{"title":"片上光子互连中的动态功耗降低技术","authors":"B. Neel, M. Kennedy, Avinash Karanth Kodi","doi":"10.1145/2742060.2742118","DOIUrl":null,"url":null,"abstract":"Photonic interconnects is a disruptive technology solution that can overcome the power and bandwidth limitations of traditional electrical Network-on-Chips (NoCs). However, the static power dissipated in the external laser may limit the performance of future optical NoCs by dominating the stringent network power budget. From the analysis of real benchmarks for multi-cores, it is observed that high static power is consumed due to the external laser even for low channel utilization. In this paper, we propose runtime power management techniques to reduce the magnitude of laser power consumption by tuning the network in response to actual application characteristics. We scale the number of channels available for communication based on link and buffer utilization. The performance on synthetic and real traffic (PARSEC, Splash-2) for 64-cores indicate that our proposed power scaling technique can reduce optical power by about 70% with less than 1% throughput penalty for real traffic.","PeriodicalId":255133,"journal":{"name":"Proceedings of the 25th edition on Great Lakes Symposium on VLSI","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Dynamic Power Reduction Techniques in On-Chip Photonic Interconnects\",\"authors\":\"B. Neel, M. Kennedy, Avinash Karanth Kodi\",\"doi\":\"10.1145/2742060.2742118\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Photonic interconnects is a disruptive technology solution that can overcome the power and bandwidth limitations of traditional electrical Network-on-Chips (NoCs). However, the static power dissipated in the external laser may limit the performance of future optical NoCs by dominating the stringent network power budget. From the analysis of real benchmarks for multi-cores, it is observed that high static power is consumed due to the external laser even for low channel utilization. In this paper, we propose runtime power management techniques to reduce the magnitude of laser power consumption by tuning the network in response to actual application characteristics. We scale the number of channels available for communication based on link and buffer utilization. The performance on synthetic and real traffic (PARSEC, Splash-2) for 64-cores indicate that our proposed power scaling technique can reduce optical power by about 70% with less than 1% throughput penalty for real traffic.\",\"PeriodicalId\":255133,\"journal\":{\"name\":\"Proceedings of the 25th edition on Great Lakes Symposium on VLSI\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-05-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 25th edition on Great Lakes Symposium on VLSI\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2742060.2742118\",\"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 25th edition on Great Lakes Symposium on VLSI","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2742060.2742118","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Dynamic Power Reduction Techniques in On-Chip Photonic Interconnects
Photonic interconnects is a disruptive technology solution that can overcome the power and bandwidth limitations of traditional electrical Network-on-Chips (NoCs). However, the static power dissipated in the external laser may limit the performance of future optical NoCs by dominating the stringent network power budget. From the analysis of real benchmarks for multi-cores, it is observed that high static power is consumed due to the external laser even for low channel utilization. In this paper, we propose runtime power management techniques to reduce the magnitude of laser power consumption by tuning the network in response to actual application characteristics. We scale the number of channels available for communication based on link and buffer utilization. The performance on synthetic and real traffic (PARSEC, Splash-2) for 64-cores indicate that our proposed power scaling technique can reduce optical power by about 70% with less than 1% throughput penalty for real traffic.