- talks - lists.cs.princeton.edu

Colloquium Speaker: Mayank Goel Friday, March 25- 12:30pm
by Nicole E. Wagenblast 24 Mar '16

24 Mar '16

Colloquium Speaker Mayank Goel , University of Washington Friday, March 25, 2016 - 12:30pm Computer Science 105 Teaching Old Sensors New Tricks A fundamental issue with any new sensing technology is the deployment burden. The new technology often comes with a rigid and perhaps expensive list of pre-requisites; and it affects the overall cost-effectiveness, deployability, and accessibility of the solution. For example, a user might find it hard to buy and carry a medical device with them everyday. The primary theme of my Ph.D. research has been to reduce the adoption and deployment barriers of new sensing technologies by using the sensors that are already around us. In this talk, I will present my research on extending the capabilities of the on-board sensors on consumer devices for various applications. First, I will discuss how we can leverage the on-device sensors to enable novel human-computer interactions and make the mobile devices more usable. Next, I will discuss my work on using the on-device sensors for building health technologies that work as well as their clinically-approved counterparts and they continue to evolve through deployments in various parts of the world. Finally, I will discuss how my recent work in extending the on-device sensors is shaping my future interests and how I plan to continue to lower the adoption barriers for new sensing technologies. Mayank Goel is a Ph.D. candidate in Computer Science and Engineering in the Ubiquitous Computing (UbiComp) Lab at the University of Washington, advised by Shwetak Patel and Gaetano Borriello. His research focuses on building sensing systems to solve hard problems in diverse application areas, ranging from health sensing, technologies for the developing world to novel user interaction; with an eye toward reducing deployment barriers. His research in the area of health technologies is currently used by hundreds of patients every week, around the world. He was awarded the Microsoft Research Ph.D. Fellowship in 2014, a University of Washington CSE Fellowship, and 7 Best Paper Nominations. He received an M.S. in Computer Science from Georgia Institute of Technology in 2009, where he was advised by Gregory Abowd and specialized in mobile and ubiquitous computing.

1 0

Colloquium Speaker: Adam Belay, Today- 12:30pm
by Nicole E. Wagenblast 24 Mar '16

24 Mar '16

Colloquium Speaker Adam Belay, Stanford University Thursday, March 24, 12:30pm Computer Science 105 Unleashing Hardware Potential through Better OS Abstractions Datacenter workloads have demanding performance requirements, including the simultaneous need for high throughput, low tail latency, and high server utilization. While modern hardware is compatible with these goals, modern operating systems remain a bottleneck. Better OS abstractions could significantly improve performance, yet deploying these abstractions has become intractable given the size and complexity of today's systems. I will first discuss Dune, a kernel extension that allows OS developers to sidestep software and hardware complexity by running an OS within an ordinary Linux process. With Dune, developers can both access the capabilities of raw hardware and fall back on the functionality of a full Linux environment where convenient. I will then discuss IX and Shinjuku, two generations of new datacenter-focused operating systems that were enabled by Dune. IX provides a novel system call interface that greatly improves network throughput without sacrificing latency. For example, IX improves Memcached's TCP throughput by 5x over Linux. Shinjuku, an ongoing research effort, aims to significantly increase CPU utilization through a centralized approach to intra-server load balancing. Adam Belay is a Ph.D. candidate in Computer Science at Stanford University, where he is a member of the Secure Computer Systems Group and the Multiscale Architecture and Systems Team. Previously, he worked on storage virtualization at VMware Inc. and contributed substantial power management code to the Linux Kernel project. Adam's research area is operating systems and networking. Much of his work has focused on restructuring computer systems so that developers can more easily reach the full performance potential of hardware. Adam has received a Stanford Graduate Fellowship, a VMware Graduate Fellowship, and an OSDI Jay Lepreau Best Paper Award.

1 0

Jude Nelson will present his Pre-FPO on Wednesday, March 30, 2016 at 2pm in CS 402.
by Nicki Gotsis 23 Mar '16

23 Mar '16

Jude Nelson will present his Pre-FPO on Wednesday, March 30, 2016 at 2pm in CS 402. The members of his committee are: Larry Peterson (adviser), John Hartman (reader; University of Arizona), Jen Rexford (reader), Brian Kernighan (non-reader), Kai Li (non-reader) Everyone is invited to attend his talk. The talk title and abstract follow below: "Syndicate: Software-defined Storage for Wide-area Networks" Abstract The proliferation of commodity cloud services presents a golden opportunity for hosting data for wide-area applications. Instead of writing a new storage system from scratch, developers can integrate existing component services into a coherent storage solution. This is highly desirable in theory, because it reduces the amount of code they must deploy while helping them achieve their desired storage cost/performance trade-offs. However, in practice this poses interesting distributed systems challenges, since each component can independently fail, become a performance bottleneck, become too costly to utilize, or change its API and behaviors. Without careful design, built-from-parts wide-area storage can result in brittle, hard-to-modify, and expensive-to-operate applications. In this thesis, we explore the challenges of integrating existing systems to create coherent wide-area storage. Our solution is Syndicate, a scalable software-defined storage system for wide-area networks. Unlike conventional built-from-parts storage, Syndicate lets developers explicitly control end-to-end data consistency, data flow processing, and administrative and trust boundaries across the wide-area. With Syndicate, an application accesses data via a stable storage interface (such as a filesystem), while developers control at runtime how data moves through an ever-changing set of underlying existing systems. In this manner, applications remain resilient to service changes--developers can "hot-swap" services for a better cost/performance trade-off, and tolerate service API changes and failures without taking the application offline. We validate Syndicate's design by using it to construct three non-trivial wide-area applications, and show that Syndicate imposes minimal runtime overhead while significantly reducing the amount of storage code a developer must write. Syndicate is open-source software comprising of approximately 30,000 lines of C++ and 13,000 lines of Python. It is available at https://github.com/syndicate-storage.

1 0

EE Seminar - March 28, 2016, 4:30 pm, E-Quad B205 - Prof. Christopher Batten
by Nicole E. Wagenblast 23 Mar '16

23 Mar '16

Speaker: Prof. Christopher Batten Cornell University Title: Architectural Specialization for Inter-Iteration Loop Dependence Patterns Date: Monday, March 28, 2016 Time: 4:30 p.m. Room: E-Quad, Room B205 Host: Prof. David Wentzlaff Abstract: Hardware specialization is an increasingly common technique to enable improved performance and energy efficiency in spite of the diminished benefits of technology scaling. Exploring hardware specialization requires a vertically integrated research approach spanning applications, compilers, run-times, instruction set design, microarchitectures, and VLSI implementation. In the first part of the talk, I will describe our work on a new architectural design pattern called explicit loop specialization (XLOOPS) based on the idea of elegantly encoding inter-iteration loop dependence patterns in the instruction set. The XLOOPS hardware/software abstraction requires only lightweight changes to a general-purpose compiler to generate XLOOPS binaries and enables executing these binaries on: (1) traditional microarchitectures with minimal performance impact, (2) specialized microarchitectures to improve performance and/or energy efficiency, and (3) adaptive microarchitectures that can seamlessly migrate loops between traditional and specialized execution to dynamically trade-off performance vs. energy efficiency. Our initial results show promising performance improvements compared to simple in-order processors and energy efficiency improvements compared to complex out-of-order processors. In the second part of the talk, I will describe PyMTL and Pydgin, two new Python-based frameworks designed to improve the productivity of vertically integrated computer architecture research. PyMTL leverages the Python programming language to create a highly productive domain-specific embedded language for concurrent-structural modeling and hardware design. The PyMTL framework encourages a philosophy of "modeling towards layout" in which a microarchitecture is incrementally refined from a high-level functional-level model, to a timing-approximate cycle-level model, to a bit-accurate RTL implementation. Pydgin is a framework for rapidly developing very fast instruction-set simulators (ISSs) from a Python-based architecture description language. Both frameworks were critical in exploring the XLOOPS architectural design pattern, and we are continuing to leverage these frameworks in our research and teaching. Biography: Christopher Batten is an Assistant Professor in the School of Electrical and Computer Engineering at Cornell University, where he leads a research group focusing on energy-efficient parallel computer architecture for both high-performance and embedded applications. His work has been recognized with several awards including an AFOSR Young Investigator Program award (2015), Intel Early Career Faculty Honor Program award (2013), an NSF CAREER award (2012), a DARPA Young Faculty Award (2012), and an IEEE Micro Top Picks selection (2004). His teaching has been recognized with a Michael Tien '72 Excellence in Teaching Award (2013) and a James M. and Marsha D. McCormick Award for Outstanding Advising of First-Year Engineering Students (2013). Prior to his appointment at Cornell, Batten received his Ph.D. in electrical engineering and computer science from the Massachusetts Institute of Technology in 2010. He received an M.Phil. in engineering as a Churchill Scholar at the University of Cambridge in 2000, and received a B.S. in electrical engineering as a Jefferson Scholar at the University of Virginia in 1999.

1 0

Colloquium Speaker: Adam Belay, Thursday, March 24- 12:30pm- reminder
by Nicole E. Wagenblast 23 Mar '16

23 Mar '16

Colloquium Speaker Adam Belay, Stanford University Thursday, March 24, 12:30pm Computer Science 105 Unleashing Hardware Potential through Better OS Abstractions Datacenter workloads have demanding performance requirements, including the simultaneous need for high throughput, low tail latency, and high server utilization. While modern hardware is compatible with these goals, modern operating systems remain a bottleneck. Better OS abstractions could significantly improve performance, yet deploying these abstractions has become intractable given the size and complexity of today's systems. I will first discuss Dune, a kernel extension that allows OS developers to sidestep software and hardware complexity by running an OS within an ordinary Linux process. With Dune, developers can both access the capabilities of raw hardware and fall back on the functionality of a full Linux environment where convenient. I will then discuss IX and Shinjuku, two generations of new datacenter-focused operating systems that were enabled by Dune. IX provides a novel system call interface that greatly improves network throughput without sacrificing latency. For example, IX improves Memcached's TCP throughput by 5x over Linux. Shinjuku, an ongoing research effort, aims to significantly increase CPU utilization through a centralized approach to intra-server load balancing. Adam Belay is a Ph.D. candidate in Computer Science at Stanford University, where he is a member of the Secure Computer Systems Group and the Multiscale Architecture and Systems Team. Previously, he worked on storage virtualization at VMware Inc. and contributed substantial power management code to the Linux Kernel project. Adam's research area is operating systems and networking. Much of his work has focused on restructuring computer systems so that developers can more easily reach the full performance potential of hardware. Adam has received a Stanford Graduate Fellowship, a VMware Graduate Fellowship, and an OSDI Jay Lepreau Best Paper Award.

1 0

Colloquium Speaker: Igor Mordatch, Today, 4:30pm
by Nicole E. Wagenblast 23 Mar '16

23 Mar '16

Colloquium Speaker Igor Mordatch, University of California, Berkeley Wednesday, March 23, 4:30pm Computer Science 105 Automated Discovery and Learning of Complex Movement Behaviours In order to create truly autonomous physical robots, understand the underlying principles behind human movement, or tell narratives in animated films and interactive games, it is necessary to synthesize movement behaviours with the same wide variety, richness and complexity observed in humans and other animals. Moreover, these behaviours should be discovered automatically from only a few core principles, and not be a result of extensive manual engineering or a mimicking of demonstrations. In this talk at the intersection of robotics, computer graphics and biomechanics, I will show work on novel trajectory and policy optimization methods that give rise to a range of behaviours such getting up, climbing, moving objects, hand manipulation, acrobatics, and various cooperative actions involving multiple characters all in a single system. The resulting movements can be used to successfully control a physical bipedal robot and coupled with detailed models of human physiology, motions that match real human motion can be produced de novo, giving the predictive power to conduct virtual biomechanics experiments. The approach is fully automatic, based on general neural network policy representations and does not require domain knowledge specific to each behaviour, pre-existing examples or motion capture data. Although discovery and learning are computationally-expensive and rely on cloud and GPU computing, the interactive animation can run in real-time on any hardware once the controllers are learned. Igor Mordatch is a post-doctoral fellow working with professor Pieter Abbeel at University of California, Berkeley. He received his PhD at University of Washington under supervision of Emanuel Todorov and Zoran Popovic and undergraduate degree in Computer Science and Mathematics at University of Toronto. He worked as a visiting researcher at Stanford University and Pixar Research. His research interests lie in the development and use of optimal control and machine learning techniques for robotics, computer graphics, and biomechanics.

1 0

Colloquium Speaker: Igor Mordatch, Wednesday, March 23, 4:30pm
by Nicole E. Wagenblast 22 Mar '16

22 Mar '16

Colloquium Speaker Igor Mordatch, University of California, Berkeley Wednesday, March 23, 4:30pm Computer Science 105 Automated Discovery and Learning of Complex Movement Behaviours In order to create truly autonomous physical robots, understand the underlying principles behind human movement, or tell narratives in animated films and interactive games, it is necessary to synthesize movement behaviours with the same wide variety, richness and complexity observed in humans and other animals. Moreover, these behaviours should be discovered automatically from only a few core principles, and not be a result of extensive manual engineering or a mimicking of demonstrations. In this talk at the intersection of robotics, computer graphics and biomechanics, I will show work on novel trajectory and policy optimization methods that give rise to a range of behaviours such getting up, climbing, moving objects, hand manipulation, acrobatics, and various cooperative actions involving multiple characters all in a single system. The resulting movements can be used to successfully control a physical bipedal robot and coupled with detailed models of human physiology, motions that match real human motion can be produced de novo, giving the predictive power to conduct virtual biomechanics experiments. The approach is fully automatic, based on general neural network policy representations and does not require domain knowledge specific to each behaviour, pre-existing examples or motion capture data. Although discovery and learning are computationally-expensive and rely on cloud and GPU computing, the interactive animation can run in real-time on any hardware once the controllers are learned. Igor Mordatch is a post-doctoral fellow working with professor Pieter Abbeel at University of California, Berkeley. He received his PhD at University of Washington under supervision of Emanuel Todorov and Zoran Popovic and undergraduate degree in Computer Science and Mathematics at University of Toronto. He worked as a visiting researcher at Stanford University and Pixar Research. His research interests lie in the development and use of optimal control and machine learning techniques for robotics, computer graphics, and biomechanics.

1 0

Jonathan Ragan-Kelley , TODAY March 22, 12:30pm
by Mitra D. Kelly 22 Mar '16

22 Mar '16

Jonathan Ragan-Kelley, Stanford March 22, 12:30pm Computer Science 105 Title: Organizing Computation for High-Performance Visual Computing Abstract: Future visual computing applications-from photorealistic real-time rendering, to 4D light field cameras, to pervasive sensing and computer vision-demand orders of magnitude more computation than we currently have. >From data centers to mobile devices, performance and energy scaling is limited by locality (the distance over which data has to move, e.g., from nearby caches, far away main memory, or across networks) and parallelism. Because of this, I argue that we should think of the performance and efficiency of an application as determined not just by the algorithm and the hardware on which it runs, but critically also by the organization of computations and data. For algorithms with the same complexity-even the exact same set of arithmetic operations and data-executing on the same hardware, the order and granularity of execution and placement of data can easily change performance by an order of magnitude because of locality and parallelism. To extract the full potential of our machines, we must treat the organization of computation as a first class concern while working across all levels from algorithms and data structures, to compilers, to hardware. This talk will present facets of this philosophy in systems I have built for visual computing applications from image processing and vision, to 3D rendering, simulation, optimization, and 3D printing. I will show that, for data-parallel pipelines common in graphics, imaging, and other data-intensive applications, the organization of computations and data for a given algorithm is constrained by a fundamental tension between parallelism, locality, and redundant computation of shared values. I will focus particularly on the Halide language and compiler for image processing, which explicitly separates what computations define an algorithm from the choices of organization which determine parallelism, locality, memory footprint, and synchronization. I will show how this approach can enable much simpler programs to deliver performance often many times faster than the best prior hand-tuned C, assembly, and CUDA implementations, while scaling across radically different architectures, from ARM cores, to massively parallel GPUs, to FPGAs and custom ASICs. Mitra Kelly Academic Secretary Princeton University Computer Science Dept 35 Olden Street Princeton NJ 08540 mkelly(a)cs.princeton.edu <mailto:mkelly@cs.princeton.edu> 609-258-4562

1 0

Princeton ACM/IEEE-CS April meeting
by Nicole E. Wagenblast 22 Mar '16

22 Mar '16

The New ABCs of Research: Achieving Breakthrough Collaborations Thursday, April 21, 2016, 8:00pm Refreshments and networking at 7:30pm Computer Science 105 How should we organize research programs in computer science and technology? Research helps us produce innovative new products (the next iPhone), and research also delivers “foundational theories” (new algorithms and supporting technologies). Solving the immense problems of the 21st century will require ambitious research teams that are skilled at producing practical solutions and foundational theories simultaneously – that is the ABC Principle: Applied & Basic Combined. Then these research teams can deliver high-impact outcomes by applying the SED Principle: Blend Science, Engineering and Design Thinking, which encourages use of the methods from all three disciplines. These guiding principles (ABC & SED) are meant to replace Vannevar Bush’s flawed linear model from 1945 that has misled researchers for 70+ years. These new guiding principles will enable students, faculty, business leaders, and government policy makers to accelerate discovery and innovation. The examples in the talk will emphasize how these guiding principles can be applied to reinvigorate computing research. Ben Shneiderman (http://www.cs.umd.edu/~ben) is a Distinguished University Professor in the Department of Computer Science at the University of Maryland. He is also the Founding Director (1983-2000) of the Human-Computer Interaction Laboratory (http://www.cs.umd.edu/hcil/), and a Member of the University of Maryland Institute for Advanced Computer Studies (UMIACS). He is a Fellow of the AAAS, ACM, IEEE, and NAI, and a Member of the National Academy of Engineering, in recognition of his pioneering contributions to human-computer interaction and information visualization. His contributions include the direct manipulation concept, clickable highlighted web-links, touchscreen keyboards, dynamic query sliders for Spotfire, development of treemaps, novel network visualizations for NodeXL, and temporal event sequence analysis for electronic health records. Ben is the co-author with Catherine Plaisant of Designing the User Interface: Strategies for Effective Human-Computer Interaction (6th ed., 2016). His book Leonardo’s Laptop (MIT Press) won the IEEE book award for Distinguished Literary Contribution. Shneiderman’s latest book is The New ABCs of Research: Achieving Breakthrough Collaborations (Oxford, February 2016). Information: Dennis Mancl (908) 285-1066 On-line info: http://PrincetonACM.acm.org All Princeton ACM / IEEE-CS meetings are open to the public. Students and their parents are welcome. There is no admission charge, and refreshments are served. A pre-meeting dinner is held at 6:00 p.m. at Ruby Tuesday’s Restaurant on Route 1. Please send email to princetonacm(a)gmail.com in advance if you plan to attend the dinner.

1 0

4:30pm Thu Mar 24 talk on automatic synthesis in cyberphysical systems in E-Quad B205
by Jennifer Rexford 21 Mar '16

21 Mar '16

> > > Speaker: > Vasumathi Raman, United Technologies Research Center > Title: > Synthesis for Autonomy: Connecting the Physical, the Logical and the Human > Day: > Thursday, March 24, 2016 > > > Time: > 4:30 pm > Room: > B205, E-Quad > Host: > Prof. Antoine Kahn > > > > > > > > > Abstract: > Autonomous cyber-physical systems like unmanned aircraft and self-driving cars stretch the limits of engineering, and reasoning precisely about their behavior is increasingly difficult. Moreover, a correct implementation is often elusive even when the desired outcome is obvious. Algorithmic synthesis makes the formal specification of desired behavior an integral part of the controller design process -- the resulting controllers are correct by construction. Synthesis enables non-expert human users to provide complex system specifications, and be assured of their fulfillment. However, this goal of automatically generating autonomous control from user-defined specifications poses a host of unprecedented challenges. > > In this talk, I will present two frameworks for automated synthesis from high-level specifications. I will first describe a system for generating, troubleshooting, and executing controllers for autonomous robots from natural language specifications, including analytical tools for automatically determining causes of failure to synthesize. I will then introduce an optimization-based controller-synthesis framework for high-dimensional systems operating in uncertain environments, bypassing the need for discretizing the state space and admitting specifications that govern not only the order of events, but also their timing. Finally, I will present new research directions that push the envelope of synthesis for autonomous systems. > > Bio: > Vasu Raman is a Senior Scientist at the United Technologies Research Center in Berkeley, CA. Her research explores algorithmic methods for designing and controlling autonomous cyber-physical systems, guaranteeing correctness with respect to user-defined specifications. She earned a PhD in Computer Science from Cornell University in 2013, and was a postdoctoral scholar in the Department of Computing and Mathematical Sciences and the Department of Control and Dynamical Systems at the California Institute of Technology from 2013-2015. She has contributed extensively to the LTLMoP toolkit for robot mission planning and the slugs reactive synthesis tool, and developed BluSTL, a toolbox for automatically generating controllers from timed temporal logic specifications. Vasu also holds a BA in Computer Science and Mathematics from Wellesley College.

1 0