{"title":"在多核架构上实现actor的自动绑定","authors":"E. Francesquini, A. Goldman, J. Méhaut","doi":"10.1145/2364489.2364501","DOIUrl":null,"url":null,"abstract":"The actor model is a high-level programming abstraction that attempts to ease the development of parallel applications, among others, by shielding the developer from the underlying platform. In this model the execution relies on a runtime environment (RE) to be able to efficiently use the underlying machine. Modern processors possess a hierarchical architecture of memory, thus making the performance of an application dependent on the placement of the application threads. This makes the choices of the RE much more important since the chosen actor placement will have a considerable impact on the application performance. In this paper we describe a work in progress that aims to create an on-line automatic actor placement engine. Using application profiling in association with hardware counters, it will pin and migrate actors to processing units aiming to optimize performance.","PeriodicalId":140676,"journal":{"name":"Erlang Workshop","volume":"132 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Towards automatic actor pinning on multi-core architectures\",\"authors\":\"E. Francesquini, A. Goldman, J. Méhaut\",\"doi\":\"10.1145/2364489.2364501\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The actor model is a high-level programming abstraction that attempts to ease the development of parallel applications, among others, by shielding the developer from the underlying platform. In this model the execution relies on a runtime environment (RE) to be able to efficiently use the underlying machine. Modern processors possess a hierarchical architecture of memory, thus making the performance of an application dependent on the placement of the application threads. This makes the choices of the RE much more important since the chosen actor placement will have a considerable impact on the application performance. In this paper we describe a work in progress that aims to create an on-line automatic actor placement engine. Using application profiling in association with hardware counters, it will pin and migrate actors to processing units aiming to optimize performance.\",\"PeriodicalId\":140676,\"journal\":{\"name\":\"Erlang Workshop\",\"volume\":\"132 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-09-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Erlang Workshop\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2364489.2364501\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Erlang Workshop","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2364489.2364501","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Towards automatic actor pinning on multi-core architectures
The actor model is a high-level programming abstraction that attempts to ease the development of parallel applications, among others, by shielding the developer from the underlying platform. In this model the execution relies on a runtime environment (RE) to be able to efficiently use the underlying machine. Modern processors possess a hierarchical architecture of memory, thus making the performance of an application dependent on the placement of the application threads. This makes the choices of the RE much more important since the chosen actor placement will have a considerable impact on the application performance. In this paper we describe a work in progress that aims to create an on-line automatic actor placement engine. Using application profiling in association with hardware counters, it will pin and migrate actors to processing units aiming to optimize performance.