Sunday, February 9

Conference reception
(7:30 pm)

Made possible by Cal-(IT)2 and the HSSoE at UCI.

Monday, February 10

Welcome (8:45am -  9:00am)


Keynote I (9:00am - 10:00am)
Chair: Laxmi Bhuyan

        Billion Transistor Chips in Mainstream Enterprise Platforms of the Future.
        Dileep Bhandarkar 
        Architect-at-Large, Enterprise Platforms Group, Intel Corporation
        (Slides)
        (Moore's Law Video)
        If you have trouble viewing the video, update to a newer version of Windows Media Player from
        http://www.microsoft.com/windows/windowsmedia/download/default.asp


Break (10:00am -  10:30am)

Session 1: Multithreading (10:30am -  12:00n)
Chair: Antonio Gonzalez

        Variability in Architectural Simulations of Multi-threaded Workloads
        Alaa Alameldeen and David Wood 

        Mini-threads: Increasing TLP on Small-Scale SMT Processors 
        Joshua Redstone, Susan Eggers, and Henry Levy

        Front-End Policies for Improved Issue Efficiency in SMT Processors 
        Ali El-Moursy and David Albonesi

Lunch (12:00n  -  1:30pm)

Session 2: Branch Prediction (1:30am -  3:00pm)
Chair: Susan Eggers

        Reconsidering Complex Branch Predictors
        Daniel Jimenez

        Incorporating Predicate Information Into Branch Predictors 
        Beth Simon, Brad Calder, and Jeanne Ferrante 

        Dynamic Data Dependence Tracking and its Application to Branch Prediction
        Lei Chen, Steve Dropsho, and David Albonesi

Break (3:00pm -  3:30pm)

Session 3: Power Efficient Designs (3:30pm -  5:30pm)
Chair: Saman Amarasinghe

        Control Techniques to Eliminate Voltage Emergencies in High-Performance Processors 
        Russ Joseph, David Brooks, and Margaret Martonosi

        Dynamic Voltage Scaling with Links for Power Optimization of Interconnection Networks 
        Li Shang, Li-Shiuan Peh, and Niraj Jha

        Power-Aware Control Speculation through Selective Throttling
        Juan L. Aragon, Jose Gonzalez, and Antonio Gonzalez

        Deterministic Clock Gating For Microprocessor Power Reduction 
        Hai Li, Swarup Bhunia, Yiran Chen, Kaushik Roy, and T.N. Vijaykumar


TCCA Meeting  (5:30pm)


BANQUET

Tuesday, February 11

Keynote II (8:30am - 9:30am)
Chair: Brad Calder

        Beyond Performance: Some (other) Challenges for Future Microprocessors.
        Eric Kronstadt 
        Director, VLSI Systems, IBM TJ Watson Research Center
        (Slides)

Break (9:30am - 10:00am)

Session 4: Superscalars (10:00am - 12:00n)
Chair: David Wood

        Runahead Execution: An Alternative to Very Large Instruction Windows for Out-of-order Processors 
        Onur Mutlu, Jared Stark, Chris Wilkerson, and Yale Patt

        Microarchitecture and Performance Analysis of a SPARC-V9 Microprocessor for Enterprise Server Systems
        Mariko Sakamoto, Akira Katsuno, Alichiro Inoue, Takeo Asakawa, Haruhiko Ueno, and Kuniki Morita
        
        Exploring the VLSI Scalability of Stream Processors 
        Brucek Khailany, William J. Dally, Scott Rixner, Ujval J. Kapasi, John Owens, and Brain Towles

        Dynamic Optimization Of Micro-Operations 
        Brian Slechta, Brian Fahs, David Crowe, Michael Fertig, Gregory Muthler,
        Justin Quek Francesco Spadini, Sanjay J. Patel, and Steven S. Lumetta


Luncheon  (12:00n  -  1:30pm)


Session 5: Multiprocessor Systems (1:30pm -  3:00pm) 
Chair: Chita Das

        Slipstream Execution Mode for CMP-Based Multiprocessors
        Khaled Ibrahim, Gregory Byrd, and Eric Rotenberg

        Tradeoffs in Buffering Memory State for Thread-Level Speculation in Multiprocessors 
        Maria Garzaran, Milos Prvulovic, Victor Vinals, Jose Llaberia, 
        Lawrence Rauchwerger, and Josep Torrellas

        Dynamic Data Replication: An approach to Providing Fault-Tolerant Shared Memory Clusters 
        Rosalia Christodoulopoulou, Reza Azimi, and Angelos Bilas

Break (3:00pm -  3:30pm)

Session 6: Memory and Communication Performance (3:30pm -  5:30pm)
Chair: Li-Shiuan Peh

        Memory System Behavior of Java-Based Middleware  
        Martin Karlsson, Kevin Moore, Erik Hagersten, and David Wood

        Evaluating the Impact of Communication Architecture on the Performability of Cluster-Based Services
        Kiran Nagaraja, Neeraj Krishnan, Ricardo Bianchini, Richard Martin, and Thu Nguyen

        Hierarchical Back-Off Lock for Non-Uniform Communication Architectures
        Zoran Radovic and Erik Hagersten

        Performance Enhancement Techniques for InfiniBand Architecture
        Eun Jung Kim, Ki Hwan Yum, Chita Das, Mazin Yousif, and Jose Duato


Wednesday, February 12

Keynote III (8:00am -  9:00am)
Chair: Josep Torrellas

        The State of State
        Peter Kogge
        McCourtney Professor of Computer Science and Engineering
        University of Notre Dame
        (Slides)


Session 7: Profiling and Simulation Support (9:00am - 10:00am)
Chair: Bill Mangione-Smith

        Catching Accurate Profiles in Hardware
        Satish Narayanasamy, Timothy Sherwood, Suleyman Sair, Brad Calder, and George Varghese

        A Statistically Rigorous Approach for Improving Simulation Methodology
        Joshua Yi, David Lilja, and Douglas Hawkins

Break (10:00am - 10:30am)

Session 8  (10:30am - 12:30 pm)
 

 
8 A: Caching and Prefetching
Chair: Soner Onder

        Caches and Merkle Trees for Efficient Memory Authentication 
        Blaise Gassend, Ed Suh, Dwaine Clarke, Marten van Dijk, and Srinivas Devadas

        Just Say No: Benefits of Early Cache Miss Determination 
        Gokhan Memik, Glenn Reinman, and William Mangione-Smith

        TCP: Tag Correlating Prefetchers  
        Zhigang Hu, Stefanos Kaxiras, and Margaret Martonosi

        Cost-sensitive Cache Replacement Algorithms 
        Jaeheon Jeong and Michel Dubois


8 B: Networks and Communication 
Chair: Qing Yang

        Scalar Operand Networks 
        Michael Taylor, Walter Lee, Saman Amarasinghe, and Anant Agarwal

        A Methodology for Designing Efficient On-Chip Interconnects on Well-Behaved Communication Patterns 
        Wai Hong Ho and Timothy Pinkston

        Inter-cluster Communication Models for Clustered VLIW processors 
        Andrei Terechko, Erwan Le Thenaff, Manish Garg, Jos van Eijndhoven, and Henk Corporaal
        
        Active I/O Switches in System Area Networks 
        Ming Hao and Mark Heinrich