This paper describes the design, implementation and performance of the NX message-passing interface on the SHRIMP multicomputer. Our implementation exploits SHRIMP's virtual memory-mapped communication facility. Unlike traditional methods, our implementation performs buffer management at user level without using a special message-passing processor, and requires no CPU intervention upon message arrival in the common cases. For a four-byte message, our implementation achieves a user-to-user latency of 12 microseconds which is about factor of four smaller than that on the Intel Paragon. For large messages, our implementation quickly approaches the bandwidth limit imposed by the SHRIMP hardware.

This technical report has been published as

Design and Implementation of NX Message Passing Using SHRIMP Virtual Memory Mapped Communication. Richard Alpert, Cezary Dubnicki, Edward Felten and Kai Li, Proc. of the Internat. Conference on Parallel Processing, August 1996.