{"title":"使用gpu的并行QR分解","authors":"Ian Schofield, A. Alimohammad","doi":"10.1109/CCECE.2019.8861519","DOIUrl":null,"url":null,"abstract":"This paper presents the performance results of a parallelized, accelerated eigendecomposition using the block Householder QR decomposition algorithm on a graphic processing unit (GPU). The QR software was developed using NVIDIA’s CUDA parallel programming and computing platform and executed on an NVIDIA Tesla GPU accelerator card. Factors affecting program performance of the GPU-accelerated QR implementation are highlighted with respect to the baseline serial implementation developed in MATLAB and executed on a conventional multi-core processor. We compare results with relevant previously published studies and discuss possible performance bottlenecks and speedups.","PeriodicalId":352860,"journal":{"name":"2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Parallelized QR decomposition using GPUs\",\"authors\":\"Ian Schofield, A. Alimohammad\",\"doi\":\"10.1109/CCECE.2019.8861519\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents the performance results of a parallelized, accelerated eigendecomposition using the block Householder QR decomposition algorithm on a graphic processing unit (GPU). The QR software was developed using NVIDIA’s CUDA parallel programming and computing platform and executed on an NVIDIA Tesla GPU accelerator card. Factors affecting program performance of the GPU-accelerated QR implementation are highlighted with respect to the baseline serial implementation developed in MATLAB and executed on a conventional multi-core processor. We compare results with relevant previously published studies and discuss possible performance bottlenecks and speedups.\",\"PeriodicalId\":352860,\"journal\":{\"name\":\"2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE)\",\"volume\":\"38 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-05-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CCECE.2019.8861519\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCECE.2019.8861519","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
摘要
本文给出了在图形处理单元(GPU)上使用块Householder QR分解算法进行并行加速特征分解的性能结果。QR软件使用NVIDIA的CUDA并行编程和计算平台开发，并在NVIDIA Tesla GPU加速卡上执行。针对在MATLAB中开发并在传统多核处理器上执行的基线串行实现，重点介绍了影响gpu加速QR实现程序性能的因素。我们将结果与先前发表的相关研究进行比较，并讨论可能的性能瓶颈和加速问题。
This paper presents the performance results of a parallelized, accelerated eigendecomposition using the block Householder QR decomposition algorithm on a graphic processing unit (GPU). The QR software was developed using NVIDIA’s CUDA parallel programming and computing platform and executed on an NVIDIA Tesla GPU accelerator card. Factors affecting program performance of the GPU-accelerated QR implementation are highlighted with respect to the baseline serial implementation developed in MATLAB and executed on a conventional multi-core processor. We compare results with relevant previously published studies and discuss possible performance bottlenecks and speedups.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
