Search

In this paper we propose a simple extension to the optical network of a scalable multiprocessor that optimizes page swap-outs significantly. More specifically, we propose to extend the network with an optical ring that not only transfers swapped-out pages between the local memories and the disks of the multiprocessor but also acts as a system-wide write cache for these pages. This extended optical network has several performance benefits: it provides a staging area where swapped-out pages can reside until the disk is free; it increases the possibility of combining several writes to disk; and it acts as a victim cache for pages that are swapped out and subsequently accessed by the same or a different processor. In order to evaluate the extent to which these benefits affect performance, we use detailed execution-driven simulations of several out-of-core parallel applications running on an 8-node scalable multiprocessor. Our results demonstrate that our optical ring provides consistent performance improvements, coming mostly from faster page swap-outs and victim caching. Based on these results and on our parameter space study, our main conclusion is that our optical ring is highly efficient under several architectural assumptions and for most out-of-core parallel applications.