27 Aug
1999
27 Aug
'99
12:31 p.m.
please see embedded comments below.
Dick
-----Original Message-----
From: Tony Duell <ard(a)p850ug1.demon.co.uk
To: Discussion re-collecting of classic computers
<classiccmp(a)u.washington.edu Date: Friday, August
27, 1999 4:40 PM
Subject: Re: PDP era and a question
[...]
> In yesterday's newspaper I noted that the local discount house (Best-Buy
for
a
Well, first of all, I think it's nice that the mfg's of these devices have
made it possible to do this work on machines costing less than a year's pay,
and if there were enough business to justify it, they'd make it possible for
you to build their devices on your HP calculator or whatever you prefer.
It's just a question of how badly you want to do it. If I didn't want to
spend the necessary money, I'd not be able to do it either. Now, I don't
know why you can't get a job. There are lots of people here in the US who
are in the same boat. If you have some physical disability, or
mental/emotional impairment, though, there are programs here and I'd be
surprised if there weren't some similar programs in the UK to "help" you
get
a low-cost PC if there are any indications at all that you'd be able to
produce useful work translatable in to substantial gainful activity with it
at your disposal.
However, if you can't get a job because you categorically refuse to learn to
use the PC because you find the Microsoft OS repugnant, I'd predict you'll
remain so.
> I recently read that the folks who sell these FPGA's have no problem at
all
Well, it's not likely that you'll encounter much cooperation in your
effort
to convince the world to share its secrets. These days, when patents are of
no use because the market window is shorter than the delay getting to court,
the only way people can defend what they perceive to be their turf is by
keeping it "close to the vest" like a hand of cards.
.>Not really. Even if I could buy a source
license, that wouldn't give me
>the right to pass the sources around. About the only way to get to do
>that is to buy the company (:-)).
It's absolutely open source, if that's
how you want to handle it, once you
buy the right to do so. I don't mean buy a copy. I mean buy ALL the
rights. Once you've acquired all the rights, by paying for them, I doubt
you'll want to give them away by making them freely distributable.
>> all of us are willing to pay the required 6.23*10^23 bucks for what we'd
>> otherwise get for less than $1k for just the objects.
>Again, I am not asking for the
'official' sources. Just for the ability
>to write my own.
Perhaps if you inquire about obtaining those
rights, you'll see what value
they are perceived to represent. Dealing with the numbers helps put things
in to prespective.
I'm surprised that there was a commonly available scf2xnf (or whatever it
was called) translator, since that essentially reverse engineered your
product for your competitor, but it would surprise me even more for the
vendor to provide you the ability to see how they've enhanced their parts if
that's reflected in their configuration files.
Nevertheless, perhaps you need to back away from your devotion to the
absolute notion of fully open source in favor of a really efficient,
particularly cost-efficient, PDP whatever you want to build. If you need to
have sources in order to fix what you consider to be an annoying bug in the
software tools with which the FPGA is to be devised, I'd point out that
noone else is able to fix it either. Sometimes it's necessary to live with
those "bugs" which annoy you most.
>-tony
>
> >Firstly, it doesn't matter how cheap the software is if you can't
use
it.
It depends more on how you define "can't" than anything else, though.
"Can't" is quite simple : I can't execute the software on that
disk/CD-ROM on any computer that I currently own. Period.
> those who care) was offering a major-brand 350 MHz
Celeron-based computer
> system without monitor but with AGP video, 6.4 GB HDD, 64 MB memory,
CDROM,
FDD, v.90
modem, keyboard, all for $399 US. A really nice (I recently
They're a little more in the UK, although I think I've seen similar
machines advertised here for \pounds 399 or thereabouts.
> bought one when the "appropriate display" (19") mentioned above
developed > margin problem.) 17" monitor for $199. That
means that for what I
typically
> earn in a couple or three days after taxes and
expenses, I can buy a
whole
computer
system capable of doing this FPGA stuff.
OK for you. Remember I can't get a job. After 'essentials', I would have
to save for about a year to get a machine like that. And there are other
things I put somewhat higher on my priority list as I already have plenty
of useable computer systems for everything else I want to do.
Please note, I am not saying that the FPGA manufacturers should support
all the possible choices of machine and OS. Just that I wish that _one_
of them would provide enough information for me to support them myself.
The reality of the matter is that these device vendors, of whom I would
assume it could be said they're in a good position to make such a
determination, have decided that it's worth their effort to invest the
effort and money in creating support tools for the PC running Windows 9x and
not the PDP-8S or whatever, running something else. This is not my
preference either, since I like and trust DOS much more than the WINDOWS
varieties, but then, they no longer put out tools for the MAC either, not
that I'd use one even if they were free.
> giving you the necessary data to enable you to
configure their parts.
They
won't give
you a disassembly tool or whatever that would be, but they'll
Interesting. That's exactly the opposite of my experiences with Xilinx
when I used the official toolkit in my last job (XC3000 and XC4000 parts
mostly).
There was a _supplied_ program that would take a configuration bitstream
and turn it back into a CLB + interconnect map - essentially a
disassembler. Of course turning that map into a schematic was a lot of
work, but the 'secret' part was there.
But no way would they tell us what any of the bits in the configuration
file actually meant.
I am told they might have supplied some documentation under an NDA, but
that's no use for open-source software, of course.
> >Secondly, I like all my software to be open-source so that I can fix
> >bugs. Now, I can quite understand why commercial software isn't like
> >this. What I am commenting on is the fact that I _can't_ write my own
> >FPGA tools if I wanted to.
> > All software is open-source if you have the
dough to buy the sources.
Not
28 Aug
28 Aug
4:49 a.m.
A non-text attachment was scrubbed...
Name: not available
Type: text
Size: 4846 bytes
Desc: not available
Url :
http://www.classiccmp.org/pipermail/cctalk/attachments/19990828/0f07490f/at…
8:46 a.m.
On Sat, 28 Aug 1999, Tony Duell wrote:
You are missing the point. I am not asking that the
FPGA companies
produce/support tools that run on <whatever>. I am simply asking that
they allow me to create said tools.
Given the information you want, it would be fairly easy to reverse
engineer someone elses IP core and repackage it as your own.
You could purchase the rights to use someone elses 8051 uC core in
your Altera device. The core is delivered to you as an encrypted,
compiled, gate level description. You compile and fit it into a
(fully documented) part, read the bitstream, and generate
essentially a compiled, gate level description. Re-encrypt it, and
sell it as your own. Since it is encrypted, the original IP owner
can't decrypt it and verify it is theirs.
This requires very little engineering work on your part.
Think of microcontrollers for the moment, particularly
the Microchip PIC.
I use that chip a lot. Now, I can either use the (free) Microchip
assembler/simulator that runs on PCs, or I can take the databook off the
shelf and write my own assembler/simulator. The necessary information is
given to do that.
True, except for "secure" microcontrollers that are being sold into
smart cards and security systems. You have to convince the uC manufacture
you are a real company that is going to buy millions of their chips.
This makes it much more difficult for a hacker to read the EPROM and
look for security holes.
There is another reason I want this information. I
want to create
self-modifying circuits, reconfigurable CPUs, etc. And I can't do that if
I am forced to use the manufacturers tools for every change in configuration.
This is a very valid reason. Have you asked for the information on
that basis? And convinced the company you are for real? This involves
convincing the tech support grunt answering the phone you really should
be allowed to talk to an aps engineer, and possiblly even a design
engineer. The documentation exists (the hardware guys didn't write
the code), you just have to social engineer your way to it.
Most (all?) of the existing work on such systems was
done using the
now-discontinued Xilinx XC6200 series. Those were fully documented (I
have the data sheets).
This implies there wasn't a good reason to continue supplying the
documentation to the public. Too many idiots trying to write their
own tools and calling tech support hourly when it didn't work?
Hmm... Since the architecture of the FPGA is already pretty well
described in the databook, releasing exactly how the bitstream configures
the chips is not giving that much more away.
But it is information, and companies get rich selling information.
clint
11:08 a.m.
A non-text attachment was scrubbed...
Name: not available
Type: text
Size: 3898 bytes
Desc: not available
Url :
http://www.classiccmp.org/pipermail/cctalk/attachments/19990829/252fff51/at…
2:08 p.m.
While the thread has wandered far from the subject line, I am compelled
to respond to some of this.
Please Tony, this is not an attack on you. There is a lot of
mis-information
about FPGAs IP, software, and architecture. This thread has just
exceeded
my "sit back and read" threshold.
Tony Duell wrote:
Anyway, the real point is that certainly for Xilinx
FPGAs, if you buy the
official tools you get a program to 'reverse engineer' a bitstream back
to the CLB map. Converting that to a schematic is still a non-trivial task...
This is ABSOLUTELY NOT TRUE. There is NO tool that can reverse engineer
the bitstream to anything. Neither internal to Xilinx or external (and
announced). There is ONE instance where the bitstream was "forward"
engineered to find the mapping between design primitives and the
resultant
bitstream, and this was done by a company called Neocad, and they were
acquired by Xilinx. The process they used did not have the capability of
taking an existing design bitstream, and decoding this into any type of
design database. The final translation from design database (NCD in
current
tools, LCA in prior generation) to bitstream is unidirectional. If you
want
to make changes to your design, you make them to the design database. If
you desperately want to make design changes to the bitstream, Xilinx
provides as part of the standard tool chain, LL files that point you to
some
but not all bits in the bitstream (LUT bits, and some FF bits. NO
routing
bits). Xilinx also provides a tool called JBITS, which can also modify
the bitstream, and might be used to create a reverse engineering tool,
but
this has not been done to my knowledge. With regard to the "and
announced"
above, it is possible that an organization like the NSA may have done
something like this, but they haven't told me about it.
Even if such reverse engineering tool existed, you would end up with a
CLB map, which I agree would be non-trivial to get into a useful
schematic.
Not just me, I know of research groups who are having
problems with this
due to the loss of the XC6200s...
While the research groups that weren't distracted by XC6200, and
continued
with the XC4000 and its descendants, have not wasted time screwing
around
with tools, and have gone on to do some real useful stuff. See the
proceedings of the annual IEEE FCCM conferences.
And yes, I've tried. The policy is that this
information will not be
available, except possibly under an NDA (which would have been no use to
me).
Flip-flop and LUT position in bitstream for an existing design:
Directly avail in LL file.
FF and LUT position for all bitstreams (alg for calculating it you self)
Avail under NDA.
Mode control, some more I/O info, but not routing info:
Avail under a tougher NDA.
The whole lot:
Avail under a very tough NDA.
> > Most (all?) of the existing work on such
systems was done using the
> > now-discontinued Xilinx XC6200 series. Those were fully documented (I
> > have the data sheets).
This product has not been discontinued. At last report, Xilinx said that
parts would continue to be available to anyone that wanted to buy them.
Further development of the family has stopped. Further development of
the
support software has stopped, but that is not an issue, because you plan
to
write your own.
see: http://www.vcc.com/RPU.html#anchor581456 status
http://www.vcc.com/Papers/6200.pdf data sheet
http://www.xilinx.com/techdocs/htm_index/utils_6200.htm
> This implies there wasn't a good reason to
continue supplying the
> documentation to the public. Too many idiots trying to write their
> own tools and calling tech support hourly when it didn't work?
Unknown. Data sheet is still available from
http://www.vcc.com/Papers/6200.pdf
and from Xilinx by request.
The official reason why the XC6200 was dropped was
because they didn't
sell enough of them. This could have been due to the fact that no
distributor that I 'phoned had ever heard of them. It could have been due
to the fact that they were so differnt from other Xilinx parts that they
didn't really do the same job, and people didn't realise what they'd be
useful for. Or maybe the real reason for dropping them is totally
different anyway.
-tony
Or maybe, they didn't sell enough. If the only people buying a chip is
university researchers, in 1-10 piece quantities, it is not a viable
product.
29 Aug
29 Aug
5:42 a.m.
A non-text attachment was scrubbed...
Name: not available
Type: text
Size: 2504 bytes
Desc: not available
Url :
http://www.classiccmp.org/pipermail/cctalk/attachments/19990829/d56175a7/at…
1:45 p.m.
Tony wrote:
There is another reason I want this information. I
want to create
self-modifying circuits, reconfigurable CPUs, etc. And I can't do that if
I am forced to use the manufacturers tools for every change in configuration.
Most FPGAs can't be used in that manner in a practical fasion anyhow.
Normally you have to put the FPGA into a special programming mode, during
which it loads its configuriation and is otherwise non-functional. The
closest you could get to self-modifying is to have an FPGA configuration that
computes a new configuration, writes it to external RAM, and then resets
itself (forcing a reconfiguration). This would almost certainly require
at least a small amount of external dedicated logic to select which
configuration memory to use and to control the timing of the update.
There was a line of FPGAs specifically designed for reconfigurable
computing; it divided up the FPGA into sections and allowed reconfiguration
at section granularity. I think it was made by either Actel or Atmel.
30 Aug
30 Aug
6:08 a.m.
A non-text attachment was scrubbed...
Name: not available
Type: text
Size: 1623 bytes
Desc: not available
Url :
http://www.classiccmp.org/pipermail/cctalk/attachments/19990830/4b8f9482/at…
9017
days inactive
9020
days old
7 comments
5 participants
participants (5)
-
ard＠p850ug1.demon.co.uk -
class＠fliptronics.com -
edick＠idcomm.com -
eric＠brouhaha.com -
vaxman＠oldy.crwolff.com