Title
Considering all starting points for simultaneous multithreading simulation.
Abstract
Commercial processors have support for Simultaneous Multithreading (SMT), yet little work has been done to pro- vide representative simulation results for SMT. Given a work- load, current simulation techniques typically run one combi- nation of those programs from a specific starting offset, or just run one combination of samples across the benchmarks. We have found that the architecture behavior and overall throughput seen can vary drastically based upon the starting points of the different benchmarks. Therefore, to completely evaluate the effect of an SMT architecture optimization on a workload, one would need to simulate many or all of the program combinations from different starting offsets. But exhaustively running all program combinations from many starting offsets is infeasible — even running single programs to completion is often infeasible with modern benchmarks. In this paper we propose an SMT simulation methodol- ogy that estimates the average performance over all possible starting points when running multiple programs concurrently on an SMT processor. This is based on our prior co-phase matrix phase analysis and simulation infrastructure. This ap- proachsamples all of the uniquephase combinationsfor a set of benchmarks to be run together. Once these phase combi- nations are sampled, our approach uses these samples, along with a trace of the phase behavior for each program, to pro- vide a CPI estimate of all starting points. This all starting point CPI estimate is precisely calculated in just minutes.
Year
DOI
Venue
2006
10.1109/ISPASS.2006.1620799
ISPASS
Keywords
Field
DocType
multi threading,multithreading,computer architecture,microarchitecture,simultaneous multithreading,computational modeling,throughput,computer simulation
Multithreading,Computer science,Workload,Matrix (mathematics),Parallel computing,Real-time computing,Simultaneous multithreading,Throughput,Phase analysis,Architecture optimization,Offset (computer science)
Conference
ISBN
Citations 
PageRank 
1-4244-0186-0
18
0.91
References 
Authors
14
3
Name
Order
Citations
PageRank
Michael Van Biesbrouck1758.71
Lieven Eeckhout22863195.11
Brad Calder34145251.59