23 Oct
2005
23 Oct
'05
4:39 p.m.
Chuck Guzis <cclist at sydex.com> wrote:
If PC-based emulators are fast enough, why bother with
the IC version?
1. I don't want an emulator, I want The Real Thing (tm).
2. A pee sea based emulator requires a pee sea. I refuse to contaminate
my house with a pee sea.
MS
23 Oct
23 Oct
5:07 p.m.
On Sun, 23 Oct 05 20:39:30 GMT
msokolov at ivan.Harhan.ORG (Michael Sokolov) wrote:
Chuck Guzis <cclist at sydex.com> wrote:
Actually, with Bochs, you can run any PC software you choose, on a multitude of
architectures. You could even layer it, running an x86 emulator on your system, running
DOS on said emulator, then running a DOS-based VAX emulator on that virtual machine.
Probably it would all keep up very nicely with your ASR-33 teletype.
--
http://sasteven.multics.org/MacSE30/MacSE30.html
If PC-based emulators are fast enough, why bother
with the IC version?
1. I don't want an emulator, I want The Real Thing (tm).
2. A pee sea based emulator requires a pee sea. I refuse to contaminate
my house with a pee sea.
MS 
5:09 p.m.
Michael Sokolov declared on Sunday 23 October 2005 03:39 pm:
Chuck Guzis <cclist at sydex.com> wrote:
Indeed. If we didn't, why would most of us have hardware laying around,
when you can find an emulator for the hardware. (Not that you can find
an emulator for everything I've got though. :)
If PC-based emulators are fast enough, why bother
with the IC
version?
1. I don't want an emulator, I want The Real Thing (tm). 2. A pee sea based emulator requires a pee sea. I
refuse to
contaminate my house with a pee sea.
SimH is very portable and runs on very non-PeeCee hardware, including
just about any UNIX that has a non-ancient version of gcc available. It
may not be the fastest emu out there, but IMO it is the best one
available, overall. And yes, I too appreciate having source code
available to me to hack on if I need/want to.
Pat
--
Purdue University ITAP/RCAC --- http://www.rcac.purdue.edu/
The Computer Refuge --- http://computer-refuge.org
5:28 p.m.
On 10/23/2005 at 4:09 PM Patrick Finnegan wrote:
Michael Sokolov declared on Sunday 23 October 2005
03:39 pm:
SimH is very portable and runs on very non-PeeCee
hardware, including
just about any UNIX that has a non-ancient version of gcc available. It
may not be the fastest emu out there, but IMO it is the best one
available, overall. And yes, I too appreciate having source code
available to me to hack on if I need/want to.
Second that on SimH. I used it to decode the mysteries of WPS I--the other
emulators I tried wouldn't run WPS. And I used the 1620 emulator to test
out the 1620 "Bottles of Beer" code. Behaved exactly as I thought it
would.
The only major gripe I have with SimH is that there's no really universal
way to preload memory and registers (LOAD on the 1620 emulation loads the
line printer carriage-control tape).
Before I got my MITS 8800 put together, I emulated the 8080 on a CDC Cyber
74 so I could write and assemble code and have it ready for the MITS box.
So emulation is very useful on both ends of the life cycle.
Cheers,
Chuck
9:27 p.m.
Patrick Finnegan wrote:
SimH is very portable and runs on very non-PeeCee
hardware, including
just about any UNIX that has a non-ancient version of gcc available. It
may not be the fastest emu out there, but IMO it is the best one
available, overall. And yes, I too appreciate having source code
available to me to hack on if I need/want to.
Indeed. I run SimH on RS/6000.
Peace... Sridhar
5:10 p.m.
Michael Sokolov wrote:
Chuck Guzis <cclist at sydex.com> wrote:
FPGA software requires a pee sea sadly enough. I suspect a 8080 could do
PCB or CUSTOM
IC design if you could use a programable character set on a terminal.
When you think about it
it is the hidden documentaion in closed hardware that is the problem. I
open source FPGA
could be done as a custom chip but getting around the hardware patents
is the problem..
If PC-based emulators are fast enough, why bother
with the IC version?
1. I don't want an emulator, I want The Real Thing (tm).
2. A pee sea based emulator requires a pee sea. I refuse to contaminate
my house with a pee sea.
7:01 p.m.
woodelf declared on Sunday 23 October 2005 04:10 pm:
Michael Sokolov wrote:
No it doesn't.
In my FPGA design class at Purdue, I never used a single PC. The
software we used ran on Sun Ultrasparc boxes running Solaris.
Unfortunately, I can't remember the name of it right now.
Pat
--
Purdue University ITAP/RCAC --- http://www.rcac.purdue.edu/
The Computer Refuge --- http://computer-refuge.org
Chuck Guzis <cclist at sydex.com> wrote:
FPGA software requires a pee sea sadly enough. If PC-based emulators are fast enough, why bother
with the IC
version?
1. I don't want an emulator, I want The Real Thing (tm).
2. A pee sea based emulator requires a pee sea. I refuse to
contaminate my house with a pee sea.
7:27 p.m.
Patrick Finnegan wrote:
No it doesn't.
Mine does use a PC. I have to use the free stuff and that is PC,
In my FPGA design class at Purdue, I never used a
single PC. The
software we used ran on Sun Ultrasparc boxes running Solaris.
Unfortunately, I can't remember the name of it right now.
I also get use CUPL for my CPLD designs. I am greatfull that I am not in a
FPGA class as I dis-agree with the languages used to write hardware, I am
still a hardware person, and the direction CPU design is going, since I
still
like to be able to see hardware and that does not seem posible.
Pat
I also don't like FPGA for the reason you can't do single persion
development
like I am doing since Serial - prom programers are expensive. A CPLD
development
kit is about $100 and I can still use 5 volt devices.
FPGA's have good features but low cost develepment is not one of them
after you have to have a stand alone design away from the host computer.
-----
Back to the vax, does the person who started this thread have VAX
software and VAX I/O devices?
5:22 p.m.
On 10/23/2005 at 8:39 PM msokolov at ivan.harhan.org wrote:
1. I don't want an emulator, I want The Real Thing
(tm).
Well, you might have a real core, but there's the problem of providing real
I/O. Are you going to implement Unibus and QBus too?
I/O is a far bigger problem than any core architecture, IMOHO. Some of
those old mainframes had really high-speed I/O channels.
Cheers,
Chuck
5:29 p.m.
>>>> "Michael" == Michael Sokolov
<msokolov at ivan.harhan.org> writes:
Michael> Chuck Guzis <cclist at sydex.com> wrote:
> If PC-based emulators are fast enough, why bother
with the IC
> version?
Michael> 2. A pee sea based emulator requires a pee sea. I refuse to
Michael> contaminate my house with a pee sea.
SIMH would run on a Mac, wouldn't it?
:-)
paul
6:03 p.m.
Paul Koning <pkoning at equallogic.com> wrote:
SIMH will run on a VAX, in fact :-).
Getting back to FPGA's, I know of a couple FPGA implementations of
PDP-11's. (They are mostly KDJ11 clones, but they differ in a couple
of tiny respects.) With extreme effort in the late 90's, they managed
to make 4 FPGA's be about a factor of 2 factor on most benchmarks than
a 11/93.
By the time the FPGA implementations made it to market the PC-based
emulators were so much more cost-effective for most applications
(despite their warts of running under a host OS...)
I suspect that a FPGA implementation of a VAX would have a
performance about equal to a 11/780 if done by an average Joe.
Someone with much experience in caching/pipelining could probably
eek out a factor of 2x or 3x by pulling out all the tricks in the
book.
Tim.
>>>> "Michael" == Michael Sokolov <msokolov at
ivan.harhan.org> writes:
Michael> Chuck Guzis <cclist at sydex.com> wrote:
> If PC-based emulators are fast enough, why
bother with the IC
> version?
Michael> 2. A pee sea based emulator requires a pee sea. I refuse to
Michael> contaminate my house with a pee sea.
SIMH would run on a Mac, wouldn't it?
:-)
paul
6:49 p.m.
On Sun, 23 Oct 2005, Tim Shoppa wrote:
Paul Koning <pkoning at equallogic.com> wrote:
SIMH will run on a VAX, in fact :-).
Getting back to FPGA's, I know of a couple FPGA implementations of
PDP-11's. (They are mostly KDJ11 clones, but they differ in a couple
of tiny respects.) With extreme effort in the late 90's, they managed
to make 4 FPGA's be about a factor of 2 factor on most benchmarks than
a 11/93.
By the time the FPGA implementations made it to market the PC-based
emulators were so much more cost-effective for most applications
(despite their warts of running under a host OS...)
I suspect that a FPGA implementation of a VAX would have a
performance about equal to a 11/780 if done by an average Joe.
Someone with much experience in caching/pipelining could probably
eek out a factor of 2x or 3x by pulling out all the tricks in the
book.
Tim.
Well since its pretty easy to get microcode to run at 75-100 MHz or so in
current cheap FPGAs, I'd say that 10 X a 780 should be trivial...
Peter Wallace
>>>> "Michael" == Michael Sokolov <msokolov at
ivan.harhan.org> writes:
Michael> Chuck Guzis <cclist at sydex.com> wrote:
> If PC-based emulators are fast enough, why
bother with the IC
> version?
Michael> 2. A pee sea based emulator requires a pee sea. I refuse to
Michael> contaminate my house with a pee sea.
SIMH would run on a Mac, wouldn't it?
:-)
paul
7:49 p.m.
Tim Shoppa wrote:
I suspect that a FPGA implementation of a VAX would have a
performance about equal to a 11/780 if done by an average Joe.
Someone with much experience in caching/pipelining could probably
eek out a factor of 2x or 3x by pulling out all the tricks in the
book.
I have to disagree. I think you're off by at least a factor of 10,
maybe even 100.
http://www.fpgacpu.org (and that's 3 year old info)
If you can build a 300mips 8051 in an fpga, you sure as heck can build a
10mips vax. I would bet on 50mips w/o breaking a sweat.
http://www.opencores.org/projects.cgi/web/yacc/overview
that's 110mips @ 165mhz. not hard at all these days. heck, you run
the sdram interface at 100mhz.
If you can keep things inside the fpga you can use clock multipliers to
run pretty fast. It's the pad ring which will slow you down, but now
days the on/off chip delays are under 10ns.
I would think the sdram interface would be the limiting factor. You'd
want to burst into a cache but that eats up a ton of resources, so you
have to find a reasonable tradeoff.
There is enough ram inside most fpga's these days to do some form of
associative caching and all of the microcode/register file you need.
Go look at NIOS and other off-the-shelf cpu's. They are moving a long at
a nice clip.
-brad
6852
days inactive
6853
days old
12 comments
10 participants
participants (10)
-
bfranchuk＠jetnet.ab.ca -
brad＠heeltoe.com -
cclist＠sydex.com -
chenmel＠earthlink.net -
msokolov＠ivan.Harhan.ORG -
pat＠computer-refuge.org -
pcw＠mesanet.com -
pkoning＠equallogic.com -
ploopster＠gmail.com -
shoppa_classiccmp＠trailing-edge.com