Design issues for dynamic voltage scaling
ISLPED '00 Proceedings of the 2000 international symposium on Low power electronics and design
An overview of the BlueGene/L Supercomputer
Proceedings of the 2002 ACM/IEEE conference on Supercomputing
The design, implementation, and evaluation of a compiler algorithm for CPU energy reduction
PLDI '03 Proceedings of the ACM SIGPLAN 2003 conference on Programming language design and implementation
Environment for Multiprocessor Simulator Development
ISPAN '00 Proceedings of the 2000 International Symposium on Parallel Architectures, Algorithms and Networks
Compiler-directed dynamic voltage and frequency scaling for cpu power and energy reduction
Compiler-directed dynamic voltage and frequency scaling for cpu power and energy reduction
Power and Energy Profiling of Scientific Applications on Distributed Systems
IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Papers - Volume 01
Exploring the Energy-Time Tradeoff in MPI Programs on a Power-Scalable Cluster
IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Papers - Volume 01
A Power-Aware Run-Time System for High-Performance Computing
SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
Minimizing execution time in MPI programs on an energy-constrained, power-scalable cluster
Proceedings of the eleventh ACM SIGPLAN symposium on Principles and practice of parallel programming
Scheduling for reduced CPU energy
OSDI '94 Proceedings of the 1st USENIX conference on Operating Systems Design and Implementation
Hi-index | 0.00 |
Although parallel systems with high peak performance have been exciting, high peak performance often means high power consumption. In this paper, power-aware parallel systems are investigated, where each node can make dynamic voltage scaling (DVS). Based on the characteristics of communication and memory access in MPI programs, a compiler is used to automatically form communication and computation regions, and to optimally assign frequency and voltage to the regions. Frequency and voltage of each node are dynamically adjusted, and energy consumption is minimized within the limit of performance loss. The results from simulations and experiments show that compiler-directed energy-time tradeoff can save 20~40% energy consumption with less than 5% performance loss.