J. Peeters, N. Ventroux, Tanguy Sassolas, L. Lacassagne
{"title":"具有不可预测通信的复杂系统分布式仿真的系统TLM框架","authors":"J. Peeters, N. Ventroux, Tanguy Sassolas, L. Lacassagne","doi":"10.1109/DASIP.2011.6136847","DOIUrl":null,"url":null,"abstract":"Increasingly complex systems need parallelized simulation engines. In the context of SystemC simulation, existing proposals require predicting communication in the simulated system. However, this is often unpredictable. In order to deal with unpredictable systems, this paper presents a parallelization approach using asynchronous communication without modification of the SystemC simulation engine. Simulated system model is cut up and distributed across separate simulation engines, each part being evaluated in parallel of others. Functional consistency is preserved thanks to the simulated system write exclusive memory access policy while temporal consistency is guaranteed using explicit synchronization. Experimental results show up a speed-up up to 13x on 16 processors.","PeriodicalId":199500,"journal":{"name":"Proceedings of the 2011 Conference on Design & Architectures for Signal & Image Processing (DASIP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":"{\"title\":\"A systemc TLM framework for distributed simulation of complex systems with unpredictable communication\",\"authors\":\"J. Peeters, N. Ventroux, Tanguy Sassolas, L. Lacassagne\",\"doi\":\"10.1109/DASIP.2011.6136847\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Increasingly complex systems need parallelized simulation engines. In the context of SystemC simulation, existing proposals require predicting communication in the simulated system. However, this is often unpredictable. In order to deal with unpredictable systems, this paper presents a parallelization approach using asynchronous communication without modification of the SystemC simulation engine. Simulated system model is cut up and distributed across separate simulation engines, each part being evaluated in parallel of others. Functional consistency is preserved thanks to the simulated system write exclusive memory access policy while temporal consistency is guaranteed using explicit synchronization. Experimental results show up a speed-up up to 13x on 16 processors.\",\"PeriodicalId\":199500,\"journal\":{\"name\":\"Proceedings of the 2011 Conference on Design & Architectures for Signal & Image Processing (DASIP)\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"14\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2011 Conference on Design & Architectures for Signal & Image Processing (DASIP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DASIP.2011.6136847\",\"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 2011 Conference on Design & Architectures for Signal & Image Processing (DASIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DASIP.2011.6136847","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A systemc TLM framework for distributed simulation of complex systems with unpredictable communication
Increasingly complex systems need parallelized simulation engines. In the context of SystemC simulation, existing proposals require predicting communication in the simulated system. However, this is often unpredictable. In order to deal with unpredictable systems, this paper presents a parallelization approach using asynchronous communication without modification of the SystemC simulation engine. Simulated system model is cut up and distributed across separate simulation engines, each part being evaluated in parallel of others. Functional consistency is preserved thanks to the simulated system write exclusive memory access policy while temporal consistency is guaranteed using explicit synchronization. Experimental results show up a speed-up up to 13x on 16 processors.