DocumentCode :
1016453
Title :
Prediction-Based Power-Performance Adaptation of Multithreaded Scientific Codes
Author :
Curtis-Maury, Matthew ; Blagojevic, Filip ; Antonopoulos, Christos D. ; Nikolopoulos, Dimitrios S.
Author_Institution :
NetApp, Inc., Research Triangle Park, NC
Volume :
19
Issue :
10
fYear :
2008
Firstpage :
1396
Lastpage :
1410
Abstract :
Computing has recently reached an inflection point with the introduction of multi-core processors. On-chip thread-level parallelism is doubling approximately every other year. Concurrency lends itself naturally to allowing a program to trade performance for power savings by regulating the number of active cores, however in several domains users are unwilling to sacrifice performance to save power. We present a prediction model for identifying energy-efficient operating points of concurrency in well-tuned multithreaded scientific applications, and a runtime system which uses live program analysis to optimize applications dynamically. We describe a dynamic, phase-aware performance prediction model that combines multivariate regression techniques with runtime analysis of data collected from hardware event counters to locate optimal operating points of concurrency. Using our model, we develop a prediction-driven, phase-aware runtime optimization scheme that throttles concurrency so that power consumption can be reduced and performance can be set at the knee of the scalability curve of each program phase. The use of prediction reduces the overhead of searching the optimization space while achieving near-optimal performance and power savings. A thorough evaluation of our approach shows a reduction in power consumption of 10.8% simultaneous with an improvement in performance of 17.9%, resulting in energy savings of 26.7%.
Keywords :
multi-threading; multiprocessing systems; program diagnostics; regression analysis; multicore processors; multithreaded scientific application; multithreaded scientific codes; multivariate regression technique; onchip thread-level parallelism; phase-aware performance prediction model; prediction-based power-performance adaptation; program analysis; runtime analysis; runtime system; Application-aware adaptation; Energy-aware systems; Modeling and prediction;
fLanguage :
English
Journal_Title :
Parallel and Distributed Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9219
Type :
jour
DOI :
10.1109/TPDS.2007.70804
Filename :
4407685
Link To Document :
بازگشت