- ATM Testbed and Research Infrastructure at UM
- Active Harmony is a software architecture that supports
distributed execution of computational objects in dynamic,
heterogeneous environments through a dynamic execution
environment, automatic application adaptation
and shared-data interfaces.
- The CHAOS research group at the University of Maryland
College Park has develope d methods that are making it
possible to produce portable compilers and runtime libraries
to map a broad range of challenging applications onto
high performance computer architectures.
E. Bennett, Chialin
Hwang Moon, Bongki
COSMIC: Compiling for Advanced
- The COSMIC project at the University of Maryland attempts
to bridge the gap between applications, operating systems,
and advanced architectures with compiler analysis and
optimization. We are evaluating our ideas using COSMIC-SUIF,
an extension to the Stanford SUIF compiler infrastructure.
Coherent Virtual Machine (CVM)
- CVM is a software distributed shared memory system that
runs on standard UNIX workstations. CVM supports experimentation
in consistency issues, fault tolerance, latency hiding,
and resource management.
- Dyninst is an Application Program Interface (API)
to permit the insertion of code into a running
program. The goal of this API is to provide a machine
independent interface to permit the creation of tools
and applications that use runtime code patching. This API
is based on the idea of Dynamic Instrumentation described
2] and used in the example here.
Earth Sciences Information
- The Earth Sciences Information Partnership, is carried
out by the Global Land Cover Facility. It's primary activities
consist of storing and serving satellite data.
Experimental Parallel Algorithmics
- A fundamental problem in parallel computing is to design
high-level, architecture independent, algorithms that
execute efficiently on general purpose parallel machines.
The purpose of this project is to advance our understanding
of the main factors required for designing practical parallel
algorithms and to develop techniques and data sets for
experimentally validating the results. As a byproduct,
we are developing portable parallel programs and data
sets for a number of specific important problems arising
in combinatorial computing and image processing. Testbed:
IBM SP-2 and Cluster of DEC AlphaServer 2100 4/275's
Grand Challenge for Land Cover
- The NSF funded Grand Challenge project focuses on employing
high performance computing to address applications in
remote sensing, specifically applications in land cover
Language Laterization in the
- Develop and study computational models of functional
cerebral asymmetries and the possible physiological mechanisms
that might give rise to cognitive and behavioral lateralizations
such as language. The models are used to examine the plausability
of various hypotheses concerning the mechanisms of hemispheric
specialization in the brain; such examination results
in many CPU-intensive, long-running simulations.
Multi-tier Programming on SMP-based
- We are extending the KeLP system to Multicomputer clusters
based on Symetric Multiprocessor nodes. This multi-tier
KeLP system permits the user to orchestrate communication
across multiple levels of data locality; hide latency
by treating it as part of the overall computational workload.
- The virtual microscope is a software system that employs
a client/server architecture to provide a realistic emulation
of a high power light microscope. The data server of the
system design relies on the computational power and high
I/O throughput available from an appropriately configured
Robert Miller (Department
of Pathology, Johns Hopkins), Alan
Angelo Demarzo (Department
of Pathology, Johns Hopkins), Renato