MICRO

Micro continues to be the major forum for conceptual ideas and relevant studies for optimal processing, both in microarchitecture and in the compiler technology that is equally critical. It is fitting that we hold the conference in Austin, one of the leading centers, both academic and industrial, for the development of this technology. At The University of Texas at Austin, we have substantive, relevant research going on in two departments, Electrical and Computer Engineering and Computer Science. In the local companies, we have some of the world's leading cutting- edge processors being developed. The Austin ecosystem benefits from the symbiotic activities of both. If you are new to Austin, I hope you will make time to visit the University and some of the Austin companies.

The program committee, Josh Fisher and Paolo Faraboschi presiding, have put together an outstanding program that deals with not only current critical problems, but also expected future requirements. I hope you find the papers useful to your needs. We are particularly fortunate to have two excellent Keynote Speakers, Harvey Cragon and Andy Wolfe. Harvey has been doing microarchitecture since before many of you were born. He is responsible for, among other things, the Texas Instruments Advanced Scientific Computer. lie is an Eckert-Mauchly Award winner, a Piore Medal winner, member of the National Academy of Engineering, and a former endowed Chair at The University of Texas at Austin. Andy is Senior Vice President and CTO at SONICblue where he is responsible for product strategy and for mergers and acquisitions. He taught at Princeton from 1991-1997 and is currently a Consulting Professor at Stanford. He is on the advisory boards of several companies. We are delighted that both accepted our invitation to participate in Micro-34.

Also, we have continued the tradition of workshops and tutorials the weekend before the actual symposium. Scott Mahlke, the Workshop/Tutorials chairman, has put together a collection of 4 workshops and 3 tutorials on timely state of the art matters. I hope you take advantage of them, as well.

I recognize the danger in holding Micro-34 so close to 6th street and Town Lake. Austin is well-known for its live music, excellent restaurants, and year-round outdoor activities. Before you arrived, I hope you produced a static schedule for your attention units that saves 6th Street for Tuesday evening and Wednesday after 2pm. I realize that dynamic scheduling could alter that, so I wish you the wisdom to make the correct dynamic scheduling decisions during the next few days.

This 34th year of the symposium confirms Micro's stature as the premier technical forum on microarchitecture. Once again, we put together an exciting program that highlights emerging research in high-performance processor microarchitecture, instruction-level parallelism, and compiler optimization.

Continuing the trends of the last few years, embedded computing and energy efficiency cover a significant fraction of the program. To give you an idea of the growing importance of this, about 25 percent of the submitted papers had the word 'Energy' or 'Power' in their titles.

As usual, Micro attracted some of the best contributions from both academia and industry in the form of 144 high-quality papers -- yet another all-time record for Micro. This presented a very challenging task to the program committee, whose job was to select the best papers among those received. Twenty-nine experts from academia and industry composed the program committee.

The entire process -- from author registration to paper submission, reviews collection and rebuttals -- was organized in an SQL database hosted by the University of Colorado. Special thanks go to Dan Connors, who personally administered the web site, and whose efforts were central to the success of the program committee.

The quality of the review process and the diligence of reviewers is a key factor in the success of a conference. Including themselves, the program committee members recruited 431 referees to generate the 872 reviews used in the paper selection process. This amounts to an average of 6.05 reviews per paper, with all but a few papers receiving at least five reviews. This year, we introduced a new step in the review process that enabled authors to provide a short rebuttal to the reviews before the paper selection phase. The authors' response was widely used during the program committee to help clarify many doubts. Despite the additional complexity that it added to the process, it was unanimously considered a successful experiment and a significant improvement to the review process.

Twenty-one Program Committee members met in an MIT conference room (Cambridge, Mass.) on August 11, and spent about eleven hours to select the 29 papers that compose the Micro-34 program. We believe that these papers contain important ideas and results that will contribute to future successful research and product development efforts.