Abstract
The needs for larger problem sizes and for more accurate results force the users in the field of scientific computing towards applying parallel machines. Besides problems with initial program development another hard task arises with parallel program debugging, where severe difficulties appear with nondeterminism and race conditions.This paper describes the tools ATEMPT and CDFA, two modules of the MAD environment which support the detection of simple errors in the communication structure and race conditions in parallel programs. While ATEMPT generates an event graph and visualizes race condition candidates of an actual execution, CDFA analyzes the source code and produces data structures for investigation of control and data flow graphs. The combination of both tools gives further insight into a program and makes the evaluation of race evaluation more efficient.KeywordsDebuggingprogram analysisrace conditionsevent manipulation
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
