15 Jan
2023
15 Jan
'23
7:09 p.m.
I just stumbled across an old letter, from a VP of Burroughs to me and
Steve Bartels, authorizing $30,000 for a port of Unix to the E-mode stack
machine. I had forgotten getting it.
Burroughs was famed for its stack machines. E-mode was a kind of last gasp
attempt to save the stack architecture, which failed as far as I know, see
this table:
http://jack.hoa.org/hoajaa/Burr126b.html
I worked as a hardware engineer on the A15. I also had been a Unix user for
7 years at that point and kept pointing out how awful the Burroughs CANDE
time-sharing system was, and how much better Unix was. At some point I
guess they asked me to put up or shut up. I got that money, and left
Burroughs a week later for grad school.
Funny note: A15 was Motorola ECL (MECL), and ran at 16 Mhz., considered
fast at that time. We used a technique called "stored logic" which was,
believe it or not, using MECL RAM to map logic inputs to outputs, i.e.
implement combinational logic with SRAM. Kind of nuts, but it worked at the
time. We also used a precursor of JTAG to scan it in. Those of you who know
JTAG have some idea of how fun this had to be.
One side effect of working with MECL is you realized just how well designed
the TI 7400 SSI/MSI parts were ... MECL always just felt like an awkward
family to design with.
Another funny story, pointing to what was about to happen to Burroughs. We
had an app that ran for hours on the stack machine. We quick ported it to a
VAX, started it up, and headed out to lunch -- "this will take a while,
let's go eat." We got to the front door and: "Oh, wait, let me hop back
into the office,I forgot my jacket". And, noticed, the program was done in
... about 3 minutes. Not 8 hours.
That's when we knew it was game over for Burroughs.
If a picture of this letter would be useful in some archive somewhere, let
me know, I can send it.
15 Jan
15 Jan
7:19 p.m.
Well, FPGAs use SRAM-based look-up tables to do their combinational
logic functions - so not that crazy - if it works and gives good enough
results for the task at hand, people will find ways of using the
technique. But I imagine there were a host of other things that weren't
done as well as possible that added up to 8 hours vs. 3 minutes.
On 01/15/2023 12:09 PM, ron minnich wrote:
I just stumbled across an old letter, from a VP of
Burroughs to me and
Steve Bartels, authorizing $30,000 for a port of Unix to the E-mode
stack machine. I had forgotten getting it.
Burroughs was famed for its stack machines. E-mode was a kind of last
gasp attempt to save the stack architecture, which failed as far as I
know, see this table:
http://jack.hoa.org/hoajaa/Burr126b.html
I worked as a hardware engineer on the A15. I also had been a Unix
user for 7 years at that point and kept pointing out how awful the
Burroughs CANDE time-sharing system was, and how much better Unix was.
At some point I guess they asked me to put up or shut up. I got that
money, and left Burroughs a week later for grad school.
Funny note: A15 was Motorola ECL (MECL), and ran at 16 Mhz.,
considered fast at that time. We used a technique called "stored
logic" which was, believe it or not, using MECL RAM to map logic
inputs to outputs, i.e. implement combinational logic with SRAM. Kind
of nuts, but it worked at the time. We also used a precursor of JTAG
to scan it in. Those of you who know JTAG have some idea of how fun
this had to be.
One side effect of working with MECL is you realized just how well
designed the TI 7400 SSI/MSI parts were ... MECL always just felt like
an awkward family to design with.
Another funny story, pointing to what was about to happen to
Burroughs. We had an app that ran for hours on the stack machine. We
quick ported it to a VAX, started it up, and headed out to lunch --
"this will take a while, let's go eat." We got to the front door and:
"Oh, wait, let me hop back into the office,I forgot my jacket". And,
noticed, the program was done in ... about 3 minutes. Not 8 hours.
That's when we knew it was game over for Burroughs.
If a picture of this letter would be useful in some archive somewhere,
let me know, I can send it.
16 Jan
16 Jan
12:51 a.m.
https://web.archive.org/web/20130521183231/http://jack.hoa.org/hoajaa/BurrM…
has the burroughs info.
On Sun, Jan 15, 2023 at 11:09 AM ron minnich <rminnich(a)gmail.com> wrote:
I just stumbled across an old letter, from a VP of
Burroughs to me and
Steve Bartels, authorizing $30,000 for a port of Unix to the E-mode stack
machine. I had forgotten getting it.
Burroughs was famed for its stack machines. E-mode was a kind of last gasp
attempt to save the stack architecture, which failed as far as I know, see
this table:
http://jack.hoa.org/hoajaa/Burr126b.html
I worked as a hardware engineer on the A15. I also had been a Unix user
for 7 years at that point and kept pointing out how awful the Burroughs
CANDE time-sharing system was, and how much better Unix was. At some point
I guess they asked me to put up or shut up. I got that money, and left
Burroughs a week later for grad school.
Funny note: A15 was Motorola ECL (MECL), and ran at 16 Mhz., considered
fast at that time. We used a technique called "stored logic" which was,
believe it or not, using MECL RAM to map logic inputs to outputs, i.e.
implement combinational logic with SRAM. Kind of nuts, but it worked at the
time. We also used a precursor of JTAG to scan it in. Those of you who know
JTAG have some idea of how fun this had to be.
One side effect of working with MECL is you realized just how well
designed the TI 7400 SSI/MSI parts were ... MECL always just felt like an
awkward family to design with.
Another funny story, pointing to what was about to happen to Burroughs. We
had an app that ran for hours on the stack machine. We quick ported it to a
VAX, started it up, and headed out to lunch -- "this will take a while,
let's go eat." We got to the front door and: "Oh, wait, let me hop back
into the office,I forgot my jacket". And, noticed, the program was done in
... about 3 minutes. Not 8 hours.
That's when we knew it was game over for Burroughs.
If a picture of this letter would be useful in some archive somewhere, let
me know, I can send it.
1:59 a.m.
I rise to defend the honor of ECL. I had designed with TTL through college and the ‘80s:
network cards, graphics controllers, the Etherphone, the CPU modules for the Firefly
MicroVAX multiprocessor, and so forth. My early designs were SSI and later ones PAL based
mostly (Like in Soul of the New Machine). In 1990 or 1991 Digital Systems Research Center
started work on the Alpha Demonstration Unit, intended for software porting. The Alpha
EV-3 and EV-4 were I/O compatible with either TTL or ECL levels, so we chose ECL 100K with
some of the new ECLinPS stuff and even some custom Gallium Arsenide address drivers for
the DRAM arrays. This all let the system run at 100 MHz, to keep up with the 100 or 200
MHz Alphas.
The short version is that if you can afford the power, ECL is <awesome>. Every wire
is a transmission line. Every signal is terminated. Almost every part (except the 5 NS
cache rams) has complementary outputs. What’s not to like about 350 ps NOR gates? The
signal integrity alone makes it worthwhile. The CACM paper is at
https://dl.acm.org/doi/10.1145/151220.151225
<https://dl.acm.org/doi/10.1145/151220.151225> but the Digital Technical Journal
version is on Bitsavers at http://www.bitsavers.org/pdf/dec/dtj/dtj_v04-04_1992.pdf
<http://www.bitsavers.org/pdf/dec/dtj/dtj_v04-04_1992.pdf>
Naturally all the production systems were TTL and CMOS, but that ECL stuff was great fun.
We had a local welding shop make 18” cables for the 400 Amps of -4.5v and 200 Amps of -2v
terminator power. They said “what kind of a welder is this for anyway?
The Unix angle, such as it is, is that the ADU ran OSF-1 and Alpha VMS <at the same
time> on different subsets of the CPU and memory boards. Not a hypervisor, but a hard
partitioning of resources. There was enough I/O stuff to run three “computers” I think.
Earlier I had been a user of the Xerox Dorado, which was 16 MHz ECL (probably MECL) in the
early 80’s. It made a wonderful personal computer :). Ken Pier’s retrospective at
http://bitsavers.trailing-edge.com/pdf/xerox/parc/techReports/ISL-83-1_A_Re…
<http://bitsavers.trailing-edge.com/pdf/xerox/parc/techReports/ISL-83-1_A_Retrospective_on_the_Dorado_A_High-Performance_Personal_Computer.pdf>
talks a bit about debugging on page 32. The Dorado had JTAG like scan logic threaded
through it, which made debugging and repair of such a complex beast possible. IIRC quite
a lot of work went into the control software for the scan logic, devoting an Alto to
having a decent UI for it.
-Larry
On 2023, Jan 15, at 7:51 PM, ron minnich
<rminnich(a)gmail.com> wrote:
https://web.archive.org/web/20130521183231/http://jack.hoa.org/hoajaa/BurrM…
<https://web.archive.org/web/20130521183231/http://jack.hoa.org/hoajaa/BurrMain.html>
has the burroughs info.
On Sun, Jan 15, 2023 at 11:09 AM ron minnich <rminnich(a)gmail.com
<mailto:rminnich@gmail.com>> wrote:
I just stumbled across an old letter, from a VP of Burroughs to me and Steve Bartels,
authorizing $30,000 for a port of Unix to the E-mode stack machine. I had forgotten
getting it.
Burroughs was famed for its stack machines. E-mode was a kind of last gasp attempt to
save the stack architecture, which failed as far as I know, see this table:
http://jack.hoa.org/hoajaa/Burr126b.html
<http://jack.hoa.org/hoajaa/Burr126b.html>
I worked as a hardware engineer on the A15. I also had been a Unix user for 7 years at
that point and kept pointing out how awful the Burroughs CANDE time-sharing system was,
and how much better Unix was. At some point I guess they asked me to put up or shut up. I
got that money, and left Burroughs a week later for grad school.
Funny note: A15 was Motorola ECL (MECL), and ran at 16 Mhz., considered fast at that
time. We used a technique called "stored logic" which was, believe it or not,
using MECL RAM to map logic inputs to outputs, i.e. implement combinational logic with
SRAM. Kind of nuts, but it worked at the time. We also used a precursor of JTAG to scan it
in. Those of you who know JTAG have some idea of how fun this had to be.
One side effect of working with MECL is you realized just how well designed the TI 7400
SSI/MSI parts were ... MECL always just felt like an awkward family to design with.
Another funny story, pointing to what was about to happen to Burroughs. We had an app
that ran for hours on the stack machine. We quick ported it to a VAX, started it up, and
headed out to lunch -- "this will take a while, let's go eat." We got to
the front door and: "Oh, wait, let me hop back into the office,I forgot my
jacket". And, noticed, the program was done in ... about 3 minutes. Not 8 hours.
That's when we knew it was game over for Burroughs.
If a picture of this letter would be useful in some archive somewhere, let me know, I can
send it.
466
days inactive
467
days old
3 comments
3 participants
participants (3)
-
Lawrence Stewart -
Luther Johnson -
ron minnich