Performance Prediction and Modeling

• SIGMA: A Simulator Infrastructure to Guide Memory Analysis ACM IEEE
  
• Compact Application Signatures for Parallel and Distributed Scientific Codes ACM IEEE
  
• Scalable Analysis Techniques for Microprocessor Performance Counter Metrics ACM IEEE

New Applications

• High Performance Computing Meets Experimental Mathematics ACM IEEE
• A High-Level Approach to Synthesis of High-Performance Codes for Quantum Chemistry ACM IEEE
• MPI and OpenMP Paradigms on Cluster of SMP Architectures ACM IEEE

Network Protocol Tuning

• The Effects of Systemic Packet Loss on Aggregate TCP Flows ACM IEEE
• Implementation and Evaluation of A QoS-Capable Cluster-Based IP Router ACM IEEE
• A TCP Tuning Daemon ACM IEEE

Innovative Middleware

• Distributed Dynamic Hash Tables Using IBM LAPI ACM IEEE
• Multivariate Resource Performance Forecasting in the Network Weather Service ACM IEEE
• Disk Cache Replacement Algorithm for Storage Resource Managers in Data Grids ACM IEEE

Non-uniform Communication Networks

• Efficient Synchronization for Nonuniform Communication Architectures ACM IEEE
• Ultra-High Performance Communication with MPI and the Sun Fire(TM) Link Interconnect ACM IEEE
• Separated High-bandwidth and Low-latency Communication in the Cluster Interconnect Clint ACM IEEE

Application Performance Evaluation

• An Empirical Performance Evaluation of Scalable Scientific Applications ACM IEEE
• UPC Performance and Potential: A NPB Experimental Study ACM IEEE
• Scaling the Unscalable: A Case Study on the AlphaServer SC ACM IEEE

Visualization

• Advanced Visualization Technology for Terascale Particle Accelerator Simulations ACM IEEE
• SmartPointers: Personalized Scientific Data Portals In Your Hand ACM IEEE
• A Framework for Performance Modeling and Prediction ACM IEEE

Scheduling and Routing

• Improving Route Lookup Performance Using Network Processor Cache ACM IEEE
• Pipelined Scheduling of Tiled Nested Loops onto Clusters of SMPs using Memory Mapped Network Interfaces ACM IEEE
• Data Reservoir: Utilization of Multi-Gigabit Backbone Network for Data-Intensive Research ACM IEEE

Sparse Linear Algebra

• A New Scheduling Algorithm For Parallel Sparse LU Factorization with Static Pivoting ACM IEEE
• Performance Optimizations and Bounds for Sparse Matrix-Vector Multiply ACM IEEE
• A New Data-Mapping Scheme For Latency-Tolerant Distributed Sparse Triangular Solution ACM IEEE

Message Passing

• Implementing the MPI Process Topology Mechanism ACM IEEE
• MPICH-V: Toward a Scalable Fault Tolerant MPI for Volatile Nodes ACM IEEE
• The Proteus Multiprotocol Message Library ACM IEEE

Compilers and Run Time Systems

• On Increasing Architecture Awareness in Program Optimizations to Bridge the Gap between Peak and Sustained Processor Performance -- Matrix-Multiply Revisited ACM IEEE
• Better Tiling and Array Contraction for Compiling Scientific Programs ACM IEEE
• Asserting Performance Expectations ACM IEEE

Gordon Bell I

• A 29.5 Tflops simulation of planetesimals in Uranus-Neptune region on GRAPE-6 ACM IEEE
• Salinas: A Scalable Software for High-Performance Structural and Solid Mechanics Simulations ACM IEEE
• NAMD: Biomolecular Simulation on Thousands of Processors ACM IEEE

Web Services

• ICENI: An Open Grid Service Architecture Implemented with Jini ACM IEEE
• The Web Service Discovery Architecture ACM IEEE
• Interoperable Web Services for Computational Portals ACM IEEE

Computational Applications

• Accelerating Parallel Maximum Likelihood-based Phylogenetic Tree Calculations using Subtree Equality Vectors ACM IEEE
• Parallel Multiscale Gauss-Newton-Krylov Methods for Inverse Wave Propagation ACM IEEE
• A Scalable Parallel Fast Multipole Method for Analysis of Scattering from Perfect Electrically Conducting Surfaces ACM IEEE
• Dual-Level Parallelism for Deterministic and Stochastic CFD Problems ACM IEEE

Run Time Systems

• Active Harmony: Towards Automated Performance Tuning ACM IEEE
• Library Support for Hierarchical Multi-Processor Tasks ACM IEEE
• STORM: Lightning-Fast Resource Management ACM IEEE

System Components

• Massive Arrays of Idle Disks For Storage Archives ACM IEEE
• Gilgamesh: A Multithreaded Processor-In-Memory Architecture for Petaflops Computing ACM IEEE
• Owner Prediction for Accelerating Cache-to-Cache Transfer Misses in a cc-NUMA Architecture ACM IEEE

Gordon Bell Earth Simulator

• 16.4 Tflops Direct Numerical Simulation of Turbulence by Fourier Spectral Method on the Earth Simulator ACM IEEE
• 14.9 TFLOPS Three-dimensional Fluid Simulation for Fusion Science with HPF on the Earth Simulator ACM IEEE
• A 26.58 Tflops Global Atmospheric Simulation with the Spectral Transform Method on the Earth Simulator ACM IEEE

Grid Scheduling

• SMP System Interconnect Instrumentation for Performance Analysis ACM IEEE
• Executing Multiple Pipelined Data Analysis Operations in the Grid ACM IEEE
• A Decoupled Scheduling Approach for the GrADS Program Development Environment ACM IEEE

Data and Queries

• Applying Chimera Virtual Data Concepts to Cluster Finding in the Sloan Sky Survey ACM IEEE
• Active Proxy-G: Optimizing the Query Execution Process in the Grid ACM IEEE
• Giggle: A Framework for Constructing Scalable Replica Location Services ACM IEEE

Hardware Architecture

• Early Evaluation of the IBM p690 ACM IEEE
• An Overview of the BlueGene/L Supercomputer ACM IEEE
• High-Density Computing: A 240-Processor Beowulf in One Cubic Meter ACM IEEE

Grid Applications

• Utilization of Departmental Computing GRID System for Development of an Artificial Intelligent Tapping Inspection Method, Tapping Sound Analysis ACM IEEE
• Collaborative Simulation Grid: Multiscale Quantum-Mechanical/Classical Atomistic Simulations on Distributed PC Clusters in the US and Japan ACM IEEE
• QMView and GAMESS: Integration into the World Wide Computational Grid ACM IEEE

Data Archives

• Scalable Directory Services Using Proactivity ACM IEEE
• Monitoring Data Archives for Grid Environments ACM IEEE
• Merging Multiple Data Streams on Common Keys Over High Performance Networks ACM IEEE