University of Washington

Displaying 1-40 of 157 results

  • White Papers // Nov 2014

    Authenticated Encryption: How Reordering Can Impact Performance

    "In this paper, the authors look at authenticated encryption schemes from a new perspective. As opposed to focusing solely on the ""Security"" implications of the different methods for constructing authenticated encryption schemes, they investigate the effect of the method used to construct an authenticated encryption scheme on the ""Performance"" of...

    Provided By University of Washington

  • White Papers // Mar 2014

    GraphChiDB: Simple Design for a Scalable Graph Database System - On Just a PC

    The authors propose a new data structure, Parallel Adjacency Lists (PAL), for efficiently managing graphs with billions of edges on disk. The PAL structure is based on the graph storage model of GraphChi, but they extend it to enable online database features such as queries and fast insertions. In addition,...

    Provided By University of Washington

  • Webcasts // Jun 2012

    The Journey of the Entrepreneur

    In this webcast, the presenter shares stories from the trenches, lessons learned and insights about what it takes for a promising technology to become an innovation that changes the world.

    Provided By University of Washington

  • Webcasts // Jun 2012

    Photo Tourism at Google

    Two years ago, researcher Steve Seitz created a new 3D computer vision group in Google's Seattle office. In this webcast, the presenter discusses what the group has been up to, including Picasa face movies, MapsGL, and the newest feature called Photo Tours.

    Provided By University of Washington

  • Webcasts // Jun 2012

    Hogwild for Machine Learning on Multicore

    In this webcast, the presenter provides both theoretical and experimental evidence demonstrating the achievement of linear speedups on multi-core workstations on several benchmark optimization problems. Stochastic Gradient Descent (SGD) is a popular optimization algorithm for solving data-driven machine learning problems such as classification, model selection, sequence labeling, and recommendation.

    Provided By University of Washington

  • White Papers // May 2012

    Verification Games: Making Verification Fun

    Program verification is the only way to be certain that a given piece of software is free of (certain types of) errors - errors that could otherwise disrupt operations in the field. To date, formal verification has been done by specially-trained engineers. Labor costs have heretofore made formal verification too...

    Provided By University of Washington

  • White Papers // May 2012

    Inference and Checking of Object Ownership

    Ownership type systems describe a heap topology and enforce an encapsulation discipline; they aid in various program correctness and understanding tasks. However, the annotation overhead of ownership type systems has hindered their widespread use. The authors present a unified framework for specification, type inference and type checking of ownership type...

    Provided By University of Washington

  • Webcasts // Mar 2012

    Crowd Computation: Social Computing and Mass Disruption

    In this webcast, the presenter describes several ways in which members of the social media crowd act to shape the information space through their actions and interactions within the space.

    Provided By University of Washington

  • Webcasts // Mar 2012

    Advancing Computer Vision by Leveraging Humans

    This discussion on human-centered contributions to computing describes recent efforts in expanding the roles humans play in advancing computer vision. In the first part of this webcast, the presenter describes the recently-introduced "Human-debugging" paradigm. It allows for identification of weak-links in machine vision approaches that require further research. In the...

    Provided By University of Washington

  • Webcasts // Mar 2012

    Predicting the Present With Google Trends

    In this webcast, the presenter explains how to use Google Trends data to measure the state of the economy in various sectors, and discuss some of the implications for research and policy.

    Provided By University of Washington

  • Webcasts // Mar 2012

    Parallel Programmability for High Performance Computing

    In this webcast, the presenter describes Chapel, an emerging language from Cray, Inc., that strives to address challenges to parallel programmability by making it more productive for both High Performance Computing (HPC) and mainstream programmers.

    Provided By University of Washington

  • Webcasts // Mar 2012

    Adventures in Scaling the Multicore Memory Wall

    In this webcast, the presenter covers three different approaches to multicore cache management that can help bridge the "Memory wall." If the application thread mapping and the cache topology are both static (i.e., do not change during runtime), then compiler enhancements that support cache topology-aware code optimization can be used...

    Provided By University of Washington

  • Webcasts // Mar 2012

    Optimizing Human Computation

    In this webcast, the presenter describes crowdsourcing work on two fronts. First, Crowd Algorithms, which view the crowd as data processors to design human computation versions of fundamental algorithms like sort, filter, and search, where the basic operations are done by people. Second, Declarative Crowdsourcing which views the crowd as...

    Provided By University of Washington

  • White Papers // Mar 2012

    User-Driven Access Control: Rethinking Permission Granting in Modern Operating Systems

    Modern client platforms, such as iOS, Android, Windows Phone, Windows 8, and web browsers, run each application in an isolated environment with limited privileges. A pressing open problem in such systems is how to allow users to grant applications access to user-owned resources, e.g., to privacy- and cost-sensitive devices like...

    Provided By University of Washington

  • Webcasts // Feb 2012

    GraphLab: A Distributed Abstraction for Machine Learning

    Today, machine learning (ML) methods play a central role in industry and science. In this webcast, the presenter describes the GraphLab framework, which naturally expresses asynchronous, dynamic graph computations that are key for state-of-the-art ML algorithms.

    Provided By University of Washington

  • Webcasts // Feb 2012

    Document Discovery: Advancing Research With Large Knowledge Networks

    By putting the world's scholarly literature online, publisher websites and digital archives have made millions articles instantly available anywhere, any time, in digital form. In this webcast, the presenter describes new approaches to measuring, mapping and evaluating documents are creating new forms of value that can be derived from the...

    Provided By University of Washington

  • White Papers // Jan 2012

    Type-Directed Completion of Partial Expressions

    Modern programming frameworks provide enormous libraries arranged in complex structures, so much so that a large part of modern programming is searching for APIs that "Surely exist" somewhere in an unfamiliar part of the framework. The authors present a novel way of phrasing a search for an unknown API: the...

    Provided By University of Washington

  • Webcasts // Dec 2011

    Towards Balanced, Data-Intensive Scalable Computing

    While many interesting systems are able to scale linearly with additional servers, per-server performance can lag behind per-server capacity by more than an order of magnitude. In this webcast, the presenter will presents Themis, a runtime supporting highly-efficient data-intensive computing.

    Provided By University of Washington

  • Webcasts // Dec 2011

    Computer Science and Engineering Distinguished Lecturer Series-Internet-Scale Storage

    The pace of innovation in data center design has been rapidly accelerating over the last 5 years, driven by the mega-service operators. In this webcast, the presenter will take apart a high-scale cloud service data center, looking at power distribution from high voltage to the server, compute and storage, networking,...

    Provided By University of Washington

  • Webcasts // Dec 2011

    Cooperative Concurrency for a Multicore World

    Multi-threaded programs are notoriously prone to unintended interference between concurrent threads. To address this problem, these presenters argue that yield annotations in the source code should document all thread interference, and they present a type system for verifying the absence of undocumented interference.

    Provided By University of Washington

  • Webcasts // Dec 2011

    Using Surrogate Benchmarks to Project the Performance of HPC Applications

    Performance projections of High Performance Computing (HPC) applications onto various hardware platforms are important for hardware vendors and HPC users. The projections aid hardware vendors in the design of future systems and help HPC users with system procurement.

    Provided By University of Washington

  • Webcasts // Nov 2011

    Full Duplex Wireless

    In this webcast, the presenter describing that a full-duplex radio - a radio that can receive and transmit simultaneously on the same frequency, like a two-lane bridge - can be built using commodity, off-the-shelf components. Full duplex has the potential to revolutionize a large number of wireless systems.

    Provided By University of Washington

  • White Papers // Aug 2011

    Energy-Efficient Low Power Listening for Wireless Sensor Networks in Noisy Environments

    Low Power Listening (LPL) is a common MAC layer technique for reducing energy consumption in wireless sensor networks, where nodes periodically wake up to sample the wireless channel for activity. However, LPL is highly susceptible to false wakeups caused by environmental noise being detected as energy on the channel, causing...

    Provided By University of Washington

  • White Papers // Aug 2011

    New Directions for Self-Destructing Data Systems

    This paper seeks to advance the state of the art in practical self-destructing data systems that secure sensitive data from disclosure in the highly mobile, social-networked, cloud-computing world. The authors' work facilitates the automatic, timed, and simultaneous destruction of all copies of a self-destructing data object (such as a message...

    Provided By University of Washington

  • White Papers // Aug 2011

    Hierarchical Scheduling for Multicores With Multilevel Cache Hierarchies

    To achieve good performance, programs must exploit locality in its memory references, i.e., it must utilize its caches effectively. For machines with a single processor or core, there is a rich history of work on external memory and hierarchical memory models and algorithms, all aimed at reducing the number of...

    Provided By University of Washington

  • White Papers // Aug 2011

    User Centered Design and Evaluation of an Eye Movement-Based Biometric Authentication System

    Biometric authentication systems offer advantages over knowledge-based and token-based systems because the authors do not require users to remember anything or carry a physical object. However, usability and acceptability issues have often been neglected in favor of optimizing technical performance. They present on the design and development of a novel...

    Provided By University of Washington

  • White Papers // Jul 2011

    Efficient Deadlock Avoidance for Streaming Computation With Filtering

    Parallel streaming computation has been studied extensively, and many languages, libraries, and systems have been designed to support this model of computation. While some streaming computations send data at a priori predictable rates on every channel between compute nodes, many natural applications lack this property. In particular, the authors consider...

    Provided By University of Washington

  • White Papers // Jun 2011

    DeSEO: Combating Search-Result Poisoning

    The authors perform an in-depth study of SEO attacks that spread malware by poisoning search results for popular queries. Such attacks, although recent, appear to be both widespread and effective. They compromise legitimate Web sites and generate a large number of fake pages targeting trendy keywords. They first dissect one...

    Provided By University of Washington

  • Webcasts // Jun 2011

    How I Learned to Stop Worrying and Trust Mobile Systems

    In this webcast, the presenter explains about "How he learned to stop worrying and trust mobile systems" and Mobile phones have become the eyes and ears of the Internet by placing digital communication, computation, and sensing at the center of nearly all human activity.

    Provided By University of Washington

  • White Papers // May 2011

    Mercury BLASTN Biosequence Similarity Search System: Technical Reference Guide

    The Mercury BLASTN application is a hybrid hardware-software implementation of DNA-to-DNA sequence comparison. It presents an interface similar to that of NCBI BLASTN 2.2 (and indeed uses much of that package's source code internally) but has many changes "Under the hood" to support very large sequence comparisons. Much of Mercury...

    Provided By University of Washington

  • White Papers // May 2011

    Region-Based Dynamic Separation for STM Haskell

    The authors present the first design and implementation of dynamic separation in STM Haskell. Dynamic separation is a recent approach to Software Transactional Memory (STM) that achieves strongly-atomic semantics with performance comparable to that of a weakly-atomic STM. STM Haskell, a lazy-versioning STM library for Haskell, previously supported strongly-atomic semantics...

    Provided By University of Washington

  • White Papers // May 2011

    Operating System Implications of Fast, Cheap, Non-Volatile Memory

    The existence of two basic levels of storage (fast/volatile and slow/non-volatile) has been a long-standing premise of most computer systems, influencing the design of OS components, including file systems, virtual memory, scheduling, execution models, and even their APIs. Emerging resistive memory technologies - such as Phase-Change Memory (PCM) and memristors...

    Provided By University of Washington

  • White Papers // May 2011

    Scheduling-Control Co-Design for WirelessHART Networks

    WirelessHART is an open standard for wireless sensor-actuator networks in process monitoring and control. Recent years have seen initial success in real-world deployment of control systems over WirelessHART networks. Due to stringent bandwidth constraints in WirelessHART networks, it is important to develop a wireless transmission scheduling and control co-design approach...

    Provided By University of Washington

  • White Papers // May 2011

    Efficient Inter-Vehicle Data Dissemination

    Data services for in-vehicle consumption are expected to become a primary driver in the development of future vehicular networks. Due to download rate limitations of present wide-area cellular connectivity such as 3G (the likely "Pipe" to/from vehicles), and direct peer-to-peer data sharing among vehicles can supplement vertical downloading. This paper...

    Provided By University of Washington

  • White Papers // May 2011

    Tunable Static Inference for Generic Universe Types

    Object ownership is useful for many applications, including program verification, thread synchronization, and memory management. However, the annotation overhead of ownership type systems hampers their widespread application. This paper addresses this issue by presenting a tunable static type inference for Generic Universe Types. In contrast to classical type systems, ownership...

    Provided By University of Washington

  • White Papers // May 2011

    Maverick: Providing Web Applications With Safe and Flexible Access to Local Devices

    Web browsers do not yet provide Web programs with the same safe, convenient access to local devices that operating systems provide to native programs. As a result, Web programmers must either wait for the slowly evolving HTML standard to add support for the device classes they want to use, or...

    Provided By University of Washington

  • White Papers // May 2011

    Webcam Image Alignment

    AMOS, The Archive of Many Outdoor Scenes, has been a major project at Washington University. The project focus has been collecting images from webcams all over the world. Images have been logged from thousands of webcams for over 5 years. The large datasets created by AMOS are useful for a...

    Provided By University of Washington

  • White Papers // Apr 2011

    Crunching Large Graphs With Commodity Processors

    Crunching large graphs is the basis of many emerging applications, such as social network analysis and bio-informatics. Graph analytics algorithms exhibit little locality and therefore present significant performance challenges. Hardware multi-threading systems (e.g., Cray XMT) show that with enough concurrency, the authors can tolerate long latencies. Unfortunately, this solution is...

    Provided By University of Washington

  • White Papers // Apr 2011

    Robust FDI Determinants: Bayesian Model Averaging In The Presence Of Selection Bias

    The literature on Foreign Direct Investment (FDI) determinants is remarkably diverse in terms of competing theories and empirical results. The authors utilize Bayesian Model Averaging (BMA) to resolve the model uncertainty that surrounds the validity of the competing FDI theories. Since the structure of existing FDI data is known to...

    Provided By University of Washington

  • White Papers // Mar 2011

    SSLShader: Cheap SSL Acceleration With Commodity Processors

    Secure end-to-end communication is becoming increasingly important as more private and sensitive data is transferred on the Internet. Unfortunately, today's SSL deployment is largely limited to security or privacy critical domains. The low adoption rate is mainly attributed to the heavy cryptographic computation overhead on the server side, and the...

    Provided By University of Washington

  • White Papers // Nov 2007

    SPINE: An Operating System for Intelligent Network Adapters

    The emergence of fast, cheap embedded processors presents the opportunity for processing to occur on the network adapter. The authors are investigating how a system design incorporating such an intelligent network adapter can be used for applications that benefit from being tightly integrated with the network subsystem. They are developing...

    Provided By University of Washington

  • White Papers // Jan 2008

    TRON: Process - Specific File Protection for the UNIX Operating System

    The file protection mechanism provided in UNIX is insufficient for current computing environments. While the UNIX file protection system attempts to protect users from attacks by other users, it does not directly address the agents of destruction - executing processes. As computing environments become more interconnected and interdependent, there is...

    Provided By University of Washington

  • White Papers // Dec 2010

    Modeling and Analysis of Detection Time Trade-Offs for Channel Searching in Cognitive Radio Networks

    A successful Cognitive Radio Network (CRN) needs a fast and reliable spectrum sensing scheme to enable secondary users to utilize available channels. In this paper, the authors first revisit conventional urn models for channel availability (the random (i.i.d) models) and introduce a correlated Markov model which is apropos for scenarios...

    Provided By University of Washington

  • White Papers // May 2011

    Efficient Inter-Vehicle Data Dissemination

    Data services for in-vehicle consumption are expected to become a primary driver in the development of future vehicular networks. Due to download rate limitations of present wide-area cellular connectivity such as 3G (the likely "Pipe" to/from vehicles), and direct peer-to-peer data sharing among vehicles can supplement vertical downloading. This paper...

    Provided By University of Washington

  • White Papers // Jul 2010

    Revisiting RFID Link Budgets for Technology Scaling: Range Maximization of RFID Tags

    Passive RFID tags are traditionally assumed to be downlink limited since typical tag sensitivity is considerably poorer than reader sensitivity, due to stringent power limitations. On the other hand, semi-passive tags are generally uplink limited since tag and reader sensitivity are comparable. In this paper, it is demonstrated that judicious...

    Provided By University of Washington

  • White Papers // Mar 2010

    Network Tomography Via Compressed Sensing

    In network tomography, the authors seek to infer link status parameters (such as delay) inside a network through end-to-end probe sending between (external) boundary nodes. The main challenge here is to estimate link-level attributes from end-to-end measurements. In this paper by using the idea of combinatorial compressed sensing, they provide...

    Provided By University of Washington

  • White Papers // Mar 2010

    Joint Optimization of Spectrum Sensing for Cognitive Radio Networks

    Cognitive radio networks require fast and reliable spectrum sensing to achieve high network utilization by secondary users. Current optimization approaches to spectrum sensing to-date have focused on maximizing aggregate throughput while considering only a single parameter variable pertinent to sensing, notably the threshold or duration, but not both. In this...

    Provided By University of Washington

  • White Papers // Jul 2009

    Analysis of Dynamic Spectrum Access With Heterogeneous Networks: Benefits of Channel Packing Scheme

    Dynamic Spectrum Access (DSA) has the potential to vastly improve spectrum utilizations among heterogeneous networks. The authors present a Continuous-Time Markov Chain (CT-MC) model to analyze the performance of three co-located cognitive systems with various priority classes and bandwidth requirements. The maximum spectrum utilization and minimum blocking probability are derived...

    Provided By University of Washington

  • White Papers // Aug 2009

    HEXA: Compact Data Structures for Faster Packet Processing

    Several common packet processing tasks make use of directed graph data structures in which edge labels are used to match symbols from a finite alphabet. Examples include tries used in IP route lookup and string-matching automata used to implement deep packet inspection for virus scanning. In this paper, the authors...

    Provided By University of Washington

  • White Papers // Aug 2009

    Emergent Task Allocation for Mobile Robots Through Intentions and Directives

    Multi-robot systems require efficient and accurate planning in order to perform mission-critical tasks. However, algorithms that find the optimal solution are usually computationally expensive and may require a large number of messages between the robots as the robots need to be aware of the global spatiotemporal information. In this paper,...

    Provided By University of Washington

  • White Papers // Aug 2009

    MLDS: A Flexible Location Directory Service for Tiered Sensor Networks

    Many emergent distributed sensing applications need to keep track of mobile entities across multiple sensor networks connected via an IP network. To simplify the realization of such applications, the authors present MLDS, a Multi-resolution Location Directory Service for tiered sensor networks. MLDS provides a rich set of spatial query services...

    Provided By University of Washington

  • White Papers // Aug 2009

    A Unified Architecture for Flexible Radio Power Management in Wireless Sensor Networks

    Radio power management is of paramount concern in wireless sensor networks that must achieve long lifetimes on scarce amounts of energy. While a multitude of power management protocols have been proposed in the literature, their usage in real-world systems has been limited by the lack of system support for the...

    Provided By University of Washington

  • White Papers // Aug 2009

    Efficient Mapping of Virtual Networks Onto a Shared Substrate

    Virtualization has been proposed as a vehicle for overcoming the growing problem of internet ossification. This paper studies the problem of mapping diverse virtual networks onto a common physical substrate. In particular, the authors develop a method for mapping a virtual network onto a substrate network in a cost-efficient way,...

    Provided By University of Washington

  • White Papers // Aug 2009

    Discovering Functional Modules by Clustering Gene Co-Expression Networks

    Identification of groups of functionally related genes from high throughput gene expression data is an important step towards elucidating gene functions at a global scale. Most existing approaches treat gene expression data as points in a metric space, and apply conventional clustering algorithms to identify sets of genes that are...

    Provided By University of Washington

  • White Papers // Aug 2009

    Agilla: A Mobile Agent Middleware for Sensor Networks

    Agilla is a mobile agent middleware for sensor networks. Mobile agents are special processes that can migrate across sensors. They increase network flexibility by enabling active in-network reprogramming. Neighbor lists and tuple spaces are used for agent coordination. Agilla was originally implemented on Mica2 motes, but has been ported to...

    Provided By University of Washington

  • White Papers // Aug 2009

    Design of Routers for Diversified Networks

    There is a growing recognition in the networking research community, that the protocols and services at the heart of the Internet have become so rigid and difficult to change, that they represent an impediment to the continuing evolution of the Internet. This poses a serious problem as the demands on...

    Provided By University of Washington

  • White Papers // Oct 2010

    Random Access Compressed Sensing in Underwater Sensor Networks

    In this paper, the authors propose a power-efficient underwater sensor network scheme employing compressed sensing and random channel access. The proposed scheme is suitable for applications where a large number of sensor nodes are deployed uniformly over a certain area to measure a physical phenomenon. The underlying assumption is that...

    Provided By University of Washington

  • White Papers // Jan 2011

    Dynamic Resource Allocation Based on Online Traffic Prediction for Video Streams

    In this paper, the authors propose a new Dynamic Resource Allocation (DRA) scheme to support the constantly increasing online video stream traffic, especially High Definition (HD) video streams. Their DRA scheme is based on online traffic prediction using seasonal time analysis. Their scheme seeks to provide accurate traffic prediction, to...

    Provided By University of Washington

  • White Papers // Aug 2011

    Hierarchical Scheduling for Multicores With Multilevel Cache Hierarchies

    To achieve good performance, programs must exploit locality in its memory references, i.e., it must utilize its caches effectively. For machines with a single processor or core, there is a rich history of work on external memory and hierarchical memory models and algorithms, all aimed at reducing the number of...

    Provided By University of Washington

  • White Papers // Aug 2011

    Energy-Efficient Low Power Listening for Wireless Sensor Networks in Noisy Environments

    Low Power Listening (LPL) is a common MAC layer technique for reducing energy consumption in wireless sensor networks, where nodes periodically wake up to sample the wireless channel for activity. However, LPL is highly susceptible to false wakeups caused by environmental noise being detected as energy on the channel, causing...

    Provided By University of Washington

  • White Papers // Jul 2011

    Efficient Deadlock Avoidance for Streaming Computation With Filtering

    Parallel streaming computation has been studied extensively, and many languages, libraries, and systems have been designed to support this model of computation. While some streaming computations send data at a priori predictable rates on every channel between compute nodes, many natural applications lack this property. In particular, the authors consider...

    Provided By University of Washington

  • White Papers // May 2011

    Mercury BLASTN Biosequence Similarity Search System: Technical Reference Guide

    The Mercury BLASTN application is a hybrid hardware-software implementation of DNA-to-DNA sequence comparison. It presents an interface similar to that of NCBI BLASTN 2.2 (and indeed uses much of that package's source code internally) but has many changes "Under the hood" to support very large sequence comparisons. Much of Mercury...

    Provided By University of Washington

  • White Papers // May 2011

    Scheduling-Control Co-Design for WirelessHART Networks

    WirelessHART is an open standard for wireless sensor-actuator networks in process monitoring and control. Recent years have seen initial success in real-world deployment of control systems over WirelessHART networks. Due to stringent bandwidth constraints in WirelessHART networks, it is important to develop a wireless transmission scheduling and control co-design approach...

    Provided By University of Washington

  • White Papers // May 2011

    Webcam Image Alignment

    AMOS, The Archive of Many Outdoor Scenes, has been a major project at Washington University. The project focus has been collecting images from webcams all over the world. Images have been logged from thousands of webcams for over 5 years. The large datasets created by AMOS are useful for a...

    Provided By University of Washington

  • White Papers // Dec 2010

    An Inexpensive Robot Platform for Teleoperation and Experimentation

    Most commercially-available robots are either aimed at the research community, or are designed with a single purpose in mind. The extensive hobbyist community has tended to focus on the hardware and the low-level software aspects. The authors claim that there is a need for a low-cost, general-purpose robot, accessible to...

    Provided By University of Washington

  • White Papers // May 2010

    Split and Merge Functions for Supporting Multiple Processing Pipelines in Mercury BLASTN

    Biosequence similarity search is an important application in computational biology. Mercury BLASTN, an FPGA-based implementation of BLAST for DNA, is one of the alternatives for fast DNA sequence comparison. The re-design of BLAST into a streaming application combined with a high-throughput hardware pipeline have enabled Mercury BLAST to emerge as...

    Provided By University of Washington

  • White Papers // May 2010

    Performance Tuning of Streaming Applications Via Search-Space Decomposition

    High-performance streaming applications are typically pipelined and deployed on architecturally diverse (hybrid) systems. Developers of such applications are interested in customizing components used, so as to benefit application performance. The authors present an efficient and automatic technique for design-space exploration of applications in this problem domain. They solve performance tuning...

    Provided By University of Washington

  • White Papers // Nov 2009

    Globally Clocked Magnetic Logic Circuits

    Magnetic spin valve devices enable the design of logic and memory elements that are suitable for use when constructing digital systems. A master-slave flip-flop design is proposed that can be clocked using an externally applied global magnetic field. With an external global clock, the digital system no longer needs to...

    Provided By University of Washington

  • White Papers // Nov 2009

    Scalable Scheduling Policy Design for Open Soft Real-Time Systems

    Open soft real-time systems, such as mobile robots, must respond adaptively to varying operating conditions, while balancing the need to perform multiple mission specific tasks against the requirement that those tasks complete in a timely manner. Setting and enforcing a utilization target for shared resources is a key mechanism for...

    Provided By University of Washington

  • White Papers // Aug 2009

    Enabling a Low-Delay Internet Service Via Built-In Performance Incentives

    The single best-effort service of the Internet struggles to accommodate divergent needs of different distributed applications. Numerous alternative network architectures have been proposed to offer diversified network services. These innovative solutions failed to gain wide deployment primarily due to economic and legacy issues rather than technical shortcomings. The authors' paper...

    Provided By University of Washington

  • White Papers // Aug 2009

    Performance-Engineered Network Overlays for High Quality Interaction in Virtual Worlds

    Overlay hosting systems such as PlanetLab, and cloud computing environments such as Amazon's EC2, provide shared infrastructures within which new applications can be developed and deployed on a global scale. This paper explores how systems of this sort can be used to enable advanced network services and sophisticated applications that...

    Provided By University of Washington

  • White Papers // Aug 2009

    Financial Monte Carlo Simulation on Architecturally Diverse Systems

    Computational finance relies heavily on the use of Monte Carlo simulation techniques. However, Monte Carlo simulation is computationally very demanding. The authors demonstrate the use of architecturally diverse systems to accelerate the performance of these simulations, exploiting both graphics processing units and field-programmable gate arrays. Performance results include a speedup...

    Provided By University of Washington

  • White Papers // Aug 2009

    Verification of Component-Based Distributed Real-Time Systems

    Component-based software architectures enable reuse by separating application-specific concerns into modular components that are shielded from each other and from common concerns addressed by underlying services. Even so, concerns such as invocation rates, execution latencies, deadlines, and concurrency and scheduling semantics still cross-cut component boundaries in many real-time systems. Verification...

    Provided By University of Washington

  • White Papers // Aug 2009

    Modeling Timed Component-Based Real-Time Systems

    Component based middleware helps to facilitate software reuse by separating application-specific concerns into modular components that are shielded from the concerns of other components and from the common concerns addressed by underlying middleware services. In real-time systems, concerns such as invocation rates, execution latencies, deadlines, and concurrency semantics cross-cut multiple...

    Provided By University of Washington

  • White Papers // Aug 2009

    Efficient Fair Algorithms for Message Communication

    A computer network serves distributed applications by communicating messages between their remote ends. Many such applications desire minimal delay for their messages. Beside this efficiency objective, allocation of the network capacity is also subject to the fairness constraint of not shutting off communication for any individual message. Processor Sharing (PS)...

    Provided By University of Washington

  • White Papers // Aug 2009

    Experimental Evaluation of a Coarse-Grained Switch Scheduler

    Modern high performance routers rely on sophisticated interconnection networks to meet ever increasing demands on capacity. Regulating the flow of packets through these interconnects is critical to providing good performance, particularly in the presence of extreme traffic patterns that result in sustained overload at output ports. Previous studies have used...

    Provided By University of Washington

  • White Papers // Aug 2009

    Combined Controllers that Follow Imperfect Input Motions for Humanoid Robots

    Humanoid robots have the potential to become a part of everyday life as their hardware and software challenges are being solved. In this paper, the authors present a system that gets as input a motion trajectory in the form of motion capture data, and produces a controller that controls a...

    Provided By University of Washington

  • White Papers // Jan 2010

    JavaML: A Markup Language for Java Source Code

    The classical plain-text representation of source code is convenient for programmers but requires parsing to uncover the deep structure of the program. While sophisticated software tools parse source code to gain access to the program's structure, many lightweight programming aids such as grep rely instead on only the lexical structure...

    Provided By University of Washington

  • White Papers // Jan 2011

    Denali: A Scalable Isolation Kernel

    The Denali project provides system support for running several mutually distrusting Internet services on the same physical infrastructure. For example, this would enable a developer to push dynamic content into third party hosting infrastructure such as content distribution networks. To accomplish this, the authors propose new kernel architecture called an...

    Provided By University of Washington

  • White Papers // Mar 2010

    The Architecture and Implementation of an Extensible Web Crawler

    Many Web services operate their own Web crawlers to discover data of interest, despite the fact that large scale, timely crawling is complex, operationally intensive, and expensive. In this paper, the authors introduce the extensible crawler, a service that crawls the Web on behalf of its many client applications. Clients...

    Provided By University of Washington