UC Berkeley

Talk: "View from the Top"
(Video) (Slides)

Friday, May 6, 2016
4:00 - 5:00 PM
International House, UC Berkeley
More information


Friday, May 6, 2016
5:30 - 8:00 PM
International House, UC Berkeley


Saturday, May 7, 2016
8:00 AM - 5:40 PM
International House, UC Berkeley

40 Years of Patterson Symposium Agenda

Saturday, May 7, 2016

International House, UC Berkeley

Symposium talks - both Friday and Saturday - now have links to abstracts, slides, and respective videos. To access them, please check the agenda below (note: for abstracts, please click on the talk title)

Session I Chair: Christos Kozyrakis (Stanford)
9:00amThe Future of Storage - Garth Gibson (CMU) (Video)(Slides)
Abstract Coming Soon.
9:30amBuilding Scientific Apps - in Vellum - Neel Smith (Holy Cross) (Video)(Slides)
As early as the third century BCE, scholars at the Library of Alexandria wrestled with problems of how to represent and analyze literary and scientific information in textual formats. The history of how their work has been transformed and transmitted to us offers valuable perspective to humanities scholars today as we develop the next step in that transmission: to digital forms. In this presentation, I first look at examples of how ancient Greek scholars working only with papyrus or parchment attempted to create interactive apps for cartography, chronological computation, and grammatical analysis. I then illustrate digital editions interpreting these apps as geographic information systems, directed graphs, and natural language parsers. The results can have implications beyond the narrow limits of humanities scholarship. Generalized approaches using finite state transducers to parse the morphology of ancient Greek uniformly fail, for example, because of the distinctive ways that morphology interacts with other features of the language. These examples not only remind us that the past is useful for thinking about the future, but also show how serious engagement with digital technology can give us insights into the past that were never previously possible.
10:00amFuture of Networks - Amin Vahdat (Google) (Video) (Slides)
Networking ties together storage, distributed computing and security in the Cloud. However, the demands of distributed processing, along with exponentially increasing data and storage, are forcing a re-think of networking technologies. Today’s realization of Moore’s Law is also shifting the industry away from the single-server computing model. We will discuss a path where the network itself becomes​​ the engine for performance gains, and how this will support the next wave of advances in compute infrastructure.
Session II Chair: David Ungar (IBM)
11:00amThe Case for Open Instruction Sets - Krste Asanovic (Video) (Slides)
The most important interface in a computer system is the instruction set architecture (ISA) as it connects software to hardware. So, given the prevalence of open standards for almost all other important interfaces, why is the ISA still proprietary? We argue that a free ISA is a necessary precursor to future hardware innovation, and there's no good technical reason not to have free, open ISAs just as we have free, open networking standards and free, open operating systems.
11:30amRemember Memory? - Mark Hill (Univ. of Wisconsin) (Video) (Slides)
Abstract: While computing gets the glory, remember that is vast memory that makes most interesting computation possible. This talk will sample some of the computer architectural challenges that arise from million-fold memory capacity growth, the introduction of general-purpose graphics processing unit computing, and non-volatile memory's fusing of memory and storage.
12:00pmThe Machine - Kim Keeton (HP) (Video) (Slides)
By end of the decade we expect over 30 billion intelligent devices connected to the Internet, resulting in unprecedented amounts of data. At the same time, scaling of today's foundational memory technologies will significantly slow down. We will need to transform the ways in which we collect, process, store, and analyze that data. "The Machine" is a new architecture from Hewlett Packard Labs that brings together byte-addressable non-volatile memory, photonic interconnects, and specialized SoCs for computing at multiple scales, ranging from handhelds to rack-scale to data center-scale. As part of this initiative, we're building hardware, a new OS, new data stores, new analytics platforms, and new programming models, with the plan to open source various parts of the software stack. This talk will discuss the technologies that comprise The Machine and their implications for systems software and application programs, as well as describe the work we're doing at HPE to address some of these challenges.
Session III Chair: Garth Gibson (CMU)
1:30pmThe Software-Defined Building: A Machine for Living - Randy Katz (Video) (Slides)
The famous 20th Century architect Le Corbusier defined a building as "a machine for living." Many of us have experienced intense frustration and unhappiness with "the machines" in which we live and work. With the ever increasing embedding of information technology within the built environment, in the form of sensors, actuators, displays, cameras, network connectivity, and programmable controllers all potentially coupled to sophisticated building management systems, the ability for buildings to become aware of and respond to the needs and desires of their occupants is finally emerging. The hoped for result is more comfortable and productive occupants inside of buildings that are more efficient and sustainable in their operation. In this talk, we discuss the computer science research challenges in creating Software-Defined Buildings, an important category of cyber-physical system, and describe a project at Berkeley to develop new technologies and frameworks to make the vision of such buildings a reality (http://sdb.cs.berkeley.edu/sdb/).
2:00pmThe Future of Big Data - Matei Zaharia (MIT) (Video) (Slides)
Large-scale data processing will transform many scientific and commercial fields. However, both the hardware landscape and the users of big data have changed since the first datacenter-scale computing systems were introduced. I'll talk about how hardware trends such as the slowdown of processing with respect to I/O affect big data systems, and what can be done to make them accessible to a wider audience.
2:30pmThe Future of Intelligent Systems - Sarah Bird (Microsoft) (Video) (Slides)
Intelligent algorithms are becoming infrastructural in the people’s everyday lives. We expect our computing systems to make complex, dynamic, personalized decisions to help us better engage with the world around us: whether it be to select the best route to take home; recommend articles to read; or create personalized health and wellness programs. In order to meet these demands, there is becoming increased focus on developing and deploying adaptive learning algorithms that can learn to identify the proper decision in complex contextual situations. These algorithms automatically observe, experiment, learn, and evolve as they run and have been shown to be extremely powerful. For example, our Multiworld Testing Decision Service achieved a 30% increase in clicks for personalized news with MSN with just a few days of learning, whereas the product team spent months unsuccessfully trying to learn a personalized model through non-adaptive techniques.
3:00pmThe Future of the Cloud - Eric Brewer (Video) (Slides)
Communications have made the world "flatter" and even grown GDP/capita in emerging regions. The impact of the Cloud, and in particular network-based services, will be even more profound, and provide more life options to the majority of the planet. We start with the simple stuff -- the ease of development and the increasing speed of innovation, then expand to why services make the world smaller. There will be much hand-wringing about fundamental changes in entitlement, privacy, education, and political correctness. The value of being human will be collectively revisited, eventually moving us to a ubiquitous Cloud that lives in the background of almost all we do.
Session IV Chair: Kathy Yelick
4:00pmThe Data Science Revolution - Michael Jordan (Video) (Slides)
The phenomenon of Data Science is creating a need for research perspectives that blend computational thinking (with its focus on, e.g., abstractions, algorithms and scalability) with inferential thinking (with its focus on, e.g., underlying populations, sampling patterns, error bars and predictions). I present several examples of such blending, in domains such as distributed inference, asynchronous optimization and private data analysis. I also discuss the design of a new freshman-level course at Berkeley in which this blend is being taught successfully to a wide range of students.
4:30pmThe Future of Jobs and MOOCs - Armando Fox (Video) (Slides)
In 2011 Dave teamed up with me to reinvent Berkeley's CS169 Software Engineering course. (I was as surprised as you are.) Although software engineering was historically not his main area (though to be fair, neither was it mine), I learned some great lessons about teamwork, about pushing your younger colleagues into the spotlight, and about the transferability of a good "playbook" into new intellectual areas. Along the way scaled the course up from 50 to 240 students, wrote a highly-praised textbook that's been translated into four other languages, delivered a MOOC that has reached tens of thousands if not hundreds of thousands of students, ruffled some feathers on the ACM/IEEE Computer Science Curriculum committee (and ultimately influenced their Software Engineering area of their 2013 Curriculum Guidelines document), and had a really great time doing it.
5:00pmCreating Great Programmers with a Software Design Studio - John Ousterhout (Stanford) (Video) (Slides)
It is well known that the best programmers are at least an order of magnitude better than average programmers, but universities don't offer courses that teach people how to become elite programmers. After years of wondering whether this is even possible, I decided to create a new course to (try to) teach the art of software design. In this talk I'll describe the course, which is taught more like an English writing seminar than a traditional programming class. I will also present a few of the key ideas from the course (example: "classes should be thick") and discuss experiences with the first offering in the Spring of 2015.
5:30pmClosing Remarks - David Patterson (Video) (Slides)
5:40pmEnd of Program


Venue & Parking

VENUE: International House (Website)

Recommended parking: Boalt Parking Lot
To reach this lot from IHouse: go north on Piedmont Ave (about 500 ft.); make a U-turn at the Stop sign (right before the bronze bear statue); go south on Piedmont for only about 100 ft., then take immediate right at the blue sign for University Eye Center (Optometry Lane); finally, take the first turn left at the Parking Lot sign. An attendant (stationed by the sign) will be on duty, selling discounted parking passes (cash only!).
For a detailed map and more parking options, please refer to our UC Berkeley Visitor Parking Map below.

Online UC Berkeley Campus Map

UC Berkeley Visitor Parking Map

Lodging Near Campus:

Hotel Shattuck Plaza
2086 Allston Way
Berkeley, CA 94704
Phone: (510) 845-7300
Toll Free: (866) 466-9199
Fax: (510) 845-7320
Website: http://www.hotelshattuckplaza.com

Hotel Durant
Address: 2600 Durant Ave.
2600 Durant Avenue
Berkeley, CA 94704
Voice: 510.845.8981
Fax: 510.486.8336
Reservations: 1.510.845.8981
Website: http://www.hoteldurant.com


Bancroft Hotel
Address: 2680 Bancroft Way
Berkeley, CA 94704
Phone: (510) 549-1000
Website: http://www.bancrofthotel.com

Berkeley Faculty Club
University of California #6050
Berkeley, CA 94720-0001
(510) 540-5678
Website: http://www.berkeleyfacultyclub.com

David A. Patterson CS Education and Research Endowment

The David A. Patterson Computer Science Education and Research Fund is dedicated to supporting the efforts of Berkeley Computer Science faculty and students to advance instruction and curriculum development in computing.

The endowed fund honors our distinguished colleague, Professor David A. Patterson, who has dedicated the last four decades to advancing the field of computer architecture, through highly visible research projects that have revolutionized the industry and a landmark series of textbooks that has transformed how computer architecture is taught throughout the world. Professor Patterson has personally taught thousands of students at Berkeley, and many more through his books and on-line courses. In addition, Professor Patterson has mentored more than 30 graduate students, many of whom are now leaders in academia and industry.

With diminishing state support for our university, the Patterson Fund will significantly assist the EECS Department to handle the enormous challenges caused by the explosive growth in computer science course enrollments, caused by the tremendous interest of students for instruction in the field.

Specifically, the payout will be used to support:

Faculty academic base salaries, especially in support of faculty whose work further advances computer science curriculum or instruction and research
CS education and research programs and activities in support of students
CS curriculum and program development and enhancement activities
General CS programmatic initiatives and efforts to benefit the Department's academic and research goals

To make a donation online, please go to give.berkeley.edu.


Click titles to open videos on YouTube.

Shorter Historical
Video Segments

Your Cal Cultural Heritage (15 mins.)
David Patterson's traditional ending of courses since 1985 for UC Berkeley students. What to emphasize? Ratings? Faculty Awards? CS Department Awards? No - It's the greatest athletic event in college history,"The Play".

IEEE Von Neumann Medal for Hennessy & Patterson (7 mins.)
The 2000 Von Neumann Medal was shared by John Hennessy and David Patterson for their research and for their book. This segment shows the awarding and their acceptance speeches.

IEEE Mulligan Medal Award (5 mins.)
The Mulligan Medal given to David Patterson for his innovative teaching and textbooks. This segment shows the awarding and his acceptance speeches. This was after the Von Neumann Medal awarding given at the same ceremony to John Hennessy and David Patterson.

Introduction to RAID (9 mins.)
First portion of 1992 talk "Terabytes are more important than Teraflops" motivates working on storage instead of processing and explains redundant arrays of inexpensive disks (RAID).

Predicting Digital Libraries as a storage application (6 mins.)
From the 1992 talk "Terabytes are more important than Teraflops" a digital library as a storage application, which explains how 1992 libraries will be seen in the future similar to the way programmers in 1992 think about how Patterson learned to program in 1968 using IBM punch cards and overnight batch processing.

Predicting Storage More Important Than Computation (2 mins.)
From the 1992 talk "Terabytes are more important than Teraflops" a 1 minute conclusion predicting non-technical obstacles a digital library and that a 1000X storage increase will have bigger impact than a 1000X processor speedup.

Inspiration for RISC and follow-on processors (12 mins.)
Where RISC ideas and motivation came from, followup projects to RISC-I and RISC-II in answer to a questions---Smalltalk On A RISC (SOAR) and Symbolic Processing Using RISCs (SPUR)---number of registers you need for a RISC, and so on.

Distinguished Teaching Award to Patterson for RISC (4 mins.)
UC Berkeley's highest teaching honor, primarily given for his development of Reduced Instruction Set Computer ideas and chips in a series of four graduate courses from winter quarter 1980 to spring quarter 1981.

Long Historical Videos
(Original Full-length sources of segments left)

IEEE Awards Ceremony (96 minutes)
Includes awards to UC Berkeley's John Whinery as well as the Von Neumann Medal to John Hennessy and David Patterson for their research and for their book and the Mulligan Education Medal to David Patterson for innovative teaching and several textbook.

Terabytes Are More Important Than Teraflops (56 minutes)
David Patterson's talk motivates working on storage instead of processing, explains redundant arrays of inexpensive disks (RAID), describes near-line storage, a global climate change application, a digital library application, and the concludes with predictions of obstacles to those visions.

Introduction to RISC with audience Q&A (110 minutes)
David Patterson's 1985 talk given at HP about Reduced Instruction Set Computers (RISC), along with a telephone call-in Q&A. Talks about followup projects to RISC-I and RISC-II in answer to a question: Smalltalk On A RISC (SOAR) and Symbolic Processing Using RISCs (SPUR).

Distiniguished Teaching Awards Ceremony (22 minutes)
1982 winners of UC Berkeley Distinguished Teaching Award. Howell Daly, Entomology (author of the leading textbook in Insect Biology and Diversity); Laura D'Andrea Tyson, Economics (became Chair of the US President's Council of Economic Advisers during the Clinton Administration); James Deetz, Anthropology (one of the fathers of historical archaeology); Dick Kirp, Public Policy (winner of several best-book-in-education awards); David Patterson, EECS (see wikipedia entry); Hanna Pitkin, Political Science (awarded the Johan Skytte Prize in Political Science in 2003).


University of California Berkeley

For more information, please call 510-402-6904 or send an email to: patterson2016@eecs.berkeley.edu

Copyright © 2016; all rights reserved