Robert A. Iannucci - Böcker

It is universally accepted today that parallel processing is here to stay but that software for parallel machines is still difficult to develop. However, there is little recognition of the fact that changes in processor architecture can significantly ease the development of software. In the seventies the availability of processors that could address a large name space directly, eliminated the problem of name management at one level and paved the way for the routine development of large programs. Similarly, today, processor architectures that can facilitate cheap synchronization and provide a global address space can simplify compiler development for parallel machines. If the cost of synchronization remains high, the pro­ gramming of parallel machines will remain significantly less abstract than programming sequential machines. In this monograph Bob Iannucci presents the design and analysis of an architecture that can be a better building block for parallel machines than any von Neumann processor. There is another very interesting motivation behind this work. It is rooted in the long and venerable history of dataflow graphs as a formalism for ex­ pressing parallel computation. The field has bloomed since 1974, when Dennis and Misunas proposed a truly novel architecture using dataflow graphs as the parallel machine language. The novelty and elegance of dataflow architectures has, however, also kept us from asking the real question: "What can dataflow architectures buy us that von Neumann ar­ chitectures can't?" In the following I explain in a round about way how Bob and I arrived at this question.

Multithreaded computer architecture has emerged as a new avenue for the exploitation of parallelism. This new field represents the confluence of several independent research directions which have united over a common set of issues and techniques. Multithreading draws on recent advances in dataflow, RISC, compiling for fine-grained parallel execution, and dynamic resource management. It offers the hope of dramatic performance increases through parallel execution for a broad spectrum of significant applications based on extensions to "traditional" approaches. "Multithreaded Computer Architecture" is divided into four parts, reflecting four major perspectives on the topic. Part I provides the reader with basic background information, definitions, and surveys of work which have in one way or another been pivotal in defining and shaping multithreading as an architectural discipline. Part II examines key elements of multithreading, highlighting the fundamental nature of latency and synchronization. This section presents clever techniques for hiding latency and supporting large synchronization name spaces.Part III looks at three major multithreaded systems, considering issues of machine organization and compilation strategy. Part IV concludes the volume with an analysis of multithreaded architectures, showcasing methodologies and actual measurements. "Multithreaded Computer Architecture: A Summary of the State of the Art" is a reference source and may be used as a text for advanced courses on the subject.

It is universally accepted today that parallel processing is here to stay but that software for parallel machines is still difficult to develop. However, there is little recognition of the fact that changes in processor architecture can significantly ease the development of software. In the seventies the availability of processors that could address a large name space directly, eliminated the problem of name management at one level and paved the way for the routine development of large programs. Similarly, today, processor architectures that can facilitate cheap synchronization and provide a global address space can simplify compiler development for parallel machines. If the cost of synchronization remains high, the pro­ gramming of parallel machines will remain significantly less abstract than programming sequential machines. In this monograph Bob Iannucci presents the design and analysis of an architecture that can be a better building block for parallel machines than any von Neumann processor. There is another very interesting motivation behind this work. It is rooted in the long and venerable history of dataflow graphs as a formalism for ex­ pressing parallel computation. The field has bloomed since 1974, when Dennis and Misunas proposed a truly novel architecture using dataflow graphs as the parallel machine language. The novelty and elegance of dataflow architectures has, however, also kept us from asking the real question: "What can dataflow architectures buy us that von Neumann ar­ chitectures can't?" In the following I explain in a round about way how Bob and I arrived at this question.