Minimizing Total Cost ($$) and Maximizing Throughput : A Metric for Node versus Core Usage in Multi-Core Clusters
Andreas de Blanche, Stefan Mankefors-Christiernin · Parallel and Distributed Processing Techniques and Applications · 2010
When most commercial clusters had one processor core each, decreasing the runtime meant executing the application over more nodes – the associated cost (in $) would scale linearly with the number o ...