Some Computer Organizations and Their Effectiveness

TLDR

Parallel and multiple‑stream computer organizations are evaluated for effectiveness, revealing intrinsic logical challenges and a degenerative impact of branching. The study develops a hierarchical tree model of computer organizations and proposes a nesting explanation for Minsky’s conjecture that parallel processor performance scales logarithmically with the number of data‑stream processors. The authors distinguish logical and physical aspects of the model, analyze SISD limitations, SIMD processors, and MIMD saturation via simplified queuing models that predict saturation when locked‑out task time approaches 1/n of total time. Resource sharing in multiprocessors can mitigate several classic organizational problems.

Abstract

A hierarchical model of computer organizations is developed, based on a tree model using request/service type resources as nodes. Two aspects of the model are distinguished: logical and physical. General parallel- or multiple-stream organizations are examined as to type and effectiveness-especially regarding intrinsic logical difficulties. The overlapped simplex processor (SISD) is limited by data dependencies. Branching has a particularly degenerative effect. The parallel processors [single-instruction stream-multiple-data stream (SIMD)] are analyzed. In particular, a nesting type explanation is offered for Minsky's conjecture-the performance of a parallel processor increases as log M instead of M (the number of data stream processors). Multiprocessors (MIMD) are subjected to a saturation syndrome based on general communications lockout. Simplified queuing models indicate that saturation develops when the fraction of task time spent locked out (L/E) approaches 1/n, where n is the number of processors. Resources sharing in multiprocessors can be used to avoid several other classic organizational problems.