IWarp: Anatomy of a Parallel Computing System

Front Cover
MIT Press, 1998 - Computers - 488 pages
0 Reviews
Although researchers have proposed many mechanisms and theories for parallel systems, only a few have actually resulted in working computing platforms. The iWarp is an experimental parallel system that was designed and built jointly by Carnegie Mellon University and Intel Corporation. The system is based on the idea of integrating a VLIW processor and a sophisticated fine-grained communication system on a single chip. This book describes the complete iWarp system, from instruction-level parallelism to final parallel applications. The authors present a range of issues that must be considered to get a real system into practice. They also provide a start-to-finish history of the project, including what was done right and what was done wrong, that will be of interest to anyone who studies or builds computer systems.
  

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

Introduction
1
iWarp Overview
13
Logical Channels
39
Pathways
71
The Processing Agent
93
The iWarp Parallel System
137
Program Development Tool Chain
165
Compilers
211
Communication Operations
313
Applications
349
iWarp Project
381
A Evolution of Systolic Computers
431
B Instruction Summary
461
System summary
469
References
477
Index
485

Runtime System
263
Communication Styles
303

Common terms and phrases

References to this book

All Book Search results »

About the author (1998)

Randal E. Bryant" received the Bachelor's degree from the University of Michigan in 1973 and then attended graduate school at the Massachusetts Institute of Technology, receiving the Ph.D. degree in computer science in 1981. He spent three years as an Assistant Professor at the California Institute of Technology and has been on the faculty at Carnegie Mellon since 1984. He is currently the President's Professor of Computer Science and head of the Department of Computer Science. He also holds a courtesy appointment with the Department of Electrical and Computer Engineering.

He has taught courses in computer systems at both the undergraduate and graduate level for over 20 years. Over many years of teaching computer architecture courses, he began shifting the focus from how computers are designed to one of how programmers can write more efficient and reliable programs if they understand the system better. Together with Prof. O'Hallaron, he developed the course "Introduction to Computer Systems" at Carnegie Mellon that is the basis for this book. He has also taught courses in algorithms and programming.

Prof. Bryant's research concerns the design of software tools to help hardware designers verify the correctness of their systems. These include several types of simulators, as well as formal verification tools that prove the correctness of a design using mathematical methods. He has published over 100 technical papers. His research results are used by major computer manufacturers including Intel, Motorola, IBM, and Fujitsu. He has won several major awards for his research. These include two inventor recognition awards and a technical achievement award from the SemiconductorResearch Corporation, the Kanellakis Theory and Practice Award from the Association for Computer Machinery (ACM), and the W. R. G. Baker Award and a Golden Jubilee Medal from the Institute of Electrical and Electronics Engineers (IEEE). He is a Fellow of both the ACM and the IEEE.

"David R. O'Hallaron" received the Ph.D. degree in computer science from the University of Virginia in 1986. After a stint at General Electric, he joined the Carnegie Mellon faculty in 1989 as a Systems Scientist. He is currently an Associate Professor in the Departments of Computer Science and Electrical and Computer Engineering.

He has taught computer systems courses at the undergraduate and graduate levels, on such topics as computer architecture, introductory computer systems, parallel processor design, and Internet services. Together with Prof. Bryant, he developed the course "Introduction to Computer Systems" that is the basis for this book.

Prof. O'Hallaron and his students perform research in the area of computer -systems. In particular, they develop software systems to help scientists and engineers simulate nature on computers. The best known example of their work is the Quake project, a group of computer scientists, civil engineers, and seismologists who have developed the ability to predict the motion of the ground during strong earthquakes, including major quakes in Southern California, Kobe, Japan, Mexico, and New Zealand. Along with the other members of the Quake Project, he received the Allen Newell Medal for Research Excellence from the CMU School of Computer Science. A benchmark he developed for the Quake project, 183.equake, was selected by SPEC for inclusion in the influentialSPEC CPU and OMP (Open MP) benchmark suites.

Bibliographic information