DMCA
Scalability analysis of spmd codes using expectations (2007)
| Venue: | In ICS ’07: Proceedings of the 21st annual international conference on Supercomputing |
| Citations: | 15 - 8 self |
BibTeX
@INPROCEEDINGS{Coarfa07scalabilityanalysis,
author = {Cristian Coarfa and John Mellor-crummey and Nathan Froyd and Yuri Dotsenko},
title = {Scalability analysis of spmd codes using expectations},
booktitle = {In ICS ’07: Proceedings of the 21st annual international conference on Supercomputing},
year = {2007},
pages = {13--22},
publisher = {ACM}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present a new technique for identifying scalability bottle-necks in executions of single-program, multiple-data (SPMD) parallel programs, quantifying their impact on performance, and associating this information with the program source code. Our performance analysis strategy involves three steps. First, we collect call path profiles for two or more executions on different numbers of processors. Second, we use our ex-pectations about how the performance of executions should differ, e.g., linear speedup for strong scaling or constant ex-ecution time for weak scaling, to automatically compute the scalability of costs incurred at each point in a program’s ex-ecution. Third, with the aid of an interactive browser, an application developer can explore a program’s performance in a top-down fashion, see the contexts in which poor scal-ing behavior arises, and understand exactly how much each scalability bottleneck dilates execution time. Our analysis technique is independent of the parallel programming model. We describe our experiences applying our technique to ana-lyze parallel programs written in Co-array Fortran and Uni-fied Parallel C, as well as message-passing programs based on MPI.
Keyphrases
scalability analysis spmd code scalability bottle-necks execution time parallel program top-down fashion program performance different number message-passing program performance analysis strategy call path profile poor scal-ing behavior arises uni-fied parallel scalability bottleneck constant ex-ecution time parallel programming model weak scaling co-array fortran interactive browser analysis technique linear speedup program ex-ecution program source code application developer strong scaling new technique ana-lyze parallel program
