Sponsored by:

Language Runtimes '04
Impact of Next Generation Processor Architectures On Virtual Machines

Morning Keynote Presentation:
Design Issues For Next Generation Processor Architectures
Speaker:
James A. Kahle IBM Austin Research Labs jakahle@us.ibm.com Jim Kahle is a IBM Fellow and Chief Architect for the Cell Architecture being designed for Sony, Toshiba, and IBM. Previously he was Chief Architect of the Power4 core used in IBM servers and Apple's G5. He was the project manager for PowerPC 603 series that are used in Apple Laptops and Nintendo game cubes. Jim has been involved in Power architecture designs since its conception. He combines broad processor knowledge, high performance teams, deep client relationships to understand future requirements to achieve break through innovations in chip design.
Abstract:
Keynote Abstract Goes Here
Presentation:
The Virtualized Virtual Machine
Speaker:
David F. Bacon IBM T.J. Watson Research Center dfb@watson.ibm.com David F. Bacon is a Research Staff Member at IBM's T.J. Watson Research Center. His algorithms are included in most compilers and run-time systems for modern object-oriented languages, and his work on Thin Locks was selected as one of the most influential contributions in the last 20 years of the Programming Language Design and Implementation (PLDI) conference. His recent work focuses on real-time and concurrent garbage collection, embedded systems, programming language design, and computer architecture. He holds a Ph.D. in computer science from the University of California, Berkeley and received his A.B. from Columbia University. He holds 5 patents and has served on the program committees of POPL, OOPSLA, and ISMM. He is a member of the ACM and IEEE.
Abstract:
David F. Bacon's Abstract Goes Here
Paper:
Download Paper
Presentation:
Streaming Virtual Machine and Two-Level Compilation Model for Streaming Architectures and Languages
Speaker:
Vassily Litvinov Reservoir Labs Inc. vass@reservoir.com Vassily Litvinov received a Diploma (M.Sc.) in Applied Mathematics and Physics from Moscow Institute of Physics and Technology, Russia, in 1992, and a M.Sc. and Ph.D. in Computer Science from the University of Washington in 1996 and 2003. His doctoral dissertation developed a type system for object-oriented languages based on a generalized notion of type constraints on parametric (generic) declarations. Vassily Litvinov joined Reservoir Labs, Inc., in 2003. He is involved in research and implementation of optimizing compilers for embedded systems.
Abstract:
Abstract Goes Here
Paper:
Download Paper
Presentation:
The Application of Virtual Machine Technology to Massive Scale
Speaker:
Christopher A. Vick Sun Microsystems Christopher.Vick@Sun.COM Christopher A. Vick is a Senior Staff Engineer at Sun Microsystems Laboratories, and is the Principal Investigator for the HPCS Runtime Executive project there. He was one of the original architects of the Java HotSpot Server Compiler, and has served as technical lead for Sun's Core Java Virtual Machine Group as well as the Core JVM Compiler Group. He has also worked on both DSP compilers and development tools and DSP processor architecture at Texas Instruments, Inc.
Abstract:
DARPA's High Productivity Computing Systems project has presented a tremendous challenge to the computing community to produce a petascale machine that embodies both high performance and high productivity. This challenge involves not only the design of new hardware architectures, but also the design of new software to effectively manage that hardware, and to make the hardware useful to human programmers. Virtual machine technologies represent a promising new avenue to improving the productivity of these systems by improving performance, making the machine more useable for programmers, and by improving the availability of the system.
Paper:
Download Paper
Afternoon Keynote Presentation:
The Cascade Petascale Architecture Architecture
Speaker:
Burton Smith Cray Inc. burton@cray.com Burton Smith is Chief Scientist of Cray Inc. He received the BSEE from the University of New Mexico in 1967 and the Sc.D. from MIT in 1972. From 1985 to 1988 he was Fellow at the Supercomputing Research Center (now the Center for Computer Sciences) of the Institute for Defense Analyses. Before that, he was Vice President, Research and Development at Denelcor, Inc. and was chief architect of the HEP computer system. Dr. Smith is a Fellow of the ACM, a Fellow of the IEEE, and a member of the National Academy of Engineering. He won the IEEE-ACM Eckert-Mauchly award in 1991 and the IEEE Seymour Cray Award in 2003. His main interest is general purpose parallel computing.
Abstract:
Keynote Abstract Goes Here
Presentation:
X10: A Programming Model for Hierarchical Heterogeneous Parallelism
Speaker:
Vivek Sarkar vsarkar@us.ibm.com IBM T.J. Watson Research Center Kemal Ebcioglu kemal@us.ibm.com IBM T.J. Watson Research Center Vijay Saraswat vsaraswa@us.ibm.com IBM T.J. Watson Research Center Dr. Vivek Sarkar is Senior Manager of the Programming Technologies Department in the IBM Research Division, and is a member of the IBM Academy of Technology. The projects under way in his department span the areas of: Programming Models --- XJ, PERCS/X10, Symbiotic Programming Tools --- Advanced Refactoring, C/C++ Grid Migration, Concern Manipulation Environment (CME), J2EE Validation and Optimization (DOMO), Legacy Transformation (Mastery), Test Prioritization (Chianti) Software Virtualization and Delivery (PDS) Advanced Virtual Machine Technologies (Jikes RVM, Parley, Memory Wall) Dr. Sarkar is also responsible for coordinating Eclipse-related projects and activities in IBM Research, including the world-wide Eclipse Innovation Grants program. Dr. Sarkar's personal research interest is in advancing the state of the art of programming language design, programming tools, and optimizing and parallelizing compilers so as to deliver improved productivity and performance benefits to users of parallel systems. He is the leader of the PERCS Programming Model and Tools project, which includes work on X10, an experimental object-oriented programming language and programming environment being developed to address the locality and scalability challenges facing parallel systems in the 2010 timeframe. He has worked on several compiler-related projects at IBM including the PTRAN and Jikes RVM research projects at Watson, and high-order transformations and OpenMP parallelization in the IBM XL Fortran product compilers. Dr. Sarkar has published over 75 papers in the area of optimizing and parallelizing compilers, and has lectured internationally on his research. Dr. Sarkar joined IBM in 1987, after obtaining a Ph.D. from Stanford University. In 1997, he was on sabbatical as a visiting associate professor at MIT.
Abstract:
X10 is a new programming model extending state-of-the-art object-programming languages to support high-end, high-performance, high-productivity computing. This paper provides a summary of the X10 language, it's programming model, and discuss its applicability to next generation processor architectures. X10 supports its design goals by introducing a few core constructs organized around the central notion of a place. A place is an abstraction of a data-coherent multi-processor. A computation, consisting of millions of activities may run over hundreds of thousands of places. Large arrays may be distributed across multiple places. X10 allows an activity to dynamically create activities at multiple places, and allows an activity to return a future to the invoking activity. An activity may update local data-objects using atomic sections. Multiple activities at multiple places may be phased through the use of clocks, which allow the repeated detection of stable properties of networks of activities.
Paper:
Download Paper
Presentation:
Designing for Diagnosability
Speaker:
Eric G. Allen Sun Microsystems Eric Allen is a member of the Programming Languages Research Group at Sun Labs. He is concerned with the design, formal analysis, and implementation of new language features to increase program robustness and programmer productivity. Eric was the lead programmer of Rice University's compiler for the NextGen programming language, an extension of the Java language with added experimental features. He was also a founding member of the DrJava project, an open-source IDE designed for interactive, test-driven development. He has moderated several forums for the online magazine JavaWorld, and has written many online articles on effective programming and debugging. He is the former lead Java programmer at Cycorp, Inc., and is also author of the book "Bug Patterns in Java", which discusses common bugs and how to avoid them. Eric received his BA in computer science and mathematics from Cornell University and his MS and PhD from Rice University
Abstract:
Paper:
Download Paper
Presentation:
Chapel: The Cascade High Productivity Language
Speaker:
Bradford Chamberlain Cray Inc. Bradford Chamberlain is an employee of Cray Inc. and is working on the design and implementation of the Chapel language as part of Cray's Cascade project in the DARPA HPCS program. He received his PhD from the University of Washington where he contributed to the ZPL parallel array language, and he remains active in that project as an affiliate faculty member.
Abstract:
Abstract: As part of Cray's effort in the DARPA HPCS program, we are developing a new parallel language called Chapel -- the Cascade High Productivity Language. Chapel is being designed both to simplify the task of prototyping new codes on parallel machines and to support the ability to tune these codes to production-level quality without abandoning the language or the initial code. In this talk, I will present our motivation for working on Chapel, an overview of its features, and a few motivating examples.
Paper:
Download Paper