Time synchronization on SP1 and SP2 parallel systems

We describe an experimental time utility for synchronizing the operating system clocks on the SP1 and SP2 parallel system nodes. It synchronizes the node clocks typically, within 5 microseconds of each other utilizing the synchronous feature of the SP1 and SP2 interconnection network. This is 2 to 3 orders of magnitude better than what can be achieved by previous methods. Synchronized clocks are useful for parallel program performance measurement and tuning, parallel program tracing and debugging, and gang scheduling of parallel processes, to name a few. We also measure the performance of a widely used time synchronization utility using the SP1 and SP2 interconnection network.<<ETX>>

[1]  Leslie Lamport,et al.  Time, clocks, and the ordering of events in a distributed system , 1978, CACM.

[2]  Craig B. Stunkel,et al.  The SP1 high-performance switch , 1994, Proceedings of IEEE Scalable High Performance Computing Conference.

[3]  Cevdet Aykanat,et al.  Routing Algorithms for IBM SP1 , 1994, PCRCW.

[4]  David L. Mills,et al.  Internet time synchronization: the network time protocol , 1991, IEEE Trans. Commun..

[5]  W. Richard Stevens,et al.  Unix network programming , 1990, CCRV.

[6]  Isaac D. Scherson,et al.  Least common ancestor networks , 1993, [1993] Proceedings Seventh International Parallel Processing Symposium.

[7]  Dennis G. Shea,et al.  Architecture and implementation of Vulcan , 1994, Proceedings of 8th International Parallel Processing Symposium.