3rd Workshop on Compiler-Driven Performance

October 06, 2004
Hilton Suites Toronto/Markham Conference Centre
Markham, ON

Associated with CASCON 2004
(http://www.cas.ibm.com/cascon)


Final Program


Mini Section 1: Chair Chen Ding - University of Rochester

10:20-10:50 abc - The AspectBench Compiler
Laurie Hendren - McGill University
10:50-11:20 Taming Pointers -- A Symbolic Approach
Jianwen Zhu - University of Toronto
11:20-11:40 The use of traces for inlining in Java programs
Borys Bradel and Tarek Abdelrahman - University of Toronto
11:40-12:00 Accelerating Java synchronization in Just-In-Time compiler-generated code
Mark Stoodley - IBM Toronto Lab

12:00-01:00 Lunch

Mini Section 2: Chair Arie Tal - IBM Toronto Lab

01:00-01:40 X10 --- New opportunities for Compiler-Driven Performance via a new Programming Model
Kemal Ebcioglu, Vijay Saraswat, Vivek Sarkar - IBM T.J. Watson Research Center
01:40-02:10 Compiler Analyses for Improved Return Value Prediction
Christopher J.F. Pickett and Clark Verbrugge - McGill University
02:10-02:30 Widening
Ian McIntosh - IBM Toronto Lab

02:30-02:40 Break

Mini Section 3: Chair Calin Cascaval - IBM T. J. Watson Research Center

02:40-03:10 Second-Order Predictive Commoning
Arie Tal - IBM Toronto Lab
03:10-03:30 A Method of Interprocedural Strength Reduction
Shimin Cui - IBM Toronto Lab
03:30-03:50 From Speculative Partial Redundancy Elimination
to Speculative Partial Dead Code Elimination
R. Nigel Horspool, David Pereira - University of Victoria
03:50-04:10 Profile-Guided Switch Statement Case Dispatching
Peng Zhao - University of Alberta
04:10-04:30 Experiments with auto-parallelizing SPEC2000FP benchmarks
Guansong Zhang, Priya Unnikrishnan, and James Ren - IBM Toronto Lab