Cost/performance analysis of 1944-1967 computers

Back in the 60s Kenneth Knight surveyed a wide range of machines and tabulated price and performance.

Each paper contains its own dataset: the first contains performance+cost data on 225 computers available between 1944 and 1963, while the second contains this information on 63 computers available between 1963 and 1967.

In the 1970s people started talking about Moore’s law, but in the 1960s there was Grosch’s law: Computer performance increases as the square of the cost, i.e., faster computers were cheaper to rent, for a given number of operations. Knight set out to empirically check Grosch’s law, i.e., he was looking for a quadratic fit.

1 Like

Since that covered the era of Valve Computers, how often did they fail vs
computer speed? Was it a constant for all machines?
I guess the rule fits because the low cost machines were serial
and the faster ones where not. Ben,

Fascinating.

The 1964 CDC 6600 was streets ahead of the competition, but at 8.2 seconds per dollar it was an expensive machine.

1 Like