Titanium performance and potential: an NPB experimental study

  • Authors:

  • Kaushik Datta;Dan Bonachea;Katherine Yelick

  • Affiliations:

  • Computer Science Division, University of California at Berkeley;Computer Science Division, University of California at Berkeley;Computer Science Division, University of California at Berkeley

  • Venue:
  • LCPC'05 Proceedings of the 18th international conference on Languages and Compilers for Parallel Computing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Titanium is an explicitly parallel dialect of JavaTM designed for high-performance scientific programming. We present an overview of the language features and demonstrate their use in the context of the NAS Parallel Benchmarks, a standard suite of common scientific kernels. We argue that parallel languages like Titanium provide greater expressive power than conventional approaches, enabling much more concise and expressive code that minimizes time to solution. Moreover, we have found that the Titanium implementations of three of the NAS Parallel Benchmarks can match or even exceed the performance of the standard Fortran/MPI implementations at realistic problem sizes and processor scales, while still using far cleaner, shorter and more maintainable code.