[SATLUG] question of the measurement of processing power past
hc at lookcee.com
Tue Aug 12 23:06:10 CDT 2008
Todd W. Bucy wrote:
> what I need to know is it fair, in terms of raw processing power, to
> compare a measurement of 0.06 kips of the IBM 650 in 1954 to the
> petraFLOPS generated by the IBM Roadrunner of today (or for that matter
> the giga flops generated by the the intell q6600). Obviously the newer
> processors (and super computers) of today are much faster then they were
> in the 50's and 60's. I guess what I am looking for is something that
> illustrates the dramatic increase of computing power over the last 50 or
> so years.
Hmmmm as I recall the 650 was a drum memory machine and used either
octal or the punched card code in a fixed word configuration I cannot
remember how the various registers were hard wired but the drum
functioned for the storage of the object code and to bring in 80 column
card data that had to then be transferred according to 'x' columns
making up a field. and this stack/deck trolley filled with trays of
cards all had been preprocessed into the correct sorting order for the
I suppose you could work out an algorithm to fit the translation of data
from the input medium (normally 80 column punched cards) into
accumulators and registers as the code called and had to be transformed
into digital octal format. today the byte is hexadecimal rather than
octal so I bog down at this point. I don't think floating point worked
you had to keep track of where the decimal point went with each calculation.
While it was soooo slllooow compared with todays blazing cpu cycles and
introducing data into both front and rear buses... it still did the
processing of dozens of comp-operators that did the math before the 650.
I worked on several installations based on the 650 but was really a long
time ago mid and late 50s.
> thanks for any help
More information about the SATLUG