Home Keynotes Program Registration Hotel Accommodation About Tsukuba Contact Us

 Cluster 2008 At A Glance

 (PDF file)

  Cluster 2008
  Technical Program

Sep 28 (Sun)

17:00 - 20:00

Registration (1F Foyer)

18:00 - 20:00

Reception (Restaurant Espoir, 1F, Tsukuba International Congress Center, EPOCHAL TSUKUBA)

Buses are the most convenient ground transportation between Tsukuba and Narita Airport.

Sep 29 (Mon)

9:30 - 9:45

Opening (Hall 300)
(including Award ceremony of Data Analysis Challenge)

9:45 - 10:45

Keynote (Hall 300)
Clouds, Clusters and ManyCore: The Revolution Ahead
Daniel A. Reed (Microsoft Research)

11:00 - 12:30

Session 1: System Tools and "Green" Computing
(Room 303)
Chair:Hiroshi Nakashima, Kyoto Univ.

Reliable Adaptable Network RAM
Tia Newhall, Daniel Amato, Alexandr Pshenichkin (Swarthmore College)

Magnet: A Novel Scheduling Policy for Power Reduction in Cluster with Virtual Machines
Liting Hu, Hai Jin, Xiaofei Liao, Xianjie Xiong, Haikun Liu (Huazhong University of Science and Technology)

Active CoordinaTion (ACT) - Toward Effectively Managing Virtualized Multicore Clouds
Mukil Kesavan, Adit Ranadive, Ada Gavrilovska, Karsten Schwan (CERCS, Georgia Institute of Technology)

Session 2: Application Algorithms and Scheduling
(Room 304)
Chair:Serge Petiton, LIFL/CNRS

Variable-grain and Dynamic Work Generation for Minimal Unique Itemset Mining
Paraskevas Yiapanis (University of Manchester), David J. Haglin (Minnesota State University, Mankato), Anna M. Manning, Ken Mayes, John Keane (University of Manchester)

A Large-Grained Parallel Algorithm for Nonlinear Eigenvalue Problems and Its Implementation Using OmniRPC
Takeshi Amako, Yusaku Yamamoto, Shao-Liao Zhang (Nagoya University)

Redistribution Aware Two-Step Scheduling for Mixed-Parallel Applications
Sascha Hunold, Thomas Rauber (University of Bayreuth), Frederic Suter (Nancy University)

Data Analysis Challenge:
Winner's Presentation and Technical Background in Info-plosion
(Hall 300)

12:30 - 13:45


13:45 - 15:15

Session 3: Profiling and Tuning
(Room 303)
Chair: Daniel Katz, LSU

Implications of non-constant clock drifts for the timestamps of concurrent events
Daniel Becker (Forschungszentrum Juelich), Rolf Rabenseifner (University of Stuttgart), Felix Wolf (Forschungszentrum Juelich)

In Search of Sweet-Spots in Parallel Performance Monitoring
Aroon Nataraj, Allen Malony, Alan Morris (University Of Oregon), Dorian C. Arnold, Barton P. Miller (University Of Wisconsin)

Workflows for Performance Evaluation and Tuning
Jeffrey L. Tilson, Mark S.C. Reed, Robert J. Fowler (Renaissance Computing Institute, University of North Carolina at Chapel Hill)

Session 4: Virtualization Technology
(Room 304)
Chair: Franck Cappello, INRIA

Combining Virtual Machine Migration with Process Migration for HPC on Multi-Clusters and Grids
Tal Maoz, Amnon Barak, Lior Amar (Department of Computer Science, The Hebrew University of Jerusalem)

Live and Incremental Whole-System Migration of Virtual Machines Using Block-Bitmap
Yingwei Luo, Binbin Zhang, Xiaolin Wang (Peking University), Zhenlin Wang (Michigan Technological University), Yifeng Sun (Peking University)

(Best Paper Award)
Efficient One-Copy MPI Shared Memory Communication in Virtual Machines
Wei Huang, Matthew Koop, Dhabaleswar K. Panda (The Ohio State University)

15:15 - 15:30

Coffee break (15min)

15:30 - 17:00

Session 5: Cluster Networking
(Room 303)
Chair: Markus Fischer, HPC Cluster Solutions

Multistage Switches are not Crossbars: Effects of Static Routing in High-Performance Networks
Torsten Hoefler (Indiana University), Timo Schneider (Technical University of Chemnitz), Andrew Lumsdaine (Indiana University)

A HyperTransport-Based Personal Parallel Computer Architecture
Xiaojun Yang, ninghui Sun, Xiaofang Zhao (Institute of Computing Technology, Chinese Academy of Sciences), Fei Chen, Hailiang Cheng (Graduate University of Chinese Academy of Sciences)

High Message Rate, NIC-Based Atomics: Design and Performance Considerations
Keith Underwood (Intel Corporation), Michael Levenhagen, Scott Hemmert, Ron Brightwell (Sandia National Labs)

Session 6: Adaptation to Multi-Core
(Room 304)
Chair: Raymond Namyst, LaBRI/CNRS

A dependency-aware task-based programming environment for multi-core architectures
Josep M. Perez, Rosa M. Badia, Jesus Labarta (Barcelona Supercomputing Center)

(Best Paper Award)
Are Non-Blocking Networks Really Needed for High-End-Computing Workloads?
Pavan Balaji, Narayan Desai (Argonne National Laboratory), P. Sadayappan, Mohammed Islam (Ohio State University)

OpenMP-centric Performance Analysis of Hybrid Applications
Karl Fuerlinger, Shirley Moore (University of Tennessee)

17:00 -

Excursion to University of Tsukuba

Sep. 30 (Tue)

9:00 - 11:00

Session 7: Parallel File Systems and I/O Libraries
(Room 303)
Chair: Gabriel Antoniu, IRISA/INRIA

DWC^2: A Dynamic Weight-based Cooperative Caching Scheme for Object-based Storage Cluster
Qingsong Wei (Data Storage Institute), Bharadwaj Veeravalli, Lingfang Zeng (National University of Singapore)

An OSD-based Approach to Managing Directory Operations in Parallel File Systems
Nawab Ali (The Ohio State University), Ananth Devulapalli, Dennis Dalessandro, Pete Wyckoff (Ohio Supercomputer Center), P Sadayappan (The Ohio State University)

DifferStore: A Differentiated Storage Service in Object-based Storage System
Qingsong Wei (Data Storage Institute)

A Novel Hint-based I/O Mechanism for Centralized File Server in cluster
Huan Chen, Jin Xiong, Ninghui Sun (Institute of Computing Technology, Chinese Academy of Sciences)

Work-in-progress presentation
(Room 304)
Chair: Takeshi Iwashita, Kyoto Univ.

Divisible Load Scheduling with Improved Asymptotic Optimality

Reiji Suda (The University of Tokyo / JST)

DLM: A Distributed Large Memory System using Remote Memory Swapping over Cluster Nodes
Hiroko Midorikawa (Seikei University), Motoyoshi Kurokawa (RIKEN), Ryutaro Himeno (RIKEN), Mitsuhisa Sato (University of Tsukuba)

RI2N: High-Bandwidth and Fault-Tolerant Network with Multi-link Ethernet for PC Clusters
Shin’ichi Miura (University of Tsukuba), Takayuki Okamoto (Fujitsu Ltd.), Taisuke Boku (University of Tsukuba), Toshihiro Hanawa (University of Tsukuba), Mitsuhisa Sato (University of Tsukuba)

The Impact of Topoloy and Link Aggregation on PC Cluster with Ethernet
Takafumi Watanabe (Doshisha University), Masahiro Nakao (Doshisha University), Tomoyuki Hiroyasu (Doshisha University), Tomohiro Otsuka (Keio University), Michihiro Koibuchi (National Institute of Informatics/The Graduate University of Advanced Studies/JST)

Predictive models for bandwidth sharing in high performance clusters
Vienne Jerome (LIG-MESCAL/BULL), Martinasso Maxime (LIG-MESCAL/BULL), Vincent Jean-Marc (LIG-MESCAL), Mehaut Jean-Francois (LIG-MESCAL)

Context-Aware Address Translation for High Performance SMP Cluster System
Moon-Sang Lee (Samsung Electronics), Joonwon Lee (KAIST), Seungryoul Maeng (KAIST)

Parallel Multistage Preconditioners by Hierarchical Interface Decomposition on “T2K Open Super Computer (Todai Combined Cluster)” with Hybrid Parallel Programming Models
Kengo Nakajima (The University of Tokyo)

Poster indexing
Chair: Takeshi Iwashita, Kyoto Univ.

Load-Balancing Methods for Parallel and Distributed Constraint Solving
Carl Christian Rolf(Lund University), Krzysztof Kuchcinski(Lund University)

Enabling Lock-Free Concurrent Fine-Grain Access to Massive Distributed Data: Application to Supernovae Detection
Bogdan Nicolae(University of Rennes 1/IRISA), Gabriel Antoniu(INRIA/IRISA), Luc Bouge(ENS Cachan, Brittany Extension/IRISA)

A multicore-enabled multirail communication engine
Elisabeth Brunet(University of Bordeaux), Francois Trahay(University of Bordeaux), Alexandre Denis(University of Bordeaux)

Multi-core Aware Optimization for MPI Collectives
Bibo Tu(Institute of Computing Technology, Chinese Academy of Sciences)

Environmental-Aware Optimization of MPI Checkpointing Intervals
Hideyuki Jitsumoto(Tokyo Institute of Technology), Toshio Endo(Tokyo Institute of Technology), Satoshi Matsuoka(Tokyo Institute of Technology)

Towards an Understanding of the Performance of MPI-IO in Lustre File Systems
Phillip Dickens(University of Maine), Jeremy Logan(University of Maine)

Gather-Arrange-Scatter: Node-Level Request Reordering for Parallel File Systems on Multi-Core Clusters
Kazuki Ohta(The University of Tokyo), Hiroya Matsuba(The University of Tokyo), Yutaka Ishikawa(The University of Tokyo)

Empirical-based Probabilistic Upper Bounds for Urgent Computing Applications
Nick Trebon(University of Chicago), Pete Beckman(Argonne National Laboratory)

Supporting Storage Resources in Urgent Computing Environments
Jason Cope(University of Colorado at Boulder), Henry Tufo(University of Colorado at Boulder, National Center for Atmospheric Research)

Runtime DVFS Control with instrumented code in Power-scalable Cluster System
Hideaki Kimura(University of Tsukuba), Mitsuhisa Sato(University of Tsukuba), Takayuki Imada(University of Tsukuba), Yoshihiko Hotta(University of Tsukuba)

11:00 - 12:00

Poster session (core time)

13:00 - 14:45

Panel Session (105min)
(Hall 300)
Will the First Exascale Machine be a Commodity Cluster, or Something Else?
Moderator: Satoshi Matsuoka (Tokyo Institute of Technology)
Panelists: Dhabaleswar K. Panda (The Ohio State University), Pete Beckman (Argonne National Laboratory), Jesus Labarta (Barcelona Supercomputing Center), Frank Cappello (INRIA), Hiroshi Nakashima (Kyoto University)

15:00 - 16:30

Session 8: High Performance Message Passing Libraries
(Room 303)
Chair: Thilo Kielmann, Vrije Universiteit

Scalable MPI Design over InfiniBand using eXtended Reliable Connection
Matthew Koop, Jaidev Sridhar, Dhabaleswar K. Panda (The Ohio State University)

Message Progression in Parallel Computing - To Thread or not to Thread?
Torsten Hoefler, Andrew Lumsdaine (Indiana University)

Improving Message Passing over Ethernet with I/O AT Copy Offload in Open-MX
Brice Goglin (INRIA - Bordeaux - Sud-Ouest)

Session 9: Performance Prediction & Modeling
(Room 304)
Chair: Kenjiro Taura, University of Tokyo

A Trace-driven Emulation Framework to Predict Scalability of Large Clusters in Presence of OS Jitter
Pradipta De, Ravi Kothari, Vijay Mann (IBM India Reasearch Laboratory)

Prediction of Behavior of MPI Applications
Marc Casas, Rosa Badia, Jesus Labarta (Technical University of Catalonia)

A Novel Model for Synthesizing Parallel I/O Workloads in Scientific Applications
Dan Feng, Qiang Zou (School of Computer, Huazhong University of Science and Technology), Hong Jiang (University of Nebraska-Lincoln), Yifeng Zhu (University of Maine)

16:30 - 16:45

Coffee Break (15min)

16:45 - 17:45

Invited Talk
(Hall 300)
Designing Next Generation Clusters with InfiniBand and 10GE/iWARP: Opportunities and Challenges
Dhabaleswar K. Panda (The Ohio State University)

18:30 -

Banquet (Sansui-tei)

The time-schedule was changed.

Oct. 1 (Wed)

9:00 - 17:00

Workshop 1
(Room 202)


Workshop 2
(Room 303)


Workshop 3
(Room 304)


Cluster 2008

Last modified: Mon Oct. 5 2008