Faria Maicon, Ferrera Adriano, Dante Carlos, Castaneda S. Zady, E. Hugo
{"title":"One and two dimensional devices electromagnetic simulation using parallelism on GPUs","authors":"Faria Maicon, Ferrera Adriano, Dante Carlos, Castaneda S. Zady, E. Hugo","doi":"10.1109/IMOC.2011.6169369","DOIUrl":null,"url":null,"abstract":"Following the efforts performed in research and development of electromagnetic devices as antennas, optical fibers and microwaves devices we report a careful implementation of the Finite-Difference Time-Domain (FDTD) in a parallel environment. We use Graphic Processor Units (GPUs) to take advantage of FDTD parallel features and observe the time evolution of the electromagnetic fields in a Single Instruction, Multiple Data parallel implementation. It was observe performance gains up to 30 times when this parallel GPU solution are compared with a serial solution in a modern CPU.","PeriodicalId":179351,"journal":{"name":"2011 SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference (IMOC 2011)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference (IMOC 2011)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IMOC.2011.6169369","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Following the efforts performed in research and development of electromagnetic devices as antennas, optical fibers and microwaves devices we report a careful implementation of the Finite-Difference Time-Domain (FDTD) in a parallel environment. We use Graphic Processor Units (GPUs) to take advantage of FDTD parallel features and observe the time evolution of the electromagnetic fields in a Single Instruction, Multiple Data parallel implementation. It was observe performance gains up to 30 times when this parallel GPU solution are compared with a serial solution in a modern CPU.