This paper describes and evaluates the application of three local learning algorithms --- nearest-neighbor, weighted-average, and locally-weighted polynomial regression --- for the prediction of run-specific resourceusage on the basis of run-time input parameters supplied to tools. A two-level knowledge base allows the learning algorithms to track short-term fluctuations in the performance of computing systems, and the use of instance editing techniques improves the scalability of the performance-modeling system. The learning algorithms assist PUNCH, a network-computing system at Purdue University, in emulating an ideal user in terms of its resource management and usage policies. 1. Introduction It is now recognized that the heterogeneous nature of the network-computing environment cannot be effectively exploited without some form of adaptive or demand-driven resource management (e.g., [10, 11, 12, 14, 18, 27]). A demand-driven resource management system can be characterized by its a...

Many of the systems that currently allow computing on the web target specific tools. Such solutions tend to be non-reusable in spite of the fact that they involve a significant amount of duplicated effort. This paper describes the issues involved in the design of a demandbased network-computing system, and presents an operational prototype (the Purdue University NetworkComputing Hubs, or PUNCH) that allows users to access and run existing software tools via standard worldwide web browsers. The tools do not have to be written in any particular language, and access to sourcecode is not required. The PUNCH infrastructure can be distributed in a manner that allows tools to be (usertransparently) executed wherever they reside. Currently, PUNCH contains over thirty tools from eight universities and four vendors, and serves more than 500 users. During the past three years, PUNCH users have logged more than 860,000 hits and have performed over 54,000 simulations. 1. Introduction There is inc...

Tools for computer architecture design and parallel programming have become essential to practicing computer architects and software developers in industry. There is significant demand for designers who can develop, use and modify them. More importantly, design and simulation tools capture fundamental engineering concepts that should be mastered by computer professionals. This paper describes an approach to the integration of tools for computer architecture simulation, performance prediction, program optimization and application characterization into computer science and engineering curricula. The approach is based on a unique, operational distributed infrastructure - the Purdue University Network Computing Hubs (PUNCH). The PUNCH infrastructure lets users with different computing platforms run a broad range of tools via standard WWW browsers. PUNCH also allows universities to share course-development efforts, tool expertise and resources while preserving the appearance of a centralize...