{"title":"在具有轮循调度的缓冲交叉栏中提供100%的吞吐量","authors":"Michael Stübert Berger","doi":"10.1109/HPSR.2006.1709743","DOIUrl":null,"url":null,"abstract":"Buffered crossbars with virtual output queuing are considered an alternative to bufferless crossbars mainly because the latter requires a complex global scheduling algorithm that matches input with output. Buffered crossbars require only simple schedulers that operate independently for each output crosspoint queue column and independently for each port card. In this paper, fluid-model techniques will be utilized to show that the necessary and sufficient speedup for a NxN buffered crossbar with 1-cell crosspoint buffers is 2-1/N to deliver 100% throughput. Round robin scheduling is assumed, both among virtual output queues in port cards and among crosspoint buffers in output columns","PeriodicalId":274390,"journal":{"name":"2006 Workshop on High Performance Switching and Routing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"17","resultStr":"{\"title\":\"Delivering 100% throughput in a buffered crossbar with round robin scheduling\",\"authors\":\"Michael Stübert Berger\",\"doi\":\"10.1109/HPSR.2006.1709743\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Buffered crossbars with virtual output queuing are considered an alternative to bufferless crossbars mainly because the latter requires a complex global scheduling algorithm that matches input with output. Buffered crossbars require only simple schedulers that operate independently for each output crosspoint queue column and independently for each port card. In this paper, fluid-model techniques will be utilized to show that the necessary and sufficient speedup for a NxN buffered crossbar with 1-cell crosspoint buffers is 2-1/N to deliver 100% throughput. Round robin scheduling is assumed, both among virtual output queues in port cards and among crosspoint buffers in output columns\",\"PeriodicalId\":274390,\"journal\":{\"name\":\"2006 Workshop on High Performance Switching and Routing\",\"volume\":\"4 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2006-10-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"17\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2006 Workshop on High Performance Switching and Routing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HPSR.2006.1709743\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2006 Workshop on High Performance Switching and Routing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPSR.2006.1709743","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Delivering 100% throughput in a buffered crossbar with round robin scheduling
Buffered crossbars with virtual output queuing are considered an alternative to bufferless crossbars mainly because the latter requires a complex global scheduling algorithm that matches input with output. Buffered crossbars require only simple schedulers that operate independently for each output crosspoint queue column and independently for each port card. In this paper, fluid-model techniques will be utilized to show that the necessary and sufficient speedup for a NxN buffered crossbar with 1-cell crosspoint buffers is 2-1/N to deliver 100% throughput. Round robin scheduling is assumed, both among virtual output queues in port cards and among crosspoint buffers in output columns