Eddy Albert Maria Odijk

DOOM: A Decentralized Object-Oriented Machine

Research into the potentials and problems of parallelism led to a new programming language and supportive parallel operating system and architecture. Studies continue on a 100-node prototype.

The Architecture of DOOM

This paper describes the architecture of DOOM, a Decentralized Object-Oriented Machine, which is being designed in the Computer Science department of Philips Research Laboratories. The paper starts by resuming the essential characteristics of POOL-T, the parallel object-oriented language designed in the framework of the project. An abstract architecture matching the computational model of the language is then described. In three successive steps this architecture is transformed to the DOOM architecture which is under design. Each of the steps reveals the requirements on the actual system that are introduced by the transformation. The DOOM architecture consists of a collection of self contained computers, consisting of a cpu, local memory and a communication unit to connect these computers via a point-to-point packet switching network. The functional requirements and the architecture of the cpu, the memory and the communication networks are then treated in greater detail, covering one section each.

The DOOM system and its applications: a survey of ESPRIT 415 subproject A, Philips Research Laboratories

This paper surveys the concepts of the Parallel Object-Oriented Language POOL and a highly parallel, general purpose computer system for execution of programs in this language: the Decentralized Object-Oriented Machine, DOOM. It reports on the approach to highly parallel computers and applications followed at Philips Research Laboratories, Eindhoven, as subproject A of Esprit project 415. The first sections present a short overview of the goals and premises of the subproject. In Section 3 the programming language POOL and its characteristics are introduced. Section 4 presents an abstract machine model for the execution of POOL programs. Section 5 describes the architecture of the DOOM-system. It is a collection of self contained computers, connected by a direct, packet-switching network. The resident operating system kernels facilitate the execution of a multitude of communicating objects, perform local management and cooperate to perform system wide resource management. In Section 6 we introduce the applications that are being designed to demonstrate the merits of the system. These symbolic applications will be shown to incorporate a high degree of parallelism. In the last section some conclusions will be drawn.

POOMA, POOL and Parallel Symbolic Computing: An Assessment

Parallel processing has been the topic of extensive research over the past decade. Three factors stimulating this are the advent of cheap and powerful dataprocessing architectures, advances in the theory of concurrency and the computing demands of novel applications. This paper describes a parallel object-oriented machine, POOMA, primarily designed for symbolic and data-intensive applications. The paper outlines the characteristics of POOMA at the level of the parallel programming language POOL and of the architecture. The second part relates these characteristics to the above factors, and provides an informal assessment of the achievements. Finally, some conclusions will be drawn and directions for further research will be pointed out.

Parallel Computers for Advanced Information Processing: The achievements of ESPRIT Project 415

The employment of parallelism to extend the performance range of computer systems and the proper programming methods and languages to exploit this parallelism are considered to be key technologies for the IT industry of the ’90s. Project 415, entitled ”Parallel Architectures and Languages for Advanced Information Processing- a VLSI directed approach”, has investigated a number of approaches towards high performance computer systems in particular for symbolic applications. Each of its six subprojects has adopted one programming model, advanced its theory and designed an architecture and language for its execution. Working groups have provided a disciplinary platform and ensured cross fertilisation between the subproject teams.