A Model for Speedup of Parallel Programs
Abstract
We propose a new model for parallel speedup that is based on two parameters, the average parallelism of a program and its variance in parallelism. We present a way to use the model to estimate these program characteristics using only observed speedup curves (as opposed to the more detailed program knowledge otherwise required). We apply this method to speedup curves from real programs on a variety of architectures and show that the model fits the observed data well. We propose several applications for the model, including the selection of cluster sizes for parallel jobs.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1997
- Accession Number
- ADA637068
Entities
People
- Allen B. Downey
Organizations
- University of California, Berkeley