This research group is involved in building high-performance application-specific parallel architectures and software for heterogeneous systems. We are currently engaged in two different research efforts. The first project, MISTE, is to design and analyze hardware features that support real-time applications on general purpose RISC processors. Our second project is to develop a flexible compiler framework, Scale, that can be easily adapted to new architectures. Once Scale is complete, we will be able to quickly build a sophisticated optimizing compiler for our special purpose architectures.
We have descriptions available for some of our prior research projects. We developed a heterogeneous, tightly coupled system for real-time knowledge-based computer vision, called the Image Understanding Architecture .In conjunction with the Real-Time Systems research group, we built a single-chip parallel array, called SSCoP, that implements the scheduling kernel of the Spring real-time operating system.
We have also constructed the ARPA Image Understanding Benchmark . This benchmark is intended to measure the appropriateness of parallel machines for image processing.
Faculty and Staff
- Dr. Charles Weems < Director >
- James H. Burrill < Senior Staff Programmer >
Graduate Students
Former Graduate Students
- Sunit Bhalla
- Katja Daumueller
- Rabi Dutta
- Arundhati Dhagat
- Joe Kiniry
- Martin Herbordt
- Deepak Rana
- Michael Scudder
Technology Transfer
burrill@www.cs.umass.edu
Return to ALI home page.
(Last changed: August 21, 2001.)
