Summary: Titanium: A High­Performance Java Dialect \Lambda
Kathy Yelick, Luigi Semenzato, Geoff Pike, Carleton Miyamoto,
Ben Liblit, Arvind Krishnamurthy, Paul Hilfinger,
Susan Graham, David Gay, Phil Colella, and Alex Aiken
Computer Science Division
University of California at Berkeley
and
Lawrence Berkeley National Laboratory
Abstract
Titanium is a language and system for high­performance parallel scientific computing. Titanium
uses Java as its base, thereby leveraging the advantages of that language and allowing us to focus
attention on parallel computing issues. The main additions to Java are immutable classes, multi­
dimensional arrays, an explicitly parallel SPMD model of computation with a global address
space, and zone­based memory management. We discuss these features and our design approach,
and report progress on the development of Titanium, including our current driving application: a
three­dimensional adaptive mesh refinement parallel Poisson solver.
1 Overview
The Titanium language is designed to support high­performance scientific applications. Historically,
few languages that made such a claim have achieved a significant degree of serious use by scientific
programmers. Among the reasons are the high learning curve for such languages, the dependence on

Source: Aiken, Alex - Department of Computer Science, Stanford University

Collections: Computer Technologies and Information Sciences