In this paper, we present two new approaches while rendering necessary extensions to Periscope to perform scalability and performance analysis on OpenMP codes. Periscope is an online-based performance analysis toolkit which consists of a user defined number of analysis agents that automatically search for the performance properties while the application is running. In order to detect the scalability and performance bottlenecks of OpenMP codes using Periscope, a few newly defined performance properties and meta properties are formalized. We manifest our implementation by evaluating NAS OpenMP benchmarks. As shown in our results, our approach identifies the code regions which do not scale well and other performance problems, e.g. load imbalance in NAS parallel benchmarks.
Publié le : 2015-02-10
Classification:  Memory accesses analysis, OpenMP, performance analysis, program transformations, speedup, supercomputers,  68M14, 68M20
@article{cai2808,
     author = {Shajulin Benedict; HPCCLoud Research Laboratory, Department of Computer Engineering, St. Xavier's Catholic College of Engineering, Nagercoil 3 and Michael Gerndt; Informatics I10, Technische Universit\"at M\"unchen, Boltzmannstrasse 3, M\"unchen},
     title = {Scalability and Performance Analysis of OpenMP Codes Using the Periscope Toolkit},
     journal = {Computing and Informatics},
     volume = {33},
     number = {3},
     year = {2015},
     language = {en},
     url = {http://dml.mathdoc.fr/item/cai2808}
}
Shajulin Benedict; HPCCLoud Research Laboratory, Department of Computer Engineering, St. Xavier's Catholic College of Engineering, Nagercoil 3; Michael Gerndt; Informatics I10, Technische Universität München, Boltzmannstrasse 3, München. Scalability and Performance Analysis of OpenMP Codes Using the Periscope Toolkit. Computing and Informatics, Tome 33 (2015) no. 3, . http://gdmltest.u-ga.fr/item/cai2808/