{"title":"MP-Queue:嵌入式流媒体平台的高效通信库","authors":"A. D. Torre, M. Ruggiero, L. Benini","doi":"10.1109/ESTMED.2007.4375813","DOIUrl":null,"url":null,"abstract":"In this paper we present MP-queue, a flexible and efficient queue-based communication library for MPSoCs. Our library is suitable for a wide range of hardware platforms and its configuration space is explored across a wide number of dimensions. We introduce an upper-bound evaluation metric to compare the efficiency of the library against an ideal point-to-point data transfer. We can thus quantitatively assess the overhead introduced by the synchronization protocol and by shared bus contention. We discuss source-level optimizations introduced in the library that enable aggressive compiler optimizations, without compromising code portability. A significant speedup is achieved w.r.t a non-optimized library (15% for small-size messages), while communication efficiency rises up to 90% for large messages.","PeriodicalId":428196,"journal":{"name":"2007 IEEE/ACM/IFIP Workshop on Embedded Systems for Real-Time Multimedia","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"MP-Queue: an Efficient Communication Library for Embedded Streaming Multimedia Platforms\",\"authors\":\"A. D. Torre, M. Ruggiero, L. Benini\",\"doi\":\"10.1109/ESTMED.2007.4375813\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper we present MP-queue, a flexible and efficient queue-based communication library for MPSoCs. Our library is suitable for a wide range of hardware platforms and its configuration space is explored across a wide number of dimensions. We introduce an upper-bound evaluation metric to compare the efficiency of the library against an ideal point-to-point data transfer. We can thus quantitatively assess the overhead introduced by the synchronization protocol and by shared bus contention. We discuss source-level optimizations introduced in the library that enable aggressive compiler optimizations, without compromising code portability. A significant speedup is achieved w.r.t a non-optimized library (15% for small-size messages), while communication efficiency rises up to 90% for large messages.\",\"PeriodicalId\":428196,\"journal\":{\"name\":\"2007 IEEE/ACM/IFIP Workshop on Embedded Systems for Real-Time Multimedia\",\"volume\":\"17 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-11-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 IEEE/ACM/IFIP Workshop on Embedded Systems for Real-Time Multimedia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ESTMED.2007.4375813\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE/ACM/IFIP Workshop on Embedded Systems for Real-Time Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ESTMED.2007.4375813","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
MP-Queue: an Efficient Communication Library for Embedded Streaming Multimedia Platforms
In this paper we present MP-queue, a flexible and efficient queue-based communication library for MPSoCs. Our library is suitable for a wide range of hardware platforms and its configuration space is explored across a wide number of dimensions. We introduce an upper-bound evaluation metric to compare the efficiency of the library against an ideal point-to-point data transfer. We can thus quantitatively assess the overhead introduced by the synchronization protocol and by shared bus contention. We discuss source-level optimizations introduced in the library that enable aggressive compiler optimizations, without compromising code portability. A significant speedup is achieved w.r.t a non-optimized library (15% for small-size messages), while communication efficiency rises up to 90% for large messages.