High Performance Computing - HiPC 2007

Manish Parashar, PhD, is an associate professor in the Department of Electrical and Computer Engineering at Rutgers, The State University of New Jersey, where he is Director of The Applied Software Systems Laboratory (TASSL). Professor Parashar is a recipient of the NSF CAREER award and the Enrico Fermi scholarship, and is a senior member of the IEEE. In addition to publishing over a hundred technical papers in international journals and conferences, Professor Parashar has coauthored/edited three books, and has contributed to several others, in the area of parallel and distributed computing.

This book constitutes the refereed proceedings of the 14th International Conference on High-Performance Computing, HiPC 2007, held in Goa, India, in December 2007. The 53 revised full papers presented together with the abstracts of five keynote talks were carefully reviewed and selected from 253 submissions. The papers are organized in topical sections on a broad range of applications including I/O and FPGAs, and microarchitecture and multiprocessor architecture.

Keynote Addresses (Abstracts).- The Future Is Parallel But It May Not Be Easy.- Petaflop/s, Seriously.- High Performance Data Mining - Application for Discovery of Patterns in the Global Climate System.- The Transformation Hierarchy in the Era of Multi-core.- Web Search: Bridging Information Retrieval and Microeconomic Modeling.- Plenary Session - Best Paper.- Distributed Ranked Search.- Session I - Applications on I/O and FPGAs.- ROW-FS: A User-Level Virtualized Redirect-on-Write Distributed File System for Wide Area Applications.- No More Energy-Performance Trade-Off: A New Data Placement Strategy for RAID-Structured Storage Systems.- Reducing the I/O Volume in an Out-of-Core Sparse Multifrontal Solver.- Experiments with a Parallel External Memory System.- An FPGA-Based Accelerator for Multiple Biological Sequence Alignment with DIALIGN.- A Speed-Area Optimization of Full Search Block Matching Hardware with Applications in High-Definition TVs (HDTV).- Session II - Microarchitecture and Multiprocessor Architecture.- Evaluating ISA Support and Hardware Support for Recursive Data Layouts.- qTLB: Looking Inside the Look-Aside Buffer.- Analysis of x86 ISA Condition Codes Influence on Superscalar Execution.- Efficient Message Management in Tiled CMP Architectures Using a Heterogeneous Interconnection Network.- Direct Coherence: Bringing Together Performance and Scalability in Shared-Memory Multiprocessors.- Constraint-Aware Large-Scale CMP Cache Design.- Session III - Applications of Novel Architectures.- FFTC: Fastest Fourier Transform for the IBM Cell Broadband Engine.- Molecular Dynamics Simulations on Commodity GPUs with CUDA.- Accelerating Large Graph Algorithms on the GPU Using CUDA.- FT64: Scientific Computing with Streams.- Implementation and Evaluation of Jacobi Iteration on the Imagine Stream Processor.- Session IV - System Software.- Compiler-Directed Dynamic Voltage Scaling Using Program Phases.- Partial Flow Sensitivity.- A Scalable Asynchronous Replication-Based Strategy for Fault Tolerant MPI Applications.- Towards a Transparent Data Access Model for the GridRPC Paradigm.- A Proxy-Based Self-tuned Overload Control for Multi-tiered Server Systems.- Session V - Scheduling.- Approximation Algorithms for Scheduling with Reservations.- Enhanced Real-Time Divisible Load Scheduling with Different Processor Available Times.- A General Distributed Scalable Peer to Peer Scheduler for Mixed Tasks in Grids.- An Energy-Aware Gradient-Based Scheduling Heuristic for Heterogeneous Multiprocessor Embedded Systems.- On Temperature-Aware Scheduling for Single-Processor Systems.- Session VI - Energy-Aware Computing.- Reuse Distance Based Cache Leakage Control.- Self-optimization of Performance-per-Watt for Interleaved Memory Systems.- Distributed Algorithms for Lifetime of Wireless Sensor Networks Based on Dependencies Among Cover Sets.- DPS-MAC: An Asynchronous MAC Protocol for Wireless Sensor Networks.- Compiler-Assisted Instruction Decoder Energy Optimization for Clustered VLIW Architectures.- Session VII - P2P and Internet Applications.- P2P Document Tree Management in a Real-Time Collaborative Editing System.- Structuring Unstructured Peer-to-Peer Networks.- Multi-objective Peer-to-Peer Neighbor-Selection Strategy Using Genetic Algorithm.- Effect of Dynamicity on Peer to Peer Networks.- Hierarchical Multicast Routing Scheme for Mobile Ad Hoc Network.- Session VIII - Communication and Routing.- The Impact of Noise on the Scaling of Collectives: The Nearest Neighbor Model [Extended Abstract].- Optimization of Collective Communication in Intra-cell MPI.- Routing-Contained Virtualization Based on Up*/Down* Forwarding.- A Routing Methodology for Dynamic Fault Tolerance in Meshes and Tori.- Fault-Tolerant Topology Adaptation by Localized Distributed Protocol Switching.- Session IX - Cluster and Grid Applications.- Accomplishing Approximate FCFS Fairness Without Queues.- A Novel Force Matrix Transformation with Optimal Load-Balance for 3-Body Potential Based Parallel Molecular Dynamics Using Atom-Decomposition in a Heterogeneous Cluster Environment.- Grid'BnB: A Parallel Branch and Bound Framework for Grids.- The CMS Remote Analysis Builder (CRAB).- Applying Internet Random Early Detection Strategies to Scheduling in Grid Environments.- Session X - Mobile Computing.- A Consistent Checkpointing-Recovery Protocol for Minimal Number of Nodes in Mobile Computing System.- MASD: Mobile Agent Based Service Discovery in Ad Hoc Networks.- Channel Adaptive Real-Time MAC Protocols for a Two-Level Heterogeneous Wireless Network.- Modeling Hierarchical Mobile Agent Security Protocol Using CP Nets.- Single Lock Manager Approach for Achieving Concurrency Control in Mobile Environments.