device_run_length_encode.cuh

Go to the documentation of this file.

/******************************************************************************
 * Copyright (c) 2011, Duane Merrill.  All rights reserved.
 * Copyright (c) 2011-2018, 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 <stdio.h>
#include <iterator>

#include "dispatch/dispatch_rle.cuh"
#include "dispatch/dispatch_reduce_by_key.cuh"
#include "../util_namespace.cuh"

CUB_NS_PREFIX

namespace cub {


struct DeviceRunLengthEncode
{

    template <
        typename                    InputIteratorT,
        typename                    UniqueOutputIteratorT,
        typename                    LengthsOutputIteratorT,
        typename                    NumRunsOutputIteratorT>
    CUB_RUNTIME_FUNCTION __forceinline__
    static cudaError_t Encode(
        void*                       d_temp_storage,                
        size_t                      &temp_storage_bytes,            
        InputIteratorT              d_in,                           
        UniqueOutputIteratorT       d_unique_out,                   
        LengthsOutputIteratorT      d_counts_out,                   
        NumRunsOutputIteratorT      d_num_runs_out,                     
        int                         num_items,                      
        cudaStream_t                stream             = 0,         
        bool                        debug_synchronous  = false)     
    {
        typedef int         OffsetT;                    // Signed integer type for global offsets
        typedef NullType*   FlagIterator;               // FlagT iterator type (not used)
        typedef NullType    SelectOp;                   // Selection op (not used)
        typedef Equality    EqualityOp;                 // Default == operator
        typedef cub::Sum    ReductionOp;                // Value reduction operator

        // The lengths output value type
        typedef typename If<(Equals<typename std::iterator_traits<LengthsOutputIteratorT>::value_type, void>::VALUE),   // LengthT =  (if output iterator's value type is void) ?
            OffsetT,                                                                                                    // ... then the OffsetT type,
            typename std::iterator_traits<LengthsOutputIteratorT>::value_type>::Type LengthT;                           // ... else the output iterator's value type

        // Generator type for providing 1s values for run-length reduction
        typedef ConstantInputIterator<LengthT, OffsetT> LengthsInputIteratorT;

        return DispatchReduceByKey<InputIteratorT, UniqueOutputIteratorT, LengthsInputIteratorT, LengthsOutputIteratorT, NumRunsOutputIteratorT, EqualityOp, ReductionOp, OffsetT>::Dispatch(
            d_temp_storage,
            temp_storage_bytes,
            d_in,
            d_unique_out,
            LengthsInputIteratorT((LengthT) 1),
            d_counts_out,
            d_num_runs_out,
            EqualityOp(),
            ReductionOp(),
            num_items,
            stream,
            debug_synchronous);
    }


    template <
        typename                InputIteratorT,
        typename                OffsetsOutputIteratorT,
        typename                LengthsOutputIteratorT,
        typename                NumRunsOutputIteratorT>
    CUB_RUNTIME_FUNCTION __forceinline__
    static cudaError_t NonTrivialRuns(
        void*               d_temp_storage,                
        size_t                  &temp_storage_bytes,            
        InputIteratorT          d_in,                           
        OffsetsOutputIteratorT  d_offsets_out,                  
        LengthsOutputIteratorT  d_lengths_out,                  
        NumRunsOutputIteratorT  d_num_runs_out,                 
        int                     num_items,                      
        cudaStream_t            stream             = 0,         
        bool                    debug_synchronous  = false)     
    {
        typedef int         OffsetT;                    // Signed integer type for global offsets
        typedef Equality    EqualityOp;                 // Default == operator

        return DeviceRleDispatch<InputIteratorT, OffsetsOutputIteratorT, LengthsOutputIteratorT, NumRunsOutputIteratorT, EqualityOp, OffsetT>::Dispatch(
            d_temp_storage,
            temp_storage_bytes,
            d_in,
            d_offsets_out,
            d_lengths_out,
            d_num_runs_out,
            EqualityOp(),
            num_items,
            stream,
            debug_synchronous);
    }


};


}               // CUB namespace
CUB_NS_POSTFIX  // Optional outer namespace(s)