Jimali Software Engineering

Circuit-level timing speculation has been proposed as a technique to reduce dependence on design margins, eliminating power and performance overheads. Recent work has proposed microarchitectural methods to dynamically detect and recover from timing errors in processor logic. This work has not evaluated or exploited the disparity of error rates at the level of static instructions. In this paper, we demonstrate pronounced locality in error rates at the level of static instructions. We propose timing error prediction to dynamically anticipate timing errors at the instruction-level and reduce the costly recovery penalty. This allows us to achieve 43.6% power savings when compared to a baseline policy and incurs only 6.9% performance penalty.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=1677b5c5b6f9935b15be049629e2e9fbp=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=1677b5c5b6f9935b15be049629e2e9fbp=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Partial bitstream relocation (PBR) on FPGAs has been gaining attention in recent years as a potentially promising technique to scale parallelism of accelerator architectures at run time, enhance fault tolerance, etc. PBR techniques to date have focused on reading inactive bitstreams stored in memory, on-chip or off-chip, whose contents are generated for a specific partial reconfiguration region (PRR) and modified on demand for configuration into a PRR at a different location. As an alternative, we propose a PRR-PRR relocation technique to generate source and destination addresses, read the bitstream from an active PRR (source) in a non-intrusive manner, and write it to destination PRR. We describe two options of realizing this on Xilinx Virtex 4 FPGAs: (a) hardware-based accelerated relocation circuit (ARC) and (b) a software solution executed on Microblaze. A comparative performance analysis to highlight the speed-up obtained using ARC is presented. For real test cases, performance of our implementations are compared to estimated performances of two state of the art methods.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=e1ec1ad431012fb1324755eb8419e903p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=e1ec1ad431012fb1324755eb8419e903p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Process variations in advanced nodes introduce significant core-to-core performance differences in single-chip multi-core architectures. Isolating each core with its own frequency and voltage island helps improving the performance of the multi-core architecture by operating at the highest frequency possible rather than operating all the cores at the frequency of the slowest core. However, inter-core communication suffers from additional cross-clock-domain latencies that can offset the performance benefits. This work proposes the concept of the configurable, variable-size frequency and voltage domain, and it is described in the context of a tile-based, massive multi-core architecture.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=78a345475a3149cc3d2494fdb8e1f632p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=78a345475a3149cc3d2494fdb8e1f632p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

The well-known drawbacks imposed by lock-based synchronization have forced researchers to devise new alternatives for concurrent execution, of which transactional memory is a promising one. Extensive research has been carried out on Software Transaction Memory (STM), most of all concentrated on program performance, leaving unattended other metrics of great importancel like energy consumption. This letter presents a thorough evaluation of energy consumption in a state-of-the-art STM. We show that energy and performance results do not always follow the same trend and, therefore, it might be appropriate to consider different strategies depending on the focus of the optimization. We also introduce a novel strategy based on dynamic voltage and frequency scaling for contention managers, revealing important energy and energy-delay product improvements in high-contended scenarios. This work is a first study towards a better understanding of the energy consumption behavior of STM systems, and could prompt STM designers to research new optimizations in this area, paving the way for an energy-aware transactional memory.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=aecf4c1bace1ac7dd95757620c8ec519p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=aecf4c1bace1ac7dd95757620c8ec519p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

While modern processors offer a wide spectrum of software-controlled power modes, most datacenters only rely on Dynamic Voltage and Frequency Scaling (DVFS, a.k.a. P-states) to achieve energy efficiency. This paper argues that, in the case of datacenter workloads, DVFS is not the only option for processor power management. We make the case for per-core power gating (PCPG) as an additional power management knob for multi-core processors. PCPG is the ability to cut the voltage supply to selected cores, thus reducing to almost zero the leakage power for the gated cores. Using a testbed based on a commercial 4-core chip and a set of real-world application traces from enterprise environments, we have evaluated the potential of PCPG. We show that PCPG can significantly reduce a processor's energy consumption (up to 40%) without significant performance overheads. When compared to DVFS, PCPG is highly effective saving up to 30% more energy than DVFS. When DVFS and PCPG operate together they can save up to almost 60%.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=b109eaa7b639cb6e9f014e36b016233ep=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=b109eaa7b639cb6e9f014e36b016233ep=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Operand register files are small, inexpensive register files that are integrated with function units in the execute stage of the pipeline, effectively extending the pipeline operand registers into register files. Explicit operand forwarding lets software opportunistically orchestrate the routing of operands through the forwarding network to avoid writing ephemeral values to registers. Both mechanisms let software capture short-term reuse and locality close to the function units, improving energy efficiency by allowing a significant fraction of operands to be delivered from inexpensive registers that are integrated with the function units. An evaluation shows that capturing operand bandwidth close to the function units allows operand registers to reduce the energy consumed in the register files and forwarding network of an embedded processor by 61%, and allows explicit forwarding to reduce the energy consumed by 26%.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=18c3ded83e67f76dd29465c825ecf491p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=18c3ded83e67f76dd29465c825ecf491p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Fast and accurate simulation of multicore systems requires a parallelized simulator. This paper describes a novel method to build cycle-accurate-capable and parallelizable functional-first simulators of multicore targets.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=32d9e09b58e1e80dd82b4990c3be26abp=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=32d9e09b58e1e80dd82b4990c3be26abp=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

IEEE Computer Architecture Letters

Existing work on placing additional relay nodes in wireless sensor networks to improve network connectivity typically assumes homogeneous wireless sensor nodes with an identical transmission radius. In contrast, this paper addresses the problem of deploying relay nodes to provide fault-tolerance with higher network connectivity in {\em heterogeneous} wireless sensor networks, where sensor nodes possess different transmission radii. Such problems can be categorized as: (1) {\em full} fault-tolerance, which aims to deploy a minimum number of relay nodes to establish $k$ $(k \geq 1)$ vertex-disjoint paths between every pair of sensor and/or relay nodes; (2) {\em partial} fault-tolerance, which aims to deploy a minimum number of relay nodes to establish $k$ $(k \geq 1)$ vertex-disjoint paths only between every pair of sensor nodes. Due to the different transmission radii of sensors, these problems are further complicated by the existence of two different kinds of communication paths, namely {\em two-way} paths, along which wireless communications exist in both directions; and {\em one-way} paths, along which wireless communications exist in only one direction. This paper comprehensively analyzes the range of problems introduced by the different levels of fault-tolerance coupled with the different types of path, and presents approximation algorithms.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=a4a04559e7829d820c2817da1f5cb590p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=a4a04559e7829d820c2817da1f5cb590p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Recently, there has been a growing interest of using network coding to improve the performance of wireless networks, for example, authors of \cite{xor} proposed the practical wireless network coding system called COPE, which demonstrated the throughput gain achieved by network coding. However, COPE has two fundamental limitations: (a) the coding opportunity is crucially dependent on the established routes; (b) the coding structure in COPE is limited within a two-hop region only. The aim of this paper is to overcome these limitations. In particular, we propose DCAR, the Distributed Coding-Aware Routing mechanism which enables (1) the discovery for available paths between a given source and destination, and (2) the detection for potential network coding opportunities over much wider network region. On interesting result is that DCAR has the capability to discover high throughput paths with coding opportunities while conventional wireless network routing protocols fail to do so. In addition, DCAR can detect coding opportunities on the entire path, thus eliminating the "two-hop" coding limitation in COPE. We also propose a novel routing metric called Coding-aware Routing Metric (CRM) which facilitates the performance comparison between "coding-possible" and "coding-impossible" paths. We implement the DCAR system in ns-2 and carry out extensive evaluation.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=f2334e7a2a34133f744d9560ff44f8a4p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=f2334e7a2a34133f744d9560ff44f8a4p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Existing code update protocols for reprogramming nodes in a sensor network are either unsuitable or inefficient when used in a mobile environment. In this paper, we propose ReMo, an energy efficient, multihop reprogramming protocol for mobile sensor networks. Without making any assumptions on the location of nodes, ReMo uses the LQI and RSSI measurements of received packets to estimate link qualities and relative distances with neighbors in order to select the best node for code exchange. The protocol is based on a probabilistic broadcast paradigm with the mobile nodes smoothly modifying their advertisement transmission rates based on the dynamic changes in network density, thereby saving valuable energy. Contrary to previous protocols, ReMo downloads pages regardless of their order, thus, exploiting the mobility of the nodes and facilitating a fast transfer of the code. Our simulation results show significant improvement in reprogramming time and number of message transmissions over other existing protocols under different settings of network mobility. Our implementation results of ReMo on a testbed of SunSPOTs also showcase its better performance than existing reprogramming protocols in terms of transfer time and number of message transmissions.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=8e7023ca19af52ec3ea6cf5f176874a8p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=8e7023ca19af52ec3ea6cf5f176874a8p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

The key feature of many emerging pervasive applications is to proactively provide services to mobile individuals. One major challenge in providing users with proactive services lies in continuously monitoring users#x2019; context based on numerous sensors in their PAN/BAN environments. The context monitoring in such environments imposes heavy workloads on mobile devices and sensor nodes with limited computing and battery power. We present SeeMon, a scalable and energy-efficient context monitoring framework for sensor-rich, resource-limited mobile environments. Running on a personal mobile device, SeeMon effectively performs context monitoring involving numerous sensors and applications. On top of SeeMon, multiple applications on the mobile device can proactively understand users#x2019; contexts and react appropriately. This paper proposes a novel context monitoring approach that provides efficient processing and sensor control mechanisms. We implement and test a prototype system on two mobile devices: a UMPC and a wearable device with a diverse set of sensors. Example applications are also developed based on the implemented system. Experimental results show that SeeMon achieves a high level of scalability and energy efficiency.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=81d4e9810422931502ad0609282b86d4p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=81d4e9810422931502ad0609282b86d4p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Many recent advances in MAC protocols for wireless sensor networks have been proposed to reduce idle listening, an energy wasteful state of the radio. Low-Power-Listening (LPL) protocols transmit packets for t_i s (the "inter-listening interval"), thereby allowing nodes to sleep for long periods of time between channel probes. The inter-listening interval as well as the particular type of LPL protocol should be well matched to the network conditions. In this paper, we propose network-aware adaptation of the specific succession of repeated packets over the t_i interval (the "MAC schedule"), which yields significant energy savings. Moreover, some LPL protocols interrupt communication between the sender and the receiver after the data packet has been successfully received. We propose a new and simple adaptation of the "transmit / receive schedule" to synchronize nodes on a slowly changing path so that energy consumption and delay are further reduced, at no cost of overhead in most cases. Our results show that using network-aware adaptation of the MAC schedule provides up to 30% increase in lifetime for different traffic scenarios. Additional adaptation of the transmit / receive schedule to automatically synchronize the nodes can reduce packet delivery delays by up to 50%, providing an additional decrease in energy consumption of 18%br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=eb85e2b4b599706138c10a3485335f30p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=eb85e2b4b599706138c10a3485335f30p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

In recent years, multiple power saving (PS) protocols have been proposed in the 802.11 standards to save energy for mobile devices. Many works have been carried out on testbeds or simulation platforms to evaluate their performances. However, there is a lack of accurate theoretical models to analyze the performance for these protocols. In an effort to fill this gap, we present a Markov chain based model to analytically study these PS protocols, with its focus on multicast services. The proposed model successfully captures the key characteristic of the power saving systems: the data delivery procedure starts periodically at the previously negotiated time, but ends at a rather random time with its distribution depending on the ending time of data delivery in the last delivery period and the the arrival rate of incoming traffic. Under the poisson assumption for incoming traffic and in light to moderate traffic loads, the amount of data delivered between consecutive delivery periods possesses the Markov property, which builds up our Markov chain model. For incoming traffic with long range dependence, a multi-state Markov Modulated Poisson Process (MMPP) is used to approximate the traffic, making the model valid in more general cases.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=e03e211e4e707eeea257018ccbc979b6p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=e03e211e4e707eeea257018ccbc979b6p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Location and inter-sensor distance estimations are important functions for the operation of wireless sensor networks, especially when protocols can benefit from the distance information prior to network deployment. The maximum multihop distance that can be covered in a given number of hops in a sensor network is one such parameter related with coverage area, delay, and minimal multihop transmission energy consumption estimations. In randomly deployed sensor networks, inter-sensor distances are random variables. Hence, their evaluations require probabilistic methods, and distance models should involve investigation of distance distribution functions. Current literature on analytical modeling of the maximum distance distribution is limited to one-dimensional networks using the Gaussian pdf. However, determination of the maximum multihop distance distribution in two dimensional networks is a quite complex problem. Furthermore, distance distributions in two dimensional networks are not accurately modeled by the Gaussian pdf. Hence, we propose a greedy method of distance maximization and evaluate the distribution of the obtained multihop distance through analytical approximations and simulations.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=c66faa4b07720bafa8885528e8399780p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=c66faa4b07720bafa8885528e8399780p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Emerging dual-mode phones incorporate a Wireless LAN (WLAN) interface along with the traditional cellular interface. The additional benefits of the WLAN interface are, however, likely to be outweighed by its greater rate of energy consumption. This is especially of concern when real-time applications, that result in continuous traffic, are involved. WLAN radios typically conserve energy by staying in sleep mode. With real-time applications like Voice over Internet Protocol (VoIP), this can be challenging since packets delayed above a threshold are lost. Moreover, the continuous nature of traffic makes it difficult for the radio to stay in the lower power sleep mode enough to reduce energy consumption significantly. In this work we propose the GreenCall algorithm to derive sleep/wakeup schedules for the WLAN radio to save energy during VoIP calls while ensuring that application quality is preserved within acceptable levels of users. We evaluate GreenCall on commodity hardware and study its performance over diverse network paths and describe our experiences in the process. We further extensively investigate the effect of different application parameters on possible energy savings through trace-based simulations. We show that, in spite of the interactive, real-time nature of voice, energy consumption during calls can be reduced by close to 80% in most instances.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=f68adb0d90484dffb12d90a856275d93p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=f68adb0d90484dffb12d90a856275d93p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Localization is an essential and important research issue in wireless sensor networks (WSNs). Most localization schemes focus on static sensor networks. However, mobile sensors are required in some applications such that the sensed area can be enlarged. As such, a localization scheme designed for mobile sensor networks is necessary. In this paper, we propose a localization scheme to improve the localization accuracy of previous work. In this proposed scheme, the normal nodes without location information can estimate their own locations by gathering the positions of location-aware nodes (anchor nodes) and the one-hop normal nodes whose locations are estimated from the anchor nodes. In addition, we propose a scheme that predicts the moving direction of sensor nodes to increase localization accuracy. Simulation results show that the localization error in our proposed scheme is lower than the previous schemes in various mobility models and moving speeds.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=b8d2cb56d3bbd59d363a1f0300d2cee8p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=b8d2cb56d3bbd59d363a1f0300d2cee8p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

In this paper, a novel scheme for Cognitive Radio (CR) spectrum sensing in Medium Access Control (MAC) layer, called Extended Knowledge-Based Reasoning (EKBR), is proposed. The target of EKBR is to improve the fine sensing efficiency by jointly considering a number of network states and environmental statistics, including fast sensing results, short-term statistical information, channel quality, data transmission rate, and channel contention characteristics. This is for a better estimation on the optimal range of spectrum for fine sensing so as to adaptively reduce the overall channel sensing time. Performance analysis is conducted on the proposed EKBR scheme using a multi-dimensional absorbing Markov chain to evaluate various performance metrics of interest, such as average sensing delay (or referred to as sensing overhead in the study), average data transmission rate, and percentage of missed spectrum opportunities. Numerical results show that the proposed EKBR scheme achieves better performance than that by the state-or-the-art techniques while yielding less computation complexity and sensing overhead.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=6156bf795782df1c256e076cf383f731p=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=6156bf795782df1c256e076cf383f731p=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Global barrier coverage is known to be an appropriate model of coverage for movement detection applications such as intrusion detection. However, it has been proved that given a sensor deployment, sensors cannot locally determine whether the deployment provides global barrier coverage, making it impossible to develop localized algorithms. In this paper, we introduce the concept of local barrier coverage to address this limitation. Motivated by the observation that movements are likely to follow a shorter path in crossing a belt region, local barrier coverage guarantees the detection of all movements whose trajectory is confined to a slice of the belt region of deployment. We prove that it is possible for individual sensors to locally determine the existence of local barrier coverage. Although local barrier coverage does not deterministically guarantee global barrier coverage, we show that for thin belt regions, local barrier coverage almost always provides global barrier coverage. To demonstrate that local barrier coverage can be used to design localized algorithms, we develop a novel sleep-wakeup algorithm for maximizing the network lifetime, called Localized Barrier Coverage Protocol (LBCP). We prove that LBCP guarantees local barrier coverage and show that LBCP provides close to optimal enhancement in the network lifetime, while providing global barrier coverage most of the time.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=b9f013f63fc6a97680ea126000ba9eddp=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=b9f013f63fc6a97680ea126000ba9eddp=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/

Third Generation (3G) cellular networks take advantage of time-varying and location-dependent channel conditions of mobile users to provide broadband services. They use opportunistic scheduling to utilize spectrum efficiently under fairness and QoS constraints. Opportunistic scheduling algorithms rely on the collaboration among all mobile users to achieve their design objectives. However, we demonstrate that rogue cellular devices can exploit vulnerabilities in popular opportunistic scheduling algorithms, such as Proprotional Fair (PF) and Temporal Fair (TF), to usurp the majority of time slots in 3G networks. Our simulations show that only five rogue device per 50-user cell can use up to 90% of the time slots, and can cause two-second end-to-end inter-packet transmission delay on VoIP applications for every user in the same cell, rendering VoIP applications useless. To defend against this attack, we propose strengthening the PF and TF schedulers and a robust handoff scheme.br clear=both style=clear: both;/ br clear=both style=clear: both;/ a href=http://ads.pheedo.com/click.phdo?s=98b9179359c213000717bf4713e333eep=1img alt= style=border: 0; border=0 src=http://ads.pheedo.com/img.phdo?s=98b9179359c213000717bf4713e333eep=1//a img alt= height=0 width=0 border=0 style=display:none src=http://a.rfihub.com/eus.gif?eui=2225/