SyNeRGy Research

Research

SyNeRGy Lab's research is primarily divided into three areas:

Systems
Networking
Renaissance

The Systems, Networking, and Renaissance Grokking () Lab conducts basic and applied research that provides scientists and engineers with scalable and efficient computational tools that enable them to concentrate on their science and engineering rather than on the computer science and engineering. To that end, we explore a breadth of complementary intellectual activities that span the high-performance & enterprise-wide spectrum - from systems software to middleware to applications software to tools - in order to empower cyber-scientists and cyber-engineers of tomorrow.

We create state-of-the-art systems & applications solutions and make them easily accessible through intuitive, but powerful, programming models, architectures, and tools. Current research projects include parallel bioinformatics sequence search; high-speed autonomic networking for supercomputers, clusters and grids; high-speed monitoring, measurement, and modeling; network traffic characterization; low-power and power-aware computing; and end-user programming environments for high-performance computing.

SYSTEMS

HPC Using Accelerators
- PlayStation 3/Cell, FPGA's, GPGPU's, and multicore
Monitoring, Measurement, and Modeling
- MAGNET: Monitoring Apparatus for General kerNel-Event Tracing and MUSE: MAGNET User-Space Environment
Low-Power & Power-Aware Computing - Supercomputing in Small Spaces, Green500
- Green Destiny: A 240-Node Low-Power Supercomputer in a Telephone Booth (5 Sq. Ft. and 3.2 kW)
- EnergyFit: Systems Software for Power-Aware Computing.

NETWORKING

Network Architecture
10-Gigabit Ethernet for the System Area and Wide Area
Autonomic Network Transport
- Dynamic Flow-Control Adaptation: Dynamic Right-Sizing
- Rate-Based Protocols: Rate-Adapting Protocol for Intelligent Delivery (RAPID)

RENAISSANCE

Bioinformatics
- mpiBLAST: An Open-Source Parallelization of BLAST Delivering Super-Linear Speedup
Virtual Computing
- Computing on Demand, Desktop Grids, Data Grids