lecture 20 networks and communication
play

Lecture 20: Networks and Communication Abhinav Bhatele, Department - PowerPoint PPT Presentation

Jan 09, 2023 •186 likes •668 views

Introduction to Parallel Computing (CMSC498X / CMSC818X) Lecture 20: Networks and Communication Abhinav Bhatele, Department of Computer Science Announcements Assignment 3 posted online Only for 818X students Due on November 23

  1. Introduction to Parallel Computing (CMSC498X / CMSC818X) Lecture 20: Networks and Communication Abhinav Bhatele, Department of Computer Science

  2. Announcements • Assignment 3 posted online • Only for 818X students • Due on November 23 • Quiz 2: November 12 Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 2

  3. High-speed interconnection networks • Typically supercomputers and HPC clusters are connected by low latency and high bandwidth networks • The connections between nodes form different topologies • Popular topologies: • Fat-tree: Charles Leiserson in 1985 • Mesh and torus networks • Dragonfly networks Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 3

  4. Network components • Network interface controller or card • Router or switch • Network cables: copper or optical Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 4

  5. N-dimensional mesh / torus networks • Each switch as a small number of nodes connected to it (typically 1) • Each switch has direct links to 2n switches where n is the number of dimensions • Torus = wraparound links • Examples: IBM Blue Gene, Cray X* machines Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 5

  6. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  7. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  8. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  9. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  10. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Level 1 Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  11. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Level 2 Level 1 Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  12. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Level 2 Level 1 Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  13. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Level 2 Level 1 Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  14. Fat-tree network • Router radix = k, Number of nodes on each router = k/2 • A pod is a group of k/2 switches, Max. number of pods = k Level 3 Level 2 Level 1 Compute Nodes Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 6

  15. Dragonfly network • Two-level hierarchical network using high-radix routers • Low network diameter � � � �� � LL �� � �� � � � � � � � �� � �� � �� � � �� � �� � � � �� � �� � �� � �� � LR �� � �� � �� � �� � �� � �� � �� � �� � �� � �� �� �� � �� � �� �� D �� �� �� �� �� �� �� � �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� � �� �� �� �� � �� �� �� �� � � �� �� �� �� �� � �� �� �� � �� � � � � �� � �� � �� � �� � �� � �� � �� � �� � �� � �� � �� � �� �� �� � �� � �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� � �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� � � � �� � �� � �� � � � � �� � �� � �� � �� � �� �� �� � �� � �� � �� � �� � �� � �� �� �� �� �� � �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� � � � �� �� �� �� �� � �� �� �� �� �� �� � �� � �� � � � �� � �� � �� � �� � �� � �� � �� � �� � �� � �� � �� �� �� � One supernode in the PERCS topology �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 7

  16. Life-cycle of a message Source Source Source Source Source Message origin points : destination, frequency, size, etc. determined by application 1 micro sec - 10s of sec Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 8

  17. Life-cycle of a message Source Packetization and injection : delay:100s of ns Source NIC Source Source Source Message origin points : destination, frequency, size, etc. determined by application 1 micro sec - 10s of sec Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 8

  18. Life-cycle of a message Source Packetization and injection : delay:100s of ns Source Routers/ NIC Source Switches Source Path finding delay ~100 ns Temp storage in buffers Source Message origin points : destination, frequency, size, etc. determined by application 1 micro sec - 10s of sec Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 8

  19. Life-cycle of a message Source Packetization and injection : Links - congestion points delay:100s of ns traversal time: 1-50 ns Source Routers/ NIC Source Switches Source Path finding delay ~100 ns Temp storage in buffers Source Message origin points : destination, frequency, size, etc. determined by application 1 micro sec - 10s of sec Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 8

  20. Life-cycle of a message Source Packetization and injection : Links - congestion points delay:100s of ns traversal time: 1-50 ns Source Routers/ Routers/ Destination NIC NIC Source Switches Switches Message destination points: Source Path finding application dependent delay ~100 ns 1 micro sec - 10s of sec Temp storage in buffers Source Message origin points : destination, frequency, size, etc. determined by application 1 micro sec - 10s of sec Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 8

  21. Congestion due to network sharing • Sharing refers to network flows of different programs using the same hardware resources: links, switches • When multiple programs communicate on the network, they all suffer from congestion on shared links Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 9

  22. Congestion due to network sharing • Sharing refers to network flows of different programs using the same hardware resources: links, switches • When multiple programs communicate on the network, they all suffer from congestion on shared links Switch/router Program A Program B Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 9

  23. Congestion due to network sharing • Sharing refers to network flows of different programs using the same hardware resources: links, switches • When multiple programs communicate on the network, they all suffer from congestion on shared links Switch/router Program A Program B Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 9

  24. Congestion due to network sharing • Sharing refers to network flows of different programs using the same hardware resources: links, switches • When multiple programs communicate on the network, they all suffer from congestion on shared links Switch/router Program A Program B Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 9

  25. Congestion due to network sharing • Sharing refers to network flows of different programs using the same hardware resources: links, switches • When multiple programs communicate on the network, they all suffer from congestion on shared links Switch/router Program A Program B Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 9

  26. Congestion due to network sharing • Sharing refers to network flows of different programs using the same hardware resources: links, switches • When multiple programs communicate on the network, they all suffer from congestion on shared links Switch/router Program A Program B Abhinav Bhatele (CMSC498X/CMSC818X) LIVE RECORDING 9

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

COMMUNICATION NETWORKS ECE 422 DATA COMMUNICATION & COMPUTER NETWORKS Wednesday, 12

COMMUNICATION NETWORKS ECE 422 DATA COMMUNICATION & COMPUTER NETWORKS Wednesday, 12

MULTIPLE ACCESS IN COMMUNICATION NETWORKS ECE 422 DATA COMMUNICATION & COMPUTER NETWORKS Wednesday, 12 February 2020 1 WHERE ARE WE IN THE SYLLABUS? Course Content: Introduction: Overview of Data Communications and Networking. Physical

922 views • 52 slides
Computer Networks 1 (M ng My Tnh 1) Lectured by: Nguy n c Thi Lecture 2:

Computer Networks 1 (M ng My Tnh 1) Lectured by: Nguy n c Thi Lecture 2:

Computer Networks 1 (M ng My Tnh 1) Lectured by: Nguy n c Thi Lecture 2: Communication Media Reference : Chapter 2 - Computer Networks , Andrew S. Tanenbaum, 4th Edition, Prentice Hall, 2003. Content Theoretical

562 views • 32 slides
Lecture 11 : Computer Networks and Internet 1 This Lecture Covers: Types of Computer

Lecture 11 : Computer Networks and Internet 1 This Lecture Covers: Types of Computer

UEC 01 : Computer Skills & Programming Concepts I Lecture 11 : Computer Networks and Internet 1 This Lecture Covers: Types of Computer Networks. Communication devices and media. Network Topology. LAN Components Network

435 views • 32 slides
3 Industrial Communication Networks Automation Overview 3 Industrial Communication Networks 3.1

3 Industrial Communication Networks Automation Overview 3 Industrial Communication Networks 3.1

EPFL, Spring 2017 3 Industrial Communication Networks Automation Overview 3 Industrial Communication Networks 3.1 Field bus principles 3.2 Field bus operation 3.3 Standard field busses 3.4 Industrial wireless communication Industrial

1.26k views • 87 slides
Computing over Unreliable Computing over Unreliable C C Communication Networks Communication

Computing over Unreliable Computing over Unreliable C C Communication Networks Communication

Computing over Unreliable Computing over Unreliable C C Communication Networks Communication Networks i i i i N N k k Nicola Elia Joint work with Jing Wang D Dept. of Electrical and Computer Engineering t f El t i l d C t E i i

833 views • 42 slides
Analysis of Peer to Peer Communication in Networks 2/15/10 Prestige Lecture Purdue University 1

Analysis of Peer to Peer Communication in Networks 2/15/10 Prestige Lecture Purdue University 1

Analysis of Peer to Peer Communication in Networks 2/15/10 Prestige Lecture Purdue University 1 Outline of presentation Overview Fluid analysis (after Massoulie and Vojnovic) Direct stochastic analysis (work with Ji Zhu)

484 views • 32 slides
CCM 4300 Lecture 3 Computer Networks: Wireless and Mobile Communication and Mobile Communication

CCM 4300 Lecture 3 Computer Networks: Wireless and Mobile Communication and Mobile Communication

CCM 4300 Lecture 3 Computer Networks: Wireless and Mobile Communication and Mobile Communication Systems

756 views • 37 slides
Information, Computation, and Communication Networks 1 ICC Module Systems Networks

Information, Computation, and Communication Networks 1 ICC Module Systems Networks

ICC Module Systems Networks Information, Computation, and Communication Networks 1 ICC Module Systems Networks Computer Networks 2 ICC Module Systems Networks Outline Communication protocols Packet switching Protocol

1.17k views • 82 slides
Electronic Communication Lecture 5 COMPSCI111 Todays lecture u Looking at how different

Electronic Communication Lecture 5 COMPSCI111 Todays lecture u Looking at how different

Electronic Communication Lecture 5 COMPSCI111 Todays lecture u Looking at how different types of electronic communication work u Email u Instant messaging u Forums u Issues with electronic communication u Spam u Netiquette u Security

511 views • 29 slides
Networks Eric McCreath Networks A communication networks provides the means by which computers

Networks Eric McCreath Networks A communication networks provides the means by which computers

Networks Eric McCreath Networks A communication networks provides the means by which computers can transfer information to and from other computing devices. The Internet has become the most extensive network for computers to communicated

635 views • 6 slides
Electronic Communication Lecture 5 COMPSCI111/111G Todays lecture u Looking at how

Electronic Communication Lecture 5 COMPSCI111/111G Todays lecture u Looking at how

Electronic Communication Lecture 5 COMPSCI111/111G Todays lecture u Looking at how different types of electronic communication work u Email u Instant messaging u Forums u Issues with electronic communication u Spam u Netiquette u Security

456 views • 29 slides
1 Agent Communication LECTURE 8: AGENT COMMUNICATION In this lecture, we cover macro-aspects of

1 Agent Communication LECTURE 8: AGENT COMMUNICATION In this lecture, we cover macro-aspects of

Lecture 8 An Introduction to Multiagent Systems 1 Agent Communication LECTURE 8: AGENT COMMUNICATION In this lecture, we cover macro-aspects of intelligent agent technology: those issues relating to the

181 views • 5 slides
1 The Worlds Undersea Data Networks Multi-Hop Networks How to deliver data

1 The Worlds Undersea Data Networks Multi-Hop Networks How to deliver data

Switches Orchestrate Link Sharing A switch is a computing device that allows many concurrent communications to share the network Communication Networks Switch 6.02 Fall 2010 Lecture #17 November 8, 2010 Sharing, a fundamental problem

399 views • 4 slides
Wireless Communication Systems @CS.NCTU Lecture 1: Introduction to Wireless Networks Instructor:

Wireless Communication Systems @CS.NCTU Lecture 1: Introduction to Wireless Networks Instructor:

Wireless Communication Systems @CS.NCTU Lecture 1: Introduction to Wireless Networks Instructor: Kate Ching-Ju Lin ( ) 1 Wireless Courses @ CS, NCTU /

720 views • 23 slides
Communication Systems SIP University of Freiburg Computer Science Computer Networks and

Communication Systems SIP University of Freiburg Computer Science Computer Networks and

Communication Systems SIP University of Freiburg Computer Science Computer Networks and Telematics Prof. Christian Schindelhauer Organization I. Data and voice communication in IP networks II. Security issues in networking

533 views • 28 slides
Communication Systems GSM University of Freiburg Computer Science Computer Networks and

Communication Systems GSM University of Freiburg Computer Science Computer Networks and

Communication Systems GSM University of Freiburg Computer Science Computer Networks and Telematics Prof. Christian Schindelhauer Organization I. Data and voice communication in IP networks II. Security issues in networking

742 views • 35 slides
Respecting Juror Privacy During Jury Selection Practical Guidance: A.B.A. Principles for Juries

Respecting Juror Privacy During Jury Selection Practical Guidance: A.B.A. Principles for Juries

Respecting Juror Privacy During Jury Selection Practical Guidance: A.B.A. Principles for Juries & Jury Trials Courts should protect juror privacyconsistent with the requirements of justice and the public interest. What info is

369 views • 4 slides
Challenges and Opportunities in Mobile Testing Alessandra Gorla IMDEA Software Institute,

Challenges and Opportunities in Mobile Testing Alessandra Gorla IMDEA Software Institute,

Challenges and Opportunities in Mobile Testing Alessandra Gorla IMDEA Software Institute, Madrid, Spain Intro B.Sc. and M.Sc. in Milano-Bicocca, Italy Data-flow testing of Java Applications Contextual Integration Testing of Classes

1.71k views • 123 slides
ON THE ROAD TO BENCHMARKING BPMN 2.0 WORKFLOW ENGINES Marigianna Skouradaki, Dieter

ON THE ROAD TO BENCHMARKING BPMN 2.0 WORKFLOW ENGINES Marigianna Skouradaki, Dieter

Architecture, Design and Web Information Systems Engineering Group ON THE ROAD TO BENCHMARKING BPMN 2.0 WORKFLOW ENGINES Marigianna Skouradaki, Dieter H. Roller, Frank Leymann Vincenzo Ferme , Cesare

650 views • 37 slides
Lists, Aliasing, g, Mutability Kelly Rivers and Stephanie Rosenthal 15-110 Fall 2019

Lists, Aliasing, g, Mutability Kelly Rivers and Stephanie Rosenthal 15-110 Fall 2019

Lists, Aliasing, g, Mutability Kelly Rivers and Stephanie Rosenthal 15-110 Fall 2019 Announcements Homework 3 Check-in 2 is due Monday at 12-noon! Start Early! Homework 3 full is also due in 2 Mondays. Learning Objectives To define

595 views • 32 slides
live stream Get More Details Online at www.cme.ucsf.edu ORTHOPAEDIC INJURIES PHYSIOLOGY

live stream Get More Details Online at www.cme.ucsf.edu ORTHOPAEDIC INJURIES PHYSIOLOGY

Presented by the Department of Medicine University of California, San Francisco in collaboration with Medicine of Cycling 2020 Medicine of Cycling Conference register today WEDNESDAY - SATURDAY October 28-31, 2020 and November 1, 2020 CME

406 views • 8 slides
Were Being Watched! Although were just passing THROUGH this pagan society, we must be

Were Being Watched! Although were just passing THROUGH this pagan society, we must be

3/28/2017 Were Being Watched! Although were just passing THROUGH this pagan society, we must be winsome witnesses as long as were still IN it! 1 Peter 2:12, NIV Live such good lives among the pagans that they may see your

160 views • 5 slides
Getting Lost In Our Own Lives A Work-Life Balance Program for New Admittees Brought to you by:

Getting Lost In Our Own Lives A Work-Life Balance Program for New Admittees Brought to you by:

11/24/2020 Getting Lost In Our Own Lives A Work-Life Balance Program for New Admittees Brought to you by: NC Lawyer Assistance Program & LAP Foundation of NC, Inc. lapfoundationnc.org 1 LETS FRAME THIS UP I am reminded of 2

159 views • 12 slides
Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery November

Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery November

Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery November 4th, 2020 Issam Laradji Pau Rodriguez Freddie Kalaitzis David Vazquez Ross Young Ed Davey Alexandre Lacoste COUNTING COWS:

559 views • 9 slides

More recommend