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
82 lines
2.1 KiB
Plaintext
82 lines
2.1 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) 2024 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <cuda/std/__algorithm/max.h>
|
|
|
|
#include <cuda/experimental/execution.cuh>
|
|
|
|
#include "testing.cuh" // IWYU pragma: keep
|
|
|
|
namespace
|
|
{
|
|
struct S0
|
|
{};
|
|
struct S1
|
|
{
|
|
int a;
|
|
};
|
|
struct S2
|
|
{
|
|
int a, b;
|
|
};
|
|
static_assert(cudax_async::structured_binding_size<S0> == 0);
|
|
static_assert(cudax_async::structured_binding_size<S1> == 1);
|
|
static_assert(cudax_async::structured_binding_size<S2> == 2);
|
|
|
|
template <class Fn>
|
|
struct recursive_lambda
|
|
{
|
|
template <class... Args>
|
|
auto operator()(Args&&... args)
|
|
{
|
|
return fn(*this, cuda::std::forward<Args>(args)...);
|
|
}
|
|
|
|
Fn fn;
|
|
};
|
|
|
|
template <class Fn>
|
|
recursive_lambda(Fn) -> recursive_lambda<Fn>;
|
|
|
|
C2H_TEST("sender visitation API works", "[visit]")
|
|
{
|
|
int leaves = 0;
|
|
int depth = 0;
|
|
|
|
auto snd = cudax_async::when_all(
|
|
cudax_async::just(3), //
|
|
cudax_async::just(0.1415),
|
|
cudax_async::then(cudax_async::just(0.1415), [](double f) {
|
|
return f;
|
|
}));
|
|
auto snd1 = std::move(snd) | cudax_async::then([](int x, double y, double z) {
|
|
return x + y + z;
|
|
});
|
|
|
|
auto count_leaves = recursive_lambda{[](auto& self, int& leaves, auto, auto&, auto&... child) {
|
|
leaves += (sizeof...(child) == 0);
|
|
((cudax_async::visit(self, child, leaves)), ...);
|
|
}};
|
|
|
|
cudax_async::visit(count_leaves, snd1, leaves);
|
|
CHECK(leaves == 3);
|
|
|
|
auto max_depth = recursive_lambda{[i = 0](auto& self, int& depth, auto, auto&, auto&... child) mutable {
|
|
++i;
|
|
depth = cuda::std::max(depth, i);
|
|
((cudax_async::visit(self, child, depth)), ...);
|
|
--i;
|
|
}};
|
|
|
|
cudax_async::visit(max_depth, snd1, depth);
|
|
CHECK(depth == 4);
|
|
}
|
|
} // namespace
|