Energy considerations for divisible load processing

Authors:
Maciej Drozdowski
Affiliations:
Institute of Computing Science, Poznań University of Technology, Poznań, Poland
Venue:
PPAM'09 Proceedings of the 8th international conference on Parallel processing and applied mathematics: Part II
Year:
2009

Citing 8
Cited 0

Partitioning Techniques for Large-Grained Parallelism

IEEE Transactions on Computers
A bridging model for parallel computation

Communications of the ACM
Scheduling Divisible Loads in Parallel and Distributed Systems

Scheduling Divisible Loads in Parallel and Distributed Systems
Optimizing Computing Costs Using Divisible Load Analysis

IEEE Transactions on Parallel and Distributed Systems
Ten Reasons to Use Divisible Load Theory

Computer
Extending Amdahl's Law for Energy-Efficient Computing in the Many-Core Era

Computer
Scheduling for Parallel Processing

Scheduling for Parallel Processing
Tech Titans Building Boom

IEEE Spectrum

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we analyze energy usage in divisible load processing. Divisible load theory (DLT) applies to computations which can be divided into parts of arbitrary sizes, and the parts can be independently processed in parallel. The shortest schedule for divisible load processing is determined by the speed of computation and communication. Energy usage for such a time-optimum schedule is analyzed in this paper. We propose a simple model of energy consumption. Two states of the computing system are taken into account: an active state and an idle state with reduced energy consumption. Energy consumption is examined as a function of system parameters. We point out possible ways of energy conservation. It is demonstrated that energy can be saved by use of parallel processing.