VMIL 2012 Program
Workshop Date: October 21, 2012
Workshop Location: Salon K
Workshop proceedings as a single PDF file.
Session I Tracing JIT Compilers
| 8:30 - 8:35 |
Welcome, organizers introduction, brief introduction to the workshop, agenda
|
|
| 8:35 - 9:30 |
Keynote Talk: A Trace-based Java JIT Compiler for Large-scale Applications
Hiroshi Inoue
IBM Research - Tokyo
Abstract: Trace-based compilation uses dynamically-identified
frequently-executed code sequences (traces) as units for
compilation. We explore trace-based compilation in Java to see if a
trace-based JIT compiler (trace-JIT) can address a limitation of
method-based JIT compilers: limited compilation scope when dealing
with those with largely flat execution profile. Although, trace-based
compilation has gained popularity in dynamic scripting languages
(e.g. TraceMonkey and pypy) or for embedded devices (e.g. Dalvik VM),
the benefits and drawbacks of trace-JIT for large-scale applications
have not yet been studied. We first describe the design and
implementation of our trace-JIT with emphasis on efficient trace
selection and code generation. Then we discuss how the trace selection
algorithm affects the performance of a large-scale Java application
server.
|
|
| 9:30 - 10:00: |
The Efficient Handling of Guards in the Design of RPython's Tracing JIT
David Schneider and Carl Friedrich Bolz
Heinrich-Heine-Universitat Dusseldorf
Germany
|
|
10:00 - 10:30:
|
Break
|
|
Session II JVM Design |
| 10:30 - 11:00: |
S-RVM: a Secure Design for a High-Performance Java Virtual Machine
Yuval Yarom, Katrina Falkner and David S. Munro
The University of Adelaide
Australia
20 minutes for talk + 10 minutes for discussion
|
| 11:00 - 11:30: |
Bypassing Portability Pitfalls of High-level Low-level Programming
Yi Lin and Steve Blackburn
Australian National University
Australia
20 minutes for talk + 10 minutes for discussion
|
| 11:30 - 12:00: |
The JVM is not observable enough (and what to do about it)
Stephen Kell, Danilo Ansaloni, Walter Binder and Lukás Marek
University of Lugano and Charles University
Switzerland
20 minutes for talk + 10 minutes for discussion
|
|
|
| 12:00 - 1:30: |
Lunch Break |
|
Session III |
| 1:30 - 2:30 |
Invited Talk: From Turtles to Hares -- speeding up a dynamic language for data analytics
Jan Vitek
Purdue University
|
|
| 2:30 - 3:00 |
Faster Work Stealing With Return Barriers
Vivek Kumar and Steve Blackburn
Australian National University
Australia
20 minutes for talk + 10 minutes for discussion
|
|
3:00 - 3:30:
|
Break
|
|
Session IV Inlining and Adaptive Compilation |
| 3:30 - 4:00: |
Some New Approaches to Partial Inlining
Bowen Alpern, Anthony Cocchi and David Grove
Lehman College, CUNY and IBM Research
USA
20 minutes for talk + 10 minutes for discussion
|
|
| 4:00 - 4:30: |
Compilation Queuing and Graph Caching for Dynamic Compilers
Lukas Stadler, Gilles Duboscq, Hanspeter Hanspeter Mössenböck and Thomas Würthinger
Johannes Kepler University and Oracle Labs
Austria
20 minutes for talk + 10 minutes for discussion
|
|
4:30 - 5:00:
|
Discussion
|
|
| 7:00 - 9:00: |
Workshop dinner [Location: TBD] (meet in lobby at 6:45pm) |
