News for hackers. Stuff that matters.

A comment on An Interview with the Old Man of Floating-Point (1998). Parent comment

Re:An Interview with the Old Man of Floating-Point (1998) by jolux on Friday October 29, 2021 @08:32PM (#29045005)
noncommutative multiplication? what the hell were they doing?
[ Parent | on HN ]
Re:An Interview with the Old Man of Floating-Point (1998) by dnautics on Saturday October 30, 2021 @11:31AM (#29049561)
My guess is they were chunking the multiplier cascade and handling using parallel circuits so that the waveform could be independent across the chunks and not be dependent?

Edit: found it.

2240004 3-24 C (you will want to search by this key, it's a long document!)

http://ed-thelen.org/comp-hist/CRAY-1-HardRefMan/CRAY-1-HRM....

"Note that reversing the multiplier and multiplicand operands could cause slightly different results, that is, A x B is not necessarily the same as [B] x A"

[ Parent | on HN ]
Re:An Interview with the Old Man of Floating-Point (1998) by jolux on Saturday October 30, 2021 @04:55PM (#29052228)
Looks like I have some weekend reading to do. Thanks!
[ Parent | on HN ]