Compilation Techniques for Embedded Data Parallel Languages

Size: px
Start display at page:

Download "Compilation Techniques for Embedded Data Parallel Languages"

Transcription

1 Compilation Techniques for Embedded Data Parallel Languages Bryan Catanzaro Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS May 11, 2011

2 Copyright 2011, by the author(s). All rights reserved. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission. Acknowledgement This research has been supported by a National Science Foundation Graduate Research Fellowship, an NVIDIA Graduate Fellowship, a Qualcomm Innovation Fellowship, the Gigascale Research Center, and the Parallel Computing Laboratory, which itself is supported by Microsoft (Award #024263), Intel (Award #024894), and by matching funding from U.C. Discovery (Award #DIG ), with additional support from affiliates National Instruments, NEC, Nokia, NVIDIA, and Samsung.

3

4

5

6

7

8

9

10

11 Ax A x

12 ψ = 1 ψ = 10 ψ = 100 ψ = 1000 ψ = ψ =

13

14 P

15

16

17

18

19

20

21

22 3 5 9

23

24

25

26

27

28

29 1/5 1/3

30

31

32

33

34

35 E x E 1,...,E n A E E 1 + E 2 E 1 < E 2 E... E 1 E 2 E 1 E 2 E 1 E p E 2 F E 1,...,E n x 1,...,x n E F, A 1,...,A n E x A E x 1,...,x n A 1,...,A n E S F A

36 S E x 1,...,x n E E f x 1,...,x n S S

37 T S P S M V M S 1 S n P V 1 V n S V T S M P V M

38 S 1, S 2 S 1 S 2 S 1 S 1 S 1,..., S n n S 1,..., S n

39

40

41

42

43

44

45 ( x i x x i ) z

46 x i x x i { x[t] i indices, t = argi indices z[i] = y[i] i / indices

47 Ax A x arg i indices y = Ax A x

48 A = y i i A ij x j j x j x

49 ˆ

50

51

52

53

54

55 Φ Φ Φ

56

57

58 n i i

59 m n [m, n], Unit

60

61

62

63 y = Ax x

64

65

66 f (x i, y i )= x i y i 2 X = {x 0, x 1,...,x n } Y = {y 0, y 1,...,y n }

67

68 x i y i x i y i m s ζ(s) P(k; s) = k s ζ(s), k > 0, s > 1 s s s m

69 s min max max min (ψ) ψ = W max W min W max W min ψ ψ = 1

70

71 m m ψm ψ ψ = 1

72 ψ = 1 ψ = 1 m > 50

73 ψ = 10 ψ = 100

74 ψ = 1000 ψ = 10000

75 ψ = m < 10 ψ = 1 ψ = m < 50 ψ = 100 ψ = 1000 ψ = ψ = ψ 1000

76

77 O P

78 P P { } { } G = N, E N n N n o, n h O P n o n n h n h E n i n j n i n j e E e b, e c, e d {False, True} C D e b e b e c n i e d n i C c C C = {None, Local, Global}

79 None Local local local local local Global global global D = {None, Backward, Forward} None None Backward n 1 0 Backward Forward 0 n 1 Forward Global None n n

80 (N, L,...,L) L (N,...,N) N (N, L, G) N (N, N, N) N (N, L) N (N, N, N) N (N, L) N (N, N, N) N (G, L) L (N, N) N (L, L, G) N (N, N, N) N (N, L,...,L) L (N,...,N) N (N, L, G) N (N, N, N) N (N, L) N (N, F, N) F (N, L) N (N, B, N) B (G, L) L (N, N) N (L, L, G) N (N, N, N) N

81 n n o n h n n e n n ec n ed n e c < n ec (n ed = None) (e d = n ed ) e b = True n n

82 k 2 k

83

84

85

86

87

88

89

90

91

92

93

94 !"#"$$$%&'(")&'*("$+&'**("$$*("$,&'("-&'***" "!./012.)"#"$'(")(",*" "!./012.%"#"$'(")("+("+("-*" "!./343"""#"$%&'(")&'("+&'(",&'("-&'*" [1, 2, 3] [1, 2, 3.0] [[1, 2], [3]] [[1, 2],3]

95 n m ψm (ψ + n 1)m ψmn ψ

96 3, 3, Unit [[1, 2, 3], [4, 5, 6], [7, 8, 9]] (3, 3) (3, 1) [1, 2, 3, 4, 5, 6, 7, 8, 9] (1, 3) [1, 4, 7, 2, 5, 8, 3, 6, 9] (1, 4) [1, 4, 7,, 2, 5, 8,, 3, 6, 9, ]

97

98 6.39s 0.52s 195µs 6.04s 0.49s 202µs 5.82s 0.49s 171µs 7.46s 0.63s 360µs

99

100

101 { } { }

102 A = M K K K M = 4 K = 3 K M

103

104 Ax = b A

105

106 A M 1 x 0 b n r 0 = b Ax 0 z 0 = M 1 r 0 p 0 = z 0 k = 0 rt k z k α k = pk T Ap k x k+1 = x k + α k p k r k+1 = r k α k Ap k z k+1 = M 1 r k+1 β k = zt k+1 r k+1 z T k r k p k+1 = z k+1 + β k p k k = k + 1 k > n M 1 a, b, c [ ] ai b m i = i [ ] 1 [ ] p i = m 1 ai b i = i 1 ci b = i b i c i a i c i b i b i b i a i b i c i

107 v i V v i V i v 1 n i V n i α i β i ff fi

108

109

110 A v 1 V i = 1 z i = Av i α i = z T i V i z i = z i VV T z i β i = z i V i+1 = z i /β i i = i + 1

111 T j j j α 1, α 2,...,α j β 1, β 2,...,β j 1 SΘS = T j

112 x R n y { 1, 1} x i, i {1,..., l} y i, i {1,..., l} max α F(α) = subject to l i=1 α i 1 2 αt Qα 0 α i C, i 1...l y T α = 0 x i R n i y i { 1, 1} x i α i C Q ij = y i y j Φ(x i, x j ) Φ(x i, x j ) Φ(x i, x j ; γ) =exp { γ x i x j 2} γ

113 α i x i y i i {1..l} τ α i f i = y i i {1..l} b high b low i high i low α ihigh α ilow f i i {1..l} b high i high b low i low α ihigh α ilow b low b high + 2τ b high = 1 i high = min{i : y i = 1} b low = 1 i low = min{i : y i = 1} i high i low α i low = α ilow + y ilow (b high b low )/η α i high = α ihigh + y ilow y ihigh (α ilow α i low ) η = Φ(x ihigh, x ihigh )+Φ(x ilow, x ilow ) 2Φ(x ihigh, x ilow ) α i low α i high 0 α i C f i = l j=1 α jy j Φ(x i, x j ) y i α f f i = f i +(α i high α ihigh )y ihigh Φ(x ihigh, x i ) +(α i low α ilow )y ilow Φ(x ilow, x i )

114 I high = {i :0< α i < C} {i : y i > 0, α i = 0} {i : y i < 0, α i = C} I low = {i :0< α i < C} {i : y i > 0, α i = C} {i : y i < 0, α i = 0} ɛ {i : ɛ < α i < (C ɛ)} b high = min{ f i : i I high } b low = max{ f i : i I low } b low b high + 2τ i high i low α i high = arg min{ f i : i I high } i low = arg max{ f i : i I low }

115

116

117

118

119

120

121 1 ψ ψ > % 100% 10% 33% 9

122 45 100%

123 {Distributed, Sequential}

124

125 45 100%

126

127

128

129

130

131

132

Fast Support Vector Machine Training and Classification on Graphics Processors

Fast Support Vector Machine Training and Classification on Graphics Processors Fast Support Vector Machine Training and Classification on Graphics Processors Bryan Christopher Catanzaro Narayanan Sundaram Kurt Keutzer Electrical Engineering and Computer Sciences University of California

More information

Copyright 2013 wolfssl Inc. All rights reserved. 2

Copyright 2013 wolfssl Inc. All rights reserved. 2 - - Copyright 2013 wolfssl Inc. All rights reserved. 2 Copyright 2013 wolfssl Inc. All rights reserved. 2 Copyright 2013 wolfssl Inc. All rights reserved. 3 Copyright 2013 wolfssl Inc. All rights reserved.

More information

PRESS RELEASE Sw y x e m b r a c e s En t e r p r i s e m a r k e t w i t h l a u n c h o f n e w I P t e l e p h o n y p o r t f o l i o t h r o u g h a s i n g l e c o m m o n p l a t f o r m - New offerings

More information

6. Cholesky factorization

6. Cholesky factorization 6. Cholesky factorization EE103 (Fall 2011-12) triangular matrices forward and backward substitution the Cholesky factorization solving Ax = b with A positive definite inverse of a positive definite matrix

More information

OPTIMAL SELECTION BASED ON RELATIVE RANK* (the "Secretary Problem")

OPTIMAL SELECTION BASED ON RELATIVE RANK* (the Secretary Problem) OPTIMAL SELECTION BASED ON RELATIVE RANK* (the "Secretary Problem") BY Y. S. CHOW, S. MORIGUTI, H. ROBBINS AND S. M. SAMUELS ABSTRACT n rankable persons appear sequentially in random order. At the ith

More information

Users Guide. Exchange ActiveSync mail account Setup: mail1.t5.fi

Users Guide. Exchange ActiveSync mail account Setup: mail1.t5.fi 1-Mar-2014 1 Users Guide Exchange ActiveSync mail account Setup: mail1.t5.fi Contents 1. Introduction...1 2. Account Setup on Samsung Galaxy S...2 3. Account Setup on Samsung Galaxy S II/S III Mini...3

More information

AdaBoost. Jiri Matas and Jan Šochman. Centre for Machine Perception Czech Technical University, Prague http://cmp.felk.cvut.cz

AdaBoost. Jiri Matas and Jan Šochman. Centre for Machine Perception Czech Technical University, Prague http://cmp.felk.cvut.cz AdaBoost Jiri Matas and Jan Šochman Centre for Machine Perception Czech Technical University, Prague http://cmp.felk.cvut.cz Presentation Outline: AdaBoost algorithm Why is of interest? How it works? Why

More information

Lecture 13 Linear quadratic Lyapunov theory

Lecture 13 Linear quadratic Lyapunov theory EE363 Winter 28-9 Lecture 13 Linear quadratic Lyapunov theory the Lyapunov equation Lyapunov stability conditions the Lyapunov operator and integral evaluating quadratic integrals analysis of ARE discrete-time

More information

= y y 0. = z z 0. (a) Find a parametric vector equation for L. (b) Find parametric (scalar) equations for L.

= y y 0. = z z 0. (a) Find a parametric vector equation for L. (b) Find parametric (scalar) equations for L. Math 21a Lines and lanes Spring, 2009 Lines in Space How can we express the equation(s) of a line through a point (x 0 ; y 0 ; z 0 ) and parallel to the vector u ha; b; ci? Many ways: as parametric (scalar)

More information

Innovation and Entrepreneurship in Renewable Energy

Innovation and Entrepreneurship in Renewable Energy Innovation and Entrepreneurship in Renewable Energy Ramana Nanda Harvard Business School Ken Younge Purdue University Lee Fleming University of California, Berkeley College of Engineering University of

More information

HowEasily Find the Best Lowest Price Possible For a Wedding

HowEasily Find the Best Lowest Price Possible For a Wedding Enabling Dynamic Content Caching for Database-Driven Web Sites K. Selçuk Candan Wen-Syan Li Qiong Luo Wang-Pin Hsiung Divyakant Agrawal C&C Research Laboratories, NEC USA, Inc., 110 Rio Robles, San Jose,

More information

Users Guide. Exchange ActiveSync mail account Setup: mail.t5.fi

Users Guide. Exchange ActiveSync mail account Setup: mail.t5.fi 1-Mar-2014 1 Users Guide Exchange ActiveSync mail account Setup: mail.t5.fi Contents 1. Introduction...1 2. Account Setup on Samsung Galaxy S...2 3. Account Setup on Samsung Galaxy S II/S III Mini...3

More information

Working Set Selection Using Second Order Information for Training Support Vector Machines

Working Set Selection Using Second Order Information for Training Support Vector Machines Journal of Machine Learning Research 6 (25) 889 98 Submitted 4/5; Revised /5; Published /5 Working Set Selection Using Second Order Information for Training Support Vector Machines Rong-En Fan Pai-Hsuen

More information

Preference and Similaritybased Behavioral Discovery of Services

Preference and Similaritybased Behavioral Discovery of Services Preference and Similaritybased Behavioral Discovery of Services Farhad Arbab 1 and Francesco Santini 1,2 1 Centrum Wiskunde & Informatica, Amsterdam, Netherlands 2 Dipartimento di Matematica e Informatica,

More information

Open Source Software Maintenance Process Framework

Open Source Software Maintenance Process Framework Open Source Software Maintenance Process Framework Timo Koponen Department of Computer Science University of Kuopio Box 163, 70211 Kuopio, Finland +358-17-162388 timo.koponen@uku.fi Virpi Hotti Department

More information

LINES AND PLANES CHRIS JOHNSON

LINES AND PLANES CHRIS JOHNSON LINES AND PLANES CHRIS JOHNSON Abstract. In this lecture we derive the equations for lines and planes living in 3-space, as well as define the angle between two non-parallel planes, and determine the distance

More information

An Investigation of Geographic Mapping Techniques for Internet Hosts

An Investigation of Geographic Mapping Techniques for Internet Hosts An Investigation of Geographic Mapping Techniques for Internet Hosts Venkata N. Padmanabhan Microsoft Research Lakshminarayanan Subramanian Ý University of California at Berkeley ABSTRACT ÁÒ Ø Ô Ô Ö Û

More information

A Study on SMO-type Decomposition Methods for Support Vector Machines

A Study on SMO-type Decomposition Methods for Support Vector Machines 1 A Study on SMO-type Decomposition Methods for Support Vector Machines Pai-Hsuen Chen, Rong-En Fan, and Chih-Jen Lin Department of Computer Science, National Taiwan University, Taipei 106, Taiwan cjlin@csie.ntu.edu.tw

More information

Ďě Ž ť č ď ť ď ú ď ť ě Ě ň Ě ě ú ň ž ú ú Ú ú ú Ě ň é é ž ú ž Ť Ť Ť ú ň Ď ú ň ď Ě ú É ž ř ú ě ň ý Ě ň ý ň ň Ť ř ď ř ň ú Ť ě ř ě ý Š Ú Ú ň ň ú Ó Ú ň Ň Ů ž ú ň Č ř ř ú É ě ň ú Ž ý ú ú Ú Ú ť ž ž ď ý ž ď ž

More information

How To Develop A Tablet Processor

How To Develop A Tablet Processor Market Intelligence & Consulting Institute http://www.marketresearch.com/market Intelligencev3289/ Publisher Sample Phone: 800.298.5699 (US) or +1.240.747.3093 or +1.240.747.3093 (Int'l) Hours: Monday

More information

technology brief RAID Levels March 1997 Introduction Characteristics of RAID Levels

technology brief RAID Levels March 1997 Introduction Characteristics of RAID Levels technology brief RAID Levels March 1997 Introduction RAID is an acronym for Redundant Array of Independent Disks (originally Redundant Array of Inexpensive Disks) coined in a 1987 University of California

More information

Section 2.4: Equations of Lines and Planes

Section 2.4: Equations of Lines and Planes Section.4: Equations of Lines and Planes An equation of three variable F (x, y, z) 0 is called an equation of a surface S if For instance, (x 1, y 1, z 1 ) S if and only if F (x 1, y 1, z 1 ) 0. x + y

More information

Computing Global Tablet and Application Processor Development Trends, 2012 and Beyond

Computing Global Tablet and Application Processor Development Trends, 2012 and Beyond Industry Intelligence Program Computing Global Tablet and Application Processor Development Trends, 2012 and Beyond Abstract The global tablet industry has begun the trends featuring high specifications

More information

Principle Two-. Learning Engages the Entire Physiology

Principle Two-. Learning Engages the Entire Physiology Principle One: The Brain Is a Parallel Processor Principle Two-. Learning Engages the Entire Physiology Photograph by Rosemary Rappoport. Htaleab Florida By providing a stimulating classroom environment,

More information

Training and Certification Guide - Axapta

Training and Certification Guide - Axapta Training and Certification Guide - Axapta Minimum Partner Certification Requirements Temporary Authorisation (must be obtained within 6 months of signing the partner agreement) No. of required certifications

More information

Network Performance Monitoring at Small Time Scales

Network Performance Monitoring at Small Time Scales Network Performance Monitoring at Small Time Scales Konstantina Papagiannaki, Rene Cruz, Christophe Diot Sprint ATL Burlingame, CA dina@sprintlabs.com Electrical and Computer Engineering Department University

More information

Redundant Array of Independent Disks (RAID)

Redundant Array of Independent Disks (RAID) For Data Centers Redundant Array of Independent Disks (RAID) Combine and control multiple storage devices for better performance and reliability Application note 2014 Samsung Electronics Co. 1. What is?

More information

PRODUCTION PLANNING AND SCHEDULING Part 1

PRODUCTION PLANNING AND SCHEDULING Part 1 PRODUCTION PLANNING AND SCHEDULING Part Andrew Kusiak 9 Seamans Center Iowa City, Iowa - 7 Tel: 9-9 Fax: 9-669 andrew-kusiak@uiowa.edu http://www.icaen.uiowa.edu/~ankusiak Forecasting Planning Hierarchy

More information

Blake Library Special Collections

Blake Library Special Collections Collection number: Aroos. MS 1 COLLECTION FINDING AID Title: Geological Survey (U.S.) aerial photographs of Fort Kent (Me.) Dates: 1975 Creator/collector: Extent: Provenance: Language: Conservation notes:

More information

Processor Architectures

Processor Architectures ECPE 170 Jeff Shafer University of the Pacific Processor Architectures 2 Schedule Exam 3 Tuesday, December 6 th Caches Virtual Memory Input / Output OperaKng Systems Compilers & Assemblers Processor Architecture

More information

Federation Proxy for Cross Domain Identity Federation

Federation Proxy for Cross Domain Identity Federation Proxy for Cross Domain Identity Makoto Hatakeyama NEC Corporation, Common Platform Software Res. Lab. 1753, Shimonumabe, Nakahara-Ku, Kawasaki, Kanagawa 211-8666, Japan +81-44-431-7663 m-hatake@ax.jp.nec.com

More information

Lecture Topic: Low-Rank Approximations

Lecture Topic: Low-Rank Approximations Lecture Topic: Low-Rank Approximations Low-Rank Approximations We have seen principal component analysis. The extraction of the first principle eigenvalue could be seen as an approximation of the original

More information

Integration of Upper Division Business Core Classes: A Lesson in Informing Science

Integration of Upper Division Business Core Classes: A Lesson in Informing Science Informing Science InSITE - Where Parallels Intersect June 2002 Integration of Upper Division Business Core Classes: A Lesson in Informing Science John D. Haney and Mary Bowers Northern Arizona University,

More information

How To Map Behavior Goals From Facebook On The Behavior Grid

How To Map Behavior Goals From Facebook On The Behavior Grid The Behavior Grid: 35 Ways Behavior Can Change BJ Fogg Persuasive Technology Lab Stanford University captology.stanford.edu www.bjfogg.com bjfogg@stanford.edu ABSTRACT This paper presents a new way of

More information

Versions Addressed: Microsoft Office Outlook 2010/2013. Document Updated: 2014. Copyright 2014 Smarsh, Inc. All right reserved

Versions Addressed: Microsoft Office Outlook 2010/2013. Document Updated: 2014. Copyright 2014 Smarsh, Inc. All right reserved Versions Addressed: Microsoft Office Outlook 2010/2013 Document Updated: 2014 Copyright 2014 Smarsh, Inc. All right reserved Table of Contents Getting Started 3 Add Your New Account 3 Account Setup 5 Basic

More information

Using Workflow Technology to Manage Flexible e-learning Services

Using Workflow Technology to Manage Flexible e-learning Services Educational Technology & Society 5(4) 2002 ISSN 1436-4522 Using Workflow Technology to Manage Flexible e-learning Services Joe Lin, Charley Ho, Wasim Sadiq, Maria E. Orlowska Distributed Systems Technology

More information

Multi-asset Minority Games

Multi-asset Minority Games Multi-asset Minority Games A De Martino (Roma) Joint work with G Bianconi and M Marsili (Trieste) 1. Minority Games with one asset a. Economists : competition under uncertainty, inductive reasoning b.

More information

Course materials. In addition to these slides, C++ API header files, a set of exercises, and solutions, the following are useful:

Course materials. In addition to these slides, C++ API header files, a set of exercises, and solutions, the following are useful: Course materials In addition to these slides, C++ API header files, a set of exercises, and solutions, the following are useful: OpenCL C 1.2 Reference Card OpenCL C++ 1.2 Reference Card These cards will

More information

ArcGIS for. Intelligence

ArcGIS for. Intelligence ArcGIS for ArcGIS for solutions.arcgis.com/intelligence Copyright 2015 Esri. All rights reserved. 146660 DUAL3M7/15rk Briefing Book ArcGIS for Briefing Book ArcGIS Web Application ArcGIS for Create and

More information

Duality in General Programs. Ryan Tibshirani Convex Optimization 10-725/36-725

Duality in General Programs. Ryan Tibshirani Convex Optimization 10-725/36-725 Duality in General Programs Ryan Tibshirani Convex Optimization 10-725/36-725 1 Last time: duality in linear programs Given c R n, A R m n, b R m, G R r n, h R r : min x R n c T x max u R m, v R r b T

More information

Overview of the Electrical Engineering and Computer Sciences Department at UC Berkeley

Overview of the Electrical Engineering and Computer Sciences Department at UC Berkeley Overview of the Electrical Engineering and Computer Sciences Department at UC Berkeley Prof. Tsu Jae King Liu, Chair Department of Electrical Engineering and Computer Sciences University of California,

More information

A Look Inside Smartphone and Tablets

A Look Inside Smartphone and Tablets A Look Inside Smartphone and Tablets Devices and Trends John Scott-Thomas TechInsights Semicon West July 9, 2013 Teardown 400 phones and tablets a year Four areas: Customer Focus Camera Display Manufacturer

More information

Write the Equation of the Line Review

Write the Equation of the Line Review Connecting Algebra 1 to Advanced Placement* Mathematics A Resource and Strategy Guide Objective: Students will be assessed on their ability to write the equation of a line in multiple methods. Connections

More information

Using Excel to Simplify Business Network Enablement:

Using Excel to Simplify Business Network Enablement: Using Excel to Simplify Business Network Enablement: Leveraging the EIDX Excel Workgroup Results to automate with SMB partners Bryan Larkin Industry Marketing GXS Getting Started Using Excel to Enable

More information

Math 55: Discrete Mathematics

Math 55: Discrete Mathematics Math 55: Discrete Mathematics UC Berkeley, Fall 2011 Homework # 5, due Wednesday, February 22 5.1.4 Let P (n) be the statement that 1 3 + 2 3 + + n 3 = (n(n + 1)/2) 2 for the positive integer n. a) What

More information

AIS Online Tools. Sophia Chen Manager, Account Information Security Singapore August 18, 2005

AIS Online Tools. Sophia Chen Manager, Account Information Security Singapore August 18, 2005 AIS Online Tools Sophia Chen Manager, Account Information Security Singapore August 18, 2005 Objectives Vulnerability Scanning what is it? Scanning Technology Overview Step-by-Step Simplified AIS Validation

More information

An Adaptive Scheduling Algorithm for Dynamic Heterogeneous Hadoop Systems

An Adaptive Scheduling Algorithm for Dynamic Heterogeneous Hadoop Systems An Adaptive Scheduling Algorithm for Dynamic Heterogeneous Hadoop Systems Aysan Rasooli, Douglas G. Down Department of Computing and Software McMaster University {rasooa, downd}@mcmaster.ca Abstract The

More information

BIG CPU, BIG DATA. Solving the World s Toughest Computational Problems with Parallel Computing. Alan Kaminsky

BIG CPU, BIG DATA. Solving the World s Toughest Computational Problems with Parallel Computing. Alan Kaminsky Solving the World s Toughest Computational Problems with Parallel Computing Alan Kaminsky Solving the World s Toughest Computational Problems with Parallel Computing Alan Kaminsky Department of Computer

More information

Measuring System Performance & User Satisfaction after Implementation of ERP

Measuring System Performance & User Satisfaction after Implementation of ERP Proceedings of Informing Science & IT Education Conference (InSITE) 2012 Measuring System Performance & User Satisfaction after Implementation of ERP Imran Batada Institute of Business Administration,

More information

Introduction to Scheduling Theory

Introduction to Scheduling Theory Introduction to Scheduling Theory Arnaud Legrand Laboratoire Informatique et Distribution IMAG CNRS, France arnaud.legrand@imag.fr November 8, 2004 1/ 26 Outline 1 Task graphs from outer space 2 Scheduling

More information

Unit Commitment and Economic Model Predictive Control for Optimal Operation of Power Systems

Unit Commitment and Economic Model Predictive Control for Optimal Operation of Power Systems Unit Commitment and Economic Model Predictive Control for Optimal Operation of Power Systems Peter Juhler Dinesen, s093053 M.Sc. Thesis, February 2015 DTU Compute Department of Applied Mathematics and

More information

15 May 2013 Version 5. for Mac OS X. Public version. Gemfor s.r.o. Tyršovo nám. 600 252 63 Roztoky Czech Republic

15 May 2013 Version 5. for Mac OS X. Public version. Gemfor s.r.o. Tyršovo nám. 600 252 63 Roztoky Czech Republic Mobile Connection Explorer for Mac OS X 15 May 2013 Version 5 Introduction and Feature s Public version Gemfor s.r.o. Contents Contents... 2 History... 2 1. Scope... 3 2. Abbreviations... 3 3. Introduction...

More information

A Survey of Enterprise Middlebox Deployments

A Survey of Enterprise Middlebox Deployments A Survey of Enterprise Middlebox Deployments Justine Sherry Sylvia Ratnasamy Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-202-24 http://www.eecs.berkeley.edu/pubs/techrpts/202/eecs-202-24.html

More information

Implementing an Interdisciplinary Masters Program in Internet Technology and E-Commerce

Implementing an Interdisciplinary Masters Program in Internet Technology and E-Commerce Informing Science InSITE - Where Parallels Intersect June 2002 Implementing an Interdisciplinary Masters Program in Internet Technology and E-Commerce Daniel J. Farkas and Narayan Murthy Pace University,

More information

Intel Atom Processor Tristan Greenidge CPTR 350 Introduction Intel Atom is Intel s line for ultra-low-voltage processors. Atoms are used in netbooks, nettops, embedded applications ranging from health

More information

Real time vehicle detection and tracking on multiple lanes

Real time vehicle detection and tracking on multiple lanes Real time vehicle detection and tracking on multiple lanes Kristian Kovačić Edouard Ivanjko Hrvoje Gold Department of Intelligent Transportation Systems Faculty of Transport and Traffic Sciences University

More information

Security Policy for FIPS 140 2 Validation

Security Policy for FIPS 140 2 Validation BitLocker Windows OS Loader Security Policy for FIPS 140 2 Validation BitLocker Windows OS Loader (winload) in Microsoft Windows 8.1 Enterprise Windows Server 2012 R2 Windows Storage Server 2012 R2 Surface

More information

MEDIA SHARE Set Up Guide for PCs with Windows 7

MEDIA SHARE Set Up Guide for PCs with Windows 7 MEDIA SHARE Set Up Guide for PCs with Windows 7 AT&T Media Share allows you to view photos and listen to music files that are stored on your PC on your U-verse-connected TV. In order to share photo and

More information

Improving MapReduce Performance in Heterogeneous Environments

Improving MapReduce Performance in Heterogeneous Environments UC Berkeley Improving MapReduce Performance in Heterogeneous Environments Matei Zaharia, Andy Konwinski, Anthony Joseph, Randy Katz, Ion Stoica University of California at Berkeley Motivation 1. MapReduce

More information

1. Oblast rozvoj spolků a SU UK 1.1. Zvyšování kvalifikace Školení Zapojení do projektů Poradenství 1.2. Financování 1.2.1.

1. Oblast rozvoj spolků a SU UK 1.1. Zvyšování kvalifikace Školení Zapojení do projektů Poradenství 1.2. Financování 1.2.1. 1. O b l a s t r o z v o j s p o l k a S U U K 1. 1. Z v y š o v á n í k v a l i f i k a c e Š k o l e n í o S t u d e n t s k á u n i e U n i v e r z i t y K a r l o v y ( d á l e j e n S U U K ) z í

More information

Archiving Scientific Data

Archiving Scientific Data Archiving Scientific Data Peter Buneman Sanjeev Khanna Ý Keishi Tajima Þ Wang-Chiew Tan Ü ABSTRACT Ï ÔÖ ÒØ Ò Ö Ú Ò Ø Ò ÕÙ ÓÖ Ö Ö Ð Ø Û Ø Ý ØÖÙØÙÖ º ÇÙÖ ÔÔÖÓ ÓÒ Ø ÒÓ¹ Ø ÓÒ Ó Ø Ñ Ø ÑÔ Û Ö Ý Ò Ð Ñ ÒØ ÔÔ Ö

More information

Introduction to Microprocessors

Introduction to Microprocessors Introduction to Microprocessors Yuri Baida yuri.baida@gmail.com yuriy.v.baida@intel.com October 2, 2010 Moscow Institute of Physics and Technology Agenda Background and History What is a microprocessor?

More information

Installation & Configuration Guide Version 1.0. TekSMTP Version 1.0 - Installation & Configuration Guide

Installation & Configuration Guide Version 1.0. TekSMTP Version 1.0 - Installation & Configuration Guide TekSMTP Installation & Configuration Guide Version 1.0 2013 KaplanSoft - http://www.kaplansoft.com/ 1 Document Revision 1.0 http://www.kaplansoft.com/ TekSMTP is built by Yasin KAPLAN Read Readme.txt for

More information

Dell Open Manage System Administrator (Free software to manage and maintain your server hardware) Hardware Dell PowerEdge T320 or R320

Dell Open Manage System Administrator (Free software to manage and maintain your server hardware) Hardware Dell PowerEdge T320 or R320 Greenway PrimeSUITE Overview This document is to be used only as a guideline when considering hardware for use with PrimeSUITE. All server and workstation specs are Dell hardware, MDS Medical's preferred

More information

SAP NetWeaver 7.5 Browser Support PAM Table of Content

SAP NetWeaver 7.5 Browser Support PAM Table of Content SAP NetWeaver 7.5 Browser Support PAM Table of Content SAP Browser Support Summary SAP Desktop Browser Support Policy SAP Mobile Browser Support Policy Desktop Browser Support SAPUI5, Desktop & Mobile

More information

Parallels Plesk Panel

Parallels Plesk Panel Parallels Plesk Panel Copyright Notice Parallels Holdings, Ltd. c/o Parallels International GmbH Vordergasse 59 CH-Schaffhausen Switzerland Phone: +41-526320-411 Fax: +41-52672-2010 Copyright 1999-2011

More information

The FOSSology Project Overview and Discussion. » The Open Compliance Program. ... By Bob Gobeille, Hewlett-Packard

The FOSSology Project Overview and Discussion. » The Open Compliance Program. ... By Bob Gobeille, Hewlett-Packard » The Open Compliance Program The FOSSology Project Overview and Discussion By Bob Gobeille, Hewlett-Packard A White Paper By The Linux Foundation FOSSology (http://fossologyorg) is an open source compliance

More information

Applications to Data Smoothing and Image Processing I

Applications to Data Smoothing and Image Processing I Applications to Data Smoothing and Image Processing I MA 348 Kurt Bryan Signals and Images Let t denote time and consider a signal a(t) on some time interval, say t. We ll assume that the signal a(t) is

More information

MEDIA SHARE Set Up Guide for PCs with Windows XP

MEDIA SHARE Set Up Guide for PCs with Windows XP MEDIA SHARE Set Up Guide for PCs with Windows XP AT&T Media Share allows you to view photos and listen to music files that are stored on your PC on your U-verse-connected TV. In order to share photo and

More information

The Harvard CSE Curriculum, Its Advantages and Disadvantages

The Harvard CSE Curriculum, Its Advantages and Disadvantages powering 21 st century discovery and innovation computational science and engineering at harvard university Institute for Applied Computational Science IACS graduate programs in computational science and

More information

Elemental functions: Writing data-parallel code in C/C++ using Intel Cilk Plus

Elemental functions: Writing data-parallel code in C/C++ using Intel Cilk Plus Elemental functions: Writing data-parallel code in C/C++ using Intel Cilk Plus A simple C/C++ language extension construct for data parallel operations Robert Geva robert.geva@intel.com Introduction Intel

More information

Get me off Your Fucking Mailing List

Get me off Your Fucking Mailing List Get me off Your Fucking Mailing List David Mazières and Eddie Kohler New York University University of California, Los Angeles http://www.mailavenger.org/ Abstract off off off mailing 1 Introduction off

More information

University of L Aquila Center of Excellence DEWS Poggio di Roio 67040 L Aquila, Italy http://www.diel.univaq.it/dews

University of L Aquila Center of Excellence DEWS Poggio di Roio 67040 L Aquila, Italy http://www.diel.univaq.it/dews University of L Aquila Center of Excellence DEWS Poggio di Roio 67040 L Aquila, Italy http://www.diel.univaq.it/dews Locating ZigBee Nodes Using the TI s CC2431 Location Engine: A Testbed Platform and

More information

Man-in-the-Middle Attack on T-Mobile Wi-Fi Calling

Man-in-the-Middle Attack on T-Mobile Wi-Fi Calling Man-in-the-Middle Attack on T-Mobile Wi-Fi Calling Jethro Beekman Christopher Thompson Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2013-18

More information

Diusion processes. Olivier Scaillet. University of Geneva and Swiss Finance Institute

Diusion processes. Olivier Scaillet. University of Geneva and Swiss Finance Institute Diusion processes Olivier Scaillet University of Geneva and Swiss Finance Institute Outline 1 Brownian motion 2 Itô integral 3 Diusion processes 4 Black-Scholes 5 Equity linked life insurance 6 Merton

More information

BACKUP BENCHMARKING OF VERY L ARGE MICROSOFT SQL S ERVER 7.0 D ATABASES DURING ACTIVE ONLINE T RANSACTION PERFORMANCE L OADING ON COMPAQ HARDWARE

BACKUP BENCHMARKING OF VERY L ARGE MICROSOFT SQL S ERVER 7.0 D ATABASES DURING ACTIVE ONLINE T RANSACTION PERFORMANCE L OADING ON COMPAQ HARDWARE BACKUP BENCHMARKING OF VERY L ARGE MICROSOFT SQL S ERVER 7.0 D ATABASES DURING ACTIVE ONLINE T RANSACTION PERFORMANCE L OADING ON COMPAQ HARDWARE By Torrey Russell Backup & Disaster Recovery for Windows

More information

The Open University s repository of research publications and other research outputs

The Open University s repository of research publications and other research outputs Open Research Online The Open University s repository of research publications and other research outputs Continued Involvement in Software Development: Motivational Factors Conference Item How to cite:

More information

Telecom Italia and WSN

Telecom Italia and WSN Telecom Italia Project Berkeley, March 2007 Telecom Italia and Project T.IE.RT.RP Summary Telecom Italia & From nodes to services Demonstrators Why a standard? Conclusion 1 Lab by Pirelli & Telecom Italia

More information

( ) = ( ) = {,,, } β ( ), < 1 ( ) + ( ) = ( ) + ( )

( ) = ( ) = {,,, } β ( ), < 1 ( ) + ( ) = ( ) + ( ) { } ( ) = ( ) = {,,, } ( ) β ( ), < 1 ( ) + ( ) = ( ) + ( ) max, ( ) [ ( )] + ( ) [ ( )], [ ( )] [ ( )] = =, ( ) = ( ) = 0 ( ) = ( ) ( ) ( ) =, ( ), ( ) =, ( ), ( ). ln ( ) = ln ( ). + 1 ( ) = ( ) Ω[ (

More information

Activities and Resources in Online Learning: From a Critical Thinking View

Activities and Resources in Online Learning: From a Critical Thinking View Proceedings of Informing Science & IT Education Conference (InSITE) 2012 Activities and Resources in Online Learning: From a Critical Thinking View Danielle Morin Concordia University, John Molson School

More information

Parallels Mac Management v4.0

Parallels Mac Management v4.0 Parallels Mac Management v4.0 Deployment Guide July 18, 2015 Copyright 1999 2015 Parallels IP Holdings GmbH and its affiliates. All rights reserved. All other marks and names mentioned herein may be trademarks

More information

Nimble Algorithms for Cloud Computing. Ravi Kannan, Santosh Vempala and David Woodruff

Nimble Algorithms for Cloud Computing. Ravi Kannan, Santosh Vempala and David Woodruff Nimble Algorithms for Cloud Computing Ravi Kannan, Santosh Vempala and David Woodruff Cloud computing Data is distributed arbitrarily on many servers Parallel algorithms: time Streaming algorithms: sublinear

More information

Video Conferencing System Requirements

Video Conferencing System Requirements Video Conferencing System Requirements TrueConf system and network requirements depend on chosen video conferencing mode and applied video quality. Video resolution and frame rate are selected automatically

More information

Outlook 2010 Setup Guide (POP3)

Outlook 2010 Setup Guide (POP3) Versions Addressed: Microsoft Office Outlook 2010 Document Updated: 8/31/2012 Copyright 2012 Smarsh, Inc. All rights Purpose: This document will assist the end user in configuring Outlook 2010 to access

More information

DATA ANALYSIS II. Matrix Algorithms

DATA ANALYSIS II. Matrix Algorithms DATA ANALYSIS II Matrix Algorithms Similarity Matrix Given a dataset D = {x i }, i=1,..,n consisting of n points in R d, let A denote the n n symmetric similarity matrix between the points, given as where

More information

Optimal Scheduling for Dependent Details Processing Using MS Excel Solver

Optimal Scheduling for Dependent Details Processing Using MS Excel Solver BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 8, No 2 Sofia 2008 Optimal Scheduling for Dependent Details Processing Using MS Excel Solver Daniela Borissova Institute of

More information

BIG CPU, BIG DATA. Solving the World s Toughest Computational Problems with Parallel Computing. Alan Kaminsky

BIG CPU, BIG DATA. Solving the World s Toughest Computational Problems with Parallel Computing. Alan Kaminsky Solving the World s Toughest Computational Problems with Parallel Computing Solving the World s Toughest Computational Problems with Parallel Computing Department of Computer Science B. Thomas Golisano

More information

Resource Utilization of Middleware Components in Embedded Systems

Resource Utilization of Middleware Components in Embedded Systems Resource Utilization of Middleware Components in Embedded Systems 3 Introduction System memory, CPU, and network resources are critical to the operation and performance of any software system. These system

More information

Distributed Machine Learning and Big Data

Distributed Machine Learning and Big Data Distributed Machine Learning and Big Data Sourangshu Bhattacharya Dept. of Computer Science and Engineering, IIT Kharagpur. http://cse.iitkgp.ac.in/~sourangshu/ August 21, 2015 Sourangshu Bhattacharya

More information

The Steepest Descent Algorithm for Unconstrained Optimization and a Bisection Line-search Method

The Steepest Descent Algorithm for Unconstrained Optimization and a Bisection Line-search Method The Steepest Descent Algorithm for Unconstrained Optimization and a Bisection Line-search Method Robert M. Freund February, 004 004 Massachusetts Institute of Technology. 1 1 The Algorithm The problem

More information

m Future of learning Zehn J a hr e N et A c a d ei n E r f o l g s p r o g r a m Cisco E x p o 2 0 0 7 2 6. J u n i 2 0 0 7, M e sse W ie n C. D or n in g e r, b m u k k 1/ 12 P r e n t t z d e r p u t

More information

Implementation of Stereo Matching Using High Level Compiler for Parallel Computing Acceleration

Implementation of Stereo Matching Using High Level Compiler for Parallel Computing Acceleration Implementation of Stereo Matching Using High Level Compiler for Parallel Computing Acceleration Jinglin Zhang, Jean François Nezan, Jean-Gabriel Cousin, Erwan Raffin To cite this version: Jinglin Zhang,

More information

SchedulAir. Airline planning & airline scheduling with Unified Optimization. decisal. Copyright 2014 Decisal Ltd. All rights reserved.

SchedulAir. Airline planning & airline scheduling with Unified Optimization. decisal. Copyright 2014 Decisal Ltd. All rights reserved. Copyright 2014 Decisal Ltd. All rights reserved. Airline planning & airline scheduling with Unified Optimization SchedulAir Overview Unified Optimization Benders decomposition Airline planning & scheduling

More information

Adaptive Stable Additive Methods for Linear Algebraic Calculations

Adaptive Stable Additive Methods for Linear Algebraic Calculations Adaptive Stable Additive Methods for Linear Algebraic Calculations József Smidla, Péter Tar, István Maros University of Pannonia Veszprém, Hungary 4 th of July 204. / 2 József Smidla, Péter Tar, István

More information

Creating Customer Value in Participating

Creating Customer Value in Participating in Participating Life Insurance Nadine Gatzert, Ines Holzmüller, and Hato Schmeiser Page 2 1. Introduction Participating life insurance contracts contain numerous guarantees and options: - E.g., minimum

More information

2015 Qualcomm Technologies, Inc. All rights reserved.

2015 Qualcomm Technologies, Inc. All rights reserved. Qualcomm Technologies, Inc Qualcomm Snapdragon 600 Processor APQ8064 MultiMediaCard/Secure Digital Card Application Note LM80-P0598-7 Rev A June 2015 2015 Qualcomm Technologies, Inc All rights reserved

More information

Laptop vs. Tablet. What Should I Buy? Presented by: Matt Harmon & Rob Germeroth

Laptop vs. Tablet. What Should I Buy? Presented by: Matt Harmon & Rob Germeroth Laptop vs. Tablet What Should I Buy? Presented by: Matt Harmon & Rob Germeroth Intro Survey Take a few minutes to answer the questions we gave you. Feel free to elaborate on your answers in the margins

More information