An Evaluation of GOAL, GAL, and CQR Routing Algorithms: Introduction to the Simulation Environment

Efficient routing algorithms are now becoming more and more necessary for productive Massively Parallel Processing (MPP) Computers, such as the Red Storm Supercomputer located at Sandia National Laboratories, NM. Some current implementations of MPP computers have used source-based routing, which during nodal failures, requires the entire network to halt and recompute routing tables. It should be considered that dynamic routing algorithms such as GOAL, GAL, and CQR have performance characteristics (throughput and latency), which rival source-based routing, but they lack data on how well they perform when nodal failures exist. The work stemming from this research will aim at evaluating GOAL, GAL, and CQR routing algorithm performance in terms of nodal failures. This paper serves as a basis for that research, extending the previous paper and now including an introduction of the simulation environment.