sdasgup3 / heterogeneity-aware-load-balancing

Power capping the cpu and exploiting heterogenity using charm++ load balancers

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Abstract

Different processors across the nodes have different execution times for the same work-loads. This performance imbalance is more prominent when the CPU power is capped to low values. This performance imbalance causes increased execution times of the parallel applications. We propose a load balancer using Charm++ parallel programming framework which minimizes the performance imbalance at the lower power caps by addressing this heterogeneity.

About

Power capping the cpu and exploiting heterogenity using charm++ load balancers


Languages

Language:TeX 91.3%Language:C 5.4%Language:Python 1.5%Language:C++ 0.7%Language:Makefile 0.5%Language:Batchfile 0.4%Language:Perl 0.1%Language:Shell 0.0%