Perfect Strong Scaling Using No Additional Energy
2013pp. 649–660
Citations Over TimeTop 10% of 2013 papers
Abstract
Energy efficiency of computing devices has become a dominant area of research interest in recent years. Most previous work has focused on architectural techniques to improve power and energy efficiency; only a few consider saving energy at the algorithmic level. We prove that a region of perfect strong scaling in energy exists for matrix multiplication (classical and Strassen) and the direct n-body problem via the use of algorithms that use all available memory to replicate data. This means that we can increase the number of processors by some factor and decrease the runtime (both computation and communication) by the same factor, without changing the total energy use.
Related Papers
- StrassenNets: Deep Learning with a Multiplication Budget.(2018)
- → StrassenNets: Deep Learning with a Multiplication Budget(2017)11 cited
- → A transform approach to fast matrix multiplication(1994)2 cited
- → KS ring theoretic approach for matrix multiplication(2011)
- Algorithms Analysis of Matrix Multiplication(2001)