John Bunda

Learn More
In any stored-program computer system, information is constantly transferred between the memory and the instruction processor. Machine instructions are a major portion of this traffic. Since transfer bandwidth is a limited resource, inefficiency in the encoding of instruction information (low code density) can have definite hardware and performance costs.(More)
Preface This thesis primarily compares the performance of a xed 16-bit RISC instruction set called D16 to a variant of the DLX RISC instruction presented by Hennessy and Patterson in their excellent treatment of computer and microprocessor architecture 32]. This was not the originally intended line of research; it is more a discovery that took on a life of(More)
We present an automatic scheme to generate programs for distributed-memory multiprocessors. We begin with a source program that contains no references to concurrency or communication. The source program corresponds to a systolic array: as such, it is a nested loop program with regular data dependences. The loop bounds may be any linear function of enclosing(More)
A pure functional notation for defining APL objects is described, and constructed with previous work in this area. The notation is extended to address both theoretical and pragmatic programming considerations. The notation is compatible with existing implementations, and is shown to straightforwardly incorporate popular extensions to the language.
VLSI devices with high power demands have several important drawbacks; power to run the chip must be supplied externally, and power is dissipated as heat, which must be removed from the circuit. Processor architects tend to view these issues as circuit technology or packaging problems. However, these solutions are limited, and do not necessarily provide(More)
  • 1