Stanford University

Displaying 1-40 of 728 results

  • White Papers // May 2012

    Channel Capacity Under General Nonuniform Sampling

    This paper develops the fundamental capacity limits of a sampled analog channel under a sub-Nyquist sampling rate constraint. In particular, the authors derive the capacity of sampled analog channels over a general class of time-preserving sampling methods including irregular non-uniform sampling. Their results indicate that the optimal sampling structures extract...

    Provided By Stanford University

  • White Papers // May 2012

    EyeQ: Practical Network Performance Isolation for the Multi-Tenant Cloud

    The shared multi-tenant nature of the cloud has raised serious concerns about its security and performance for high valued services. Of many shared resources like CPU, memory, etc., the network is pivotal for distributed applications. Benign, or perhaps malicious traffic interference between tenants can cause significant performance degradation that hurts...

    Provided By Stanford University

  • White Papers // Apr 2012

    Shannon Meets Nyquist: Capacity Limits of Sampled Analog Channels

    The authors explore two fundamental questions at the intersection of sampling theory and information theory: how is channel capacity affected by sampling below the channel's Nyquist rate, and what sub-Nyquist sampling strategy should be employed to maximize capacity. In particular, they first derive the capacity of sampled analog channels for...

    Provided By Stanford University

  • White Papers // Apr 2012

    Synthesis for Optimal Two-Player Decentralized Control Over TCP Erasure Channels With State Feedback

    Recent advances in communication networks and VLSI have made it possible to provide services remotely. In fact, an increasing number of current services and future deployments, such as distributed database management, grid computing, and the smart grid, are now being built over the cloud, making it inevitable that the control,...

    Provided By Stanford University

  • White Papers // Apr 2012

    Coding Strategies for a Class of Decentralized Control Problems With Limited Communication

    The authors propose a large class of decentralized control problems with non-classical information structure for which a coding strategy is optimal. This class is a generalized version of the hats problem with statistically dependent hat colors where implicit communication via action is allowed. They propose a sufficient condition on the...

    Provided By Stanford University

  • White Papers // Mar 2012

    Optimal Cooperative Control of Dynamically Decoupled Systems

    The authors consider optimal cooperative control problems where multiple dynamically decoupled players cooperate to optimize a coupled objective under limited communication between each player. They present the explicit optimal control in terms of the solutions to a series of Riccati equations, therefore it can be computed in a distributed manner...

    Provided By Stanford University

  • White Papers // Mar 2012

    Achievable Error Exponents in the Gaussian Channel With Rate-Limited Feedback

    The authors investigate the achievable error probability in communication over an AWGN discrete time memoryless channel with noiseless delay-less rate-limited feedback. For the case where the feedback rate RFB is lower than the data rate R transmitted over the forward channel, they show that the decay of the probability of...

    Provided By Stanford University

  • White Papers // Mar 2012

    Identity-Based Encryption Is Secure in the Quantum Random Oracle Model

    The authors give the first proof of security for an identity-based encryption scheme in the quantum random oracle model. This is the first unconditional proof of security for any scheme in this model. Their techniques are quite general and they use them to obtain (unconditional) security proofs for two random...

    Provided By Stanford University

  • White Papers // Mar 2012

    Improved Security for Linearly Homomorphic Signatures: A Generic Framework

    The authors propose a general framework that converts (ordinary) signature schemes having certain properties into linearly homomorphic signature schemes, i.e., schemes that allow authentication of linear functions on signed data. The security of the homomorphic scheme follows from the same computational assumption as is used to prove security of the...

    Provided By Stanford University

  • White Papers // Feb 2012

    Header Space Analysis: Static Checking for Networks

    Today's networks typically carry or deploy dozens of protocols and mechanisms simultaneously such as MPLS, NAT, ACLs and route redistribution. Even when individual protocols function correctly, failures can arise from the complex interactions of their aggregate, requiring network administrators to be masters of detail. The authors' goal is to automatically...

    Provided By Stanford University

  • White Papers // Feb 2012

    Less is More: Trading a Little Bandwidth for Ultra-Low Latency in the Data Center

    Traditional measures of network goodness - goodput, quality of service, fairness - are expressed in terms of bandwidth. Network latency has rarely been a primary concern because delivering the highest level of bandwidth essentially entails driving up latency - at the mean and, especially, at the tail. Recently, however, there...

    Provided By Stanford University

  • White Papers // Jan 2012

    Initial Thoughts on Custom Network Processing Via Waypoint Services

    Network operators want additional functionality from the networks they manage. The current approach to add functionality is to deploy middleboxes. Unfortunately middle-boxes raise concerns regarding robustness, correctness, and efficiency due to their need to be deployed at chokepoints. This paper provides some initial thoughts for solving the middlebox problem in...

    Provided By Stanford University

  • White Papers // Jan 2012

    SCD: A Scalable Coherence Directory With Flexible Sharer Set Encoding

    Large-scale CMPs with hundreds of cores require a directory-based protocol to maintain cache coherence. However, previously proposed coherence directories are hard to scale beyond tens of cores, requiring either excessive area or energy, complex hierarchical protocols, or inexact representations of sharer sets that increase coherence traffic and degrade performance. The...

    Provided By Stanford University

  • White Papers // Jan 2012

    Network Congestion Avoidance Through Speculative Reservation

    Congestion caused by hot-spot traffic can significantly degrade the performance of a computer network. In this paper, the authors present the Speculative Reservation Protocol (SRP), a new network congestion control mechanism that relieves the effect of hot-spot traffic in high bandwidth, low latency, lossless computer networks. Compared to existing congestion...

    Provided By Stanford University

  • White Papers // Jan 2012

    A Methodology for Mapping Multiple Use-Cases Onto Networks on Chips

    A communication-centric design approach, Networks on Chips (NoCs), has emerged as the design paradigm for designing a scalable communication infrastructure for future Systems on Chips (SoCs). As technology advances, the number of applications or use-cases integrated on a single chip increases rapidly. The different use-cases of the SoC have different...

    Provided By Stanford University

  • White Papers // Jan 2012

    Mapping and Configuration Methods for Multi-Use-Case Networks on Chips

    To provide a scalable communication infrastructure for Systems on Chips (SoCs), Networks on Chips (NoCs), a communication centric design paradigm is needed. To be cost effective, SoCs are often programmable and integrate several different applications or use-cases on to the same chip. For the SoC platform to support the different...

    Provided By Stanford University

  • White Papers // Jan 2012

    The Role of SNR in Achieving MIMO Rates in Cooperative Systems

    The authors compare the rate of a multiple-antenna relay channel to the capacity of multiple-antenna systems to characterize the cooperative capacity in different SNR regions. While it is known that in the asymptotic regime, at a high SNR or with a large number of cooperating nodes, cooperative systems lack full...

    Provided By Stanford University

  • White Papers // Jan 2012

    Minimum Expected Distortion in Gaussian Layered Broadcast Coding With Successive Refinement

    A transmitter without Channel State Information (CSI) wishes to send a delay-limited Gaussian source over a slowly fading channel. The source is coded in superimposed layers, with each layer successively refining the description in the previous one. The receiver decodes the layers that are supported by the channel realization and...

    Provided By Stanford University

  • White Papers // Jan 2012

    Service Differentiation in the Internet to Support Multimedia Traffic

    The current best-effort infrastructure in the Internet lacks key characteristics in terms of delay, jitter, and loss, which are required for multimedia applications (voice, video, and data). Recently, significant progress has been made toward specifying the service differentiation to be provided in the Internet for supporting multimedia applications. In this...

    Provided By Stanford University

  • White Papers // Jan 2012

    Architectural Support for the Stream Execution Model on General-Purpose Processors

    There has recently been much interest in stream processing, both in industry (e.g., Cell, NVIDIA G80, ATI R580) and academia (e.g., Stanford Merrimac, MIT RAW), with stream programs becoming increasingly popular for both media and more general-purpose computing. Although a special style of programming called stream programming is needed to...

    Provided By Stanford University

  • White Papers // Oct 2011

    Efficient Parallel Graph Exploration on Multi-Core CPU and GPU

    Graphs are a fundamental data representation that have been used extensively in various domains. In graph-based applications, a systematic exploration of the graph such as a Breadth-First Search (BFS) often serves as a key component in the processing of their massive data sets. In this paper, the authors present a...

    Provided By Stanford University

  • White Papers // Oct 2011

    Reduced-Dimension Multiuser Detection

    The authors present a Reduced-Dimension MultiUser Detector (RD-MUD) structure that significantly decreases the number of required correlation branches at the receiver front-end, while still achieving performance similar to that of the conventional Matched-Filter (MF) bank. RD-MUD exploits the fact that the number of active users is typically small relative to...

    Provided By Stanford University

  • White Papers // Oct 2011

    An Explicit Solution for Optimal Two-Player Decentralized Control Over TCP Erasure Channels With State Feedback

    The authors develop an optimal controller synthesis algorithm for decentralized control problems where control actions are transmitted through TCP-like erasure channels. They consider a simple two-player interconnected linear system and Bernoulli distributed erasure channels. They recast the problem to a centralized Partially Observed Markov Decision Process (POMDP) under the fictitious...

    Provided By Stanford University

  • White Papers // Sep 2011

    Decoupling Datacenter Studies From Access to Large-Scale Applications: A Modeling Approach for Storage Workloads

    The cost and power impact of suboptimal storage configurations is significant in DataCenters (DCs) as inefficiencies are aggregated over several thousand servers and represent considerable losses in capital and operating costs. Designing performance, power and cost-optimized systems requires a deep understanding of target workloads, and mechanisms to effectively model different...

    Provided By Stanford University

  • White Papers // Sep 2011

    Micro-Interactions With NFC-Enabled Mobile Phones

    This paper coins the term micro-interactions to refer to the class of small exchanges between devices that occur almost instantaneously. For example, a mobile payment using Near-Field Communication (NFC) is a micro-interaction. The arrival of NFC on smart phones makes possible a wide array of applications using micro-interactions, from sharing...

    Provided By Stanford University

  • White Papers // Aug 2011

    Buffer Sizing in 802.11 Wireless Mesh Networks

    The authors analyze the problem of buffer sizing for TCP flows in 802.11-based Wireless Mesh Networks. Their objective is to maintain high network utilization while providing low queueing delays. The problem is complicated by the time-varying capacity of the wireless channel as well as the random access mechanism of 802.11...

    Provided By Stanford University

  • White Papers // Aug 2011

    Dynamic Fine-Grain Scheduling of Pipeline Parallelism

    Scheduling pipeline-parallel programs, defined as a graph of stages that communicate explicitly through queues, is challenging. When the application is regular and the underlying architecture can guarantee predictable execution times, several techniques exist to compute highly optimized static schedules. However, these schedules do not admit run-time load balancing, so variability...

    Provided By Stanford University

  • White Papers // Aug 2011

    Black-Box Randomized Reductions in Algorithmic Mechanism Design

    The authors give the first black-box reduction from arbitrary approximation algorithms to truthful approximation mechanisms for a non-trivial class of multi-parameter problems. Specifically, they prove that every welfare-maximization problem that admits an FPTAS and can be encoded as a packing problem also admits a truthful-in-expectation randomized mechanism that is an...

    Provided By Stanford University

  • White Papers // Aug 2011

    On the Role of Mobility for Multi-Message Gossip

    In wireless ad hoc or social networks, a variety of scenarios require agents to share their individual information or resources with each other for mutual benefit. A partial list includes file sharing and rumor spreading, distributed computation and parameter estimation, and scheduling and control. Due to the huge centralization overhead...

    Provided By Stanford University

  • White Papers // Jul 2011

    Time and Cost-Efficient Modeling and Generation of Large-Scale TPCC/TPCE/TPCH Workloads

    Large-scale TPC workloads are critical for the evaluation of datacenter-scale storage systems. However, these workloads have not been previously characterized, in-depth, and modeled in a DC environment. In this paper, the authors categorize the TPC workloads into storage threads that have unique features and characterize the storage activity of TPCC,...

    Provided By Stanford University

  • White Papers // Jul 2011

    Uplink Resource Allocation for Frequency Selective Channels and Fractional Power Control in LTE

    The authors consider the allocation of spectral and power resources every subframe (1 ms) on the uplink of the Long Term Evolution (LTE) wideband Orthogonal Frequency Division Multiple Access (OFDMA) cellular network. System bandwidth is divided into multiple sub-bands. The fractional power control to manage interference is allowed to be...

    Provided By Stanford University

  • White Papers // Jun 2011

    Targeted Malleability: Homomorphic Encryption for Restricted Computations

    The authors put forward the notion of targeted malleability: given a homomorphic encryption scheme, in various scenarios they would like to restrict the homomorphic computations one can perform on encrypted data. They introduced a precise framework, generalizing the foundational notion of non-malleability introduced by Dolev, Dwork, and Naor (SICOMP '00),...

    Provided By Stanford University

  • White Papers // Jun 2011

    Parallelizing Machine Learning - Functionally

    Implementing machine learning algorithms for large data, such as the Web graph and social networks, is challenging. Even though much research has focused on making sequential algorithms more scalable, their running times continue to be prohibitively long. Meanwhile, parallelization remains a formidable challenge for this class of problems, despite frameworks...

    Provided By Stanford University

  • Webcasts // May 2011

    Innovate For America

    The presenter focuses on advancing technology and innovation to unlock national economic growth and prosperity. In this webcast, the presenter challenges students and entrepreneurs to take action now to bring innovation to the healthcare, education and government sectors.

    Provided By Stanford University

  • White Papers // May 2011

    Performance Implications of Age-Based Allocation in On-Chip-Networks

    Age-based priority is a common mechanism used to improve the fairness and Quality-of-Service (QoS) characteristics of interconnection networks. Packet age can provide remote network state information that enables routers to service packets in a globally optimal fashion. In the Network-on-Chip (NoC) setting, age-based allocation is implemented by assigning priorities to...

    Provided By Stanford University

  • Webcasts // May 2011

    The Value Of True Partnerships

    The presenters are serial entrepreneurs who believe in the fundamental power of partnerships. Empowered by working in close collaboration for years, these co-founders have started multiple companies including Patagon, Lemon Bank and Bling Nation. In this webcast, the presenters describe the value of over-communication, the decision process in making a...

    Provided By Stanford University

  • Webcasts // May 2011

    From Stanford To Startup

    In this webcast, the presenters challenge many of the myths surrounding startups and the lives of entrepreneurs. Both the presenters share their first-hand experiences of the entrepreneurial process, including identifying good problems to solve and the value in building simple solutions and minimum viable products.

    Provided By Stanford University

  • White Papers // May 2011

    The Case for Prefetching and Prevalidating TLS Server Certificates

    A key bottleneck in a full TLS handshake is the need to fetch and validate the server certificate before a secure connection can be established. The authors propose a mechanism by which a browser can pre-fetch and pre-validate server certificates so that by the time the user clicks on an...

    Provided By Stanford University

  • Webcasts // May 2011

    Reach Your Escape Velocity

    In this webcast, the presenter discusses how companies can build the escape velocity necessary to move beyond the successes and failures of the past. The presenter argues that when companies focus too much on performance, they miss out on building the power to become the industry leaders that other companies...

    Provided By Stanford University

  • White Papers // Apr 2011

    A Dynamic Programming Algorithm for Decentralized Markov Decision Processes With a Broadcast Structure

    The authors give an optimal dynamic programming algorithm to solve a class of finite-horizon decentralized Markov Decision Processes (MDPs). They consider problems with a broadcast information structure that consists of a central node that only has access to its own state but can affect several outer nodes, while each outer...

    Provided By Stanford University

  • White Papers // Jan 2011

    Monitoring Stream Properties for Continuous Query Processing

    The authors' query processor can be thought of as two separate components: a Query Execution component and a Property Monitoring component. Properties used by the Query Execution component, such as stream characteristics and plan operator behavior, are monitored by the Property Monitoring component. Of course, monitoring of operator behavior would...

    Provided By Stanford University

  • White Papers // Jan 2011

    Vision Paper: Enabling Privacy for the Paranoids

    P3P is a set of standards that allow corporations to declare their privacy policies. Hippocratic Databases have been proposed to implement such policies within a corporation's datastore. From an end-user individual's point of view, both of these rest on an uncomfortable philosophy of trusting corporations to protect his/her privacy. Recent...

    Provided By Stanford University

  • White Papers // Jan 2011

    Two Can Keep a Secret: A Distributed Architecture for Secure Database Services

    Recent trends towards database outsourcing, as well as concerns and laws governing data privacy, have led to great interest in enabling secure database services. Previous approaches to enabling such a service have been based on data encryption, causing a large overhead in query processing. The authors propose a new, distributed...

    Provided By Stanford University

  • White Papers // Oct 2010

    Market Panic On Different Time-Scales

    Cross-sectional signatures of market panic were recently discussed on daily time scales in, extended here to a study of cross-sectional properties of stocks on intraday time scales. The authors confirm specific intraday patterns of dispersion and kurtosis, and find that the correlation across stocks increases in times of panic yielding...

    Provided By Stanford University

  • White Papers // Apr 2011

    Software or Hardware: The Future of Green Enterprise Computing

    Over the last few years, interest in "Green computing" has motivated research into energy-saving techniques for enterprise systems, from network proxies and virtual machine migration to the return of thin clients. This paper tries to answer a possibly contentious question: would the authors be better served by the embarrassingly simple...

    Provided By Stanford University

  • White Papers // May 2009

    Language-Based Isolation of Untrusted JavaScript

    Web sites that incorporate untrusted content may use browser- or language-based methods to keep such content from maliciously altering pages, stealing sensitive information, or causing other harm. The authors study language based methods for filtering and rewriting JavaScript code, using Yahoo! ADSafe and Facebook FBJS as motivating examples. They explain...

    Provided By Stanford University

  • White Papers // Sep 2009

    Isolating JavaScript With Filters, Rewriting, and Wrappers

    The authors study methods that allow web sites to safely combine JavaScript from untrusted sources. If implemented properly, filters can prevent dangerous code from loading into the execution environment, while rewriting allows greater expressiveness by inserting run-time checks. Wrapping properties of the execution environment can prevent misuse without requiring changes...

    Provided By Stanford University

  • White Papers // Jan 2011

    One Torus to Rule Them All: Multidimensional Queries in P2P Systems

    Peer-to-peer systems enable access to data spread over an extremely large number of machines. Most P2P systems support only simple lookup queries. However, many new applications, such as P2P photo sharing and massively multi-player games, would benefit greatly from support for multi-dimensional range queries. The authors show how such queries...

    Provided By Stanford University

  • White Papers // Feb 2011

    NS2 & Networking Using Desktop Virtualization: An Application of Virtual Box

    Information technology has dominated almost all the areas of human life now. Education is not exception in this. How to utilize the technology for imparting the education effectively and efficiently is more important rather than just using the technology. Often users must access applications in Operating System (OS) environments other...

    Provided By Stanford University

  • White Papers // Dec 2010

    Bankruptcy As Implicit Health Insurance

    This paper examines the interaction between health insurance and the implicit insurance that people have because they can file (or threaten to file) for bankruptcy. With a simple model that captures key institutional features, the author demonstrates that the financial risk from medical shocks is capped by the assets that...

    Provided By Stanford University

  • White Papers // Nov 2008

    Wealthier But Not Much Healthier: Effects Of A Health Insurance Program For The Poor In Mexico

    In 2002 the Mexican government began a very large expansion of government-funded healthcare for the poor - specifically, people not employed in the formal sector. The program, Seguro Popular (SP), was rolled out sequentially across different areas in Mexico. This paper uses the variation in program intensity over time and...

    Provided By Stanford University

  • White Papers // Jun 2011

    Targeted Malleability: Homomorphic Encryption for Restricted Computations

    The authors put forward the notion of targeted malleability: given a homomorphic encryption scheme, in various scenarios they would like to restrict the homomorphic computations one can perform on encrypted data. They introduced a precise framework, generalizing the foundational notion of non-malleability introduced by Dolev, Dwork, and Naor (SICOMP '00),...

    Provided By Stanford University

  • White Papers // Apr 2011

    CDE: Using System Call Interposition to Automatically Create Portable Software Packages

    It can be painfully difficult to take software that runs on one person's machine and get it to run on another machine. Online forums and mailing lists are filled with discussions of users' troubles with compiling, installing, and configuring software and their myriad of dependencies. To eliminate this dependency problem,...

    Provided By Stanford University

  • White Papers // Oct 2010

    Rehearse: Helping Programmers Adapt Examples by Visualizing Execution and Highlighting Related Code

    Instructive example code is a central part of programming. Web search enables programmers to quickly locate relevant examples. However, existing code editors offer little support for helping users interactively explore examples. This paper proposes that effective use of examples hinges on the programmer's ability to quickly identify a small number...

    Provided By Stanford University

  • White Papers // Apr 2009

    Example-Centric Programming: Integrating Web Search Into the Development Environment

    The ready availability of online source code examples has changed the cost structure of programming by example modification. However, current search tools are wholly separate from editing tools. What benefits might be realized by integrating them? This paper describes the design, implementation, and evaluation of Blueprint, a tool that integrates...

    Provided By Stanford University

  • White Papers // Apr 2009

    Run-Time Enforcement of Secure JavaScript Subsets

    Many Web-based applications such as advertisement, social networking and online shopping benefit from the interaction of trusted and unstrusted content within the same page. If the untrusted content includes JavaScript code, it must be prevented from maliciously altering pages, stealing sensitive information, or causing other harm. The authors study filtering...

    Provided By Stanford University

  • White Papers // Mar 2010

    Making Aggregation Work in Uncertain and Probabilistic Databases

    The authors describe how aggregation is handled in the Trio system for uncertain and probabilistic data. Because "Exact" aggregation in uncertain databases can produce exponentially-sized results, they provide three alternatives: a low bound on the aggregate value, a high bound on the value, and the expected value. These variants return...

    Provided By Stanford University

  • White Papers // Jul 2008

    Should Ad Networks Bother Fighting Click Fraud?

    Suppose an ad network decides that a given click-through is invalid (or "Fraudulent"). The implication is that the ad network will not bill the advertiser for that click-through. On the other hand, if the ad network decides that the click-through was valid, they could charge full price. Therefore, arguably, the...

    Provided By Stanford University

  • White Papers // May 2008

    Privacy, Preservation and Performance: The 3 P's of Distributed Data Management

    Privacy, Preservation and Performance ("3 P's") are central design objectives for secure distributed data management systems. However, these objectives tend to compete with one another. This paper introduces a model for describing distributed data management systems, along with a framework for measuring privacy, preservation and performance. The framework enables a...

    Provided By Stanford University

  • White Papers // Jun 2008

    Data Modifications and Versioning in Trio

    Motivated by a diverse set of applications including data integration, deduplication, scientific data management, information extraction, and others, the Trio project at Stanford has been studying the combination of uncertainty and lineage as the basis for a new type of database management system. In this paper, the authors address data...

    Provided By Stanford University

  • White Papers // Jan 2011

    On the Relationships Between Notions of Simulation-Based Security

    Several compositional forms of simulation-based security have been proposed in the literature, including universal composability, black-box simulatability, and variants thereof. These relations between a protocol and an ideal functionality are similar enough that they can be ordered from strongest to weakest according to the logical form of their definitions. However,...

    Provided By Stanford University

  • White Papers // Nov 2008

    KLEE: Unassisted and Automatic Generation of High-Coverage Tests for Complex Systems Programs

    The authors present a new symbolic execution tool, KLEE, capable of automatically generating tests that achieve high coverage on a diverse set of complex and environmentally-intensive programs. They used KLEE to thoroughly check all 89 stand-alone programs in the GNU COREUTILS utility suite, which form the core user-level environment installed...

    Provided By Stanford University

  • White Papers // Aug 2010

    The Future of the Internet is Coordination

    The key functionality of a Coordinated Internet would be that the Internet actively watches what people do (analogous to search completion on desktops today), correlates these activities, and actively notifies people when and how their current tasks affect and are affected by the activities of other people. Such a Coordinated...

    Provided By Stanford University

  • White Papers // Feb 2011

    Enterprise Coordination on the Internet

    Enterprises are now connected internally and externally to other Enterprises via the Internet in ways that are increasingly difficult to manage, especially as these interconnections become more dynamic. Current methods of coordinating the effects of change as they propagate through these networks of connections are not likely to scale. What...

    Provided By Stanford University

  • White Papers // Apr 2009

    Planning Process Instances With Web Services

    Planning is an important approach to developing complex applications composed of web services, based upon semantic annotations of these services. Despite numerous publications in recent years, the problems considered in the literature typically do not require planning as it has been well-defined in computer science. This could lead to confusion...

    Provided By Stanford University

  • White Papers // Jan 2011

    Complex Instruction and Software Library Mapping for Embedded Software Using Symbolic Algebra

    With growing demand for embedded multimedia applications, time to market of embedded software has become a crucial issue. As a result, embedded software designers often use libraries that have been pre-optimized for a given processor to achieve higher code quality. Unfortunately, current software design methodology often leaves high-level arithmetic optimizations...

    Provided By Stanford University

  • White Papers // Sep 2009

    Cycle-Accurate Simulation of Energy Consumption in Embedded Systems

    This paper presents a methodology for cycle-accurate simulation of energy dissipation in embedded systems. The ARM Ltd instruction-level cycle-accurate simulator is extended with energy models for the processor the L2 cache, the memory the interconnect and the DC-DC converter. A SmartBadge which can be seen as an embedded system consisting...

    Provided By Stanford University

  • White Papers // Sep 2009

    Event-Driven Power Management of Portable Systems

    The policy optimization problem for dynamic power management has received considerable attention in the recent past. The authors formulate policy optimization as a constrained optimization problem on continuous-time Semi-Markov Decision Processes (SMDP). SMDPs generalize the stochastic optimization approach based on discrete-time Markov Decision Processes (DTMDP) presented in the earlier work...

    Provided By Stanford University

  • White Papers // Sep 2009

    Optimally Tuned Iterative Reconstruction Algorithms for Compressed Sensing

    The authors conducted an extensive computational experiment, lasting multiple CPU-years, to optimally select parameters for two important classes of algorithms for finding sparse solutions of underdetermined systems of linear equations. They make the optimally tuned implementations available; they run 'Out of the box' with no user tuning: It is not...

    Provided By Stanford University

  • White Papers // Mar 2011

    Fast Crash Recovery in RAMCloud

    RAMCloud is a DRAM-based storage system that provides inexpensive durability and availability by recovering quickly after crashes, rather than storing replicas in DRAM. RAMCloud scatters backup data across hundreds or thousands of disks, and it harnesses hundreds of servers in parallel to reconstruct lost data. The system uses a log-structured...

    Provided By Stanford University

  • White Papers // Jun 2010

    Managing State for Ajax-Driven Web Components

    Ajax-driven Web applications require state to be maintained across a series of server requests related to a single Web page. This conflicts with the stateless approach used in most Web servers and makes it difficult to create modular components that use Ajax. The authors implemented and evaluated two approaches to...

    Provided By Stanford University

  • White Papers // Dec 2009

    The Case for RAMClouds: Scalable High-Performance Storage Entirely in DRAM

    Disk-oriented approaches to online storage are becoming increasingly problematic: they do not scale gracefully to meet the needs of large-scale Web applications, and improvements in disk capacity have far outstripped improvements in access latency and bandwidth. This paper argues for a new approach to datacenter storage called RAMCloud, where information...

    Provided By Stanford University

  • White Papers // Dec 2008

    Learning Bounded Treewidth Bayesian Networks

    With the increased availability of data for complex domains, it is desirable to learn Bayesian network structures that are sufficiently expressive for generalization while at the same time allow for tractable inference. While the method of thin junction trees can, in principle, be used for this purpose, its fully greedy...

    Provided By Stanford University

  • White Papers // Feb 2010

    Kronecker Graphs: An Approach to Modeling Networks

    How can people generate realistic networks? In addition, how can they do so with a mathematically tractable model that allows for rigorous analysis of network properties? Real networks exhibit a long list of surprising properties: Heavy tails for the in- and out-degree distribution, heavy tails for the eigen-values and eigenvectors,...

    Provided By Stanford University

  • White Papers // Sep 2009

    Counter Braids

    In this paper the authors summarize recent work they have done on the design of a novel counter architecture for estimating flow sizes in high-speed networks, the algorithms and the theory that goes along with it. This note will provide a description of the problem and the authors' approach. It...

    Provided By Stanford University

  • White Papers // Jan 2011

    Bloom Filters: Design Innovations and Novel Applications

    Bloom filters have been very interesting in networking because they enable the high speed, low cost implementation of various hardware algorithms. The paper introduces the idea of variable-length signatures, as opposed to the current practice of using fixed-length signatures. This idea naturally enables Bloom filters to perform flow deletions, a...

    Provided By Stanford University

  • White Papers // Mar 2010

    CHOKe a Stateless Mechanism for Providing Quality of Service in the Internet

    The authors investigate the problem of providing a fair bandwidth allocation to each of n flows that share the outgoing link of a congested router. The buffer at the outgoing link is a simple FIFO, shared by packets belonging to the n flows. They devise a simple packet dropping scheme,...

    Provided By Stanford University

  • White Papers // Jan 2011

    Optimal Throughput-Delay Scaling in Wireless Networks - Part II: Constant-Size Packets

    In Part I the authors characterized the optimal throughput-delay trade-off in static wireless networks as D(n) = ?(nT(n)), where D(n) and T(n) are the average packet delay and throughput in a network of n nodes, respectively. While this trade-off captures the essential network dynamics, packets need to scale down with...

    Provided By Stanford University

  • White Papers // Jan 2011

    Optimal Throughput-Delay Scaling in Wireless Networks - Part I: The Fluid Model

    A wireless network consists of a collection of nodes, each capable of transmitting to or receiving from other nodes. When a node transmits to another node, it creates interference for other nodes in its vicinity. When several nodes transmit simultaneously, a receiver can successfully receive the data sent by the...

    Provided By Stanford University

  • White Papers // Jan 2011

    The CQL Continuous Query Language: Semantic Foundations and Query Execution

    CQL, a Continuous Query Language, is supported by the STREAM prototype Data Stream Management System at Stanford. CQL is an expressive SQL-based declarative language for registering continuous queries against streams and updatable relations. The authors begin by presenting an abstract semantics that relies only on "Black box" mappings among streams...

    Provided By Stanford University