work_queue_persistent.h

Go to the documentation of this file.

/*
 * nvbio
 * Copyright (c) 2011-2014, NVIDIA CORPORATION. All rights reserved.
 * 
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *    * Redistributions of source code must retain the above copyright
 *      notice, this list of conditions and the following disclaimer.
 *    * Redistributions in binary form must reproduce the above copyright
 *      notice, this list of conditions and the following disclaimer in the
 *      documentation and/or other materials provided with the distribution.
 *    * Neither the name of the NVIDIA CORPORATION nor the
 *      names of its contributors may be used to endorse or promote products
 *      derived from this software without specific prior written permission.
 * 
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#pragma once

#include <nvbio/basic/types.h>
#include <nvbio/basic/numbers.h>
#include <thrust/device_vector.h>

namespace nvbio {
namespace cuda {


// queue tags
struct PersistentWarpsQueueTag {};
struct PersistentThreadsQueueTag {};

template <
    typename WorkUnitT,
    uint32   BLOCKDIM>
struct WorkQueue<
    PersistentWarpsQueueTag,
    WorkUnitT,
    BLOCKDIM>
{
    typedef WorkUnitT   WorkUnit;

    WorkQueue() : m_capacity(uint32(-1)) {}

    void set_capacity(const uint32 capacity) { m_capacity = capacity; }

    template <typename WorkStream>
    void consume(const WorkStream stream, WorkQueueStats* stats = NULL) { consume( stream, DefaultMover(), stats ); }

    template <typename WorkStream, typename WorkMover>
    void consume(const WorkStream stream, const WorkMover mover, WorkQueueStats* stats = NULL);

private:
    thrust::device_vector<uint32>   m_pool;
    uint32                          m_capacity;
};

template <
    typename WorkUnitT,
    uint32   BLOCKDIM>
struct WorkQueue<
    PersistentThreadsQueueTag,
    WorkUnitT,
    BLOCKDIM>
{
    typedef WorkUnitT   WorkUnit;

    WorkQueue() : m_capacity(uint32(-1)), m_min_utilization(0.75f) {}

    void set_capacity(const uint32 capacity) { m_capacity = capacity; }

    void set_min_utilization(const float min_utilization) { m_min_utilization = min_utilization; }

    template <typename WorkStream>
    void consume(const WorkStream stream, WorkQueueStats* stats = NULL) { consume( stream, DefaultMover(), stats ); }

    template <typename WorkStream, typename WorkMover>
    void consume(const WorkStream stream, const WorkMover mover, WorkQueueStats* stats = NULL);

private:
    thrust::device_vector<uint32> m_pool;
    uint32                        m_capacity;
    float                         m_min_utilization;
};

} // namespace cuda
} // namespace nvbio

#include <nvbio/basic/cuda/work_queue_persistent_inl.h>