DEBUGGING PARALLEL PROGRAMS USING EVENT GRAPH MANIPULATION

The need for more accurate results and larger problem sizes pushes the users in certain fields towards using supercomputing power. Besides p roblems with initial program development, another problem arises with debugging this kind of program. Debugging parallel programs is one of the hard tasks that users have to deal with when using parallel archit ectures. Where memory hot spots and bus contention are problems with s hared memory architectures, nondeterminism arising from race condition s and the lack of a global clock are severe problems in using distribu ted memory architectures. We will discuss a new approach for detecting and/or studying concurrent events in distributed memory machines if r ace conditions occur in a certain program run. Through event graph man ipulation the user can investigate whether wrong results may appear th rough different ordering of events.