I wonder if it was somehow related to figuring out how long it would take to retrieve something from memory? The bands on the device remind me of tracks on a hard drive, and the fact that speed of access was based on how long it would take the drive to rotate so the desired spot on the track was under the read head for that track. It wouldn't be hard drive because that technology is later, but I do note that the Univac 2, which is from about the right period, had memory on a rotating drum, which it seems might have similar latency issues.
This page (http://www.computer-history.info/Page4.dir/pages/Univac.dir/index.html) talks about the Univac having used a programming style called Minimum Latency Coding which apparently meant laying out the program in such a way that the next operands would become available just as they were needed, which seems to lend support to my theory.
![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
(no subject)
Date: 2012-09-26 03:05 am (UTC)This page (http://www.computer-history.info/Page4.dir/pages/Univac.dir/index.html) talks about the Univac having used a programming style called Minimum Latency Coding which apparently meant laying out the program in such a way that the next operands would become available just as they were needed, which seems to lend support to my theory.