{"title":"静态连接mimd的构建块概念:构建块模块的开发","authors":"T.M. Kahveci, H. Martin","doi":"10.1109/SSST.1992.712344","DOIUrl":null,"url":null,"abstract":"Multiprocessor interconnection topologies usually implement specific algorithms that can map various types of connections, i.e. binary tree, N-Cube, etc. However, the research conducted uncovered the lack of uniformity incorporated in network topology designs. In other words, the lack of uniformity reduced the capability for expandability within a topology. Within a mesh type connectivity pattern, the topology is very scalable and is truly uniform, but nonetheless there is a problem with the structure due to topology-inherent communication delays. Therefore, having identified the problem, the approach taken to attempt a solution was to somehow realize the possibility of developing a network topology (TM-Cube) that is purely uniform and still performs at maximum efficiency. Comparison will be based on our assumed reference model, the N-Cube.","PeriodicalId":359363,"journal":{"name":"The 24th Southeastern Symposium on and The 3rd Annual Symposium on Communications, Signal Processing Expert Systems, and ASIC VLSI Design System Theory","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Building Block Concept for Static Connected MIMDs: Development of Building Block Modules\",\"authors\":\"T.M. Kahveci, H. Martin\",\"doi\":\"10.1109/SSST.1992.712344\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multiprocessor interconnection topologies usually implement specific algorithms that can map various types of connections, i.e. binary tree, N-Cube, etc. However, the research conducted uncovered the lack of uniformity incorporated in network topology designs. In other words, the lack of uniformity reduced the capability for expandability within a topology. Within a mesh type connectivity pattern, the topology is very scalable and is truly uniform, but nonetheless there is a problem with the structure due to topology-inherent communication delays. Therefore, having identified the problem, the approach taken to attempt a solution was to somehow realize the possibility of developing a network topology (TM-Cube) that is purely uniform and still performs at maximum efficiency. Comparison will be based on our assumed reference model, the N-Cube.\",\"PeriodicalId\":359363,\"journal\":{\"name\":\"The 24th Southeastern Symposium on and The 3rd Annual Symposium on Communications, Signal Processing Expert Systems, and ASIC VLSI Design System Theory\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1992-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The 24th Southeastern Symposium on and The 3rd Annual Symposium on Communications, Signal Processing Expert Systems, and ASIC VLSI Design System Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SSST.1992.712344\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 24th Southeastern Symposium on and The 3rd Annual Symposium on Communications, Signal Processing Expert Systems, and ASIC VLSI Design System Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SSST.1992.712344","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Building Block Concept for Static Connected MIMDs: Development of Building Block Modules
Multiprocessor interconnection topologies usually implement specific algorithms that can map various types of connections, i.e. binary tree, N-Cube, etc. However, the research conducted uncovered the lack of uniformity incorporated in network topology designs. In other words, the lack of uniformity reduced the capability for expandability within a topology. Within a mesh type connectivity pattern, the topology is very scalable and is truly uniform, but nonetheless there is a problem with the structure due to topology-inherent communication delays. Therefore, having identified the problem, the approach taken to attempt a solution was to somehow realize the possibility of developing a network topology (TM-Cube) that is purely uniform and still performs at maximum efficiency. Comparison will be based on our assumed reference model, the N-Cube.