The SIMD Model of Parallel Computation

1. Front Matter

   Pages i-v

   PDF

2. Introduction

   • Robert Cypher, Jorge L. C. Sanz

   Pages 1-3

3. Parallel Computer Architectures

   • Robert Cypher, Jorge L. C. Sanz

   Pages 4-11

4. High-Level Models

   • Robert Cypher, Jorge L. C. Sanz

   Pages 12-19

5. Mesh Connected Computers

   • Robert Cypher, Jorge L. C. Sanz

   Pages 20-33

6. Algorithms for Mesh Connected Computers

   • Robert Cypher, Jorge L. C. Sanz

   Pages 34-50

7. Pyramid Machines

   • Robert Cypher, Jorge L. C. Sanz

   Pages 51-55

8. Algorithms for Pyramid Machines

   • Robert Cypher, Jorge L. C. Sanz

   Pages 56-60

9. Hypercube Computers

   • Robert Cypher, Jorge L. C. Sanz

   Pages 61-68

10. Hypercube-Derived Computers

    • Robert Cypher, Jorge L. C. Sanz

    Pages 69-77

11. Communication Primitives for Hypercube Computers

    • Robert Cypher, Jorge L. C. Sanz

    Pages 78-110

12. Algorithms for Hypercube Computers

    • Robert Cypher, Jorge L. C. Sanz

    Pages 111-123

13. Conclusions

    • Robert Cypher, Jorge L. C. Sanz

    Pages 124-126

14. Back Matter

    Pages 127-149

    PDF

1.1 Background There are many paradigmatic statements in the literature claiming that this is the decade of parallel computation. A great deal of research is being de­ voted to developing architectures and algorithms for parallel machines with thousands, or even millions, of processors. Such massively parallel computers have been made feasible by advances in VLSI (very large scale integration) technology. In fact, a number of computers having over one thousand pro­ cessors are commercially available. Furthermore, it is reasonable to expect that as VLSI technology continues to improve, massively parallel computers will become increasingly affordable and common. However, despite the significant progress made in the field, many funda­ mental issues still remain unresolved. One of the most significant of these is the issue of a general purpose parallel architecture. There is currently a huge variety of parallel architectures that are either being built or proposed. The problem is whether a single parallel computer can perform efficiently on all computing applications.

• VLSI
• algorithms
• architecture
• architectures
• computation
• computer
• computer science
• eXist
• image processing
• interaction
• model
• parallel computation
• parallel computer
• technology
• topology

• Research Center, IBM T. J. Watson, Yorktown Heights, USA

  Robert Cypher

• Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, USA

  Jorge L. C. Sanz

Policies and ethics