FPUs for small computers (Was: What to download for a PDP-8)

[Brent Hilpert]

Roger Ivie wrote:
> 
> On Wed, 17 Oct 2007, Chuck Guzis wrote:
> > On 17 Oct 2007 at 12:09, Jim Battle wrote:
> >
> >> Finally, I recall seeing an article where somebody took a pocket
> >> calculator chip and essentially poked simulated keystrokes at it and
> >> then decoded the LED driver output to determine the answer.  It was very
> >> slow, though, so all it saved was the space of the floating point
> >> library code.
> >
> > I remember that one.  It may have been an early issue of Byte.  I
> > also wondered at the time if any speed was gained over just running
> > plain old x80 code.
> 
> IIRC, it was in the .01-centennial issue of Dr. Dobb's. I have a copy of
> it somewhere, but there's no way I could find it without a lot of
> effort.

The book "How to Design, Build & Program Your Own _Advanced_ Working Computer
System" (1981/TAB Books) has an entire chapter devoted to this, mentioning 
a couple of chips. 

Note the underlining (part of the title) of "Advanced" to distinguish it from
the earlier book, which was about designing, building & programming
not-so-advanced working computer systems.

I rather questioned the performance aspect too, esp. with using chips from
pocket calcs, which typically weren't too fast. It all seemed like a hardware
hacker's solution to something rather than learning some math and doing some
programming.


Fred Cisin wrote:
> Well, at least it's better than using solenoids and photocells (which
> would have permitted a wider choice of calculators)

The book mentions a programming interface to calculators using relays for the
keyboard matrix and calls such a device a "compulator" (only place I've ever
heard the expression).