Last visit was: Sun Nov 28, 2021 12:19 pm
It is currently Sun Nov 28, 2021 12:19 pm

 [ 4 posts ] 
 Am9511 Arithmetic Processing Unit - an FPU for 1978 
Author Message

Joined: Wed Jan 09, 2013 6:54 pm
Posts: 1644
Prompted by Garth's recollection:
Garth wrote:
Regarding speed of the Apple II: There was a Forth engine plug-in board that would have been cool to try. I was looking at a programming magazine from 1982 and came across an ad for MicroSpeed for the Apple II. At the top it says in big letters, "TEST-FLY A $20 MILLION JET ON AN APPLE? YES. WITH MICROSPEED." It starts by saying,

    At the Bethesda Naval Research Center, they've discovered the power of MicroSPEED. The Navy's engineers use this remarkable hardware/software combination to "fly" an advanced fighter aircraft in real time-- even making vertical landings on a simulated carrier deck. A "crash" is merely another learning experience, and an opportunity to modify the research aircraft-- inside the Apple-- to improve tomorrow's combat planes. Surprised that such a sophisticated task is possible on the Apple? So were the Navy's officials, and many others who have discovered THE MICROSPEED DIFFERENCE <snip> ...and incredible Forth extensibility <snip>
As I understand it, this was a 4MHz Forth-hardware (ie, stack computer) plug-in board for the Apple II, and the MicroSpeed software for it came on a single 5.25" floppy.

I found the advert at ... h/bethesda
and it seems to me that the product, from Applied Analytics Inc., was a 6502 Forth for the AppleII, with an expansion card supplying the floating point capability, for $495. That card had an AMD Am9511 on it, running at 4MHz. It is stack-based, offering fixed-point operations at 16 and 32 bit widths and a 32 bit floating point format. Basic operations took hundreds of clock cycles, transcendental operations took thousands (up to 12000 for POW.) Lots more about that chip in the datasheet: ... %20FPU.pdf
and the algorithm details: ... etails.pdf
(where we learn that the transcendental functions use up all of the 4-level stack for temporaries.)

For a user-friendly overview of the development of floating point coprocessors, see ... n-and-now/

There's a product announcement in the 24 Nov 1980 issue of Infoworld:
which says the product can do over 100 square root operations per second, speeds up development time by 2x, and is 6 to 60 times faster than the base Apple II.


Last edited by BigEd on Fri Aug 07, 2020 8:42 am, edited 1 time in total.

fix linkrot

Sun Aug 24, 2014 8:43 am

Joined: Wed Jan 09, 2013 6:54 pm
Posts: 1644
Someone hooked one up to a Z80 to make a scientific calculator: ... h2dFrqwSLx

Sun Aug 24, 2014 11:26 am

Joined: Sat Feb 02, 2013 9:40 am
Posts: 1528
Location: Canada
Good stuff to study. For 1978 the transistor count must have been low. Makes me almost want to try replicating something similar in an FPGA.
Registers, ALU, and microcode all tied together.
Recently I've been looking at 96 bit (69.27) fixed point arithmetic for currency operations. (20.8) decimal digits.

Robert Finch

Wed Aug 27, 2014 11:13 am WWW

Joined: Wed Jan 09, 2013 6:54 pm
Posts: 1644
Another 9511 device, on a small expansion card for the Apple II, from Redshift.

I began selling the systems through an ad in Physics Today in March of 1983. I think with ad lead times, I submitted in November or December of 1982 in order to make the March issue.




Mon Jan 04, 2016 9:51 am
 [ 4 posts ] 

Who is online

Users browsing this forum: AhrefsBot, CCBot, DotBot and 3 guests

You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Jump to:  
Powered by phpBB® Forum Software © phpBB Group
Designed by ST Software