Phase-aware adaptive hardware selection for power-efficient scientific computations

Authors:
Konrad Malkowski;Padma Raghavan;Mahmut Kandemir;Mary Jane Irwin
Affiliations:
The Pennsylvania State University;The Pennsylvania State University;The Pennsylvania State University;The Pennsylvania State University
Venue:
ISLPED '07 Proceedings of the 2007 international symposium on Low power electronics and design
Year:
2007

Citing 13
Cited 0

NAS parallel benchmark results

Proceedings of the 1992 ACM/IEEE conference on Supercomputing
The SimpleScalar tool set, version 2.0

ACM SIGARCH Computer Architecture News
Wattch: a framework for architectural-level power analysis and optimizations

Proceedings of the 27th annual international symposium on Computer architecture
Performance modeling and tuning of an unstructured mesh CFD application

Proceedings of the 2000 ACM/IEEE conference on Supercomputing
Design Challenges of Technology Scaling

IEEE Micro
Using SimPoint for accurate and efficient simulation

SIGMETRICS '03 Proceedings of the 2003 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Iterative Methods for Sparse Linear Systems

Iterative Methods for Sparse Linear Systems
Dynamic voltage and frequency scaling based on workload decomposition

Proceedings of the 2004 international symposium on Low power electronics and design
Reducing Power with Performance Constraints for Parallel Sparse Applications

IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 11 - Volume 12
A Power-Aware Run-Time System for High-Performance Computing

SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
Just In Time Dynamic Voltage Scaling: Exploiting Inter-Node Slack to Save Energy in MPI Programs

SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
Live, Runtime Phase Monitoring and Prediction on Real Systems with Application to Dynamic Power Management

Proceedings of the 39th Annual IEEE/ACM International Symposium on Microarchitecture
Conjugate gradient sparse solvers: performance-power characteristics

IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Increased power consumption and heat dissipation have become the major limiters of available computational resources at many high performance computing (HPC) centers. Applications that run at suchcenters typically operate in single user mode, run for longperiods of time, and have long lasting application phases. Their users are interested in obtaining the maximum performance. We propose a phase aware adaptive hardware selection technique,featuring data prefetchers and dynamic voltage and frequency scaling. Ourtechnique takes advantage of memory bound phases in scientific codes, resulting in significant power (39%) and energy (37%) reductions while maintainingor exceeding the performance of an unoptimized system.