dedf08166a
Added 863 files from NVIDIA/cccl sparse checkout: - c2h/ (27 files): Catch2 test helpers — generators, validators, runner - nvbench_helper/ (10 files): Benchmark harness utilities - cmake/ (29 files): CMake presets and build helpers - cudax/ (794 files): Experimental CUDA extensions - AGENTS.md: NVIDIA's official AI agent instructions for CCCL - CMakePresets.json: Standardized build configurations - cccl-version.json: Version tracking Also added CCCL_ASSET_MAP.md mapping all 4295 CCCL files to competition value and PRD items. cccl_upstream now covers 100% of competition-critical assets: - 27 tuning headers (SM80/90/100 benchmark data) - 32 dispatch headers (algorithm implementations) - 60 Thrust examples (correctness verification) - 217 CUB Catch2 tests (regression matrix) - 153 CUB benchmarks (parameter space search) - 18 CUB examples (API verification) - 27 test helpers + benchmark harness - 794 cudax experimental extensions
121 lines
3.6 KiB
Plaintext
121 lines
3.6 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.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#pragma once
|
|
|
|
#include <cuda/__utility/immovable.h>
|
|
|
|
#include <cuda/experimental/execution.cuh>
|
|
|
|
#include "testing.cuh" // IWYU pragma: keep
|
|
|
|
namespace
|
|
{
|
|
struct _stopped_scheduler_attrs_t
|
|
{
|
|
template <class _Env>
|
|
_CCCL_HOST_DEVICE auto
|
|
query(cudax_async::get_completion_scheduler_t<cudax_async::set_value_t>, const _Env& env) const noexcept
|
|
-> decltype(cudax_async::get_completion_scheduler<cudax_async::set_value_t>(env, env))
|
|
{
|
|
return cudax_async::get_completion_scheduler<cudax_async::set_value_t>(env, env);
|
|
}
|
|
|
|
template <class _Env>
|
|
_CCCL_HOST_DEVICE auto
|
|
query(cudax_async::get_completion_scheduler_t<cudax_async::set_stopped_t>, const _Env& env) const noexcept
|
|
-> decltype(cudax_async::get_completion_scheduler<cudax_async::set_stopped_t>(env, env))
|
|
{
|
|
return cudax_async::get_completion_scheduler<cudax_async::set_stopped_t>(env, env);
|
|
}
|
|
|
|
template <class _Env>
|
|
_CCCL_HOST_DEVICE auto
|
|
query(cudax_async::get_completion_domain_t<cudax_async::set_value_t>, const _Env& env) const noexcept
|
|
-> decltype(cudax_async::get_completion_domain<cudax_async::set_value_t>(env, env))
|
|
{
|
|
return cudax_async::get_completion_domain<cudax_async::set_value_t>(env, env);
|
|
}
|
|
|
|
template <class _Env>
|
|
_CCCL_HOST_DEVICE auto
|
|
query(cudax_async::get_completion_domain_t<cudax_async::set_stopped_t>, const _Env& env) const noexcept
|
|
-> decltype(cudax_async::get_completion_domain<cudax_async::set_stopped_t>(env, env))
|
|
{
|
|
return cudax_async::get_completion_domain<cudax_async::set_stopped_t>(env, env);
|
|
}
|
|
|
|
_CCCL_HOST_DEVICE static constexpr auto query(cudax_async::get_completion_behavior_t) noexcept
|
|
{
|
|
return cudax_async::completion_behavior::inline_completion;
|
|
}
|
|
};
|
|
|
|
//! Scheduler that returns a sender that always completes with stopped.
|
|
struct stopped_scheduler : _stopped_scheduler_attrs_t
|
|
{
|
|
private:
|
|
template <class Rcvr>
|
|
struct _opstate_t : cuda::__immovable
|
|
{
|
|
using operation_state_concept = cudax_async::operation_state_t;
|
|
|
|
Rcvr _rcvr;
|
|
|
|
_CCCL_HOST_DEVICE void start() noexcept
|
|
{
|
|
cudax_async::set_stopped(static_cast<Rcvr&&>(_rcvr));
|
|
}
|
|
};
|
|
|
|
struct _sndr_t
|
|
{
|
|
using sender_concept = cudax_async::sender_t;
|
|
|
|
template <class Self>
|
|
_CCCL_HOST_DEVICE static constexpr auto get_completion_signatures()
|
|
{
|
|
return cudax_async::completion_signatures<cudax_async::set_value_t(), cudax_async::set_stopped_t()>();
|
|
}
|
|
|
|
template <class Rcvr>
|
|
_CCCL_HOST_DEVICE auto connect(Rcvr rcvr) const noexcept -> _opstate_t<Rcvr>
|
|
{
|
|
return {{}, static_cast<Rcvr&&>(rcvr)};
|
|
}
|
|
|
|
_CCCL_HOST_DEVICE auto get_env() const noexcept -> _stopped_scheduler_attrs_t
|
|
{
|
|
return {};
|
|
}
|
|
};
|
|
|
|
public:
|
|
using scheduler_concept = cudax_async::scheduler_t;
|
|
|
|
stopped_scheduler() = default;
|
|
|
|
_CCCL_HOST_DEVICE auto schedule() const noexcept -> _sndr_t
|
|
{
|
|
return {};
|
|
}
|
|
|
|
_CCCL_HOST_DEVICE friend constexpr bool operator==(stopped_scheduler, stopped_scheduler) noexcept
|
|
{
|
|
return true;
|
|
}
|
|
|
|
_CCCL_HOST_DEVICE friend constexpr bool operator!=(stopped_scheduler, stopped_scheduler) noexcept
|
|
{
|
|
return false;
|
|
}
|
|
};
|
|
} // namespace
|