Rajeev Sivaram, Ram Kesavan, et al.
ICPP 1998
While the interconnection network topology is one of the most important determinants of the performance of a parallel system, no single topology offers an ideal cost/performance trade-off for all classes of applications in parallel processing. The modular units used in the IBM RS/6000 SP topologies allow the construction of a large variety of topologies including 4-ary fat-tree networks. In our experience, however, cost and cost/performance ratio are often the primary concerns of customers. Therefore, while fat-tree topologies offer excellent performance, they are not always the most attractive choice for customers of large-scale parallel systems. This paper presents the lower-cost RS/6000 SP topologies for large systems designed with fewer switching elements than fat-tree networks, and describes some of the rationale behind the choices made.
Rajeev Sivaram, Ram Kesavan, et al.
ICPP 1998
Bulent Abali, Craig B. Stunkel, et al.
Journal of Parallel and Distributed Computing
Bulent Abali, Craig B. Stunkel, et al.
Journal of Parallel and Distributed Computing
Rajeev Sivaram, Dhabaleswar K. Panda, et al.
IEEE TPDS