag1);
|
|
CHECK(flag2);
|
|
}
|
|
} // namespace
|