Bin Wei, Gordon Stoll, D. Clark, E. Felten, Kai Li, P. Hanrahan
{"title":"Synchronization for a multi-port frame buffer on a mesh-connected multicomputer","authors":"Bin Wei, Gordon Stoll, D. Clark, E. Felten, Kai Li, P. Hanrahan","doi":"10.1145/218327.218341","DOIUrl":null,"url":null,"abstract":"Parallel rendering on multicomputers involves the parallelization of geometry processing, rasterization and composition. A known approach to support the back end of parallel rendering on multicomputers is to connect a multiport frame buffer directly to the multicomputer routing network to take advantage of the aggregate bandwidth available on the network. However, a multi-port frame buffer design raises the question of how to synchronize the processors with the frame buffer in order to perform global control operations. The challenge is to provide a simple and efficient synchronization algorithm that requires minimal hardware support. This paper describes a softwarebased solution to the synchronization problem for a multiport frame buffer on the Paragon mesh routing network. Simulations on the Paragon multicomputer show that our algorithm is indeed efficient.","PeriodicalId":101947,"journal":{"name":"Proceedings of the IEEE symposium on Parallel rendering","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1995-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the IEEE symposium on Parallel rendering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/218327.218341","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9
Abstract
Parallel rendering on multicomputers involves the parallelization of geometry processing, rasterization and composition. A known approach to support the back end of parallel rendering on multicomputers is to connect a multiport frame buffer directly to the multicomputer routing network to take advantage of the aggregate bandwidth available on the network. However, a multi-port frame buffer design raises the question of how to synchronize the processors with the frame buffer in order to perform global control operations. The challenge is to provide a simple and efficient synchronization algorithm that requires minimal hardware support. This paper describes a softwarebased solution to the synchronization problem for a multiport frame buffer on the Paragon mesh routing network. Simulations on the Paragon multicomputer show that our algorithm is indeed efficient.