VELO: A Novel Communication Engine for Ultra-Low Latency Message Transfers

This paper presents a novel stateless, virtualized communication engine for sub-microsecond latency. Using a Field-Programmable-Gate-Array (FPGA) based prototype we show a latency of 970 ns between two machines with our Virtualized Engine for Low Overhead (VELO). The FPGA device is directly connected to the CPUs by a HyperTransport link. The described hardware architecture is optimized for small messages and avoids the overhead typically found with Direct-Memory Access (DMA) controlled transfers. The stateless approach allows to use the hardware unit directly from many threads and processes simultaneously. It provides a secure user level communication with an extremely optimized start-up phase. Microbenchmarks results are reported both based on proprietary API and OpenMPI basis.

• Type: Conference
• Year: 2008
• Where: ICPP
• Authors: Heiner Litz, Holger Fröning, Mondrian Nüssle, Ulrich Brüning
• Keywords: Distributed And Parallel Computing, ICPP 2008, Stateless Approach, Sub-microsecond Latency, Virtualized Communication Engine