Optimizing Communication for Massively Parallel Processing

127 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2005.In this thesis, we motivate the need for hardware collectives, as processor based collectives can be delayed by intermediate that processors busy with computation. We show the performance gains of a next generation network with hardware collectives, through synthetic benchmarks.U of I OnlyRestricted to the U of I community idenfinitely during batch ingest of legacy ETD