Attributes of the performance of central processing units: a relative performance prediction model
Communications of the ACM
Characterizing computer performance with a single number
Communications of the ACM
Computer architecture: a quantitative approach
Computer architecture: a quantitative approach
A Performance Comparison of the IBM RS/6000 and the Astronautics ZS-1
Computer - Special issue on experimental research in computer architecture
Vector performance analysis of the NEC SX-2
ICS '90 Proceedings of the 4th international conference on Supercomputing
Performance of various computers using standard linear equations software
ACM SIGARCH Computer Architecture News
| Hi-index | 0.00 |
The capability of the MIPS measure as an indicator of computer performance is highly questionable and is often rejected by most researchers. On the other hand, the MFLOPS measure is commonly used, mainly in mainframes and workstations for scientific and engineering tasks. The MFLOPS measure, as described by Dongarra, is widely employed because of its efficiency and effectiveness in terms of simplicity and its indicative abilities. The question of the value of the MFLOPS measure and the ways it should be applied is treated in this article. We suggest evaluation models, based on architectural and configurational parameters of the computer, and examine their validity. The analysis shows a correlation between the MFLOPS measure and the MIPS measure for various specific time periods and various specific manufacturers.