Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Engineering Concurrent Software Guided by Statistical Performance Analysis. / Scheuermann, Bernd; Grelck, Clemens; Hammond, Kevin; Hertlein, Heinz; Hoelzenspies, Philip; Jesshope, Chris; Kirner, Raimund; Shafarenko, Alex; te Boekhorst, Rene; Wieser, Volkmar.
Applications, Tools and Techniques on the Road to Exascale Computing: Proceedings ParCo 2011. IOS Press, 2011. p. 385-394 (Advances in Parallel Computing; Vol. 22).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Engineering Concurrent Software Guided by Statistical Performance Analysis
AU - Scheuermann, Bernd
AU - Grelck, Clemens
AU - Hammond, Kevin
AU - Hertlein, Heinz
AU - Hoelzenspies, Philip
AU - Jesshope, Chris
AU - Kirner, Raimund
AU - Shafarenko, Alex
AU - te Boekhorst, Rene
AU - Wieser, Volkmar
PY - 2011
Y1 - 2011
N2 - This paper introduces the ADVANCE approach to engineering concurrent systems using a new component-based approach. A cost-directed tool-chainmaps concurrent programs onto emerging hardware architectures, where costs areexpressed in terms of programmer annotations for the throughput, latency and jitter of components. These are then synthesized using advanced statistical analysistechniques to give overall cost information about the concurrent system that canbe exploited by the hardware virtualisation layer to drive mapping and schedulingdecisions. Initial performance results are presented, showing that the ADVANCEtechnologies provide a promising approach to dealing with near- and future-termcomplexities of programming heterogeneous multi-core systems.
AB - This paper introduces the ADVANCE approach to engineering concurrent systems using a new component-based approach. A cost-directed tool-chainmaps concurrent programs onto emerging hardware architectures, where costs areexpressed in terms of programmer annotations for the throughput, latency and jitter of components. These are then synthesized using advanced statistical analysistechniques to give overall cost information about the concurrent system that canbe exploited by the hardware virtualisation layer to drive mapping and schedulingdecisions. Initial performance results are presented, showing that the ADVANCEtechnologies provide a promising approach to dealing with near- and future-termcomplexities of programming heterogeneous multi-core systems.
U2 - 10.3233/978-1-61499-041-3-385
DO - 10.3233/978-1-61499-041-3-385
M3 - Conference contribution
SN - 978-1-61499-040-6
T3 - Advances in Parallel Computing
SP - 385
EP - 394
BT - Applications, Tools and Techniques on the Road to Exascale Computing
PB - IOS Press
ER -