Final Program
4th Workshop on Binary Translation
WBT-2002
September 22, 2002, Morning
Omni Charlottesville Hotel
235 W. Main St.
Charlottesville, VA
Held in conjunction with the
Commercializing Binary Translation
Binary translation and optimization have reached a high profile in the
research community in recent years, and a consensus is growing among
researchers that the technology has a valuable part to play in the creation
of future computing systems, whether in a revised structuring of existing
run-time software interfaces, or as a component in the design of future
CPUs. The number of commercial deployments of these technologies, however,
has lagged this enthusiasm. In this keynote, I will describe some
experiences gained in Transitive Technologies, which is commercializing
machine-independent dynamic binary translation and optimization technology.
Adaptive Optimization in the Jikes RVM
This talk will present an overview of the Jikes Research Virtual
Machine(RVM), an open source VM for Java from the Jalapeņo project at IBM.
The Jikes RVM provides a flexible open testbed to prototype new virtual
machine technologies. The system includes state-of-the-art techniques for
dynamic compilation, adaptive optimization, garbage collection, thread
scheduling, and synchronization. The system is implemented in the Java
programming language and is self-hosted i.e., its Java code runs on itself
without requiring a second virtual machine. The system runs on Linux/IA-32,
AIX/PowerPC, and Linux/PowerPC platforms.
In the first ten months since its open source release, the system was
downloaded by over 1,500 different sites. Academic researchers using the
system have published over fifteen papers in leading conferences in 2002.
Three professors have used the system to teach courses.
This presentation will highlight various components of the Jikes RVM, and
focus on results from the adaptive optimization system, which uses on-line
profile data to guide selective optimization and feedback-directed
optimizations.
Stephen Fink is a Research Staff Member at the IBM T.J. Watson Research
Center. His recent research focuses on virtual machine and optimizing
compiler technology, with emphasis on adaptive and on-line optimization.
He is one of the main contributors to the open-source Jikes Research
Virtual Machine, developed by Jalapeno project at IBM. Dr. Fink received
the B.S. degree from Duke University, and the M.S. and Ph.D. degrees from
the University of San Diego, California. His other research interests
include parallel and scientific computation, and Java enterprise software
technology.
Final Program
Introduction and Keynote (8:30 ~ 9:45am)
Keynote Talk: ``Commercializing Binary Translation''
Alasdair Rawsthorne
CTO, Transitive Technologies
Session A (9:45 ~ 10:35)
DIOTA: Dynamic Instrumentation, Optimization and Translation
of Applications
Jonas Maebe, Michiel Ronsse and Koen De Bosschere
Ghent University
Detecting Memory Performance Bottlenecks via Binary Rewriting
Jaydeep Marathe and Frank Mueller
North Carolina State University
Break (10:35 ~ 11:00)
Session B (11:00 ~ 11:50)
Walkabout - A Retargetable Dynamic Binary Translation Framework
Cristina Cifuentes, Brian Lewis and David Ung
Sun Microsystems
Fast Dynamic Binary Translation - The Yirr-Ma Framework
Jens Troger and John Gough
Queensland University of Technology
Invited Talk (11:50 ~ 12:30)
Invited Talk: "Adaptive Optimization in the Jikes RVM"
Stephen Fink, IBM T.J. Watson Research Center, Yorktown Heights, NY