{"title":"在 CUDA 上使用并行计算函数式编程库","authors":"M. M. Krasnov, O. B. Feodoritova","doi":"10.1134/s0361768824010055","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Modern graphics accelerators (GPUs) can significantly speed up the execution of numerical problems. However, porting programs to graphics accelerators is not an easy task, sometimes requiring their almost complete rewriting. CUDA graphics accelerators, thanks to technology developed by NVIDIA, allow one to have a single source code for both conventional processors (CPUs) and CUDA. However, parallelization on shared memory is still done differently and should be specified explicitly. The use of a functional programming library developed by the authors makes it possible to hide the use of one or another parallelization mechanism on shared memory within the library and make the user’s source code completely independent of the computing device used (CPU or CUDA). This article shows how this can be done.</p>","PeriodicalId":54555,"journal":{"name":"Programming and Computer Software","volume":null,"pages":null},"PeriodicalIF":0.7000,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The Use of Functional Programming Library for Parallel Computing on CUDA\",\"authors\":\"M. M. Krasnov, O. B. Feodoritova\",\"doi\":\"10.1134/s0361768824010055\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3 data-test=\\\"abstract-sub-heading\\\">Abstract</h3><p>Modern graphics accelerators (GPUs) can significantly speed up the execution of numerical problems. However, porting programs to graphics accelerators is not an easy task, sometimes requiring their almost complete rewriting. CUDA graphics accelerators, thanks to technology developed by NVIDIA, allow one to have a single source code for both conventional processors (CPUs) and CUDA. However, parallelization on shared memory is still done differently and should be specified explicitly. The use of a functional programming library developed by the authors makes it possible to hide the use of one or another parallelization mechanism on shared memory within the library and make the user’s source code completely independent of the computing device used (CPU or CUDA). This article shows how this can be done.</p>\",\"PeriodicalId\":54555,\"journal\":{\"name\":\"Programming and Computer Software\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2024-05-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Programming and Computer Software\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1134/s0361768824010055\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Programming and Computer Software","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1134/s0361768824010055","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0
摘要
摘要现代图形加速器(GPU)可以大大加快数值问题的执行速度。然而,将程序移植到图形加速器上并非易事,有时几乎需要完全重写。得益于英伟达™(NVIDIA®)公司开发的 CUDA 图形加速器技术,人们可以用一个源代码同时处理传统处理器(CPU)和 CUDA。不过,共享内存上的并行化仍然采用不同的方式,并应明确指定。通过使用作者开发的函数式编程库,可以将共享内存上的一种或另一种并行化机制隐藏在库中,使用户的源代码完全独立于所使用的计算设备(CPU 或 CUDA)。本文展示了如何做到这一点。
The Use of Functional Programming Library for Parallel Computing on CUDA
Abstract
Modern graphics accelerators (GPUs) can significantly speed up the execution of numerical problems. However, porting programs to graphics accelerators is not an easy task, sometimes requiring their almost complete rewriting. CUDA graphics accelerators, thanks to technology developed by NVIDIA, allow one to have a single source code for both conventional processors (CPUs) and CUDA. However, parallelization on shared memory is still done differently and should be specified explicitly. The use of a functional programming library developed by the authors makes it possible to hide the use of one or another parallelization mechanism on shared memory within the library and make the user’s source code completely independent of the computing device used (CPU or CUDA). This article shows how this can be done.
期刊介绍:
Programming and Computer Software is a peer reviewed journal devoted to problems in all areas of computer science: operating systems, compiler technology, software engineering, artificial intelligence, etc.