/* Copyright (c) 2021, 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 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 ``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 THE COPYRIGHT OWNER OR * CONTRIBUTORS 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. */ //////////////////////////////////////////////////////////////////////////////// // Shortcut definitions //////////////////////////////////////////////////////////////////////////////// typedef unsigned int uint; #define SHARED_SIZE_LIMIT 1024U #define SAMPLE_STRIDE 128 //////////////////////////////////////////////////////////////////////////////// // Extensive sort validation routine //////////////////////////////////////////////////////////////////////////////// extern "C" uint validateSortedKeys(uint *resKey, uint *srcKey, uint batchSize, uint arrayLength, uint numValues, uint sortDir); extern "C" void fillValues(uint *val, uint N); extern "C" int validateSortedValues(uint *resKey, uint *resVal, uint *srcKey, uint batchSize, uint arrayLength); //////////////////////////////////////////////////////////////////////////////// // CUDA merge sort //////////////////////////////////////////////////////////////////////////////// extern "C" void initMergeSort(void); extern "C" void closeMergeSort(void); extern "C" void mergeSort(uint *dstKey, uint *dstVal, uint *bufKey, uint *bufVal, uint *srcKey, uint *srcVal, uint N, uint sortDir); //////////////////////////////////////////////////////////////////////////////// // CPU "emulation" //////////////////////////////////////////////////////////////////////////////// extern "C" void mergeSortHost(uint *dstKey, uint *dstVal, uint *bufKey, uint *bufVal, uint *srcKey, uint *srcVal, uint N, uint sortDir);