Foilset Search Full Index for Scripted foilset

CPS615 - Overview of Computer Architectures

Given by Geoffrey C. Fox at CPS615 Basic Simulation Track for Computational Science on Fall Semester 98. Foils prepared 17 November 1998

Various HPCC Resource Lists for Foil 2

This presentation came from material developed by David Culler and Jack Dongarra available on the Web
See summary of Saleh Elmohamed and Ken Hawick at http://nhse.npac.syr.edu/hpccsurvey/
We discuss several examples in detail including T3E, Origin 2000, Sun E10000 and Tera MTA
These are used to illustrate major architecture types
We discuss key sequential architecture issues including cache structure
We also discuss technologies from today's commodities through Petaflop ideas and Quantum Computing


This mixed presentation uses parts of the following base foilsets which can also be looked at on their own!
Master Foilset for HPC Achitecture Overview
Master Set of Foils for 1996 Session of CPS615
Master Set of Foils for 1997 Session of CPS615
Title and Abstract of FakeFoilset
Master Set A of Overview Material on Parallel Computing for CPS615 Foils
Master Set B of Overview Material on Parallel Computing for CPS615 Foils
PetaFlop(JNAC) Overview Presentations -- Results of Studies and Next Steps Sep 19,96
Variety of Foils Used Starting January 97
Miscellaneous Presentation Material used in 1996
Master Foils for A Short Overview of HPCC -- From GigaFlops to PetaFlops and From Tightly Coupled MPP's to the World Wide Web
Processing-In-Memory (PIM) Architectures for Very High Performance MPP Computing

Table of Contents for CPS615 - Overview of Computer Architectures

There are two types of foils -- html and image which are each available in basic and JavaScript enabled "focused" style
(basic:)(focus style:) Denote Foils where Image Critical
(basic:)(focus style:) Denote Foils where Image has important information
(basic:)(focus style:) Denote Foils where HTML is sufficient
(basic:(focus style:) Denote Foils where Image is not available
denotes presence of Additional linked information which is greyed out if missing


A Brief Discussion of Computer Architectures
Various HPCC Resource Lists for Foil 1 1 Computer Architecture for Computational Science
Various HPCC Resource Lists for Foil 2 2 Abstract of Computer Architecture Overview
3 Some NPAC Parallel Machines

Technologies of Relevance
4 Technologies for High Performance Computers
5 Architectures for High Performance Computers - I
6 Architectures for High Performance Computers - II
7 There is no Best Machine!

Commodity Driving Forces
8 Architectural Trends I
9 Architectural Trends
10 3 Classes of VLSI Design?
11 Ames Summer 97 Workshop on Device Technology -- Moore's Law - I
12 Ames Summer 97 Workshop on Device Technology -- Moore's Law - II
13 Ames Summer 97 Workshop on Device Technology -- Alternate Technologies I
14 Ames Summer 97 Workshop on Device Technology -- Alternate Technologies II
15 Architectural Trends: Bus-based SMPs
16 Bus Bandwidth
17 Economics

Parallel Computing Architectures
18 Important High Performance Computing Architectures
19 Some General Issues Addressed by High Performance Architectures
20 Architecture Classes of High Performance Computers
21 Flynn's Classification of HPC Systems

Performance Issues
Description of Linpack as used by Top500 List 22 Raw Uniprocessor Performance: Cray v. Microprocessor LINPACK n by n Matrix Solves
Description of Linpack as used by Top500 List 23 Raw Parallel Performance: LINPACK
Description of Linpack as used by Top500 List 24 Linear Linpack HPC Performance versus Time
Top 500 Supercomputer List from which you can get customized sublists 25 Top 10 Supercomputers November 1998
Top 500 and Jack Dongarra Links for Foil 26 26 Distribution of 500 Fastest Computers
Top 500 and Jack Dongarra Links for Foil 27 27 CPU Technology used in Top 500 versus Time
Top 500 and Jack Dongarra Links for Foil 28 28 Geographical Distribution of Top 500 Supercomputers versus time
Top 500 and Jack Dongarra Links for Foil 29 29 Node Technology used in Top 500 Supercomputers versus Time
Top 500 and Jack Dongarra Links for Foil 30 30 Total Performance in Top 500 Supercomputers versus Time and Manufacturer
Top 500 and Jack Dongarra Links for Foil 31 31 Number of Top 500 Systems as a function of time and Manufacturer
Top 500 and Jack Dongarra Links for Foil 32 32 Total Number of Top 500 Systems Installed June 98 versus Manufacturer
33 Netlib Benchweb Benchmarks
34 Linpack Benchmarks
35 Java Linpack Benchmarks
36 Java Numerics

Sequential Computer Architecture
37 von Neuman Architecture in a Nutshell

Pipelining
38 What is a Pipeline -- Cafeteria Analogy?
39 Instruction Flow in A Simple Machine Pipeline
40 Example of MIPS R4000 Floating Point
41 MIPS R4000 Floating Point Stages

Caches
42 Illustration of Importance of Cache
43 Sequential Memory Structure
44 Cache Issues I
45 Cache Issues II
46 Spatial versus Temporal Locality I
47 Spatial versus Temporal Locality II

Cray T3E as an Example of a Cache
Interesting Article from SC97 proceedings on T3E performance 48 Cray/SGI memory latencies
NPAC Summary of T3E Architecture 49 Architecture of Cray T3E
NPAC Summary of T3E Architecture 50 T3E Messaging System
Interesting Article from SC97 proceedings on T3E performance 51 Cray T3E Cache Structure
Interesting Article from SC97 proceedings on T3E performance 52 Cray T3E Cache Performance
Interesting Article from SC97 proceedings on T3E performance 53 Finite Difference Example for T3E Cache Use I
Interesting Article from SC97 proceedings on T3E performance 54 Finite Difference Example for T3E Cache Use II
Interesting Article from SC97 proceedings on T3E performance 55 How to use Cache in Example I
Interesting Article from SC97 proceedings on T3E performance 56 How to use Cache in Example II

Vector Architecture
NPAC Survey of Cray Systems 57 Cray Vector Supercomputers
58 Vector Supercomputers in a Nutshell - I
59 Vector Supercomputing in a picture
60 Vector Supercomputers in a Nutshell - II

Parallel Memory Structure
61 Parallel Computer Architecture Memory Structure
62 Comparison of Memory Access Strategies
63 Types of Parallel Memory Architectures -- Physical Characteristics
64 Diagrams of Shared and Distributed Memories

Parallel Control Structure
65 Parallel Computer Architecture Control Structure

MIMD Architectures
66 Mark2 Hypercube built by JPL(1985) Cosmic Cube (1983) built by Caltech (Chuck Seitz)
67 64 Ncube Processors (each with 6 memory chips) on a large board
68 ncube1 Chip -- integrated CPU and communication channels
More Details on IBM SP2 69 Example of Message Passing System: IBM SP-2
70 Example of Message Passing System: Intel Paragon
ASCI Red Intel Supercomputer at Sandia 71 ASCI Red -- Intel Supercomputer at Sandia

Parallel Computing Cache Issues
72 Parallel Computer Memory Structure
73 Cache Coherent or Not?
74 Cache Coherence

Origin 2000 as an Example of Cache Coherence
NPAC Summary of Origin 2000 Architecture 75 SGI Origin 2000 I
NPAC Summary of Origin 2000 Architecture 76 SGI Origin II
NPAC Summary of Origin 2000 Architecture 77 SGI Origin Block Diagram
NPAC Summary of Origin 2000 Architecture 78 SGI Origin III
NPAC Summary of Origin 2000 Architecture 79 SGI Origin 2 Processor Node Board
NCSA Performance Measurements 80 Performance of NCSA 128 node SGI Origin 2000
81 Summary of Cache Coherence Approaches

SIMD Architectures
82 Some Major Hardware Architectures - SIMD
83 SIMD (Single Instruction Multiple Data) Architecture
84 Examples of Some SIMD machines
Computer Museum Entry for Connection Machine 85 SIMD CM 2 from Thinking Machines
Computer Museum Entry for Connection Machine 86 Official Thinking Machines Specification of CM2

Metacomputers
87 Some Major Hardware Architectures - Mixed
88 Some MetaComputer Systems
89 Clusters of PC's 1986-1998
NCSA Performance Measurements 90 HP Kayak PC (300 MHz Intel Pentium II) vs Origin 2000

Special Purpose Devices
91 Comments on Special Purpose Devices
Description of GRAPE 4 5 and 6 Machines:1 to 200 Teraflops 92 The GRAPE N-Body Machine
Description of GRAPE 4 5 and 6 Machines:1 to 200 Teraflops 93 Why isn't GRAPE a Perfect Solution?
Grape Special Purpose Machine 94 GRAPE Special Purpose Machines
Special Purpose Physics Machines for Foil 100 95 Quantum ChromoDynamics (QCD) Special Purpose Machines

Granularity
96 Granularity of Parallel Components - I
97 Granularity of Parallel Components - II

Parallel Computer Networks
98 Classes of Communication Networks
99 Switch and Bus based Architectures
100 Examples of Interconnection Topologies
101 Useful Concepts in Communication Systems

Network Performance
102 Latency and Bandwidth of a Network
103 Transfer Time in Microseconds for both Shared Memory Operations and Explicit Message Passing
104 Latency/Bandwidth Space for 0-byte message(Latency) and 1 MB message(bandwidth).
105 Communication Performance of Some MPP's
106 Implication of Hardware Performance
NASA Ames Comparison of MPI on Origin 2000 and Sun E10000 107 MPI Bandwidth on SGI Origin and Sun Shared Memory Machines
NASA Ames Comparison of MPI on Origin 2000 and Sun E10000 108 Latency Measurements on Origin and Sun for MPI

Architectures according to Culler
109 Two Basic Programming Models
110 Shared Address Space Architectures
111 Shared Address Space Model
112 Communication Hardware
113 History -- Mainframe
114 History -- Minicomputer
115 Scalable Interconnects
116 Message Passing Architectures
117 Message-Passing Abstraction e.g. MPI
118 First Message-Passing Machines

Intel SMP
119 SMP Example: Intel Pentium Pro Quad

Sun E10000 as Example of UMA Commodity System
Descriptions of Sun HPC Systems for Foil 69 120 Sun E10000 in a Nutshell
Descriptions of Sun HPC Systems for Foil 70 121 Sun Enterprise Systems E6000/10000
Descriptions of Sun HPC Systems for Foil 71 122 Starfire E10000 Architecture I
Descriptions of Sun HPC Systems for Foil 72 123 Starfire E10000 Architecture II
Descriptions of Sun HPC Systems for Foil 73 124 Sun Enterprise E6000/6500 Architecture
Descriptions of Sun HPC Systems for Foil 74 125 Sun's Evaluation of E10000 Characteristics I
Descriptions of Sun HPC Systems for Foil 75 126 Sun's Evaluation of E10000 Characteristics II
Descriptions of Sun HPC Systems for Foil 76 127 Scalability of E1000

Current Near Term Trends
128 Consider Scientific Supercomputing
129 Toward Architectural Convergence
130 Convergence: Generic Parallel Architecture

Emerging Architectures MTA and COMA
Tera Architecture and System Links for Foil 79 131 Tera Multithreaded Supercomputer
Tera Architecture and System Links for Foil 80 132 Tera Computer at San Diego Supercomputer Center
Tera Architecture and System Links for Foil 81 133 Overview of the Tera MTA I
Tera Architecture and System Links for Foil 82 134 Overview of the Tera MTA II
Tera Architecture and System Links for Foil 83 135 Tera 1 Processor Architecture from H. Bokhari (ICASE)
Tera Architecture and System Links for Foil 84 136 Tera Processor Characteristics
Tera Architecture and System Links for Foil 85 137 Tera System Diagram
Tera Architecture and System Links for Foil 86 138 Interconnect / Communications System of Tera I
Tera Architecture and System Links for Foil 87 139 Interconnect / Communications System of Tera II
Tera Architecture and System Links for Foil 88 140 T90/Tera MTA Hardware Comparison
Tera Architecture and System Links for Foil 89 141 Tera Configurations / Performance
Tera Architecture and System Links for Foil 90 142 Performance of MTA wrt T90 and in parallel
Tera Architecture and System Links for Foil 91 143 Tera MTA Performance on NAS Benchmarks Compared to T90
144 Cache Only COMA Machines

Application Motivation for PetaFlops

145 III. Key drivers: The Need for PetaFLOPS Computing
146 10 Possible PetaFlop Applications
147 Petaflop Performance for Flow in Porous Media?
148 Target Flow in Porous Media Problem (Glimm - Petaflop Workshop)
149 NASA's Projection of Memory and Computational Requirements upto Petaflops for Aerospace Applications

The 3 classes of PetaFlop Designs

150 Supercomputer Architectures in Years 2005-2010 -- I
151 Supercomputer Architectures in Years 2005-2010 -- II
152 Supercomputer Architectures in Years 2005-2010 -- III
153 Performance Per Transistor
154 Comparison of Supercomputer Architectures

The Processor in Memory Design

155 Current PIM Chips
156 New "Strawman" PIM Processing Node Macro
157 "Strawman" Chip Floorplan
158 SIA-Based PIM Chip Projections

Exotic Technology: Quantum Computing
159 Quantum Computing - I
160 Quantum Computing - II
161 Quantum Computing - III

Exotic Technology: Superconducting Technology
162 Superconducting Technology -- Past
163 Superconducting Technology -- Present
164 Superconducting Technology -- Problems

Full WebWisdom URL and this Foilset Search
This contains all WebWisdom links preceded by those referenced in this foilset
© Northeast Parallel Architectures Center, Syracuse University, npac@npac.syr.edu

If you have any comments about this server, send e-mail to webmaster@npac.syr.edu.

Page produced by wwwfoil on Mon Apr 12 1999