Computer structures: Readings and examples (McGraw-Hill computer science series)
Computer structures: Readings and examples (McGraw-Hill computer science series)
| Hi-index | 0.00 |
Over the last decade, continuing advancement in semiconductor technology has resulted in significant improvement in the cost-performance ratio of microcomputer processors and the consequent proliferation of minicomputers in evidence today in an ever-widening sphere of application. Figure 1 shows the minicomputer processor pricing trends over a decade [cf. 1]. Large computers exhibit an economy of scale, evidenced by the IBM 360 series which spans two orders of mangitude in processing power [cf.2]. This paper attempts to compare the cost and performance of currently available computers. The cost of computer systems can vary widely with configurations. Typical small, medium and large configurations are defined in the GML Corporation's Computer Characteristics Review [cf. 3]. It is very difficult to characterize the performance of a wide variety of computer architectures by a single number. Meaningful comparisons can be obtained by comparing the execution times for a benchmark program that typifies the problem environment. For the purpose of a general study, a simpler performance index has to be used. The register-memory add time is widely accepted for such comparisons [3]. A comparison of this performance index with some benchmark results shows it to be a reasonable measure for high level comparisons.