Yokemate of Keyboards
Posts: 4977 from 2009/1/28
From: Delaware, USA
Quote:
Andreas_Wolf wrote:
> similar to a 25 MHz 68882
...in one single test (Mandelbrot single precision). Worst result was that of a 3 MHz 68882 (SciMark2 LU). On average, it's similar to 10 MHz 68882.
Hmm, 10 MHz, not all all good.
Still, we first systems we sold didn't even have the option of a floating point co-processor.
We did move to the '020 until our second model was introduced (and the board I'm looking for predates both systems).
So 10 MHz would be better than nothing.
At least it will allow fpu dependent code to run.
Do you think Gunnar actually has a (
fully) functional fpu?
I get the impression it isn't the easiest component to design.
"Never attribute to malice what can more readily explained by incompetence"
