Title :
Load balancing HPF programs by migrating virtual processors
Author :
Perez, Christian
Author_Institution :
LIP, Ecole Normale Superieure de Lyon, France
Abstract :
The paper explores the integration of load balancing features in the data parallel language, HPF, targeting semi regular applications. We show that the HPF virtual processors are good candidates to be the unit of migration. Then, we compare 3 possible implementations and show that threads provide a good trade-off between efficiency and ease of implementation. We finally describe a preliminary implementation. The experimental results, obtained with the Gaussian elimination with partial pivoting are promising
Keywords :
FORTRAN; parallel languages; parallel programming; resource allocation; virtual machines; Gaussian elimination; HPF virtual processors; data parallel language; load balancing HPF programs; load balancing features; migrating virtual processors; partial pivoting; semi regular applications; threads; Continuous improvement; Data mining; Hardware; Load management; Operating systems; Parallel languages; Parallel processing; Program processors; Programming profession; Yarn;
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.1997.582959
