The 20th International Workshop on Languages
and Compilers for Parallel Computing

University of Illinois at Urbana-Champaign
Siebel Center for Computer Science
Urbana, Illinois, October 11-13, 2007

LCPC 2007 Program
Room 2405 Siebel

Thursday, October 11, 2007
8:00 Breakfast
8:45-9:00 Opening Remarks

Vikram Adve, Maria J. Garzaran, and Paul Petersen

9:00-10:00 Reliability

Compiler-Enhanced Incremental Checkpointing
Greg Bronevetsky, Daniel Marques, Keshav Pingali and Radu Rugina

Techniques for Efficient Software Checking
Jing Yu, Maria J. Garzaran and Marc Snir

10:00-10:30 Break
10:30-12:00 Languages

(This paper will not be presented because of travel difficulties) Revisiting SIMD programming
Anton Lokhmotov, Benedict Gaster, Alan Mycroft, Neil Hickey and David Stuttard

Multidimensional Blocking Factors in UPC
Christopher Barton, Calin Cascaval, George Almasi, Rahul Garg, Jose Nelson Amaral and Montse Farreras

An Experimental Evaluation of the New OpenMP Tasking Model
Eduard Ayguade, Alejandro Duran, Jay Hoeflinger, Federico Massaioli and Xavier Teruel

Language Extensions in Support of Compiler Parallelization
Jun Shirako, Hironori Kasahara and Vivek Sarkar

12:00-13:00 Lunch
13:00-14:00 Panel Discussion: How is Multicore Programming Different From Traditional Parallel Computing?
14:00-16:00 Parallel Compiler Technology I

Concurrency Analysis for Shared Memory Programs with Textually Unaligned Barriers
Yuan Zhang, Evelyn Duesterwald and Guang Gao

Iteration Disambiguation for Parallelism Identification in Time-Sliced Applications
Shane Ryoo, Christopher Rodrigues and Wen-mei Hwu

A Novel Asynchronous Software Cache Implementation for the CELL/BE Processor
Jairo Balart, Marc Gonzalez, Xavier Martorell, Eduard Ayguade, Zehra Sura, Tong Chen, Tao Zhang, Kevin O'brien and Kathryn O'Brien

Pillar: A Parallel Implementation Language
Todd Anderson, Neal Glew, Peng Guo, Brian Lewis, Wei Liu, Zhanglin Liu, Leaf Petersen, Mohan Rajagopalan,James Stichnoth, Gansha Wu and Dan Zhang

16:00-16:30 Break and Poster Session
16:30-17:30 Poster Session Continues
18:00 Conference Dinner and Keynote Speech: David Kirk, Chief Scientist, nVidia Corp.

NVIDIA CUDA Software and GPU Parallel Computing Architecture

Friday, October 12, 2007
8:00 Breakfast
8:30-11:00 Panel: What have we learned after 20 LCPCs?

Panelists: David Kuck (Intel), Arvind (MIT), Monica Lam (Stanford University), Alexandru Nicolau (University of California Irvine), Keshav Pingali (University of Texas, Austin), Burton Smith (Microsoft Research), and Michael Wolfe (the Portland Group).

Moderator: David Padua (University of Illinois at Urbana-Champaign).

11:00-11:30 Break
11:30-12:30 Libraries

Associative Parallel Containers in STAPL
Gabriel Tanase, Chidambareswaran Raman, Mauro Bianco, Nancy M. Amato and Lawrence Rauchwerger

Explicit Dependence Metadata in an Active Visual Effects Library
Jay L. T. Cornwall, Paul H. J. Kelly, Phil Parsonage and Bruno Nicoletti

12:30-14:00 Lunch
14:00-16:00 Run-time Systems and Performance Analysis

Supporting Huge Address Spaces in a Virtual Machine for Java on a Cluster
Ronald Veldema and Michael Philippsen

Modeling Relations Between Inputs and Dynamic Behavior for General Programs
Xipeng Shen and Feng Mao

Evaluation of RDMA opportunities in an Object-Oriented DSM
Ronald Veldema and Michael Philippsen

Automatic Communication Performance Debugging in PGAS Languages
Jimmy Su and Katherine Yelick

16:00-16:30 Break
16:30-17:30 Parallel Compiler Technology II

Exploiting SIMD Parallelism with the CGiS Compiler Framework
Nicolas Fritz, Philipp Lucas and Reinhard Wilhelm

Critical Block Scheduling: a Thread-Level Parallelizing Mechanism for a Heterogeneous Chip Multiprocessor Architecture
Slo-Li Chu

Saturday, October 13, 2007
8:00 Breakfast
9:00-10:00 Languages II

Capsules: Expressing Composable Computations in a Parallel Programming Model
Hasnain Mandviwala, Umakishore Ramachandran and Kathleen Knobe

Communicating Multiprocessor-Tasks
Jorg Dummler, Thomas Rauber and Gudula Runger

10:00-10:30 Break
10:30-12:00 General Compiler Techniques

An Effective Automated Approach to Specialization of Code
Minhaj Ahmad Khan, Henri-Pierre Charles and Denis Barthou

Flow-Sensitive Loop-Variant Variable Classification in Linear Time
Yixin Shou, Robert A. van Engelen and Johnnie Birch

Using ZBDDs in Points-to Analysis
Ondrej Lhotak, Stephen Curial and Jose Nelson Amaral