Live Webcast 15th Annual Charm++ Workshop

Quantifying Network Contention on Large Parallel Machines
Parallel Processing Letters (PPL) 2009
Publication Type: Paper
Repository URL: 200907_ContentionPPL
Impact of network topology on application performance has become important again with the emergence of very large supercomputers, typically connected as a 3D torus or mesh. This article presents a quantitative study on the effect of contention on message latencies on torus and mesh networks. Several MPI benchmarks are used to evaluate the effect of hops (links) traversed by messages, on their latencies. The benchmarks demonstrate that when multiple messages compete for network resources, link occupancy or contention can increase message latencies by up to a factor of 8 times on some architectures. Results are shown for two parallel machines -- ANL's IBM Blue Gene/P (Surveyor) and PSC's Cray XT3 (BigBen).

Significant theoretical research was done on interconnect topologies and topology aware mapping for parallel computers in the 80s. With the deployment of virtual cut-through, wormhole routing and faster interconnects, message latencies reduced and research in the area died down. Findings in this article suggest that application developers should now consider interconnect topologies when mapping tasks to processors in order to obtain the best performance on large parallel machines.
Abhinav Bhatele, Laxmikant V. Kale, "Quantifying Network Contention on Large Parallel Machines", Parallel Processing Letters (Special Issue on Large-Scale Parallel Processing), Vol: 19 Issue: 4, Pages: 553-572, 2009
Research Areas