Newsgroups: comp.sys.transputer
From: Charles Sweeney <CharlesSweeney@compuserve.com>
Reply-To: CharlesSweeney@compuserve.com
Subject: Re: Short memories
Organization: Embedded Solutions Ltd
Date: Mon, 17 Nov 1997 17:05:17 +0000
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Message-ID: <3470794D.CDAD7FEE@compuserve.com>

For a PCI plug-in board  with ARM and Atmel FPGA have a look at

http://www.comlab.ox.ac.uk/oucl/users/ian.page/hwcomp/aspire/aspire.html

Aspire is a project between Oxford Unicersity and ARM to develop the board,
and port Embedded Solutions' FPGA programming language Handel-C to it.

Charles

steve wrote:

> Paul Walker wrote:
>
> > Buyers please!  --for an ARM based transputer replacement
>
> Me!
>
> > With a bit more money, and perhaps with a more limited choice of
> > processor, it would be possible to put DRAM on the same chip, say 1 or 2
> > Mbytes. So the single-chip TRAM with 16 pins (or so) would be a reality.
>
> Not sure about 16 pins.... 4 links was never enough for a lot of things
> we needed to do. I think there's also a need for 8 pins worth of general
> purpose I/O.  I guess a question is whether to go for a bloated first
> implementation and strip things off for 'real' customers, or go with a
> lightweight first implementation and add bits...
> My absolute requirement is that the end product be able to run legacy
> and new occam, and, as ever, the software is the bit of the project
> that's out of my league. The hardware's pretty simple, though, and ought
> to be easily prototypable in VHDL then FPGAs bolted to the side of an
> ARM
> (Or StrongARM). A port to ASIC should be little more than a licensing
> and
> handle-turning exercise?
> I'm certainly up for it. Do I sense a sabbatical coming up?
>
> Steve