{"title":"具有较低延迟的新型超立方体","authors":"A. Ahmed","doi":"10.1109/ISPAN.1994.367172","DOIUrl":null,"url":null,"abstract":"In this paper, we present a hypercube with reduced diameter and latencies. This is achieved by reconnecting the hypercube with twisted and random connections while keeping the number of wires constant. This new topology is called RT-cube. The RT-cubes offer smaller diameter and reduced latencies compared to the normal hypercubes, resulting in a faster interconnection network topology. A packet switched routing algorithm and the router design model is also proposed for message passing in RT-cubes. The simulations and analysis have shown that RT-cube based proposed communication architecture is faster than the conventional hypercubes with the same wire cost, and scales well for massively parallel computing systems.<<ETX>>","PeriodicalId":142405,"journal":{"name":"Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A novel hypercube with lower latency\",\"authors\":\"A. Ahmed\",\"doi\":\"10.1109/ISPAN.1994.367172\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present a hypercube with reduced diameter and latencies. This is achieved by reconnecting the hypercube with twisted and random connections while keeping the number of wires constant. This new topology is called RT-cube. The RT-cubes offer smaller diameter and reduced latencies compared to the normal hypercubes, resulting in a faster interconnection network topology. A packet switched routing algorithm and the router design model is also proposed for message passing in RT-cubes. The simulations and analysis have shown that RT-cube based proposed communication architecture is faster than the conventional hypercubes with the same wire cost, and scales well for massively parallel computing systems.<<ETX>>\",\"PeriodicalId\":142405,\"journal\":{\"name\":\"Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN)\",\"volume\":\"13 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1994-12-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISPAN.1994.367172\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISPAN.1994.367172","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
In this paper, we present a hypercube with reduced diameter and latencies. This is achieved by reconnecting the hypercube with twisted and random connections while keeping the number of wires constant. This new topology is called RT-cube. The RT-cubes offer smaller diameter and reduced latencies compared to the normal hypercubes, resulting in a faster interconnection network topology. A packet switched routing algorithm and the router design model is also proposed for message passing in RT-cubes. The simulations and analysis have shown that RT-cube based proposed communication architecture is faster than the conventional hypercubes with the same wire cost, and scales well for massively parallel computing systems.<>