Paper Info
Title
Energy Evaluation for Applications with Different Thread Affinities on the Intel Xeon Phi
Abstract
The Intel Xeon Phi coprocessor offers high parallelism on energy-efficient hardware to minimize energy consumption while maintaining performance. Dynamic frequency and voltage scaling is not accessible on the Intel Xeon Phi. Hence, saving energy relies mainly on tuning application performance. One general optimization technique is thread affinity, which is an important factor in multi-core architectures. This work investigates the effects of varying thread affinity modes and reducing core utilization on energy and execution time for the NASA Advanced Supercomputing Parallel Benchmarks (NPB). Energy measurements are captured using the micsmc utility tool available on Xeon Phi. The measurements are checked against total power captured using Watts up power meters. The results are compared to the system-default thread affinity and granularity modes. Mostly positive impacts on performance and energy are observed: When executed at the maximum thread count on all unoccupied cores, all the benchmarks but one exhibited energy savings if a specific affinity mode is set.
Year
DOI
Venue
2014
10.1109/SBAC-PADW.2014.12
Computer Architecture and High Performance Computing Workshop
Keywords
Field
DocType
coprocessors,multiprocessing systems,parallel architectures,performance evaluation,Intel Xeon Phi coprocessor,energy evaluation,energy-efficient hardware parallelism,multicore architectures,thread affinity,tuning application performance,Energy Savings,Intel Xeon Phi,Performance Evaluation,Thread Affinity,micsmc
Supercomputer,Xeon Phi,Computer science,Parallel computing,Voltage,Thread (computing),Processor affinity,Granularity,Energy consumption,Scaling
Conference
Citations 
PageRank 
References 
10
0.73
10
Authors
3
Name
Order
Citations
PageRank
Gary Lawson1324.14
Masha Sosonkina227245.62
Yuzhong Shen318421.96