Prof. John Hennessy and Prof. David Patterson received the 2017 ACM A.M. Turing Award for “pioneering a systematic, quantitative approach to the design and evaluation of computer architectures with enduring impact on the microprocessor industry”. I used to read many articles and personal interviews about the two masters, which are full of inspirations and wisdom.
In this article, I will present a virtual interview with John and David by quoting words from their previous articles and interviews with a montage editing technique. The original documents are listed as follows:
- John Mashey, “Oral History of John Hennessy”, Computer History Museum, 2007.
- John Mashey, “Oral History of David Patterson”, Computer History Museum, 2007.
- David Patterson, “Grand Challenges and Great Teams”, Eckert-Mauchly Award Speech, 2008.
- David Patterson, “An Interview with Stanford University President John Hennessy”，Communications of the ACM, 2016.
- David Patterson, “How to have a bad career”, Talk at Google, 2015.
- David Patterson, “Your Students are Your Legacy”, Communications of the ACM, 2009.
- David Patterson, “How to Build a Bad Research Center“, Communications of the ACM, 2014.
- David Patterson, “My Last Lecture: How to be a bad professor”, Talk at UC Berkeley, 2016.
- Doug Swanson, “Favorite Son”, Stanford Alumni, 2000.
- Alan S. Brown, “John Hennessy: The Godfather of Silicon Valley”, THE BENT OF TAU BETA PI, 2016.
- David Patterson, “Passing the Baton”, 2015.
- John L. Hennessy, “Leading Matters: Lessons from My Journey”, 2018.
Figure 1. Prof. John Hennessy and Prof. David Patterson
Pre-College Education on Computer Science
Bao: When you entered the universities in the 1970s, there were few computer science departments in universities. How did you choose the major of computer science?
Hennessy: “My father was an engineer, worked in the aerospace industry. [He] probably got me interested in the early days in computing and I think probably what really got me going was the opportunity to do a little programming on a timeshare machine using good old paper tape to store our programs. And then in high school with a buddy of mine we undertook a high school science project which was to do some experiments, including design of a tic-tac-toe machine…… We figured out a lot of things about how to build a decision tree for tic-tac-toe, not very hard. But in those times stunning to people that a machine could beat them at tic-tac-toe.” [1]
“I started off in electrical engineering but then I already had this computing interest and it continued to build when I took my first programming course which I was in the advanced section because I had already had a little Fortran programming in high school.” [1]
Patterson: “I was the first member in my family to actually graduate from college. At our high school, we had the AP math program. We got calculus at the time. I was a math major and then a course was canceled at UCLA in my junior year. So I had to fill a program, took a class in computers. I’m sure I knew what computers were. They were popular but I have absolutely no interest anytime before I took that course, that I would be possibly interested in computers.” [2]
Love and Marriage
Bao: Let’s talk about marriage. How did you meet your wife?
Patterson: “My main teammate is my beautiful and intelligent wife, Linda. We first met when we were 12 years old, and started dating when we were 16. We married at 19 and had our first kid at 21. Now, we have been married 50 years.” [3]
“I think proudest moment is probably family things. I’m pretty sure of that. That’s a tough one. Getting married to my high school sweetheart, having a child was kind of shocking. Having a second son, for somehow I had enough insecurities that when my second son was born. Hey, I’m a real man.” [2]
Hennessy: “I won my wife Andrea, by the way, with the help of hard work and science. At 17, I had an after-school job at the King Kullen grocery story in Huntington, and I kept my eye on 17-year-old Andrea Berti.” [9]
“Dave married his early. I waited until we were done with college but then we got married four years after in 1974. Four years after we started as undergraduates.” [1]
Berti (Hennessy’s Wife): “Our first date was his senior prom. Then he brought the tic-tac-toe machine over to my house. That really impressed my mother.” [9]
Bao: So both of you are the cases with a high school sweetheart turned wife.
Hennessy: “It’s a good thing. It keeps life stable in one part of it so you can pursue other things.” [1]
Academic Career
Bao: Why did you continue into an academic career after getting a PhD degree?
Patterson: “My wife plays an extraordinarily important role in my life. At that time, I had my offer letters (of Berkeley and Bell Labs).
I say, ‘Linda, I’ve stayed in graduate school all this time and we’ve sacrificed economically for all this time. I perfectly understand if you would like me to get a job at a real company so we can get a house.’
She’s asking the question, ‘If you turn this job down and go to industry, can you change your mind and go to Berkeley?’
‘Ah, no, very unlikely.’
‘If you go to Berkeley and you don’t like it and decide to go to industry, can you do that?’
‘Oh yeah, that’s pretty easy to do.’
She says, ‘Okay, we’ll be poor but proud.’” [3]
Hennessy: “I decided I wanted to be an academic from the very beginning so I interviewed only at universities and I started interviewing all across the country. Actually, Stanford was the 14th institution, university I interviewed at.” [1]
Research Taste
Bao: What are good research work in your opinion? What do you think of the increasing publications in the computer science field?
Patterson: “There is a lot of concern in CS about publishing. When you see how many dozen papers new Ph.D.’s have, it looks like lots of LPU (least publishable unit), where quantity trumps quality.” [4]
“The goal of research is to have impact and change the way people do computing and engineering. I agree with Richard Hamming’s opinion: If you don’t work on important problems, you are not going to do important things. So it is important to do ‘Real Stuff’, solving problem that others think is important. And make sure it is exciting that you want to work on it for several years. What I’ve found is a compelling prototype. If we can build this thing, it is really going to be amazing……People count the number of projects you finished, not the ones you started.” [5]
Hennessy: “I do worry that in this drive to publish and the use of conferences that we have become a little incremental. It’s easy enough in the academic setting to say: tell me about the five or six things that you’ve done in preparation for tenure? What are the most important five or six papers?
Because the reality is, nobody is going to look much deeper than that, if they look carefully. We need to move away from just counting the number of publications and saying: okay, that’s enough publications. What has the person really done? In the end, it’s about impact. What impact did they have, either on an industry or on other researchers; because that’s what you really care about when you’re trying to evaluate the research work of a faculty member.” [4]
Collaborations between Academy and Industry
Bao: I found both of you have done many projects that had strong connections with the industry. John even found the MIPS company. What are your experiences of the interactions between academy and industry?
Hennessy: “There’s always been a belief at Stanford that the interaction, whether it be through consulting or some other role, was a valuable thing, added to the not only enabled the university to have some greater impact but also added to the understanding and insight that faculty had as they became teachers and I think that’s certainly true.
If you think about the students in a typical classroom, most of them aren’t going on to be academics. Even in a graduate program most of them aren’t going on to be academics. Most of them are going on to work in the industry and the more experience I think that a faculty member has in that the better they are. They’re certainly going to teach principles and fundamentals still because those are the things that have lasting value, but that experience and understanding how to apply those things can often be incredibly valuable for an instructor to have experience with.” [1]
Patterson: “We were in architecture and there are people selling microprocessors, this was like the ground truth. This is really great. It’s not like philosophy or something which is argued endlessly. There are these ideas and then you have a place to test these ideas. So, it’ll be important to continue to interact with industry to test your ideas when you think you have a good idea. Plus, obviously the industry will help you figure out what the problems are. They will help you with this difficult problem in academia to find out: Is this an important problem or not? How important are they if you solve them? I always have used the crutch of interacting with industry to help figure out whether this problem is important or not.” [2]
Interacting with industry is also beneficial for students. “It gives them a chance to communicate and spread their ideas, interact with others.” [5]
Impact of Textbooks
Bao: You co-authored two famous textbooks which have huge impact in the computer architecture field. Why did you do books?
Patterson: “John and I had gotten together over the years and we were frustrated by the books, the architecture textbooks at the time, which were kind of shopping catalogs. Like, here’s a research project, here’s a computer. So, we should write a book.” [2]
“Impacts, I think both the RISC ideas and the book kind of changed the way people thought about designing computers. There was a different mindset after that.” [2]
Hennessy: “I picked a really good partner to write the books with. I think that’s probably the first and foremost answer. In the late 1980s, probably, Dave and I were both very disappointed with the textbooks that were out there. We felt that there had been a lot of interesting things happening in the RISC side. And as much as the particular architectural insights, probably the methodology for thinking about computer architecture was actually in some ways, more important in the long term then. And thinking about it as a quantitative science that you can think about and measure performance. So we decided to try to write a book crafted around a quantitative approach; an engineering approach to computer architecture. And that was the beginning of that book.” [1]
“I have to say that the textbooks brought me one of my proudest moment in the career. when I visited China a few years ago and we were walking down the hall in a research lab in Tsinghua University and my wife pointed out. She said, ‘Look, there’s a copy of your book. Why don’t you sign it for that young lady?’ So I stopped to sign it and in 30 seconds 50 or 60 students piled out of their little cubicles holding copies of the book. You realized that through this book you’ve touched people worlds away.” [1]
Students
Bao: Both of you should be proud advisors who supervised many great students. Can you share some experience and advices to young faculty?
Hennessy: “I love being a faculty member. I love teaching. I love working with graduate students in a research setting. I really thought that was some of the best moments of my life.” [1]
“I have a lot of students out there that I’ve been privileged to teach and work with in the graduate setting. Of course, for all the great research accomplishments or things I’ve contributed in that side, what they will do will make all my accomplishments look small because they’re a tremendous magnifier and I think that’s one of the great things about universities: the role of students as magnifiers, is really a tremendous one.” [1]
Patterson: “I can confirm that hypothesis: your main academic legacy is the dozens of students you mentor, not the hundreds of papers you publish. My advice to advisors is to get your students off to a good start, create stimulating research environments, help them acquire research taste, be a good role model, bolster student confidence, teach them to speak well publicly, and help them up if they stumble, for students are the real coins of the academic realm.” [6]
Spirit of Service
Bao: Let’s talk about management and service. John had been Dean of Engineering, the Provost of Stanford, and later the President for 16 years. Dave also served as department chair, present of the ACM and so on. What are your opinions on these management and service positions?
Hennessy: “When I was considering the dean of engineering job, the current dean told me, ‘This is a service job. You’re serving the faculty and the students.’ That sunk in deeply. I’ve always felt that I’m here to help them thrive.”[10]
“As my wife says, it’s the best job that I’ve ever had. Being a Dean, at slightly over 200 faculty but the range of intellectual disciplines, I could understand what everybody was doing. I certainly couldn’t be an expert in what somebody in mechanical engineering, but I could understand enough about what they were doing that I could appreciate it. I could know all the faculty on a first name basis which was a wonderful, wonderful opportunity.” [1]
Patterson: “When I was CS division chair for three years, I started an award committee for senior faculty and I was one the guys we’ve gotten the awards. I was on the campus Budget Committee and I did a graph which shows Berkeley is getting the lowest salary increase compared to the ‘Comparison 8’. That helped make the case on campus to give everybody a pay raise, and I was one of the guys gotten benefited. So about my experience from service, I did this to be community spirited, but I found that eventually I personally benefited from it.” [8]
Teamwork
Bao: Most of your research works are done by a large team. Why did you choose this research style? Are there any suggestions on team building?
Hennessy: “One of the difficulties that we discovered was to really deliver and demonstrate this technology. You had to build an engineering team that could build, essentially, an entire computer system.
MIPS was a good project. It’s amazing when you think… I mean we had a team which by today’s standards for what you need to implement a piece of silicon was tiny but we were naïve, willing to work hard and try some things that were a little outrageous.
Probably one of the most important things I learned in that, hire great people from the beginning. Hire the very best people. We need people who are creative.” [1]
Patterson: “I try to work with colleagues to create exciting, five-year projects that I would die to work on if I were a graduate student again. We self-assemble into teams of typically two to four faculty members with the right areas of expertise to tackle a challenging and important problem, then recruit 10 to 20 graduate students to work toward building a prototype that demonstrates our proposed solution.” [6]
“You need to find someone willing to spend the time to pull people together, to create a shared vision, to build team spirit, and in who investigators believe will make decisions in the best interest of the center.” [7]
“(To summarize), I believe we’ve leapfrogged the competition (with other universities) because of: 1) Our practice of attracting and nurturing great young faculty; 2) Our radical faculty collaborative teamwork on research projects; 3) Our tradition of working in ways that are best for the department versus for our area or for ourselves.” [11]
Life Lessons
Bao: Let’s end up with the last question—what are your most important life lessons as your advice for young generations?
Hennessy: “Well, the one piece of advice I often give is people should not be timid. Helen Keller once said ‘The cautious are caught as often as the bold’ and I think it is true. One rarely accomplishes much if you’re not willing to take some risk. Every year I encourage the students to take some risk and that’s all kinds of risks. That’s going through a door that you might not have contemplated going through and possibly not trying to program where that path is going to lead to.” [1]
“You might want to read this book [12] which contains lots of my life lessons.”
Patterson: “I think optimism has served me well. Not unbridled optimism, but cautious optimism. There have been many times in my life where it’s been a 50/50 or maybe 60/40 or 40/60, and I said, ‘Let’s go ahead. Let’s try.’ That has served me really well. I think had I been more pessimistic, I doubt that I would have been a Berkeley professor and certainly not a Turing laureate.” [2] (revised by David in 2022)
Bao: Thank you very much, John and David.
Acknowledgement: The author is grateful to Prof. John Hennessy and Prof. David Patterson for their encouragement and advice.
About the author: Yungang is a professor of the State Key Laboratory of Computer Architecture, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). He is the director of Research Center for Advanced Computer System (ACS).
Disclaimer: These posts are written by individual contributors to share their thoughts on the Computer Architecture Today blog for the benefit of the community. Any views or opinions represented in this blog are personal, belong solely to the blog author and do not represent those of ACM SIGARCH or its parent organization, ACM.
