Past, Present, Parallel: A Survey of Available Parallel Computer Systems

ISBN-13: 9783540196648 / Angielski / Miękka / 1991 / 392 str.

Arthur Trew; Greg Wilson

Opis

Past, Present, Parallel is a survey of the current state of the parallel processing industry. In the early 1980s, parallel computers were generally regarded as academic curiosities whose natural environment was the research laboratory. Today, parallelism is being used by every major computer manufacturer, although in very different ways, to produce increasingly powerful and cost-effec- tive machines. The first chapter introduces the basic concepts of parallel computing; the subsequent chapters cover different forms of parallelism, including descriptions of vector supercomputers, SIMD computers, shared memory multiprocessors, hypercubes, and transputer-based machines. Each section concentrates on a different manufacturer, detailing its history and company profile, the machines it currently produces, the software environments it supports, the market segment it is targetting, and its future plans. Supplementary chapters describe some of the companies which have been unsuccessful, and discuss a number of the common software systems which have been developed to make parallel computers more usable. The appendices describe the technologies which underpin parallelism. Past, Present, Parallel is an invaluable reference work, providing up-to-date material for commercial computer users and manufacturers, and for researchers and postgraduate students with an interest in parallel computing.

Spis treści

1 Introduction.- 1.1 An Introduction to Parallel Processing: Greg Wilson.- 1.1.1 B. P. (Before Parallelism).- 1.1.2 Computer Architectures.- 1.1.3 Computer Software.- 1.1.4 Types of Parallelism.- 2 SIMD: Specialisation Equals Success.- 2.1 Active Memory Technology: Arthur Trew.- 2.1.1 The Company.- 2.1.2 The Machine.- 2.1.3 The Development System.- 2.1.4 Programming Languages.- 2.1.5 The Market Niche.- 2.1.6 The Competition.- 2.1.7 The Future.- 2.2 MasPar Computer Corporation: Arthur Trew.- 2.2.1 The Company.- 2.2.2 The Machine.- 2.2.3 The Program Development System.- 2.2.4 Programming Languages.- 2.2.5 The Market.- 2.2.6 The Competitors.- 2.2.7 The Future.- 2.3 Thinking Machines Corporation: Arthur Trew.- 2.3.1 The Company.- 2.3.2 The Machine.- 2.3.3 The Development System.- 2.3.4 Programming Languages.- 2.3.5 The Market Niche.- 2.3.6 The Competition.- 2.3.7 The Future.- 3 Shared Memory Multiprocessors: The Evolutionary Approach.- 3.1 Alliant Computer Systems: Malcolm Brown & Billy Taylor.- 3.7 Sequent Computer Systems: Sandy Robertson.- 3.7.1 The Company.- 3.7.2 The Machine.- 3.7.3 The Operating System.- 3.7.4 Programming Languages.- 3.7.5 The Market Niche.- 3.7.6 The Competition.- 3.7.7 The Future.- 4 Hypercubes: A Geometry that Works.- 4.1 Intel Scientific Computers: Rob Scott.- 4.1.1 The Company.- 4.1.2 The Hardware.- 4.1.3 The Concurrent I/O Facility.- 4.1.4 The Software.- 4.1.5 Sales.- 4.1.6 The Market Niche.- 4.1.7 The Future.- 4.2 NCUBE Corporation: Rob Scott.- 4.2.1 The Company.- 4.2.2 The Hardware.- 4.2.3 The Software.- 4.2.4 The Market Niche.- 4.2.5 The Opposition.- 4.2.6 The Future.- 5 The Transputer and Its Offspring.- 5.1 Inmos Limited: Mark Smith.- 5.1.1 The Company.- 5.1.2 The Transputer.- 5.1.3 The Software.- 5.1.4 The Market Niche.- 5.1.5 The Future.- 5.2 Caplin Cybernetics: Mark Smith.- 5.2.1 The Company.- 5.2.2 Caplin’s Product Range.- 5.2.3 The Market Niche.- 5.2.4 Present Applications.- 5.2.5 The Future.- 5.3 Meiko Scientific Limited: Neil MacDonald.- 5.3.1 The Company.- 5.3.2 The Hardware.- 5.3.3 Programming Environments.- 5.3.4 CS Tools.- 5.3.5 Sales and Marketing.- 5.3.6 The Future.- 5.4 Parsys Limited: Mark Smith.- 5.4.1 The Company.- 5.4.2 The Hardware.- 5.4.3 The Software.- 5.4.4 The Market Niche.- 5.4.5 The Competition.- 5.4.6 Current Applications.- 5.4.7 The Future.- 5.5 Parsytec GmbH: Malcolm Brown.- 5.5.1 The Company.- 5.5.2 System Overview.- 5.5.3 Applications and Performance.- 5.5.4 The Software.- 5.5.5 The Market.- 5.5.6 The Future.- 6 New Machines For New Niches.- 6.1 Cogent Research Incorporated: Neil MacDonald.- 6.1.1 The Company.- 6.1.2 The Hardware.- 6.1.3 The Software.- 6.1.4 The Market Niche.- 6.1.5 The Future.- 6.2 Silicon Graphics Incorporated: Mark Smith & Matthew White.- 6.2.1 The Company.- 6.2.2 The Hardware.- 6.2.3 The Software.- 6.2.4 The Market Niche.- 6.2.5 The Future.- 6.3 Stardent Computer Incorporated: Mark Smith & Matthew White.- 6.3.1 The Company.- 6.3.2 The Hardware.- 6.3.3 The Software.- 6.3.4 The Market.- 6.3.5 The Future.- 6.4 Teradata Corporation: Greg Wilson.- 6.4.1 The Company.- 6.4.2 The Hardware.- 6.4.3 Interface Software.- 6.4.4 Internal Software.- 6.4.5 Support for Critical Environments.- 6.4.6 The Marketplace.- 6.4.7 The Future.- 7 Vector Supercomputers: It’s Never too Late to Parallelise.- 7.1 Cray Research Inc.: Rob Scott.- 7.1.1 The Company.- 7.1.2 Cray X-MP ? Cray Y-MP ? C90.- 7.1.3 Cray-2 ? Cray-3.- 7.1.4 The Software.- 7.1.5 The Market Niche.- 7.1.6 The Competition.- 7.1.7 The Future.- 7.2 NEC: Greg Wilson.- 7.2.1 The Company.- 7.2.2 The Hardware.- 7.2.3 The Software.- 7.2.4 The Market.- 7.3 Supercomputer Systems Inc: Rob Scott.- 7.3.1 The Company.- 7.3.2 Who is Steve Chen?.- 7.3.3 SSI’s Options.- 8 The Giants: Biding Their Time.- 8.1 Digital Equipment Corporation: Colin Brough.- 8.1.1 The Company.- 8.1.2 The Hardware.- 8.1.3 The Software.- 8.1.4 The Market.- 8.1.5 The Future.- 8.2 Fujitsu: Greg Wilson.- 8.2.1 The Company.- 8.2.2 Vector Computers.- 8.2.3 The CAP-05 Array Processor.- 8.2.4 The AP-1000 Array Processor.- 8.2.5 The Future.- 8.3 IBM Corporation: Arthur Trew & Mark Smith.- 8.3.1 The Company.- 8.3.2 The ES/9000.- 8.3.3 Operating Systems.- 8.3.4 Programming Languages.- 8.3.5 The Market.- 8.3.6 The Future.- 9 Software: Efficiency vs. Protability?.- 9.1 Express: Mike Norman.- 9.1.1 The Express Family of Products.- 9.1.2 History and Philosophy.- 9.1.3 Express.- 9.1.4 Cubix and Plotix.- 9.1.5 Other Utilities.- 9.2 Helios: Malcolm Brown.- 9.2.1 Perihelion and Helios.- 9.2.2 The Helios Model.- 9.2.3 The Helios Network.- 9.2.4 Helios Programming Environment.- 9.2.5 Helios as an Environment.- 9.2.6 The Market for Helios.- 9.3 Linda: Neil MacDonald.- 9.3.1 Linda Operations.- 9.3.2 Linda Examples.- 9.3.3 The Future.- 9.4 STRAND$$ \underline $$: Mark Smith.- 9.4.1 History.- 9.4.2 Design.- 9.4.3 Markets for STRAND$$ \underline $$.- 9.4.4 The Competition.- 9.4.5 The Future.- 10 Machines Past.- 10.1 BiiN: Greg Wilson.- 10.1.1 The Company.- 10.1.2 The Hardware.- 10.1.3 The Software.- 10.1.4 The Market.- 10.1.5 BiiN’s Demise.- 10.2 ETA Systems: Rob Scott.- 10.2.1 The Company.- 10.2.2 The Hardware.- 10.2.3 The Software.- 10.2.4 Costs and Sales.- 10.2.5 What Went Wrong?.- 10.3 Multiflow: Neil MacDonald.- 10.3.1 Going Up.- 10.3.2 Going Down.- 10.3.3 Why Did Multiflow Fail?.- 10.3.4 A Future for VLIW Technology?.- 10.4 Myrias Research Corporation: Greg Wilson.- 10.4.1 The Company.- 10.4.2 User-Level Model.- 10.4.3 Claims About the User-Level Model.- 10.4.4 Compromises in the User-Level Model.- 10.4.5 The Virtual Machine and Its Implementation.- 10.4.6 The Product Range.- 10.4.7 Sales.- 10.4.8 The End.- 10.5 Symult Incorporated: Malcolm Brown.- 10.5.1 Ametek and Symult.- 10.5.2 The Symult S2010.- 10.5.3 The Communications Network.- 10.5.4 Why did the S2010 Fail?.- 11 Machines Future.- Appendices:.- A Technology.- A.1 Cache Memory: Sandy Robertson.- A.1.1 Performance.- A.1.2 Cache Update Policies.- A.1.3 Multicache Consistency.- A.2 Message Passing Systems: Mike Norman.- A.2.1 Addressing of Messages.- A.2.2 Deadlock and Related Issues.- A.2.3 Controlling Message Transfer.- A.2.4 Delivering Messages.- A.2.5 Message Selection.- A.2.6 Placing Tasks.- A.3 Visualisation: Matthew White & Greg Wilson.- A.3.1 Doing It In Hardware.- A.4 Parallel Compilers: Neil MacDonald & Colin Brough.- A.4.1 Vectorising Compilers.- A.4.2 Parallelising Compilers.- B Units.- C Glossary.- D Trademarks.