2.2.1. Latency optimizations

Latency optimizations have been implemented. The minimum MPI latency for a 0-byte message within a single system has been reduced from approximately 78 user seconds to 60 user seconds.

Latency is the time between when a processor requests data and when it is able to use that data.

2.2.2. More MPI processes

This release includes support for up to 63 MPI processes within a single Cray SV1 system.