Title :
A rule-based approach for automatic bottleneck detection in programs on shared virtual memory systems
Author :
Gerndt, Michael ; Krumme, A.
Author_Institution :
Central Inst. for Appl. Math., Res. Center Julich, Germany
Abstract :
Programming distributed memory multiprocessors requires program parallelization as well as program optimization with respect to data locality. SVM-Fortran is a programming language for shared virtual memory architectures with special language features for specifying the distribution of parallel tasks onto the processors. It is realized on top of a shared virtual memory implementation on Intel Paragon. A programming environment provides performance analysis tools helping the user in the optimization of data locality. The paper outlines the environment, describes the basic concepts of the performance analysis support, and presents a design for the automation of performance analysis
Keywords :
distributed memory systems; knowledge based systems; parallel languages; parallel programming; shared memory systems; software performance evaluation; virtual storage; Intel Paragon; SVM-Fortran; automatic bottleneck detection; data locality; distributed memory multiprocessor programming; parallel task distribution; performance analysis automation; performance analysis support; performance analysis tools; program optimization; program parallelization; programming environment; programming language; rule based approach; shared virtual memory implementation; shared virtual memory systems; special language features; Automatic programming; Computer languages; Concurrent computing; Design automation; Design optimization; Mathematical programming; Mathematics; Parallel programming; Performance analysis; Programming environments;
Conference_Titel :
High-Level Programming Models and Supportive Environments, 1997. Proceedings., Second International Workshop on
Conference_Location :
Geneva
Print_ISBN :
0-8186-7882-8
DOI :
10.1109/HIPS.1997.582960
