Engineering Concurrent Software Guided by Statistical Performance Analysis

被引:0
|
作者
Grelck, Clemens [1 ]
Hammond, Kevin [2 ]
Hertlein, Heinz [3 ]
Hoelzenspies, Philip [2 ]
Jesshope, Chris [1 ]
Kirner, Raimund [4 ]
Scheuermann, Bernd [5 ]
Shafarenko, Alex [4 ]
te Boekhorst, Iraneus [4 ]
Wieser, Volkmar [6 ]
机构
[1] Univ Amsterdam, Inst Informat, NL-1012 WX Amsterdam, Netherlands
[2] Univ St Andrews, Sch Comp Sci, St Andrews KY16 9AJ, Fife, Scotland
[3] BioID GmbH, Nurnberg, Germany
[4] Univ Hertfordshire, Sch Comp Sci, Hatfield AL10 9AB, Herts, England
[5] SAP AG, SAP Res Ctr Karlsruhe, Karlsruhe, Germany
[6] Software Competence Ctr Hagenberg, Hagenberg, Austria
关键词
multicore; software engineering; parallel programming; stream-processing; statistical performance analysis; virtualization; S-NET; LANGUAGE; SAC;
D O I
10.3233/978-1-61499-041-3-385
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This paper introduces the ADVANCE approach to engineering concurrent systems using a new component-based approach. A cost-directed tool-chain maps concurrent programs onto emerging hardware architectures, where costs are expressed in terms of programmer annotations for the throughput, latency and jitter of components. These are then synthesized using advanced statistical analysis techniques to give overall cost information about the concurrent system that can be exploited by the hardware virtualisation layer to drive mapping and scheduling decisions. Initial performance results are presented, showing that the ADVANCE technologies could provide a promising approach to dealing with near- and future-term complexities of programming heterogeneous multi-core systems.
引用
收藏
页码:385 / 394
页数:10
相关论文
共 50 条