- Parallel Computing and Optimization Techniques
- Advanced Data Storage Technologies
- Embedded Systems Design Techniques
- Distributed and Parallel Computing Systems
- Wireless Networks and Protocols
- Interconnection Networks and Systems
- Advanced MIMO Systems Optimization
- Cloud Computing and Resource Management
- Cooperative Communication and Network Coding
- Mobile Ad Hoc Networks
- Internet Traffic Analysis and Secure E-voting
- Distributed systems and fault tolerance
- Caching and Content Delivery
- Wireless Communication Networks Research
- Cognitive Radio Networks and Spectrum Sensing
- Advanced Wireless Network Optimization
- Network Security and Intrusion Detection
- Opportunistic and Delay-Tolerant Networks
- Millimeter-Wave Propagation and Modeling
- Radiation Effects in Electronics
- Network Traffic and Congestion Control
- Software-Defined Networks and 5G
- Low-power high-performance VLSI design
- Green IT and Sustainability
- Power Line Communications and Noise
University of Colorado Boulder
2014-2025
University of Colorado System
2010-2024
Shandong University
2022
Institute of Engineering
2020
United States Military Academy
2008
United States Department of Defense
2007
University of Illinois System
2003
University of California, Santa Barbara
2003
University of Illinois Urbana-Champaign
1986-1988
Article Share on Anonymous Usage of Location-Based Services Through Spatial and Temporal Cloaking Authors: Marco Gruteser View Profile , Dirk Grunwald Authors Info & Claims MobiSys '03: Proceedings the 1st international conference Mobile systems, applications servicesMay 2003Pages 31–42https://doi.org/10.1145/1066116.1189037Published:05 May 2003Publication History 1,618citation6,645DownloadsMetricsTotal Citations1,618Total Downloads6,645Last 12 Months247Last 6 weeks14 Get Citation AlertsNew...
Prefetching is one approach to reducing the latency of memory operations in modern computer systems. In this paper, we describe Markov prefetcher. This prefetcher acts as an interface between on-chip and off-chip cache, can be added existing designs. The distinguished by prefetching multiple reference predictions from subsystem, then prioritizing delivery those references processor.This design results a system that provides good coverage, accurate produces timely effectively used processor....
Branch prediction has enabled microprocessors to increase instruction level parallelism (ILP) by allowing programs speculatively execute beyond control boundaries. Although speculative execution is essential for increasing the instructions per cycle (IPC), it does come at a cost. A large amount of unnecessary work results from wrong-path entering pipeline due branch misprediction. Results generated with SimpleScalar tool set using 4-way issue and various predictors show an overhead 16% 105%...
Tor has become one of the most popular overlay networks for anonymizing TCP traffic. Its popularity is due in part to its perceived strong anonymity properties and relatively low latency service. Low achieved through Tor's ability balance traffic load by optimizing router selection probabilistically favor routers with high bandwidth capabilities.
In this paper we provide a thorough and up to date survey of path loss prediction methods, spanning more than 60 years fairly continuous research. These methods take variety approaches modeling the signal attenuation between wireless transceivers: purely theoretical models, empirically fitted (often statistical) deterministic ray-optical measurement-directed methods. Our work here extends updates excellent, but now dated prior surveys important field. We new taxonomy for reasoning about...
We present a vision of the future emergency management that better supports inclusion activities and information from members public during disasters mass events. Such relies on integration multiple subfields computer science, commitment to an understanding domain application. It hopes grid/cyberinfrastructure-enabled makes use social software. However, in contrast how is often understood, it aims push beyond idea monitoring on-line activity, instead focuses understudied but critical aspect...
The declining costs of commodity disk drives is rapidly changing the economics deploying large amounts online or near-line storage. Conventional mass storage systems use either high performance RAID clusters, automated tape libraries a combination and disk. In this paper, we analyze an alternative design using massive arrays idle disks, MAID. We argue that organization provides densities matching exceeding those with similar to arrays. Moreover, show effective power management individual...
Pocket computers are beginning to emerge that provide sufficient processing capability and memory capacity run traditional desktop applications operating systems on them. The increasing demand placed these by software is competing against the continuing trend in design of low-power microprocessors towards amount computation per unit energy. Consequently, spite advances circuit design, microprocessor likely continue account for a significant portion overall power consumption pocket...
In this paper we propose a cache design that provides the same miss rate as two-way set associative cache, but with an access time closer to direct-mapped cache. As other designs, traditional is conceptually partitioned into multiple banks, and blocks in each are probed, or examined, sequentially. Other designs either probe fixed order add extra delay path for all accesses. We use prediction sources guide examination, reducing amount of searching thus average latency. A variety accurate...
The declining costs of commodity disk drives is rapidly changing the economics deploying large amounts online or near-line storage. Conventional mass storage systems use either high performance RAID clusters, automated tape libraries a combination and disk. In this paper, we analyze an alternative design using massive arrays idle disks, MAID. We argue that organization provides densities matching exceeding those with similar to arrays. Moreover, show effective power management individual...
Modern computer architectures increasingly depend on mechanisms that estimate future control flow decisions to increase performance. Mechanisms such as speculative execution and prefetching are becoming standard architectural rely prediction prefetch speculatively execute instructions. At the same time, programmers turning object-oriented languages their productivity. These commonly use run time dispatching implement object polymorphism. Dispatching is usually implemented using an indirect...
In this paper we analyze the efficacy of basic path loss models at predicting median in urban environments. We attempt to bound practical error these and look how they may hinder wireless applications, particular dynamic spectrum access networks. This analysis is made using a large set measurements from production networks two US cities. are able show quantitatively what many experienced radio engineers understand: perform poorly even relatively simple outdoor environments little use aside...
In this paper we present results from the first application of robust geostatistical modeling techniques to radio environment and coverage mapping wireless networks. We perform our analysis these methods with a case study 2.5 GHz WiMax network at University Colorado, Boulder. Drawing experiences, propose several new extensions basic theory that are necessary for use in application. also derive set best practices discuss potential areas future work. find approach is feasible produces maps...
Although central processor speeds continues to improve, improvements in overall system performance are increasingly hampered by memory latency, especially for pointer-intensive applications. To counter this loss of performance, numerous data and instruction prefetch mechanisms have been proposed. Recently, several proposals posited a memory-side prefetcher; typically, these prefetchers involve distinct that executes program slice would effectively needed the primary program. Alternative...
Prefetching is one approach to reducing the latency of memory operations in modern computer systems. In this paper, we describe Markov prefetcher. This prefetcher acts as an interface between on-chip and off-chip cache can be added existing designs. The distinguished by prefetching multiple reference predictions from subsystem, then prioritizing delivery those references processor. design results a system that provides good coverage, accurate, produces timely effectively used We also...
Modern processors improve instruction level parallelism by speculation. The outcome of data and control decisions is predicted, the operations are speculatively executed only committed if original predictions were correct. There a number other ways that processor resources could be used, such as threading or eager execution. As use speculation increases, we believe more will need some form to balance benefits against possible activities.Confidence estimation one technique can exploited...
Branch prediction has enabled microprocessors to increase instruction level parallelism (ILP) by allowing programs speculatively execute beyond control boundaries. Although speculative execution is essential for increasing the instructions per cycle (IPC), it does come at a cost. A large amount of unnecessary work results from wrong-path entering pipeline due branch misprediction. Results generated with SimpleScalar tool set using 4-way issue and various predictors show an overhead 16% 105%...
Software-defined/cognitive radio has recently made the jump from a purely research driven endeavor to one that is now being commercially. Such radios offer promise of spectrum agility and re-configurability through flexibility at MAC physical layers. In wireless domain, it been shown hybrid-MAC layer algorithms can lead improved overall performance in varying network conditions. A hybrid uses CSMA low-contention periods switches TDMA high-contention outperform or individually. However, such...
This work was motivated by a discussion that two of the coauthors (computer science professors) had with other coauthor (a law professor and former computer crime Trial Attorney at U.S. Department Justice), in which it pointed out some network measurements scientists were thinking making might potentially violate Federal laws.
Deployments of wireless LANs consisting hundreds 802.11 access points with a large number users have been reported in enterprises as well college campuses. However, due to the unreliable nature links, frequently encounter degraded performance and lack coverage. This problem is even worse unplanned networks, such numerous deployed by homeowners. Existing approaches that aim diagnose these problems are inefficient because they troubleshoot at too high level, unable distinguish among root...
We present a vision of the future emergency management that better supports inclusion activities and information from members public during disasters mass events. Such relies on integration multiple subfields computer science, commitment to an understanding domain application. It hopes grid/cyberinfrastructure-enabled makes use social software. However, in contrast how is often understood, it aims push beyond idea monitoring on-line activity, instead focuses understudied but critical aspect...