PACT'99 Final Program at a Glance

Back to PACT'99 homepage

PACT'99 Final Program: PAPER SESSIONS

DAY 1: October 13, 1999

Session 1: Microarchitecture (Jeff Koller)

• Exploring Instruction-Fetch Bandwidth Requirement in Wide-Issue Superscalar Processors (P. Michaud, A. Seznec and S. Jourdan)
• MPEG-2 Video Decompression on Simultaneous Multithreaded Multimedia Processors (H. Oehring, U. Sigmund and T. Ungerer)
• A Fully Asynchronous Superscalar Processor (D. Arvind and R. Mullins)

Session 2: Multithreading (Makoto Amamiya)

• The Need for Fast Communication in Hardware-Based Speculative Chip Multiprocessors (V. Krishnan and J. Torellas)
• A Multithreaded Java Microcontroller for Thread-oriented Real-time Event-Handling (U. Brinkschulte, C. Krakowski, J. Kreuzinger and T. Ungerer)
• On Dynamic Speculative Thread Partitioning and the MEM-slicing Algorithm (L. Codrescu and D. Wills)

Session 3: Prediction Mechanisms (Sally McKee)

• Branch Prediction using Selective Branch Inversion (S. Manne, A. Klauser and D. Grunwald)
• Control-Flow Speculation through Value Prediction for Superscalar Processors (J. Gonzalez and A. Gonzalez)
• Exploring Last n Value Prediction (M. Burtscher and B. Zorn)

Session 4: Compilation Techniques (Mary Hall)

• Evaluating Register Allocation and Instruction Scheduling Techniques in Out-Of-Order Issue Processors (M. Valluri and R. Govindarajan)
• Containers on the Parallelization of General-purpose Java Programs (P. Wu and D. Padua)
• The Modulo Interval: A Simple and Practical Representation for Program Analysis (T. Nakanishi, K. Joe, C. Polychronopoulos and A. Fukuda)

Session 5: Performance Characterization (Akira Fukuda)

• Memory System Support for Image Processing (L. Zhang, B. Carter, W. Hsieh and S. McKee)
• Performance Characteristics of a Network of Commodity Multiprocessors for the NAS Benchmarks Using a Hybrid Memory Model (F. Cappello and O. Richard)
• A Characterisation of Parallel SPECint Programs in Simultaneous Multi-Threading Architectures (D. Ortega, I. Martel, V. Krishnan, E. Ayguade and M. Valero)

DAY 2: October 14, 1999

Session 6: Advanced Compilation (Constantine Polychronopoulos)

• LaTTe: A Java VM Just-in-Time Compiler with Fast and Efficient Register Allocation (B-S. Yang, S-M. Moon, S. Park, J. Lee, S. Lee, J. Park, Y. Chung, S. Kim, K. Ebcioglu and E. Altman)
• Automatic Parallelization of Recursive Procedures (M. Gupta, S. Mukhopadhyay and N. Sinha)
• On the complexity of loop fusion (A. Darte)

Session 7: Micro-clusters, Clusters, and SMPs (Yale Patt)

• A Cost-Effective Clustered Architecture (R. Canal, J-M. Marcerisa and A. Gonzalez)
• Optimizing Data Locality for SCI-based PC-Clusters with the SMiLE Monitoring Approach (W. Karl, M. Leberecht and M. Schultz)
• Dynamic Linking on a Shared-Memory Multiprocessor (B. Alpern, M. Charney, J-D. Choi, A. Cocchi and D. Lieber)
• Reducing Cache Conflicts by Partitioning and Privatizing Shared Arrays (Z. Li)

Session 8: Applied Analytical Techniques (Lawrence Rauchwerger)

• Localizing Non-Affine Array References (N. Mitchell, L. Carter and J. Ferrante)
• On Reducing False Sharing While Improving Locality on Shared Memory Multiprocessors (M. Kandemir, A. Choudhary, J. Ramanujam and P. Banerjee)
• Lower Bounding Techniques for the Multiprocessor Scheduling Problem with Communication Delay (s. Fujita and T. Nakagawa)
• Automatic Analytical Modeling for the Estimation of Cache Misses (B. Fraguela, R. Doallo and E. Zapata)

DAY 3: October 15, 1999

Session 9: Architecture-Driven Compilation (Mateo Valero)

• Cameron: High Level Language Compilation for Reconfigurable Computing (J. Hammes, B. Rinker, W. Bohm, W. Najjar, B. Draper and R. Beveridge)
• Predicated Static Single Assignment (L. Carter, B. Simon, B. Calder, L. Carter and J. Ferrante)
• The Effect of Program Optimization on Trace Cache Efficiency (D. Howard and M. Lipasti)

Session 10: Advanced Parallelization (Greg Egan)

• Data Dependence Testing in Practice (K. Psarris and k. Kyriakopoulos)
• On Index Set Splitting (M. Griebl, P. Feautrier and C. Lenguaer)
• Efficient Parallelisation using Combined Loop and Data Transformations (M. O'boyle and P. Knijnenburg)

Session 11: Prediction and Speculation (Kemal Ebcioglu)