Media
Back
Process technology now provides the resources of 200 million transistors on a single chip, wherein the transistors switch fast enough that we can readily run at 2 GHz. In a few years, we will have available one billion transistors on a chip, and frequencies of 6 to 10 GHz. But the Naysayers suggest we are wasting our time trying to harness that capability, that we have run out of steam, that there is no point trying, that Moore's Law is dead, and that we would be better off forgetting about microarchitecture and putting our energies to use elsewhere. In this talk, Professor Patt will first examine their arguments: diminishing returns, the memory wall, Pentium IV is good enough, CAD tools can't verify, and others. Then, he will look at some of the things we can do at the microarchitecture level, and in some cases at the compiler and algorithm levels, to stay on the curve of uniprocessor performance.
Professor Patt is Professor of Electrical and Computer Engineering, Professor of Computer Sciences, and the Ernest Cockrell, Jr. Centennial Chair in Engineering at The University of Texas at Austin. He enjoys equally teaching freshmen, teaching graduate students, and directing the research of 11 Ph.D. students in high performance computer implementation.
He has, for more than 30 years, combined an active research program with extensive consulting and a strong commitment to teaching. He has received a number of very prestigious awards for his research and teaching, including the IEEE Emmanuel R. Piore Medal in 1995, the IEEE/ACM Eckert-Mauchly Award in 1996, the IEEE Wallace W. McDowell Award in 1999, and the ACM Karl V. Karlstrom Outstanding Educator Award in 2000. He is named Outstanding ACM Lecturer for 2000-2001.
Professor Patt is the co-author (with his former student Professor Sanjay J. Patel of the University of llinois) of a new introduction to Computing for serious students of computer science and engineering: Introduction to Computing Systems, from Bits and Gates to C and Beyond, McGraw-Hill, 2001. He earned his BS at Northeastern and MS and PhD at Stanford, all in electrical engineering. He is a Fellow of the IEEE and of the ACM.
Members of the Press and interested party are cordially invited to attend.
Chair Professor in Engineering and Professor of Electrical and Computer Engineering to deliver Lecture at HKU
07 Mar 2002
Professor Yale Patt, Chair Professor in Engineering of the University of Texas, is to deliver a William Mong Distinguished Lecture entitled Higher and Higher Performance Microprocessors: There is still plenty we can do at 5:30pm on Friday, March 8, at Lecture Theatre A, Chow Yei Ching Building, the University of Hong Kong.
Process technology now provides the resources of 200 million transistors on a single chip, wherein the transistors switch fast enough that we can readily run at 2 GHz. In a few years, we will have available one billion transistors on a chip, and frequencies of 6 to 10 GHz. But the Naysayers suggest we are wasting our time trying to harness that capability, that we have run out of steam, that there is no point trying, that Moore's Law is dead, and that we would be better off forgetting about microarchitecture and putting our energies to use elsewhere. In this talk, Professor Patt will first examine their arguments: diminishing returns, the memory wall, Pentium IV is good enough, CAD tools can't verify, and others. Then, he will look at some of the things we can do at the microarchitecture level, and in some cases at the compiler and algorithm levels, to stay on the curve of uniprocessor performance.
Professor Patt is Professor of Electrical and Computer Engineering, Professor of Computer Sciences, and the Ernest Cockrell, Jr. Centennial Chair in Engineering at The University of Texas at Austin. He enjoys equally teaching freshmen, teaching graduate students, and directing the research of 11 Ph.D. students in high performance computer implementation.
He has, for more than 30 years, combined an active research program with extensive consulting and a strong commitment to teaching. He has received a number of very prestigious awards for his research and teaching, including the IEEE Emmanuel R. Piore Medal in 1995, the IEEE/ACM Eckert-Mauchly Award in 1996, the IEEE Wallace W. McDowell Award in 1999, and the ACM Karl V. Karlstrom Outstanding Educator Award in 2000. He is named Outstanding ACM Lecturer for 2000-2001.
Professor Patt is the co-author (with his former student Professor Sanjay J. Patel of the University of llinois) of a new introduction to Computing for serious students of computer science and engineering: Introduction to Computing Systems, from Bits and Gates to C and Beyond, McGraw-Hill, 2001. He earned his BS at Northeastern and MS and PhD at Stanford, all in electrical engineering. He is a Fellow of the IEEE and of the ACM.
Members of the Press and interested party are cordially invited to attend.
Facebook 
HKU IOS App 
HKU Android App 
Social Media and Apps