Publications

T. Peterka and R. Ross, "Versatile Communication Algorithms for Data Analysis," Preprint ANL/MCS-P2080-0512, May 2012. [pdf]

Large-scale parallel data analysis, where global information from a variety of problem domains is resolved in a distributed memory space, relies on communication. Three communication algorithms motivated by data analysis workloads merge based reduction, swap based reduction, and neighborhood exchange are presented, and their performance is benchmarked. These algorithms communicate custom data types among blocks assigned to processes in flexible ways, and their performance is optimized by tunable parameters. Performance is compared to an MPI implementation and to previous communication algorithms on an IBM Blue Gene/P supercomputer at a variety of message sizes and process counts.