How to Build a Beowulf: A Guide to the Implementation and Application of PC Clusters (Scientific and Engineering Computation)
How to Build a Beowulf: A Guide to the Implementation and Application of PC Clusters (Scientific and Engineering Computation)
ISBN: 026269218X
EAN: 2147483647
EAN: 2147483647
Year: 1999
Pages: 134
Pages: 134
- Cover
- Contents
- Series forword
- Foreword
- Preface
- 1 Introduction
- 1.1 A Brief History
- 1.2 The Beowulf Book
- 2 Overview of Beowulf Systems
- 2.1 What Is a Beowulf?
- 2.2 A Taxonomy of Parallel Computing
- 2.3 Benefits of Beowulf
- 2.4 A Critical Technology Convergence
- 2.5 The Beowulf System Node
- 2.6 The Beowulf Network
- 2.7 Linux
- 2.8 Message Passing for Interprocessor Communication
- 2.9 Beowulf System Management
- 2.10 The Beowulf Challenge
- 3 Node Hardware
- 3.1 Overview of a Beowulf Node
- 3.1.1 Principal Specifications
- 3.1.2 Basic Elements
- 3.2 Processors
- 3.2.1 Intel PentiumII
- 3.2.2 DEC Alpha
- 3.2.3 AMD K6
- 3.2.4 Future Processors
- 3.3 Motherboard
- 3.3.1 A Typical Beowulf Motherboard
- 3.3.2 Selection Considerations
- 3.3.3 Layout of Major Components
- 3.4 Memory
- 3.4.1 Memory Capacity
- 3.4.2 Memory Speed
- 3.4.3 Memory Types
- 3.4.4 Memory HierarchyL1 and L2 Caches
- 3.4.5 Package Styles
- 3.5 BIOS
- 3.6 Secondary Storage
- 3.7 PCI Bus
- 3.8 Examples of a Beowulf Node
- 3.8.1 Intel Pentium II Based Node
- 3.8.2 DEC Alpha Based Node
- 3.9 Boxes, Shelves, Piles, and Racks
- 3.10 Node Assembly
- 3.10.1 Motherboard Pre-assembly
- 3.10.2 The Case
- 3.10.3 Minimal Peripherals
- 3.10.4 Booting the System
- 3.10.5 Installing the Other Components
- 3.10.6 Troubleshooting a PC that Won t Boot
- 4 The Linux Operating System
- 4.1 History of Linux
- 4.2 Linux Kernels and Linux Distributions
- 4.3 Linux Features
- 4.4 File Systems
- 4.5 System Configuration
- 4.6 Tools for Program Development
- 4.7 Linux s Unique Features
- 4.8 Installing an Initial System
- 4.8.1 Installation by CD or Network?
- 4.8.2 Installation Summary
- 4.9 Keeping Up with Linux
- 4.10 Suggested References
- 4.10.1 Web Sites
- 4.10.2 Books
- 5 Network Hardware and Software
- 5.1 Fast Ethernet
- 5.1.1 Ethernet Arbitration
- 5.1.2 Packet Format
- 5.1.3 NIC Architecture
- 5.1.4 Hubs and Switches
- 5.1.5 Gigabit Ethernet
- 5.2 Alternative Network Technologies
- 5.2.1 Asynchronous Transfer Mode
- 5.2.2 FDDI
- 5.2.3 Scalable Coherent Interface
- 5.2.4 Myrinet
- 5.3 TCPIP
- 5.3.1 IP Addresses
- 5.3.2 Zero-copy Protocols
- 5.4 Sockets
- 5.5 Higher Level Protocols
- 5.5.1 Remote Procedure Calls
- 5.5.2 Distributed Objects: CORBA and Java RMI
- 5.6 Distributed File Systems
- 5.6.1 NFS
- 5.6.2 AFS
- 5.6.3 Autofs: The Automounter
- 5.7 Remote Command Execution
- 5.7.1 BSD R Commands
- 5.7.2 SSHThe Secure Shell
- 6 Managing Ensembles
- 6.1 System Access Models
- 6.1.1 The Stand-alone System
- 6.1.2 The Universally Accessible Machine
- 6.1.3 The Guarded Beowulf
- 6.2 Assigning Names
- 6.2.1 Dynamically Assigned Addresses
- 6.3 Cloning Nodes
- 6.3.1 Creating Tar Images
- 6.3.2 Setting up a Clone Root Partition
- 6.3.3 Setting up BOOTP
- 6.3.4 Building a Boot Clone Floppy
- 6.4 Basic System Administration
- 6.4.1 Booting and Shutting Down
- 6.4.2 The Node File System
- 6.4.3 Account Management
- 6.4.4 PRSHParallel Remote Shell
- 6.5 Defending the Pack: Security Strategies
- 6.5.1 System Configuration
- 6.5.2 IP Masquerading
- 6.5.3 Restricting Host Access
- 6.5.4 SSH: Secure Shell Revisited
- 6.6 Job Scheduling
- 7 Parallel Applications
- 7.1 Parallelism
- 7.2 Broad Categories of Parallel Algorithms
- 7.2.1 Regular and Irregular
- 7.2.2 Synchronous and Asynchronous
- 7.2.3 Coarse and Fine Grained
- 7.2.4 Bandwidth Greedy and Frugal
- 7.2.5 Latency Tolerant and Intolerant
- 7.2.6 Distributed and Shared Address Spaces
- 7.2.7 Beowulf Systems and Choices of Parallelism
- 7.3 Process-level Parallelism
- 7.3.1 Example: Ray Tracing Animation
- 7.3.2 Utilities for Process-parallel Computing
- 7.3.3 OverheadsRSH and File IO
- 7.3.4 Summary
- 8 MPIA User-level Message-passing Interface
- 8.1 History
- 8.2 MPI Basic Functionality
- 8.2.1 Example: Hello World
- 8.3 Parallel Data Structures with MPI
- 8.3.1 Example: A Parallel Array
- 8.3.2 Example: A One-dimensional Cellular Automaton
- 8.4 MPI Advanced Features
- 8.4.1 Blocking and Non-blocking Calls and Alternative Sending Modes
- 8.4.2 Virtual Topologies and Attribute Caching
- 8.4.3 Derived Data Types
- 8.4.4 Intercommunicators
- 8.4.5 MPI-2
- 9 Programming with MPIA Detailed Example
- 9.1 Example: Sorting a List of Uniformly Distributed Integers
- 9.2 Analysis of Integer Sort
- 9.2.1 Communication
- 9.2.2 Redundancy
- 9.2.3 Extra Work
- 9.2.4 Load Imbalance
- 9.2.5 Waiting
- 9.3 Measurement of Integer Sort
- 9.4 Example: Sorting with User-supplied Comparator
- 9.5 Analysis of a More General Sort
- 9.5.1 Choosing the Number of Fenceposts
- 9.6 Summary
- 10 Conclusions and Views
- 10.1 New Generation Beowulfs
- 10.2 New Opportunities
- 10.2.1 Databases
- 10.2.2 Web Servers
- 10.2.3 Dynamic Interactive Simulation
- 10.2.4 Virtual Reality
- 10.2.5 Process Control
- 10.2.6 Artificial Intelligence
- 10.2.7 Genetic Programming
- 10.3 True Costs
- 10.4 Total Work versus Peak Performance
- 10.5 Big Memory versus Out-of-core
- 10.6 Bounding Influences on the Beowulf Domain
- 10.7 New Programming Models
- 10.8 Will Linux Survive the Mass Market?
- 10.9 Final Thoughts
- Index of Acronyms
How to Build a Beowulf: A Guide to the Implementation and Application of PC Clusters (Scientific and Engineering Computation)
ISBN: 026269218X
EAN: 2147483647
EAN: 2147483647
Year: 1999
Pages: 134
Pages: 134