DETERMINING INTUITIONISTIC FUZZY DEGREE OF OVERLAPPING OF COMPUTATION AND COMMUNICATION IN PARALLEL APPLICATIONS USING GENERALIZED NETS
|
|
- Chrystal Cummings
- 5 years ago
- Views:
Transcription
1 DETERMINING INTUITIONISTIC FUZZY DEGREE OF OVERLAPPING OF COMPUTATION AND COMMUNICATION IN PARALLEL APPLICATIONS USING GENERALIZED NETS Pave Tchesmedjiev, Peter Vassiev Centre for Biomedica Engineering, Bugarian Academy of Sciences Acad. G. Bonchev Str., B. 05, Sofia-3, Bugaria E-mais: Abstract Overapping of computation and communication can reduce overa appication execution time and a parae appications coud benefit to a certain degree. In order to achieve this we present a new approach for determining the degree of overapping. Keywords: Communication, Computation, Generaized net, Intuitionistic fuzzy sets, Modeing, MPI, Overapping, Parae process INTRODUCTION Overapping is a high performance software mechanism that enabes concurrent execution of independent communication and computation activities. The major objective of overapping is to reduce the overa appication time by utiizing hardware and software architectures that offer concurrent progress of communication and computation. Overapping is one of the fundamenta agorithmic approaches for improving parae performance. A parae appications coud benefit from overapping to a certain degree. This paper focuses on a new approach for determining degree of overapping. This approach incudes evauating the intuitionistic fuzzy vaue of the degree, using a generaized net mode (GN, see []). 2 COMMON GENERALIZED NET MODEL FOR MPI PARALLEL FUNCTIONS In order to determine the vaue of overapping we wi introduce a common generaized net for modeing and simuating parae appications. The foowing MPI functions (definitions are given in the C programming anguage; see [3]) are commony used in parae programs: 50
2 int MPI_Bcast(void *buf, int count, MPI_Datatype datatype, int root, MPI_Comm comm) the vaue of the data, pointed by *buf, of type datatype and containing count eements, is sent to a other processes(associated to the communicator comm). So afer caing the function every process ends with a copy of the data. int MPI_Reduce(void *sendbuf, void *recvbuf, int count, MPI_Datatype datatype, MPI_Op op, int root, MPI_Comm comm) the vaue of the data, pointed by *sendbuf, of type datatype and containing count eements from each process are sent to the process with rank root and paced in the *recvbuf, as operation op is committed before that. int MPI_Send(void *buf, int count, MPI_Datatype datatype, int dest, int tag, MPI_Comm comm) the vaue of the data, pointed by *buf, of type datatype and containing count eements is sent to the destination process from the communicator comm - dest, using additiona information tag. int MPI_Recv(void *buf, int count, MPI_Datatype datatype, int source, int tag, MPI_Comm comm, MPI_Status *status) the master process requests for information from another process source from the communicator comm and bocks unti the an answer is returned. The information is represented by the vaue, pointed by *buf, of type datatype and containing count eements with additiona information tag. Status is returned by the variabe *status. The described parae routines can be represented in the common GN mode for n parae processes and one master process that activates them see Fig.. For the master process, represented by transition Z 0 : Z 0 = <{ 0 },{, 3,... 2i+,... 2n+ }, r 0 > r 0 = 0 W 0, W 3 0,3 L L W 2i+ 0,2i+ L L W 2n+ 0,2n+ For one of the parae processes, represented by transition Z i+, i = {0,n}: Z i+ = <{ 2i+ },{ 2i+2 }, r i+ > r = 2i+ 2 i+ true The transitions represent parae processes. When the master process sends a message to other parae processes a token is created and the 2i+ 5
3 respective transition is activated. The tokens have the foowing properties data, count and datatype. The conditions W 0,, W 0,3, W 0,2i+, W 0,2n+ for the case of MPI_Bcast, MPI_Reduce and MPI_Send functions are aways TRUE. Figure. 52
4 When the used function is MPI_Recv, W 0,, W 0,3, W 0,2i+, W 0,2n+ are initiay FALSE and become TRUE when the master process is ready with the requested token (data). 3 DEFINITION OF OVERLAPPING If the tota execution time (see [2]) of a parae appication is T p the computation time is T comp and the communication time is T c, the objective of overapping can be expressed as foows: T p = T comp + T c T o, Where T o is the time saving achieved through overapping. Traditiona approaches for parae performance improvement emphasize minimization of T comp and T c and typicay rey on increasing raw processor speed and network speeds. Ceary, overapping presents aternative approach for improving performance. Overapping depends primariy on efficient software and hardware architectures rather than on top speed components. Overapping utiizes software techniques such as asynchronous message-competion notification, ow processor overhead, independent message progress. Major hardware features of the parae system needed for effective overapping are avaiabiity of excess bandwidth of the memory subsystem and inteigent network interface controers capabe of accessing host memory. The introduced common GN mode provides the needed abstraction of a hardware and software ayers of a rea parae system. The reation between the communication and computation activities pays an important roe in achieving effective overapping. To iustrate this importance, a computation activity X and a communication activity Y are reviewed. The durations of these activities are, respectivey, t x and t y. For simpicity we can assume that there are no preparation times and the entire communication and computation times can be represented as s sum of N individua activities, such as T comp (estimated) = t x and T c (estimated) = t y or if we want to be more precise T comp (actua) = ( + π(t comp )).T comp (estimated) and T c (actua) = ( + π(t c )).T c (estimated), where π(t comp ), π(t c ) are numbers between 0 and that refect the deays of the tasks (in the idea case the vaue woud be 0). We aso assume that X and Y shoud be agorithmicay independent they can be executed concurrenty without vioating the correct semantics of the agorithm. 53
5 If the reviewed computation and communication activities are not overapped, the seria time for their competion is t s = t x + t y. If the two activities are ideay overapped, the tota time t o wi be the arger of t x and t y and t o = max(t x, t y ). The overa time reduction is S = (t x + t y ) / max(t x, t y ) In order to quantify the speedup because of overapping, the reationship between X and Y is represented as t y = q.t x, where q > 0 is a factor that represents how much Y is onger or shorter than X. Then speedup is as foows: S = (t x + q.t x ) / max(t x, q.t x ) = ( + q)t x / max(t x, q.t x ) In the first case et q >, that is, communication is onger than computation, then S = ( + q).t x / (q.t x ) = ( + q) / q. This expression shows that if q approaches, then S approaches 2, and when q approaches positive infinity, S approaches. In the second case when 0 < q, meaning that the communication time is shorter than the computation time, then S = + q. So when q approaches 0, S approaches whie for q approaches, S approaches 2. So S 2, the maximum achieved when t x = t y. 4 DETERMINING INTUITIONISTIC FUZZY DEGREE OF OVERLAPPING We wi introduce a new metric, used for accurate modeing of overapping degree of overapping, denoted by µ(d 0 ) and degree of indeterminacy (uncertainty) π(d 0 ). As in a Intuitionistic Fuzzy Set (IFS, see [4]) we wi impose the restrictions µ+π. The degree of overapping is used as a quantitive description of the capabiities of a system in order to perform effective overapping of communication and computation. This quantification is necessary for devising a reaistic mode of parae execution time. Overapping is now expressed in the form: T p = T comp + T pc (( π(t o )).T o (µ(d 0 ))), for 0 µ(d 0 ), where measures π(t o ) the uncertainty of the time of the executed agorithm. Degree µ(d 0 ) is chosen so that the maximum impact of overapping on the overa performance is achieved as the vaue of µ(d 0 ) approaches. As we assumed earier, π(d 0 ) wi approach 0 and that s why 0 µ(d 0 ). There are severa reasons for introducing degree-of-overapping metric. First it can be 54
6 used to distinguish between hardware patforms and software systems that have specific optimizations for achieving effective overapping and those that do not provide such optimizations. Second, this new metric heps to provide more reaistic mode of overapping that accuratey quantifies the performance benefits to appications. And third it can be used for a guideine for improving parae patform architectures and appication agorithms impementation. Using the proposed common GN mode and IF vaues wi hep even more for achieving this tasks. Degree µ(d 0 ) = means that the system can achieve idea overapping and µ(d 0 ) = 0 means that no overapping is possibe. Idea overapping is impossibe because the communication activities require certain processor overhead and the message transfers compete to some degree with the centra processor to access to the main memory. As a resut of CPU anaysis, the communication activity Y, introduced earier, can be presented as a sum of two sub-activities Y h and Y c, where Y h denotes a activity that cause processor overhead and resource contention, and Y c is the component that can be overapped with computation. During Y h no overapping is possibe, because CPU is busy with communication-reated work. The time of activity Y can be represented as sum of two components t y = t yh + t yc then the seria time of X and Y is: t s = t x + t yh + t yc and the overapped time is: t o = t xh + max(t yc, t x ) Ceary the onger the overhead time t xh is, the smaer the effect of overapping wi be. So we can formay define the degree of overapping as: µ(d 0 ) = t y / t xy = t yc / t yh + t yc and finay t o = t x + ( µ(d 0 )).t y, when t x > t xc and t o = t y, when t x t yc We wi consider the case when when t x > t y since this condition can be easiy identified by a singe experiment. In summary the vaues of the degree of overapping are in the range 0 µ(d 0 ). Degree µ(d 0 ) can be determined using the GN mode s execution times as foows: µ(d 0 ) = + (t x t o ) /t y = (t s t o ) /t y Common generaized net for executing parae appication and determining the degree of overapping is shown on Fig. 2. The transitions from Z to Z n+ represent the n parae processes that are executing computation and communication activities. Each token keeps the needed time vaues. The degree of overapping µ(d 0 ) is cacuated by the token in pace 3n+4. 55
7 Figure 2. 56
8 5 CONCLUSION By determining the IF vaue of the degree of overapping capabiities of a system we can perform effective overapping of communication and computation. By using common generaized net mode we can evauate this vaue and use it for further enhancements of the parae system and software. ACKNOWLEDGEMENTS This work was supported by Grant BIn-2/09 Design and deveopment of intuitionistic fuzzy ogic toos in information technoogies of the Nationa Science Fund of Bugaria. REFERENCES [] Atanassov, K., Generaized Nets, Word Scientific, Singapore, 99 [2] Dimitrov, Rossen, Overapping of communication and computation and eary binding, University of Mississipi, 200 [3] Gropp, Wiiam, Lusk, Ewing, Skjeum, Anthony, Using MPI Portabe Parae Programming with the Message-Passing Interface, The Mit Press, 997 [4] Atanassov, K, Intuitionsitic Fuzzy Sets. Springer Physica-Verag, Heideberg,
A Memory Grouping Method for Sharing Memory BIST Logic
A Memory Grouping Method for Sharing Memory BIST Logic Masahide Miyazai, Tomoazu Yoneda, and Hideo Fuiwara Graduate Schoo of Information Science, Nara Institute of Science and Technoogy (NAIST), 8916-5
More informationA METHOD FOR GRIDLESS ROUTING OF PRINTED CIRCUIT BOARDS. A. C. Finch, K. J. Mackenzie, G. J. Balsdon, G. Symonds
A METHOD FOR GRIDLESS ROUTING OF PRINTED CIRCUIT BOARDS A C Finch K J Mackenzie G J Basdon G Symonds Raca-Redac Ltd Newtown Tewkesbury Gos Engand ABSTRACT The introduction of fine-ine technoogies to printed
More informationA Comparison of a Second-Order versus a Fourth- Order Laplacian Operator in the Multigrid Algorithm
A Comparison of a Second-Order versus a Fourth- Order Lapacian Operator in the Mutigrid Agorithm Kaushik Datta (kdatta@cs.berkeey.edu Math Project May 9, 003 Abstract In this paper, the mutigrid agorithm
More informationLanguage Identification for Texts Written in Transliteration
Language Identification for Texts Written in Transiteration Andrey Chepovskiy, Sergey Gusev, Margarita Kurbatova Higher Schoo of Economics, Data Anaysis and Artificia Inteigence Department, Pokrovskiy
More informationNeural Network Enhancement of the Los Alamos Force Deployment Estimator
Missouri University of Science and Technoogy Schoars' Mine Eectrica and Computer Engineering Facuty Research & Creative Works Eectrica and Computer Engineering 1-1-1994 Neura Network Enhancement of the
More informationMessage Passing Interface. most of the slides taken from Hanjun Kim
Message Passing Interface most of the slides taken from Hanjun Kim Message Passing Pros Scalable, Flexible Cons Someone says it s more difficult than DSM MPI (Message Passing Interface) A standard message
More informationHigh-Performance Computing: MPI (ctd)
High-Performance Computing: MPI (ctd) Adrian F. Clark: alien@essex.ac.uk 2015 16 Adrian F. Clark: alien@essex.ac.uk High-Performance Computing: MPI (ctd) 2015 16 1 / 22 A reminder Last time, we started
More informationMessage Passing Interface
MPSoC Architectures MPI Alberto Bosio, Associate Professor UM Microelectronic Departement bosio@lirmm.fr Message Passing Interface API for distributed-memory programming parallel code that runs across
More informationTSR: Topology Reduction from Tree to Star Data Grids
03 Seventh Internationa Conference on Innovative Mobie and Internet Services in biquitous Computing TSR: Topoogy Reduction from Tree to Star Data Grids Ming-Chang Lee #, Fang-Yie Leu *, Ying-ping Chen
More informationTopics 1. Manipulators and robots
Proceedings of the Internationa Symposium of Mechanism and Machine Science, 017 AzCIFToMM Azerbaijan Technica University 11-14 September 017, Baku, Azerbaijan Topics 1. Manipuators and robots Anaysis and
More informationOutline. Parallel Numerical Algorithms. Forward Substitution. Triangular Matrices. Solving Triangular Systems. Back Substitution. Parallel Algorithm
Outine Parae Numerica Agorithms Chapter 8 Prof. Michae T. Heath Department of Computer Science University of Iinois at Urbana-Champaign CS 554 / CSE 512 1 2 3 4 Trianguar Matrices Michae T. Heath Parae
More informationMessage Passing Interface
Message Passing Interface DPHPC15 TA: Salvatore Di Girolamo DSM (Distributed Shared Memory) Message Passing MPI (Message Passing Interface) A message passing specification implemented
More informationA Fast Block Matching Algorithm Based on the Winner-Update Strategy
In Proceedings of the Fourth Asian Conference on Computer Vision, Taipei, Taiwan, Jan. 000, Voume, pages 977 98 A Fast Bock Matching Agorithm Based on the Winner-Update Strategy Yong-Sheng Chenyz Yi-Ping
More informationBasic MPI Communications. Basic MPI Communications (cont d)
Basic MPI Communications MPI provides two non-blocking routines: MPI_Isend(buf,cnt,type,dst,tag,comm,reqHandle) buf: source of data to be sent cnt: number of data elements to be sent type: type of each
More informationIntermediate MPI features
Intermediate MPI features Advanced message passing Collective communication Topologies Group communication Forms of message passing (1) Communication modes: Standard: system decides whether message is
More informationMCSE Training Guide: Windows Architecture and Memory
MCSE Training Guide: Windows 95 -- Ch 2 -- Architecture and Memory Page 1 of 13 MCSE Training Guide: Windows 95-2 - Architecture and Memory This chapter wi hep you prepare for the exam by covering the
More informationIntroducing a Target-Based Approach to Rapid Prototyping of ECUs
Introducing a Target-Based Approach to Rapid Prototyping of ECUs FEBRUARY, 1997 Abstract This paper presents a target-based approach to Rapid Prototyping of Eectronic Contro Units (ECUs). With this approach,
More informationCS 179: GPU Programming. Lecture 14: Inter-process Communication
CS 179: GPU Programming Lecture 14: Inter-process Communication The Problem What if we want to use GPUs across a distributed system? GPU cluster, CSIRO Distributed System A collection of computers Each
More informationOn-Chip CNN Accelerator for Image Super-Resolution
On-Chip CNN Acceerator for Image Super-Resoution Jung-Woo Chang and Suk-Ju Kang Dept. of Eectronic Engineering, Sogang University, Seou, South Korea {zwzang91, sjkang}@sogang.ac.kr ABSTRACT To impement
More informationLayout Conscious Approach and Bus Architecture Synthesis for Hardware-Software Co-Design of Systems on Chip Optimized for Speed
Layout Conscious Approach and Bus Architecture Synthesis for Hardware-Software Co-Design of Systems on Chip Optimized for Speed Nattawut Thepayasuwan, Member, IEEE and Aex Doboi, Member, IEEE Abstract
More information15-440: Recitation 8
15-440: Recitation 8 School of Computer Science Carnegie Mellon University, Qatar Fall 2013 Date: Oct 31, 2013 I- Intended Learning Outcome (ILO): The ILO of this recitation is: Apply parallel programs
More informationIntroduction to the Message Passing Interface (MPI)
Introduction to the Message Passing Interface (MPI) CPS343 Parallel and High Performance Computing Spring 2018 CPS343 (Parallel and HPC) Introduction to the Message Passing Interface (MPI) Spring 2018
More informationunderstood as processors that match AST patterns of the source language and translate them into patterns in the target language.
A Basic Compier At a fundamenta eve compiers can be understood as processors that match AST patterns of the source anguage and transate them into patterns in the target anguage. Here we wi ook at a basic
More information1682 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 22, NO. 6, DECEMBER Backward Fuzzy Rule Interpolation
1682 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 22, NO. 6, DECEMBER 2014 Bacward Fuzzy Rue Interpoation Shangzhu Jin, Ren Diao, Chai Que, Senior Member, IEEE, and Qiang Shen Abstract Fuzzy rue interpoation
More informationMPI. (message passing, MIMD)
MPI (message passing, MIMD) What is MPI? a message-passing library specification extension of C/C++ (and Fortran) message passing for distributed memory parallel programming Features of MPI Point-to-point
More informationCommunity-Aware Opportunistic Routing in Mobile Social Networks
IEEE TRANSACTIONS ON COMPUTERS VOL:PP NO:99 YEAR 213 Community-Aware Opportunistic Routing in Mobie Socia Networks Mingjun Xiao, Member, IEEE Jie Wu, Feow, IEEE, and Liusheng Huang, Member, IEEE Abstract
More informationNOWDAYS, our ways of living are under gradual but
Transmission Management of Deay-Sensitive Medica Packets in Beyond Wireess Body Area Networks: A Queueing Game Approach Changyan Yi, Student Member, IEEE, and Jun Cai, Senior Member, IEEE Abstract In this
More informationLoad Balancing by MPLS in Differentiated Services Networks
Load Baancing by MPLS in Differentiated Services Networks Riikka Susitaiva, Jorma Virtamo, and Samui Aato Networking Laboratory, Hesinki University of Technoogy P.O.Box 3000, FIN-02015 HUT, Finand {riikka.susitaiva,
More informationDistributed Memory Systems: Part IV
Chapter 5 Distributed Memory Systems: Part IV Max Planck Institute Magdeburg Jens Saak, Scientific Computing II 293/342 The Message Passing Interface is a standard for creation of parallel programs using
More informationOAuth 2.0 Token Binding https://tools.ietf.org/html/draft-ietf-oauth-token-binding-04
OAuth 2.0 Token Binding https://toos.ietf.org/htm/draft-ietf-oauth-token-binding-04 Brian Campbe Michae B. Jones John Bradey IETF 99 Prague Juy 2017 from IETF 93 1 The Setting of the Context Provide an
More informationPart - II. Message Passing Interface. Dheeraj Bhardwaj
Part - II Dheeraj Bhardwaj Department of Computer Science & Engineering Indian Institute of Technology, Delhi 110016 India http://www.cse.iitd.ac.in/~dheerajb 1 Outlines Basics of MPI How to compile and
More informationNearest Neighbor Learning
Nearest Neighbor Learning Cassify based on oca simiarity Ranges from simpe nearest neighbor to case-based and anaogica reasoning Use oca information near the current query instance to decide the cassification
More informationAs Michi Henning and Steve Vinoski showed 1, calling a remote
Reducing CORBA Ca Latency by Caching and Prefetching Bernd Brügge and Christoph Vismeier Technische Universität München Method ca atency is a major probem in approaches based on object-oriented middeware
More informationReplication of Virtual Network Functions: Optimizing Link Utilization and Resource Costs
Repication of Virtua Network Functions: Optimizing Link Utiization and Resource Costs Francisco Carpio, Wogang Bziuk and Admea Jukan Technische Universität Braunschweig, Germany Emai:{f.carpio, w.bziuk,
More informationResearch of Classification based on Deep Neural Network
2018 Internationa Conference on Sensor Network and Computer Engineering (ICSNCE 2018) Research of Emai Cassification based on Deep Neura Network Wang Yawen Schoo of Computer Science and Engineering Xi
More informationOutline. Communication modes MPI Message Passing Interface Standard
MPI THOAI NAM Outline Communication modes MPI Message Passing Interface Standard TERMs (1) Blocking If return from the procedure indicates the user is allowed to reuse resources specified in the call Non-blocking
More informationParallel programming MPI
Parallel programming MPI Distributed memory Each unit has its own memory space If a unit needs data in some other memory space, explicit communication (often through network) is required Point-to-point
More informationPARALLEL AND DISTRIBUTED COMPUTING
PARALLEL AND DISTRIBUTED COMPUTING 2013/2014 1 st Semester 1 st Exam January 7, 2014 Duration: 2h00 - No extra material allowed. This includes notes, scratch paper, calculator, etc. - Give your answers
More informationl Tree: set of nodes and directed edges l Parent: source node of directed edge l Child: terminal node of directed edge
Trees & Heaps Week 12 Gaddis: 20 Weiss: 21.1-3 CS 5301 Fa 2016 Ji Seaman 1 Tree: non-recursive definition Tree: set of nodes and directed edges - root: one node is distinguished as the root - Every node
More informationCSE 613: Parallel Programming. Lecture 21 ( The Message Passing Interface )
CSE 613: Parallel Programming Lecture 21 ( The Message Passing Interface ) Jesmin Jahan Tithi Department of Computer Science SUNY Stony Brook Fall 2013 ( Slides from Rezaul A. Chowdhury ) Principles of
More informationfile://j:\macmillancomputerpublishing\chapters\in073.html 3/22/01
Page 1 of 15 Chapter 9 Chapter 9: Deveoping the Logica Data Mode The information requirements and business rues provide the information to produce the entities, attributes, and reationships in ogica mode.
More informationFrom i* to istar 2.0: An Evolving Social Modelling Language
From i* to istar 2.0: An Evoving Socia Modeing Language Lin Liu 1 Schoo of Software, Tsinghua University, Beijing, 100084, China iniu@tsinghua.edu.cn Abstract. Conceptua Modeing, as a thought too, heps
More informationUnixWare 7 System Administration UnixWare 7 System Configuration
UnixWare 7 System Administration - CH 3 - UnixWare 7 System Configuration Page 1 of 8 [Figures are not incuded in this sampe chapter] UnixWare 7 System Administration - 3 - UnixWare 7 System Configuration
More informationA HIGH PERFORMANCE, LOW LATENCY, LOW POWER AUDIO PROCESSING SYSTEM FOR WIDEBAND SPEECH OVER WIRELESS LINKS
A HIGH PERFORMANCE, LOW LATENCY, LOW POWER AUDIO PROCESSING SYSTEM FOR WIDEBAND SPEECH OVER WIRELESS LINKS Etienne Cornu 1, Aain Dufaux 2, and David Hermann 1 1 AMI Semiconductor Canada, 611 Kumpf Drive,
More informationAuthorization of a QoS Path based on Generic AAA. Leon Gommans, Cees de Laat, Bas van Oudenaarde, Arie Taal
Abstract Authorization of a QoS Path based on Generic Leon Gommans, Cees de Laat, Bas van Oudenaarde, Arie Taa Advanced Internet Research Group, Department of Computer Science, University of Amsterdam.
More informationHour 3: The Network Access Layer Page 1 of 10. Discuss how TCP/IP s Network Access layer relates to the OSI networking model
Hour 3: The Network Access Layer Page 1 of 10 Hour 3: The Network Access Layer At the base of the TCP/IP protoco stack is the Network Access ayer, the coection of services and specifications that provide
More informationAn Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc.
[Type text] [Type text] [Type text] ISSN : 0974-7435 Voume 10 Issue 16 BioTechnoogy 014 An Indian Journa FULL PAPER BTAIJ, 10(16), 014 [999-9307] Study on prediction of type- fuzzy ogic power system based
More informationParallel Programming. Using MPI (Message Passing Interface)
Parallel Programming Using MPI (Message Passing Interface) Message Passing Model Simple implementation of the task/channel model Task Process Channel Message Suitable for a multicomputer Number of processes
More informationResponse Surface Model Updating for Nonlinear Structures
Response Surface Mode Updating for Noninear Structures Gonaz Shahidi a, Shamim Pakzad b a PhD Student, Department of Civi and Environmenta Engineering, Lehigh University, ATLSS Engineering Research Center,
More informationIntro to Programming & C Why Program? 1.2 Computer Systems: Hardware and Software. Why Learn to Program?
Intro to Programming & C++ Unit 1 Sections 1.1-3 and 2.1-10, 2.12-13, 2.15-17 CS 1428 Spring 2018 Ji Seaman 1.1 Why Program? Computer programmabe machine designed to foow instructions Program a set of
More informationEndoscopic Motion Compensation of High Speed Videoendoscopy
Endoscopic Motion Compensation of High Speed Videoendoscopy Bharath avuri Department of Computer Science and Engineering, University of South Caroina, Coumbia, SC - 901. ravuri@cse.sc.edu Abstract. High
More informationFor Review Only. CFP: Cooperative Fast Protection. Bin Wu, Pin-Han Ho, Kwan L. Yeung, János Tapolcai and Hussein T. Mouftah
Journa of Lightwave Technoogy Page of CFP: Cooperative Fast Protection Bin Wu, Pin-Han Ho, Kwan L. Yeung, János Tapocai and Hussein T. Mouftah Abstract We introduce a nove protection scheme, caed Cooperative
More informationService Scheduling for General Packet Radio Service Classes
Service Scheduing for Genera Packet Radio Service Casses Qixiang Pang, Amir Bigoo, Victor C. M. Leung, Chris Schoefied Department of Eectrica and Computer Engineering, University of British Coumbia, Vancouver,
More informationStandard MPI - Message Passing Interface
c Ewa Szynkiewicz, 2007 1 Standard MPI - Message Passing Interface The message-passing paradigm is one of the oldest and most widely used approaches for programming parallel machines, especially those
More informationTelephony Trainers with Discovery Software
Teephony Trainers 58 Series Teephony Trainers with Discovery Software 58-001 Teephony Training System 58-002 Digita Switching System 58-003 Digita Teephony Training System 58-004 Digita Trunk Network System
More informationMobile App Recommendation: Maximize the Total App Downloads
Mobie App Recommendation: Maximize the Tota App Downoads Zhuohua Chen Schoo of Economics and Management Tsinghua University chenzhh3.12@sem.tsinghua.edu.cn Yinghui (Catherine) Yang Graduate Schoo of Management
More informationModelling and Performance Evaluation of Router Transparent Web cache Mode
Emad Hassan A-Hemiary IJCSET Juy 2012 Vo 2, Issue 7,1316-1320 Modeing and Performance Evauation of Transparent cache Mode Emad Hassan A-Hemiary Network Engineering Department, Coege of Information Engineering,
More informationHigh Performance Computing
High Performance Computing Course Notes 2009-2010 2010 Message Passing Programming II 1 Communications Point-to-point communications: involving exact two processes, one sender and one receiver For example,
More informationA Top-to-Bottom View: Energy Analysis for Mobile Application Source Code
A Top-to-Bottom View: Energy Anaysis for Mobie Appication Source Code Xueiang Li John P. Gaagher Roskide University Emai: {xueiang, jpg}@ruc.dk arxiv:1510.04165v1 [cs.oh] 14 Oct 2015 Abstract Energy efficiency
More informationRDF Objects 1. Alex Barnell Information Infrastructure Laboratory HP Laboratories Bristol HPL November 27 th, 2002*
RDF Objects 1 Aex Barne Information Infrastructure Laboratory HP Laboratories Bristo HPL-2002-315 November 27 th, 2002* E-mai: Andy_Seaborne@hp.hp.com RDF, semantic web, ontoogy, object-oriented datastructures
More informationAN EVOLUTIONARY APPROACH TO OPTIMIZATION OF A LAYOUT CHART
13 AN EVOLUTIONARY APPROACH TO OPTIMIZATION OF A LAYOUT CHART Eva Vona University of Ostrava, 30th dubna st. 22, Ostrava, Czech Repubic e-mai: Eva.Vona@osu.cz Abstract: This artice presents the use of
More informationConflict graph-based Markovian model to estimate throughput in unsaturated IEEE networks
Confict graph-based Markovian mode to estimate throughput in unsaturated IEEE 802 networks Marija STOJANOVA Thomas BEGIN Anthony BUSSON marijastojanova@ens-yonfr thomasbegin@ens-yonfr anthonybusson@ens-yonfr
More informationOn Finding the Best Partial Multicast Protection Tree under Dual-Homing Architecture
On inding the est Partia Muticast Protection Tree under ua-homing rchitecture Mei Yang, Jianping Wang, Xiangtong Qi, Yingtao Jiang epartment of ectrica and omputer ngineering, University of Nevada Las
More informationHiding secrete data in compressed images using histogram analysis
University of Woongong Research Onine University of Woongong in Dubai - Papers University of Woongong in Dubai 2 iding secrete data in compressed images using histogram anaysis Farhad Keissarian University
More informationEfficient Histogram-based Indexing for Video Copy Detection
Efficient Histogram-based Indexing for Video Copy Detection Chih-Yi Chiu, Jenq-Haur Wang*, and Hung-Chi Chang Institute of Information Science, Academia Sinica, Taiwan *Department of Computer Science and
More informationparms: A Package for Solving General Sparse Linear Systems on Parallel Computers
parms: A Package for Soving Genera Sparse Linear Systems on Parae Computers Y. Saad 1 and M. Sosonkina 2 1 University of Minnesota, Minneapois, MN 55455, USA, saad@cs.umn.edu, http://www.cs.umn.edu/ saad
More informationChapter 5: Transactions in Federated Databases
Federated Databases Chapter 5: in Federated Databases Saes R&D Human Resources Kemens Böhm Distributed Data Management: in Federated Databases 1 Kemens Böhm Distributed Data Management: in Federated Databases
More informationCLOUD computing has become commercially popular,
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT VOL:11 NO:1 YEAR 2014 Consistency as a Service: Auditing Coud Consistency Qin Liu, Guojun Wang, IEEE, Member, and Jie Wu, IEEE Feow Abstract Coud storage
More informationA Novel Congestion Control Scheme for Elastic Flows in Network-on-Chip Based on Sum-Rate Optimization
A Nove Congestion Contro Scheme for Eastic Fows in Network-on-Chip Based on Sum-Rate Optimization Mohammad S. Taebi 1, Fahimeh Jafari 1,3, Ahmad Khonsari 2,1, and Mohammad H. Yaghmae 3 1 IPM, Schoo of
More informationWATERMARKING GIS DATA FOR DIGITAL MAP COPYRIGHT PROTECTION
WATERMARKING GIS DATA FOR DIGITAL MAP COPYRIGHT PROTECTION Shen Tao Chinese Academy of Surveying and Mapping, Beijing 100039, China shentao@casm.ac.cn Xu Dehe Institute of resources and environment, North
More informationA Method for Calculating Term Similarity on Large Document Collections
$ A Method for Cacuating Term Simiarity on Large Document Coections Wofgang W Bein Schoo of Computer Science University of Nevada Las Vegas, NV 915-019 bein@csunvedu Jeffrey S Coombs and Kazem Taghva Information
More informationUNIVERSITY OF MORATUWA
UNIVERSITY OF MORATUWA FACULTY OF ENGINEERING DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING B.Sc. Engineering 2012 Intake Semester 8 Examination CS4532 CONCURRENT PROGRAMMING Time allowed: 2 Hours March
More informationHolistic Aggregates in a Networked World: Distributed Tracking of Approximate Quantiles
Hoistic Aggregates in a Networked Word: Distributed Tracking of Approximate Quanties Graham Cormode Be Laboratories cormode@be-abs.com Minos Garofaakis Be Laboratories minos@be-abs.com S. Muthukrishnan
More informationMACHINE learning techniques can, automatically,
Proceedings of Internationa Joint Conference on Neura Networks, Daas, Texas, USA, August 4-9, 203 High Leve Data Cassification Based on Network Entropy Fiipe Aves Neto and Liang Zhao Abstract Traditiona
More informationNon-Blocking Communications
Non-Blocking Communications Deadlock 1 5 2 3 4 Communicator 0 2 Completion The mode of a communication determines when its constituent operations complete. - i.e. synchronous / asynchronous The form of
More informationParallel Computing Paradigms
Parallel Computing Paradigms Message Passing João Luís Ferreira Sobral Departamento do Informática Universidade do Minho 31 October 2017 Communication paradigms for distributed memory Message passing is
More informationWindows NT, Terminal Server and Citrix MetaFrame Terminal Server Architecture
Windows NT, Termina Server and Citrix MetaFrame - CH 3 - Termina Server Architect.. Page 1 of 13 [Figures are not incuded in this sampe chapter] Windows NT, Termina Server and Citrix MetaFrame - 3 - Termina
More informationA SIMPLE APPROACH TO SPECIFYING CONCURRENT SYSTEMS
Artificia Inteigence and Language Processing ]acques Cohen Editor A SIMPLE APPROACH TO SPECIFYING CONCURRENT SYSTEMS LESLIE LAMPORT Over the past few years, I have deveoped an approach to the forma specification
More informationUNCORRECTED PROOF ARTICLE IN PRESS. , Scott Schoenfeld b. SMM 4402 No. of Pages 5, DTD = July 2003 Disk used
SMM 2 No. of Pages 5, DTD =.3. 2 Juy 23 Disk used 2 Evoution of crysta orientation distribution coefficients 3 during pastic deformation D.S. Li a, H. Garmestani a, *, Scott Schoenfed b 5 a Schoo of Materias
More informationParallel Programming, MPI Lecture 2
Parallel Programming, MPI Lecture 2 Ehsan Nedaaee Oskoee 1 1 Department of Physics IASBS IPM Grid and HPC workshop IV, 2011 Outline 1 Point-to-Point Communication Non Blocking PTP Communication 2 Collective
More informationSPT: Storyboard Programming Tool
SPT: Storyboard Programming Too The MIT Facuty has made this artice openy avaiabe. Pease share how this access beneits you. Your story matters. Citation As Pubished Pubisher Singh, Rishabh, and Armando
More informationIncremental Discovery of Object Parts in Video Sequences
Incrementa Discovery of Object Parts in Video Sequences Stéphane Drouin, Patrick Hébert and Marc Parizeau Computer Vision and Systems Laboratory, Department of Eectrica and Computer Engineering Lava University,
More informationA Petrel Plugin for Surface Modeling
A Petre Pugin for Surface Modeing R. M. Hassanpour, S. H. Derakhshan and C. V. Deutsch Structure and thickness uncertainty are important components of any uncertainty study. The exact ocations of the geoogica
More informationIntroduction to USB Development
Introduction to USB Deveopment Introduction Technica Overview USB in Embedded Systems Recent Deveopments Extensions to USB USB as compared to other technoogies USB: Universa Seria Bus A seria bus standard
More informationTHE PERCENTAGE OCCUPANCY HIT OR MISS TRANSFORM
17th European Signa Processing Conference (EUSIPCO 2009) Gasgow, Scotand, August 24-28, 2009 THE PERCENTAGE OCCUPANCY HIT OR MISS TRANSFORM P. Murray 1, S. Marsha 1, and E.Buinger 2 1 Dept. of Eectronic
More informationBacking-up Fuzzy Control of a Truck-trailer Equipped with a Kingpin Sliding Mechanism
Backing-up Fuzzy Contro of a Truck-traier Equipped with a Kingpin Siding Mechanism G. Siamantas and S. Manesis Eectrica & Computer Engineering Dept., University of Patras, Patras, Greece gsiama@upatras.gr;stam.manesis@ece.upatras.gr
More informationEvolving Role Definitions Through Permission Invocation Patterns
Evoving Roe Definitions Through Permission Invocation Patterns Wen Zhang EECS Dept. Vanderbit University Nashvie, TN, USA wen.zhang.1@vanderbit.edu David Liebovitz Dept. of Medicine Northwestern University
More informationCLOUD RADIO ACCESS NETWORK WITH OPTIMIZED BASE-STATION CACHING
CLOUD RADIO ACCESS NETWORK WITH OPTIMIZED BASE-STATION CACHING Binbin Dai and Wei Yu Ya-Feng Liu Department of Eectrica and Computer Engineering University of Toronto, Toronto ON, Canada M5S 3G4 Emais:
More informationApplication of Intelligence Based Genetic Algorithm for Job Sequencing Problem on Parallel Mixed-Model Assembly Line
American J. of Engineering and Appied Sciences 3 (): 5-24, 200 ISSN 94-7020 200 Science Pubications Appication of Inteigence Based Genetic Agorithm for Job Sequencing Probem on Parae Mixed-Mode Assemby
More informationECEn 528 Prof. Archibald Lab: Dynamic Scheduling Part A: due Nov. 6, 2018 Part B: due Nov. 13, 2018
ECEn 528 Prof. Archibad Lab: Dynamic Scheduing Part A: due Nov. 6, 2018 Part B: due Nov. 13, 2018 Overview This ab's purpose is to expore issues invoved in the design of out-of-order issue processors.
More informationReference trajectory tracking for a multi-dof robot arm
Archives of Contro Sciences Voume 5LXI, 5 No. 4, pages 53 57 Reference trajectory tracking for a muti-dof robot arm RÓBERT KRASŇANSKÝ, PETER VALACH, DÁVID SOÓS, JAVAD ZARBAKHSH This paper presents the
More informationProviding Hop-by-Hop Authentication and Source Privacy in Wireless Sensor Networks
The 31st Annua IEEE Internationa Conference on Computer Communications: Mini-Conference Providing Hop-by-Hop Authentication and Source Privacy in Wireess Sensor Networks Yun Li Jian Li Jian Ren Department
More informationDynamic Symbolic Execution of Distributed Concurrent Objects
Dynamic Symboic Execution of Distributed Concurrent Objects Andreas Griesmayer 1, Bernhard Aichernig 1,2, Einar Broch Johnsen 3, and Rudof Schatte 1,2 1 Internationa Institute for Software Technoogy, United
More informationTopics. Lecture 7. Review. Other MPI collective functions. Collective Communication (cont d) MPI Programming (III)
Topics Lecture 7 MPI Programming (III) Collective communication (cont d) Point-to-point communication Basic point-to-point communication Non-blocking point-to-point communication Four modes of blocking
More informationFurther Optimization of the Decoding Method for Shortened Binary Cyclic Fire Code
Further Optimization of the Decoding Method for Shortened Binary Cycic Fire Code Ch. Nanda Kishore Heosoft (India) Private Limited 8-2-703, Road No-12 Banjara His, Hyderabad, INDIA Phone: +91-040-3378222
More informationHPC Parallel Programing Multi-node Computation with MPI - I
HPC Parallel Programing Multi-node Computation with MPI - I Parallelization and Optimization Group TATA Consultancy Services, Sahyadri Park Pune, India TCS all rights reserved April 29, 2013 Copyright
More informationReducing Response-Time Bounds for DAG-Based Task Systems on Heterogeneous Multicore Platforms
Reducing Response-Time Bounds for DAG-Based Task Systems on Heterogeneous Muticore Patforms Kecheng Yang, Ming Yang, and James H. Anderson Department of Computer Science University of North Caroina at
More informationCSE120 Principles of Operating Systems. Prof Yuanyuan (YY) Zhou Scheduling
CSE120 Principes of Operating Systems Prof Yuanyuan (YY) Zhou Scheduing Announcement Homework 2 due on October 25th Project 1 due on October 26th 2 CSE 120 Scheduing and Deadock Scheduing Overview In discussing
More informationLOAD BALANCING DISTRIBUTED OPERATING SYSTEMS, SCALABILITY, SS Hermann Härtig
LOAD BALANCING DISTRIBUTED OPERATING SYSTEMS, SCALABILITY, SS 2016 Hermann Härtig LECTURE OBJECTIVES starting points independent Unix processes and block synchronous execution which component (point in
More informationIntroduction to MPI. HY555 Parallel Systems and Grids Fall 2003
Introduction to MPI HY555 Parallel Systems and Grids Fall 2003 Outline MPI layout Sending and receiving messages Collective communication Datatypes An example Compiling and running Typical layout of an
More information