[TUHS] Why did PDPs become so popular?

[TUHS] Why did PDPs become so popular?

[Dave Ritchie]

I think that steep educational discounts and equipment grants from Digital to major collages also had a major impact,as did the existence of DECUS that made a lot of software readily available. 

Best regards, 
David Ritchie
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171227/fb3337b1/attachment.html>

[TUHS] Why did PDPs become so popular?

[Dave Horsfall]

On Wed, 27 Dec 2017, Dave Ritchie via TUHS wrote:

> I think that steep educational discounts and equipment grants from 
> Digital to major collages also had a major impact, as did the existence 
> of DECUS that made a lot of software readily available.

IBM practically gave away their kit to educational institutions too (and 
made their money from the maintenance); there was no way that the 
University of NSW e.g. could've afforded their 360/50 otherwise,

And IBM had their SHARE group, which was pretty much the same as DECUS.

-- 
Dave Horsfall DTM (VK2KFU)  "Those who don't understand security will suffer."

[TUHS] Why did PDPs become so popular?

[Paul Winalski]

On 12/27/17, Dave Horsfall <dave at horsfall.org> wrote:
> On Wed, 27 Dec 2017, Dave Ritchie via TUHS wrote:
>
>> I think that steep educational discounts and equipment grants from
>> Digital to major collages also had a major impact, as did the existence
>> of DECUS that made a lot of software readily available.
>
> IBM practically gave away their kit to educational institutions too (and
> made their money from the maintenance); there was no way that the
> University of NSW e.g. could've afforded their 360/50 otherwise,

That may have been true in the 1960s, but by the mid-1970s IBM
System/360/370 was no longer competitive in the educational market.
Circa 1973, Boston College--a true Blue IBM shop with a
System/370-145--wanted to provide time-sharing services to the student
body.  For less than the cost to upgrade the model 145 to a 158, they
bought a PDP-11/70 and ran RSTS on it.  Similarly Holy Cross (my alma
mater) had outgrown their System/370-125 by 1976.  For the price of an
upgrade to a model 135, they could by a complete VAX-11/780 system for
academic use and retain the S/370-125 exclusively for college admin
purposes.  The 11/780 was equivalent in compute power and memory
capacity to a S/370-158, but for about 1/4 the cost.

-Paul W.

[TUHS] Why did PDPs become so popular?

[Kevin Bowling]

I understand IBM systems history a lot better, but it looks
simplistically to me that, in business terms, DEC created or became
the brand leader for a net new market for minicomputers rather than
competing against the establish(ed, ing) market of large systems.  I'm
sure their marketers worked very hard to differentiate the systems
from large systems, precisely because they didn't want to compete with
anyone.  This is one of the most common motifs in technology business,
start with a small niche and build out.  It happened with UNIX, PCs,
networking, etc.  These things also usually follow power laws, where
only a couple companies control the market.  There are awesome plate
tectonics and associated earthquakes, disasters, and rebuilding from
ashes where markets collide, like UNIX systems taking on system of
record, transaction processing, CAD in the '80s-'90s against
mainframes, and the associated brand names tend to reshuffle (i.e. Sun
for a while).

Regards,

On Wed, Dec 27, 2017 at 3:25 PM, Dave Ritchie via TUHS
<tuhs at minnie.tuhs.org> wrote:
>
> I think that steep educational discounts and equipment grants from Digital
> to major collages also had a major impact,
> as did the existence of DECUS that made a lot of software readily available.
>
> Best regards,
> David Ritchie

[TUHS] Why did PDPs become so popular?

[Paul Winalski]

On 12/27/17, Kevin Bowling <kevin.bowling at kev009.com> wrote:
> I understand IBM systems history a lot better, but it looks
> simplistically to me that, in business terms, DEC created or became
> the brand leader for a net new market for minicomputers rather than
> competing against the establish(ed, ing) market of large systems.

By the mid 1960s IBM had established a huge market presence and took
advantage of it to reap large profit margins by not passing along the
ever-decreasing manufacturing costs (corollary of Moore's law) to its
customers.  DEC, Data General, etc. were willing to accept lower
profit margins.  This allowed them to sell into new markets (e.g.,
small research groups) that IBM had priced themselves out of, and from
that base to make inroads into the general business marketplace.

>  I'm
> sure their marketers worked very hard to differentiate the systems
> from large systems, precisely because they didn't want to compete with
> anyone.

Not really, in my experience and from my perspective both as a DEC
customer and as a DEC development engineer.  DEC's original customer
base were experienced research engineers and scientists who knew what
they wanted and didn't have to be sold to.  Ken Olsen grew up simply
taking customer orders, and he never understood or really supported
marketing.  Lack of marketing skill eventually caught up to DEC by the
late 1980s and was a principal reason for its downfall.

In the days of the PDP-11 and VAX, DEC also didn't provide the level
of customer service, support, and hand-holding that IBM did (this was
part of the reason why IBM systems were so expensive).  Among IBM
customers the saying was, "minicomputers aren't sold, they're
abandoned".  When our VAX arrived in 1978, we were appalled at DEC's
inability to send on-site customer engineers to help us with software
problems.

Someone (Scott McNealy?) once said to survive a computer company has
to be prepared to eat its own children.  That is, to accept the
faster, lower cost technology as it comes along and not to try to
protect high profit margins on the older technology.  Minicomputers
ate the floor out from under mainframes, and IBM lost market dominance
by attempting to protect the mainframe cost structure.  PCs did the
same thing to minicomputers in the early 1990s, and DEC repeated IBM's
mistake by trying to defend against PCs instead of embracing them.

-Paul W.

[TUHS] Why did PDPs become so popular?

[Kevin Bowling]

On Wed, Dec 27, 2017 at 5:07 PM, Paul Winalski <paul.winalski at gmail.com> wrote:
> Not really, in my experience and from my perspective both as a DEC
> customer and as a DEC development engineer.  DEC's original customer
> base were experienced research engineers and scientists who knew what
> they wanted and didn't have to be sold to.

That is the very definition of good market development and sales, and
it is quite hard and never accidental.  The marketing might not look
like any marketing ever done before i.e. you don't take out TV spots
to sell minicomputers, but showing research engineers your machine and
your instruction set any chance you create might do it.  Typically
founders (or some equivalent like a GM or fellow in a technology
company) are intimately involved, because they can hold the entire
calculus in their working set, at least for a while.  As a company
grows and goes on, it becomes harder to fight people that thrive on
the illusion of work and hubris instead of what the actual market is
or what customers need that nobody else is giving them.

> Someone (Scott McNealy?) once said to survive a computer company has
> to be prepared to eat its own children.  That is, to accept the
> faster, lower cost technology as it comes along and not to try to
> protect high profit margins on the older technology.  Minicomputers
> ate the floor out from under mainframes, and IBM lost market dominance
> by attempting to protect the mainframe cost structure.  PCs did the
> same thing to minicomputers in the early 1990s, and DEC repeated IBM's
> mistake by trying to defend against PCs instead of embracing them.

That's a common view but I don't see it as black and white as a
downward race.  I see it more as entrepreneurs vying to reshuffle the
deck, most customers (executives?, corporate governance?) don't really
care that much about the specific technology they use but don't want
to be seen as too conservative nor reckless.  But there is opportunity
to make a lot of money as a startup or technology company when you get
technology to switch up drastically.  If you can convince people to go
back to timesharing on semi-proprietary equipment there is a lot of
money to be made.. Amazon has done this marvelously and will have a
nice 10+ year run yet doing that.  Most developers enthusiastically
using AWS don't think they were marketed or sold to either.  Great
market development and sales.

[TUHS] Why did PDPs become so popular?

[Ron Natalie]

The PDP-8 and 11 were cheap and this allowed them to be used both in lab situations (I remember working with PDP-8's around 1975 at UofM in non engineering departments like psychological-pharmacology) and at the departmental level, in contrast to the central data centers.    I cut my teeth on the PDP-11/45 (running UNIX) in the Electrical Engineering department.   One of the Biomedical Engineering labs used an LSI-11 running miniunix followed by an 11/23 also running UNIX.   I used PDP-11's in several locations in the Psych department and in the biomedical and opthomological departmetns at the Med School.     All this typically by people they wouldn't let anywhere near the campus computing mainframes.     The CS Department at the UofM taught a OS course (where students wrote one of their own) on a pair of 11's upstairs from the computer center.

Amusingly, on the cloud subject, years later those PDP-11's were getting long in the tooth (and you had to share them single user between a large class).   The computer center downstairs had installed several IBM VM/CMS systems.    We offered to rewrite the course curriculum, very centered on the PDP-11, to allow them to teach it on VM (writing their own hosted OS under VM).   Couldn't convince the faculty.   Made too much sense.

[TUHS] Why did PDPs become so popular?

[Rudi Blom]

A bit off the PDPs, but to do a minor correction on mail below

The commercial version of 'UNIX' on Alpha was maybe first called
Digital Unix OSF/1, but quickly changed to Digital Unix at least with
v3 and v4.0 (A - G). From there we had a 'break' which only in part
was due to take over by Compaq and we had Tru64 UNIX v5.1A and V5.1B.
The V5.1B saw updates till B-6.

As for the Digital C compiler, I'm still using
 DTCCMPLR650  installed  Compaq C Version 6.5 for Compaq Tru64 UNIX Systems

When I get some old source (some even developed on SCO UNIX 3.2V4.2) I
like to run it through all compiler /OS-es I got handy. With the
Compaq C compiler and HP-UX ANSI C I mostly get pages of warning and a
few errors. By the time I 'corrected' what I think is relevant some
nasty coredumps tend to disappear :-)

Compile for a better 2018,
uncle rubl

>Date: Fri, 29 Dec 2017 21:30:11 -0500.
>From: Paul Winalski <paul.winalski at gmail.com>
>To: Ron Natalie <ron at ronnatalie.com>
>Cc: TUHS main list <tuhs at minnie.tuhs.org>
>Subject: Re: [TUHS] Why did PDPs become so popular?
>Message-ID:     <CABH=_VRwNXUctFPav5rHX83wfUS0twMQuBhinRZ6QEY1cB3TNQ at mail.gmail.com>
Content-Type: text/plain; charset="UTF-8"
>
>On 12/29/17, Ron Natalie <ron at ronnatalie.com> wrote:
> The Alpha was hot
> stuff for about nine months.   Ran OSF/1 formerly DigitalUnix formerly
> OSF/1.

>Digital UNIX for the VAX was indeed derived from OSF/1.  The port to
>Alpha was called Tru64 UNIX.

>Tru64 UNIX was initially a pure 64-bit system, with no provision for
>building or running 32-bit program images.  This turned out to be a
>mistake .  DEC found out that a lot of ISVs had code that implicitly
>"knew" that sizeof() a pointer was the same as sizeof(int) was the
>same as 4 bytes.  Tru64 was forced to implement a 32-bit compatibility
>mode.

>There was also a problem with the C compiler initially developed at
>DECwest in Seattle.  It supported ONLY ANSI standard C and issued
>fatal errors for violations/extensions of the standard.  We (DEC
>mainstream compiler group) called it the Rush Limbaugh
>compiler--extremely conservative, and you can't argue with it.

[TUHS] Why did PDPs become so popular?

[Clement T. Cole]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 1896 bytes --]



> On Dec 31, 2017, at 12:20 AM, Rudi Blom <rudi.j.blom at gmail.com> wrote:
> 
> .With the
> Compaq C compiler and HP-UX ANSI C I mostly get pages of warning and a
> few errors. By the time I 'corrected' what I think is relevant some
> nasty coredumps tend to disappear :-)

I had to chuckle when we read these two lines.   As Paul I’m sure also remembers and mentioned about the 32/64 bit issues, when we released Alpha there we very few to zero tools available to help find errors in ISV or customer created C code that was caused by assumptions of size.   As you point out with the new ‘Gem’ compilers a great deal of work was spent by Paul and his brothers and sisters in the compiler group putting in just those messages.  For C++ it was worse than C because the language was so new at the time few tools for it existed.  So one of our engineers, Judy Ward, lead the effort to make the C++ front end be extremely useful and offered extremely good errors and warnings (she also had worked on the C FE before that).

When people complained about the compiler before no so “noisy” my response was “Listen to Judy’s advise.  She’s seeing something you are not and she knows more about C and C++ that all of the rest of us.”

We discovered a curious thing.  The ISVs reported way fewer bugs after the Alpha port because Judy’s messages forced them to clean up long standing issues that were silently causing problem on other systems.    I’ve always said Alpha C and C++ compilers was the greatest gift to the Sparc ISVs there was.

Like you to this day, except for possibly Gimple’s Flexilint product, the old DEC compilers are still the best tools I have ever used to clean up code.

I’ve reminded and thanked Judy for this many times when I seen her.  That was a labor of love by some folks that really cared to make a great product as useful as it could be.

Clem

[TUHS] Why did PDPs become so popular?

[Steve Simon]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 2343 bytes --]

The Plan9 c Alpha compiler also uses 64bit pointers and 32bit ints. For several
years Bell labs kept the port alive, checking builds on real Alpha hardware long
after it was no-longer competitive on the basis that “It keeps us honest”.

-Steve

PS:  Gimple’s Llint is a truly wonderful tool, it has saved me from myself many times.

> On 31 Dec 2017, at 12:56, Clement T. Cole <clemc at ccc.com> wrote:
> 
> 
> 
>> On Dec 31, 2017, at 12:20 AM, Rudi Blom <rudi.j.blom at gmail.com> wrote:
>> 
>> .With the
>> Compaq C compiler and HP-UX ANSI C I mostly get pages of warning and a
>> few errors. By the time I 'corrected' what I think is relevant some
>> nasty coredumps tend to disappear :-)
> 
> I had to chuckle when we read these two lines.   As Paul I’m sure also remembers and mentioned about the 32/64 bit issues, when we released Alpha there we very few to zero tools available to help find errors in ISV or customer created C code that was caused by assumptions of size.   As you point out with the new ‘Gem’ compilers a great deal of work was spent by Paul and his brothers and sisters in the compiler group putting in just those messages.  For C++ it was worse than C because the language was so new at the time few tools for it existed.  So one of our engineers, Judy Ward, lead the effort to make the C++ front end be extremely useful and offered extremely good errors and warnings (she also had worked on the C FE before that).
> 
> When people complained about the compiler before no so “noisy” my response was “Listen to Judy’s advise.  She’s seeing something you are not and she knows more about C and C++ that all of the rest of us.”
> 
> We discovered a curious thing.  The ISVs reported way fewer bugs after the Alpha port because Judy’s messages forced them to clean up long standing issues that were silently causing problem on other systems.    I’ve always said Alpha C and C++ compilers was the greatest gift to the Sparc ISVs there was.
> 
> Like you to this day, except for possibly Gimple’s Flexilint product, the old DEC compilers are still the best tools I have ever used to clean up code.
> 
> I’ve reminded and thanked Judy for this many times when I seen her.  That was a labor of love by some folks that really cared to make a great product as useful as it could be.
> 
> Clem

[TUHS] Why did PDPs become so popular?

[Larry McVoy]

On Fri, Dec 29, 2017 at 04:04:01AM -0700, Kevin Bowling wrote:
> Alpha generally maintained integer/ALU and clockspeed leadership for
> most of the '90s
> http://www.cs.columbia.edu/~sedwards/classes/2012/3827-spring/advanced-arch-2011.pdf

Wow, that first graph is the most misleading graph on CPU performance
I've ever seen.  Ever.

So from 1993 to 2000 the only CPUs released were Alphas?

That era was when I was busy measuring performance across cpus and
operating systems and I don't ever remember any processor being a
factor of 2 better than its peers.  And maybe I missed it, I only 
owned a couple of alpha systems, but I never saw an Alpha that was
a game changer.  Alpha was cool but it was too little, too late to
save DEC.

In that time period, even more so now, you had to be 2x better to get
a customer to switch to your platform.

	2x cheaper
	2x faster
	2x more reliable

Do one of those and people would consider switching platforms.  Less than
that was really tough and it was always, so far as I remember, less than
that.  SMP might be an exception but we went through that whole learning
process of "well, we advertised symmetric but when we said that what we
really meant was you should lock your processes down to a processor
because caches turn out to matter".  So in theory, N processors were N
times faster than 1 but in practice not so much.

I was very involved in performance work and cpu architecture and I'd love
to be able to claim that we had a 2x faster CPU than someone else but we
didn't, not at Sun and not at SGI.

It sort of make sense that there weren't huge gaps, everyone was more or
less using the same sized transistors, the same dram, the same caches.
There were variations, Intel had/has the biggest and most advanced
foundries but IBM would push the state of the art, etc.  But I don't
remember anyone ever coming out with a chip that was 2x faster.  I
suspect you can find one where chip A is introduced at the end of chip
B's lifespan and A == 2*B but wait a few month's and B gets replaced 
and A == .9*C.

Can anyone point to a 2x faster than it's current peers chip introduction?
Am I just not remembering one or is that not a thing?

--lm

[TUHS] Why did PDPs become so popular?

[Kevin Bowling]

I trust your judgement and experience WRT the Alpha.

If you're looking for massive performance deltas, what about ECL
designs like the IBM 3090 and Cray designs in the late '80s/ early
'90s?  I believe those were not a multiple but a magnitude faster than
contemporaries.

Regards,

On Fri, Dec 29, 2017 at 9:38 AM, Larry McVoy <lm at mcvoy.com> wrote:
> On Fri, Dec 29, 2017 at 04:04:01AM -0700, Kevin Bowling wrote:
>> Alpha generally maintained integer/ALU and clockspeed leadership for
>> most of the '90s
>> http://www.cs.columbia.edu/~sedwards/classes/2012/3827-spring/advanced-arch-2011.pdf
>
> Wow, that first graph is the most misleading graph on CPU performance
> I've ever seen.  Ever.
>
> So from 1993 to 2000 the only CPUs released were Alphas?
>
> That era was when I was busy measuring performance across cpus and
> operating systems and I don't ever remember any processor being a
> factor of 2 better than its peers.  And maybe I missed it, I only
> owned a couple of alpha systems, but I never saw an Alpha that was
> a game changer.  Alpha was cool but it was too little, too late to
> save DEC.
>
> In that time period, even more so now, you had to be 2x better to get
> a customer to switch to your platform.
>
>         2x cheaper
>         2x faster
>         2x more reliable
>
> Do one of those and people would consider switching platforms.  Less than
> that was really tough and it was always, so far as I remember, less than
> that.  SMP might be an exception but we went through that whole learning
> process of "well, we advertised symmetric but when we said that what we
> really meant was you should lock your processes down to a processor
> because caches turn out to matter".  So in theory, N processors were N
> times faster than 1 but in practice not so much.
>
> I was very involved in performance work and cpu architecture and I'd love
> to be able to claim that we had a 2x faster CPU than someone else but we
> didn't, not at Sun and not at SGI.
>
> It sort of make sense that there weren't huge gaps, everyone was more or
> less using the same sized transistors, the same dram, the same caches.
> There were variations, Intel had/has the biggest and most advanced
> foundries but IBM would push the state of the art, etc.  But I don't
> remember anyone ever coming out with a chip that was 2x faster.  I
> suspect you can find one where chip A is introduced at the end of chip
> B's lifespan and A == 2*B but wait a few month's and B gets replaced
> and A == .9*C.
>
> Can anyone point to a 2x faster than it's current peers chip introduction?
> Am I just not remembering one or is that not a thing?
>
> --lm

[TUHS] Why did PDPs become so popular?

[Larry McVoy]

On Fri, Dec 29, 2017 at 04:54:25PM -0700, Kevin Bowling wrote:
> I trust your judgement and experience WRT the Alpha.
> 
> If you're looking for massive performance deltas, what about ECL
> designs like the IBM 3090 and Cray designs in the late '80s/ early
> '90s?  I believe those were not a multiple but a magnitude faster than
> contemporaries.

For vector operations, yes.  For stuff that you and I care about,
running the OS, serving up data, not so much.

As I recall, the supercomputers were pretty crappy on anything that
wasn't a vector operation.  I helped port Unix to a CDC spinoff, the
ETA-10, and it was faster to cross compile stuff on a Sun 3/280 than
compile it natively.

I haven't run on either the 3090 or the Crays but I've got friends who
did (some of whom still work at Cray) and when I was crowing about what
I could do a Sun nobody told me that it was faster on a cray.

If you were doing scalar floating point, especially at the larger
precisions, yeah, the super computers were better.  If you were doing
that sort of thing as a vector, so a vector of 128 bit floats, yeah,
I could imagine that could be a lot faster than a Sun.  

SGI did a tick/tock where it was floating point focus, then integer focus.
It's possible that one of their floating point designs kept pace with the
super computers, I know that they went to the super computing conference
each year (I did the power wall over NFS at one).  But I don't know much
about floating point, never use it in my code :)

--lm

[TUHS] Why did PDPs become so popular?

[Lawrence Stewart]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 2274 bytes --]

I'll chime in just to say that designing with ECL was one hell of a lot of fun compared to TTL.

The first Alpha chip (EV3) had pad drivers that could be configured for TTL levels or for ECL levels.  In fact, a good chunk of the ISSCC paper is about the pad driver.

I was part of the team that built the first Alpha machine, the Alpha Demonstration Unit, see 
ftp://ftp.linux-mips.org/pub/linux/mips/people/macro/DEC/DTJ/DTJ803/DTJ803PF.PDF <ftp://ftp.linux-mips.org/pub/linux/mips/people/macro/DEC/DTJ/DTJ803/DTJ803PF.PDF>

For a limited number of machines, with power no object we were able to make an unabashed ECL design using the ECL 100K logic family, the ECLinPS family (300 ps gate delays) and some custom Gigabit Logic Gallium Arsenide parts for the memory board address line drivers.

We got power supply cables from a local valley welding shop and had them cut to length.  The shop owner wanted to know “what kind of a welder needs 18” cables?”  The issue was the 400 Amps of -4.5 v.   Each jelly bean chip was between 1/2 and 1 watt IIRC.

The beauty of ECL is that it is perfectly happy to drive 50 ohm transmission lines, with shunt termination.  This gives you incident wave switching and really beautiful signal integrity.  I think if Cray had tried to build the Cray 1 with anything other than ECL it just would never have worked reliably, especially with such long wires needed.

Essentially, ECL let you build big machines with the same reliability that could only be achieved with small machines using TTL.  Great stuff if you can afford the power consumption.

In the same way that it is worthwhile to own a sports car at least once in your life, it was a joy to build an ECL design.

-Larry


> On 2017, Dec 29, at 6:54 PM, Kevin Bowling <kevin.bowling at kev009.com> wrote:
> 
> I trust your judgement and experience WRT the Alpha.
> 
> If you're looking for massive performance deltas, what about ECL
> designs like the IBM 3090 and Cray designs in the late '80s/ early
> '90s?  I believe those were not a multiple but a magnitude faster than
> contemporaries.
> 
> Regards,

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171229/e508a1e8/attachment.html>

[TUHS] Why did PDPs become so popular?

[Kevin Bowling]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 3253 bytes --]

That is awesome, thanks for the story and link.  Enlightening to read
about how the coherence protocol was developed in software.  How was
the ISA, and I assume even implementation detail, kept equal or close
enough to the eventual microprocessor parts?  Does the "Privileged
Architecture Library" mean it was effectively microcoded?  What kind
of software structure was used to provide the I/O channel on the
DECStations, for instance did it map the other TURBOChannel devices
into the demo's address space so it ran the stock device drivers, or
was the I/O server software intermediating a mailbox for doing SCSI,
Ethernet etc with a different device model?

Reminds me of a book I really liked "The Supermen: The Story of
Seymour Cray and the Technical Wizards Behind the Supercomputer",
especially Seymour Cray's willingness to throw out convention and
redefine the game.  Corollary to Larry's point about CPU designers
losing by only competing against their own last design.. you can
either make new markets or lead in the ongoing one, not a lot of air
outside that.

Regards,

On Fri, Dec 29, 2017 at 5:54 PM, Lawrence Stewart <stewart at serissa.com> wrote:
> I'll chime in just to say that designing with ECL was one hell of a lot of
> fun compared to TTL.
>
> The first Alpha chip (EV3) had pad drivers that could be configured for TTL
> levels or for ECL levels.  In fact, a good chunk of the ISSCC paper is about
> the pad driver.
>
> I was part of the team that built the first Alpha machine, the Alpha
> Demonstration Unit, see
> ftp://ftp.linux-mips.org/pub/linux/mips/people/macro/DEC/DTJ/DTJ803/DTJ803PF.PDF
>
> For a limited number of machines, with power no object we were able to make
> an unabashed ECL design using the ECL 100K logic family, the ECLinPS family
> (300 ps gate delays) and some custom Gigabit Logic Gallium Arsenide parts
> for the memory board address line drivers.
>
> We got power supply cables from a local valley welding shop and had them cut
> to length.  The shop owner wanted to know “what kind of a welder needs 18”
> cables?”  The issue was the 400 Amps of -4.5 v.   Each jelly bean chip was
> between 1/2 and 1 watt IIRC.
>
> The beauty of ECL is that it is perfectly happy to drive 50 ohm transmission
> lines, with shunt termination.  This gives you incident wave switching and
> really beautiful signal integrity.  I think if Cray had tried to build the
> Cray 1 with anything other than ECL it just would never have worked
> reliably, especially with such long wires needed.
>
> Essentially, ECL let you build big machines with the same reliability that
> could only be achieved with small machines using TTL.  Great stuff if you
> can afford the power consumption.
>
> In the same way that it is worthwhile to own a sports car at least once in
> your life, it was a joy to build an ECL design.
>
> -Larry
>
>
> On 2017, Dec 29, at 6:54 PM, Kevin Bowling <kevin.bowling at kev009.com> wrote:
>
> I trust your judgement and experience WRT the Alpha.
>
> If you're looking for massive performance deltas, what about ECL
> designs like the IBM 3090 and Cray designs in the late '80s/ early
> '90s?  I believe those were not a multiple but a magnitude faster than
> contemporaries.
>
> Regards,
>
>

[TUHS] Why did PDPs become so popular?

[Lawrence Stewart]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 5131 bytes --]

(Both the ADU and the DECstation front end ran OSF-1 or Ultrix, which was unix-y, although the ADU itself did run VMS as a second OS :) )

If I remember correctly, the OS running on the ADU itself had what we would now call paravirtualized drivers - they just handed off packets or disk block I/Os to the I/O service program running on the DECStation.  The ADU device drivers just managed ring buffers of requests, rather than raw SCSI commands destined for the real I/O devices.

PALcode is an Alpha thing, so that code running in PAL mode was responsible for things like TLB loads that might be different from model to model.  Anything that was too expensive to implement in hardware or too infrequent to bother with got punted to PAL.  PALcode was just ordinary Alpha assembler code, sometimes written in C I imagine, but it had to be very careful not to cause any faults or traps that required PALcode to implement.

The EV3 was an early Alpha chip, in, I think, .9 micron CMOS, that did not have an FPU, so the floating point was emulated.  The first products were 200 MHz EV4 machines that were in .75 micron CMOS.

The 3 and 4 refer to Digital code names for CMOS processes.  The EV stands for “Electric Vlasic” because the chip design team was fond of sticking nails into dill pickles and plugging them into the wall.  The pickles could be seen to glow in a dark room before starting to smoke.

Ken Olsen came to visit the lab and wanted to know why we had christmas tree lights decorating the ADU chassis.  We explained it was a safety feature, to remind people the power was on.  400 amps was nothing to fool around with.  No wedding rings allowed in the lab.

-Larry


> On 2017, Dec 29, at 8:47 PM, Kevin Bowling <kevin.bowling at kev009.com> wrote:
> 
> That is awesome, thanks for the story and link.  Enlightening to read
> about how the coherence protocol was developed in software.  How was
> the ISA, and I assume even implementation detail, kept equal or close
> enough to the eventual microprocessor parts?  Does the "Privileged
> Architecture Library" mean it was effectively microcoded?  What kind
> of software structure was used to provide the I/O channel on the
> DECStations, for instance did it map the other TURBOChannel devices
> into the demo's address space so it ran the stock device drivers, or
> was the I/O server software intermediating a mailbox for doing SCSI,
> Ethernet etc with a different device model?
> 
> Reminds me of a book I really liked "The Supermen: The Story of
> Seymour Cray and the Technical Wizards Behind the Supercomputer",
> especially Seymour Cray's willingness to throw out convention and
> redefine the game.  Corollary to Larry's point about CPU designers
> losing by only competing against their own last design.. you can
> either make new markets or lead in the ongoing one, not a lot of air
> outside that.
> 
> Regards,
> 
> On Fri, Dec 29, 2017 at 5:54 PM, Lawrence Stewart <stewart at serissa.com> wrote:
>> I'll chime in just to say that designing with ECL was one hell of a lot of
>> fun compared to TTL.
>> 
>> The first Alpha chip (EV3) had pad drivers that could be configured for TTL
>> levels or for ECL levels.  In fact, a good chunk of the ISSCC paper is about
>> the pad driver.
>> 
>> I was part of the team that built the first Alpha machine, the Alpha
>> Demonstration Unit, see
>> ftp://ftp.linux-mips.org/pub/linux/mips/people/macro/DEC/DTJ/DTJ803/DTJ803PF.PDF
>> 
>> For a limited number of machines, with power no object we were able to make
>> an unabashed ECL design using the ECL 100K logic family, the ECLinPS family
>> (300 ps gate delays) and some custom Gigabit Logic Gallium Arsenide parts
>> for the memory board address line drivers.
>> 
>> We got power supply cables from a local valley welding shop and had them cut
>> to length.  The shop owner wanted to know “what kind of a welder needs 18”
>> cables?”  The issue was the 400 Amps of -4.5 v.   Each jelly bean chip was
>> between 1/2 and 1 watt IIRC.
>> 
>> The beauty of ECL is that it is perfectly happy to drive 50 ohm transmission
>> lines, with shunt termination.  This gives you incident wave switching and
>> really beautiful signal integrity.  I think if Cray had tried to build the
>> Cray 1 with anything other than ECL it just would never have worked
>> reliably, especially with such long wires needed.
>> 
>> Essentially, ECL let you build big machines with the same reliability that
>> could only be achieved with small machines using TTL.  Great stuff if you
>> can afford the power consumption.
>> 
>> In the same way that it is worthwhile to own a sports car at least once in
>> your life, it was a joy to build an ECL design.
>> 
>> -Larry
>> 
>> 
>> On 2017, Dec 29, at 6:54 PM, Kevin Bowling <kevin.bowling at kev009.com> wrote:
>> 
>> I trust your judgement and experience WRT the Alpha.
>> 
>> If you're looking for massive performance deltas, what about ECL
>> designs like the IBM 3090 and Cray designs in the late '80s/ early
>> '90s?  I believe those were not a multiple but a magnitude faster than
>> contemporaries.
>> 
>> Regards,
>> 
>> 

[TUHS] Why did PDPs become so popular?

[Paul Winalski]

On 12/29/17, Lawrence Stewart <stewart at serissa.com> wrote:
>
> The EV3 was an early Alpha chip, in, I think, .9 micron CMOS, that did not
> have an FPU, so the floating point was emulated.  The first products were
> 200 MHz EV4 machines that were in .75 micron CMOS.

Yes.  EV3 was a prototype, really, released as a development
breadboard platform for early adopters and ISVs.  EV4 was the first
production Alpha.

-Paul W.

[TUHS] Why did PDPs become so popular?

[Paul Winalski]

On 12/29/17, Kevin Bowling <kevin.bowling at kev009.com> wrote:
> Enlightening to read
> about how the coherence protocol was developed in software.  How was
> the ISA, and I assume even implementation detail, kept equal or close
> enough to the eventual microprocessor parts?  Does the "Privileged
> Architecture Library" mean it was effectively microcoded?

Yes, IMO the Alpha PALcode was a form of microcode.  DEC designed the
Alpha ISA with the hardware folks working closely with the VMS and DEC
UNIX (soon to become Tru64 UNIX) OS groups to insure that the correct
balance of PALcode vs. implemented-in-hardware was struck.

-Paul W.

[TUHS] Why did PDPs become so popular?

[Henry Bent]

On 29 December 2017 at 19:54, Lawrence Stewart <stewart at serissa.com> wrote:

>
> I was part of the team that built the first Alpha machine, the Alpha
> Demonstration Unit, see
> ftp://ftp.linux-mips.org/pub/linux/mips/people/macro/DEC/
> DTJ/DTJ803/DTJ803PF.PDF
>

I couldn't access this on my phone - no FTP client - so I blindly assumed
that it was DEC Technical Journal Vol. 8 no. 3.  That turned out to be
completely untrue, but in a perhaps amusing way - one of the articles was
Bob Supnik discussing the reasoning behind the original development of
SIM(H), intended to preserve computing history.

As far as the article you posted - from Vol. 4 no. 3 - the idea that 35
prototypes were created in ECL and running as a multiprocessor system,
taking over 4kW not including the front end, is absolutely remarkable to
me.  Does any of that original code for the front end still exist?

-Henry
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171230/7163e763/attachment.html>

[TUHS] Why did PDPs become so popular?

[Ron Natalie]

In my second career after UNIX, I spent a lot of time writing high performance image processing software that ran on just about every platform out there:   Sun3 , Spark, the DEC SPIM, ALPHA, the iTanium (or as we called it the iTanic), HP PA/RISC, Apollo DN10000, SGI from the O2 and the Indy all the way up to the reality engines, Stellar, Ardent, IBM RS6000,  Masspar,  weird IBM things like the W4 card in the PS/2, i860 OKI workstatiosn, Intergraph Clippers, and probably more I'm forgetting.    The Alpha was hot stuff for about nine months.   Ran OSF/1 formerly DigitalUnix formerly OSF/1.

I remember one day Stardant called and said they needed the G1000 they loaned us right back.   I boxed it up (it was a tradeshow machine and came in a road case).   I set it on the loading dock.   The next day Stardent announced they were going out of business.    A year later I was out on the loading dock and "hey, is this stupid thing still here."   A few minutes later I get a call from our sales guy.   He's got a call from a guy looking for a copy of Motif for the Stellar G1000.   I laugh.   He says "I know, they're out of business."   I said, "Yes, but today's your lucky day.   I still have one."   I powed it up, pulled off the Motif to send the guy and then trashed the machine.   One of my  coowrkers "decapitated" the WysePC the thing had on top of it as a control/bootup processor.    We had one of the CPU cards on the wall as a "art" for a while.

[TUHS] Why did PDPs become so popular?

[Paul Winalski]

On 12/29/17, Ron Natalie <ron at ronnatalie.com> wrote:
> The Alpha was hot
> stuff for about nine months.   Ran OSF/1 formerly DigitalUnix formerly
> OSF/1.

Digital UNIX for the VAX was indeed derived from OSF/1.  The port to
Alpha was called Tru64 UNIX.

Tru64 UNIX was initially a pure 64-bit system, with no provision for
building or running 32-bit program images.  This turned out to be a
mistake .  DEC found out that a lot of ISVs had code that implicitly
"knew" that sizeof() a pointer was the same as sizeof(int) was the
same as 4 bytes.  Tru64 was forced to implement a 32-bit compatibility
mode.

There was also a problem with the C compiler initially developed at
DECwest in Seattle.  It supported ONLY ANSI standard C and issued
fatal errors for violations/extensions of the standard.  We (DEC
mainstream compiler group) called it the Rush Limbaugh
compiler--extremely conservative, and you can't argue with it.

-Paul W.

[TUHS] Why did PDPs become so popular?

[Henry Bent]

On 29 December 2017 at 21:30, Paul Winalski <paul.winalski at gmail.com> wrote:

> On 12/29/17, Ron Natalie <ron at ronnatalie.com> wrote:
> > The Alpha was hot
> > stuff for about nine months.   Ran OSF/1 formerly DigitalUnix formerly
> > OSF/1.
>
> Digital UNIX for the VAX was indeed derived from OSF/1.  The port to
> Alpha was called Tru64 UNIX.
>
> Tru64 UNIX was initially a pure 64-bit system, with no provision for
> building or running 32-bit program images.  This turned out to be a
> mistake .  DEC found out that a lot of ISVs had code that implicitly
> "knew" that sizeof() a pointer was the same as sizeof(int) was the
> same as 4 bytes.  Tru64 was forced to implement a 32-bit compatibility
> mode.
>
> There was also a problem with the C compiler initially developed at
> DECwest in Seattle.  It supported ONLY ANSI standard C and issued
> fatal errors for violations/extensions of the standard.  We (DEC
> mainstream compiler group) called it the Rush Limbaugh
> compiler--extremely conservative, and you can't argue with it.
>

I'm curious about this.  As far as I know the development of the released
OS for the Alpha went this way:
(OSF/1 reference) -> (OSF/1 for MIPS) -> OSF/1 V[1.2, 2, 3.0] -> Digital
UNIX [3.2, 4] -> Tru64[5].  Was there ever a branch of this for the VAX?

And was the frontend for the compiler for the Alpha not the same as for the
DECstations?  That had the -std options to switch between K&R,
"compatibility," and pure ANSI.  My DECstation isn't up right now but I
believe its compiler under OSF/1 could even take the Sun compiler options,
-Xc, -Xa, etc.

-Henry
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171230/d750faee/attachment.html>

[TUHS] Why did PDPs become so popular?

[Arrigo Triulzi]

On 31 Dec 2017, at 04:00, Henry Bent <henry.r.bent at gmail.com> wrote:
> I'm curious about this.  As far as I know the development of the released OS for the Alpha went this way:
> (OSF/1 reference) -> (OSF/1 for MIPS) -> OSF/1 V[1.2, 2, 3.0] -> Digital UNIX [3.2, 4] -> Tru64[5].  Was there ever a branch of this for the VAX?

Actually OSF/1 T1.0 was shipped to customers. I know because it was on the three Alphas we received at Imperial College in the UK. It also came with an early version of MX, the 32-bit MIPS to 64-bit Alpha translator which we used to get Ghostscript working (essential for our Mathematicians, after getting TeX to compile).

We tried to get Ghostscript ported as soon as the machines were up but failed miserably and were (still am, actually) grateful for MX saving the day.

Arrigo 

[TUHS] Why did PDPs become so popular?

[Paul Winalski]

On 12/30/17, Henry Bent <henry.r.bent at gmail.com> wrote:
> On 29 December 2017 at 21:30, Paul Winalski <paul.winalski at gmail.com>
> wrote:
>
> I'm curious about this.  As far as I know the development of the released
> OS for the Alpha went this way:
> (OSF/1 reference) -> (OSF/1 for MIPS) -> OSF/1 V[1.2, 2, 3.0] -> Digital
> UNIX [3.2, 4] -> Tru64[5].  Was there ever a branch of this for the VAX?

No, you are correct; I was misremembering.  I wasn't paying much
attention to UNIX at the time.

-Paul W.

[TUHS] Why did PDPs become so popular?

[Noel Chiappa]

    > From: Paul Winalski

    > Lack of marketing skill eventually caught up to DEC by the late 1980s
    > and was a principal reason for its downfall.

I got the impression that fundamentally, DEC's engineering 'corporate culture'
was the biggest problem; it wasn't suited to the commodity world of computing,
and it couldn't change fast enough. (DEC had always provided very well built
gear, lots of engineering documentation, etc, etc.)

I dunno, maybe my perception is wrong? There's a book about DEC's failure:

  Edgar H. Schein, "DEC is Dead, Long Live DEC", Berett-Koehler, San
	  Francisco, 2003

which probably has some good thoughts. Also:

  Clayton M. Christensen, "The Innovator's Dilemma: When New Technologies
	  Cause Great Firms to Fail", Harvard Business School, Boston, 1997

briefly mentions DEC.

	Noel

[TUHS] Why did PDPs become so popular?

[Paul Winalski]

On 12/28/17, Noel Chiappa <jnc at mercury.lcs.mit.edu> wrote:
>     > From: Paul Winalski
>
>     > Lack of marketing skill eventually caught up to DEC by the late 1980s
>     > and was a principal reason for its downfall.
>
> I got the impression that fundamentally, DEC's engineering 'corporate culture'
> was the biggest problem; it wasn't suited to the commodity world of computing,
> and it couldn't change fast enough. (DEC had always provided very well built
> gear, lots of engineering documentation, etc, etc.)
>
> I dunno, maybe my perception is wrong?

I think you're right.  The disinterest in marketing and advertising
(Ken Olsen, and therefore DEC, had a "build it and they will come"
mentality) was one aspect of the corporate culture.  An example of its
negative impact:  When the Alpha EV5 came out, it was several times
faster than anything else around.  At the same time, Intel and AMD
were involved in the clock rate race.  Every time Intel leapfrogged
AMD, they trumpeted in the media (both trade and public) that they'd
produced the fastest microprocessor in the world.  DEC did nothing to
counter this false impression.

DEC's corporate culture also led to slow decision making.  DEC
believed in consensus building--everyone had to buy into a decision
before it was final.  We low-level DEC engineers used to joke that any
decision worth making was worth making ten times.  Consensus building
is great if you can reach a consensus, but terrible when you can't.
What was needed was something more like Sun's "lead, follow, or get
out of the way", or Intel's "disagree and commit".

DEC was also prone to over-engineering its products.  This slowed down
time to market and also increased production costs.  It's true that,
particularly in software, spending extra time in design up front pays
back in reduced maintenance costs down the road, but if you can't get
V1.0 out the door within its market time frame, there will never be a
V2.0.

-Paul W.

[TUHS] Why did PDPs become so popular?

[Larry McVoy]

On Thu, Dec 28, 2017 at 10:59:29AM -0500, Paul Winalski wrote:
> On 12/28/17, Noel Chiappa <jnc at mercury.lcs.mit.edu> wrote:
> >     > From: Paul Winalski
> >
> >     > Lack of marketing skill eventually caught up to DEC by the late 1980s
> >     > and was a principal reason for its downfall.
> >
> > I got the impression that fundamentally, DEC's engineering 'corporate culture'
> > was the biggest problem; it wasn't suited to the commodity world of computing,
> > and it couldn't change fast enough. (DEC had always provided very well built
> > gear, lots of engineering documentation, etc, etc.)
> >
> > I dunno, maybe my perception is wrong?
> 
> I think you're right.  The disinterest in marketing and advertising
> (Ken Olsen, and therefore DEC, had a "build it and they will come"
> mentality) was one aspect of the corporate culture.  An example of its
> negative impact:  When the Alpha EV5 came out, it was several times
> faster than anything else around.  

Got a reference for that performance claim?  Wasn't that mid 1990's?
If so, I was heavily into benchmarking and performance work during
that period.  If there was a processor that was 2x faster, let alone
several times faster, I would have noticed.

http://www.bitmover.com/lmbench/lmbench-usenix.pdf

-- 
---
Larry McVoy            	     lm at mcvoy.com             http://www.mcvoy.com/lm 

[TUHS] Why did PDPs become so popular?

[Theodore Ts'o]

On Thu, Dec 28, 2017 at 08:08:11AM -0800, Larry McVoy wrote:
> > I think you're right.  The disinterest in marketing and advertising
> > (Ken Olsen, and therefore DEC, had a "build it and they will come"
> > mentality) was one aspect of the corporate culture.  An example of its
> > negative impact:  When the Alpha EV5 came out, it was several times
> > faster than anything else around.  
> 
> Got a reference for that performance claim?  Wasn't that mid 1990's?
> If so, I was heavily into benchmarking and performance work during
> that period.  If there was a processor that was 2x faster, let alone
> several times faster, I would have noticed.
> 
> http://www.bitmover.com/lmbench/lmbench-usenix.pdf

"Digital's 21164 Reaches 500 MHz: Alpha Regains Performance Lead,
Leaves Pentium Pro in Dust" -- Microprocessor Report July 8, 1996.

http://noel.feld.cvut.cz/vyu/scs/alpha/164_500.pdf

Looks to me from the article that Alpha was certain participating in
the clock speed wars, though.

					- Ted

[TUHS] Why did PDPs become so popular?

[Kevin Bowling]

I can mostly only comment from my readings, but this is IMHO a
non-trivial question even in retrospect because it depends on what you
or your workload valued.  I do like how lmbench categorizes across
multiple "interesting" vectors, showing some of the design tradeoffs
of CPU architecture and then how the OS plays a role in real world
applications.

Alpha generally maintained integer/ALU and clockspeed leadership for
most of the '90s
http://www.cs.columbia.edu/~sedwards/classes/2012/3827-spring/advanced-arch-2011.pdf

For intel the Pentium Pro was pivotal in being able to position vs the
contemporary RISC CPUs with multi-MB caches.  And federating cost
effective CPUs together with Laissez-faire mainboard/system
packaging/OSes turned out to be more important than pretty much
anything else.

I know that IBM Austin did some wizard of oz stuff in early POWER..
Bi-CMOS superscalar that put it 4-5 years ahead of most competing
microprocessor designs in floating point, though SGI and HP traded
respectable volleys.  But POWER also had fat memory bandwidth, they
tended to make well balanced braniacs that didn't blindly pursue the
clockspeed war (http://www.cs.virginia.edu/~mccalpin/papers/balance/).
They got into a weird spot in the second half of the 90s with an
out-dated bus, internal competition from PowerPC and RS64, but
returned to leadership with POWER4 and up to today. POWER's IO
leadership made it a good fit for many early internet routers in the
early '90s, NSFNET and others.  Interestingly modern POWER retains
that leadership on memory and I/O which can put it 2 to 4 years ahead
of everything else depending on what you value (Google seems to see
the light using it for gluing GPUs together..).  From IBM Rochester,
RS64 was kind of interesting in being the first use of SMT and having
incredibly low TDP which were both interesting clairvoyance into the
next decade.

In retrospect I don't think SPARC ever had a reasonable showing pound
for pound vs other microprocessors :)

Regards,

On Thu, Dec 28, 2017 at 4:28 PM, Theodore Ts'o <tytso at mit.edu> wrote:
> On Thu, Dec 28, 2017 at 08:08:11AM -0800, Larry McVoy wrote:
>> > I think you're right.  The disinterest in marketing and advertising
>> > (Ken Olsen, and therefore DEC, had a "build it and they will come"
>> > mentality) was one aspect of the corporate culture.  An example of its
>> > negative impact:  When the Alpha EV5 came out, it was several times
>> > faster than anything else around.
>>
>> Got a reference for that performance claim?  Wasn't that mid 1990's?
>> If so, I was heavily into benchmarking and performance work during
>> that period.  If there was a processor that was 2x faster, let alone
>> several times faster, I would have noticed.
>>
>> http://www.bitmover.com/lmbench/lmbench-usenix.pdf
>
> "Digital's 21164 Reaches 500 MHz: Alpha Regains Performance Lead,
> Leaves Pentium Pro in Dust" -- Microprocessor Report July 8, 1996.
>
> http://noel.feld.cvut.cz/vyu/scs/alpha/164_500.pdf
>
> Looks to me from the article that Alpha was certain participating in
> the clock speed wars, though.
>
>                                         - Ted

[TUHS] Why did PDPs become so popular?

[Jon Forrest]

On 12/29/2017 3:04 AM, Kevin Bowling wrote:

> Alpha generally maintained integer/ALU and clockspeed leadership for
> most of the '90s
> http://www.cs.columbia.edu/~sedwards/classes/2012/3827-spring/advanced-arch-2011.pdf

I worked in the Computer Science Dept. at UC Berkeley in the 1990s
when Richard Sites, the chief architect of the Alpha, gave a talk
describing the Alpha. I remember him saying that there was nothing
out there from any other vendor that would be able to compete with
the Alpha for the next 10 years (I'm pretty sure he said 10 years but
it might have been longer).

Because I was the system manager for the Sequoia 2000 project, DEC's big
external research project after Project Athena, I got the first Alpha
delivered to UC Berkeley. I remember it being quite fast, although I
don't recall any specific benchmarks. The OS (OSF/1) was fairly
primitive as first and didn't even support multiple processor systems.
We were able to port Postgres to it fairly quickly in spite of various
issues related to the 64-bit Alpha architecture. In fact, the Postgres
group was using Alpha desktops when SQL was added to Postgres.

As nice as the Alphas were, I don't recall any compelling reason we
would have used them if we had to pay for them. In fact, at the same
time Mike Stonebraker and I wrote a grant proposal to Sun to get a
couple of SparcStation 10s to use to port Postgres to Solaris. The
SparcStations were just as nice to use as the Alphas.

DEC's later demise was quite sad to me, since before joining UC Berkeley
I had been a VAX/VMS person. DEC did a great job supporting Project
Sequoia 2000, and they were very generous with both their hardware and
money. Judging from Sites' presentation, they thought they were going
to win.

Jon Forrest

[TUHS] Why did PDPs become so popular?

[Larry McVoy]

On Fri, Dec 29, 2017 at 03:35:27PM -0800, Jon Forrest wrote:
> >Alpha generally maintained integer/ALU and clockspeed leadership for
> >most of the '90s
> >http://www.cs.columbia.edu/~sedwards/classes/2012/3827-spring/advanced-arch-2011.pdf
> 
> As nice as the Alphas were, I don't recall any compelling reason we
> would have used them if we had to pay for them. In fact, at the same
> time Mike Stonebraker and I wrote a grant proposal to Sun to get a
> couple of SparcStation 10s to use to port Postgres to Solaris. The
> SparcStations were just as nice to use as the Alphas.

Yeah, that's my memory as well.  Alpha was fine but it wasn't the bat
it out of the park that DEC thought it would be.

I've worked at Sun and SGI and had some influence on some of their 
processor work (Andy B redesigned the memory interconnect on one of
the SparcStation SMP boxes because I showed him data that proved that
we were about to suck; got a processor at SGI cancelled because it 
was just beyond hopeless, it was a floating point machine called
Beast and it was being developed as the focus was shifting heavily
from floating point to integer.  The stupid thing had pins on all
6 sides - top, bottom, and the edges.  The socket, just the socket,
was predicted to cost SGI $1400/each at volume.  No CPU, just the
socket.  And it had miserable integer performance.  Bzzt.)

What I've seen over and over is teams compete against their previous
design rather than the competition.  Many, many times I've seen 
designers who had barely a passing knowledge of what the other guys
could do.  Blew my mind.  It was part of the reason I wrote LMbench,
at least that gives you an idea of what the other guys can do.

--lm

[TUHS] Why did PDPs become so popular?

[Alec Muffett]

I apologise if this is too far from the main topic, but I wanted to check
an urban legend.

There is a story - as I have heard it told - that PDPs established their
place (and popularity) in the marketplace by pointedly *not* advertising
themselves as "computers", but instead as "programmed data processors".

This was because - so the story goes - that everyone in corporations of the
time simply *knew* that "computers" came only from IBM, lived in big
datacentres, had million-dollar price-tags, and required extensive project
management to purchase; whereas nobody cared enough about a thing called a
"programmed data processor" to bother bikeshedding the
few-tens-or-hundreds-of-thousands-of-dollars purchase proposal to an
inevitable death. Thus, they flitted under the purchasing radar, and sold
like hotcakes.

I wonder: does this story have substance, please?

Aside from anything else: I draw parallels to the adoption of Linux by Wall
St, and the subsequent adoption of virtualisation / AWS by business - now
reflected in companies explaining to ISO27001 auditors that "well, we don't
actually possess any physical servers..."

    - alec

-- 
http://dropsafe.crypticide.com/aboutalecm
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171227/148f453a/attachment.html>

[TUHS] Why did PDPs become so popular?

[Grant Taylor]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 3938 bytes --]

On 12/27/2017 02:02 PM, Alec Muffett wrote:
> There is a story - as I have heard it told - that PDPs established their 
> place (and popularity) in the marketplace by pointedly *not* advertising 
> themselves as "computers", but instead as "programmed data processors".

That jives with what I understand as well.

> This was because - so the story goes - that everyone in corporations of 
> the time simply *knew* that "computers" came only from IBM, lived in big 
> datacentres, had million-dollar price-tags, and required extensive 
> project management to purchase; whereas nobody cared enough about a 
> thing called a "programmed data processor" to bother bikeshedding the 
> few-tens-or-hundreds-of-thousands-of-dollars purchase proposal to an 
> inevitable death. Thus, they flitted under the purchasing radar, and 
> sold like hotcakes.

I don't agree with "…only came from IBM…".  Please point your web 
browser to your preferred search engine and ask it for Snow White and 
the Seven Dwarfs as it relates to the computer industry.

It's my (mis?)understanding that PDPs had a significant advantage that 
they came in with a significantly lower price tag which allowed them to 
get through finance / bursar office with less scrutiny.

> I wonder: does this story have substance, please?

It mostly jive with what I've heard / read a number of places.  Further, 
I'm not aware of any stories countermanding it.

> Aside from anything else: I draw parallels to the adoption of Linux by 
> Wall St, and the subsequent adoption of virtualisation / AWS by business

I don't know that I agree with that assessment.  -  Though as sure as I 
say that, what I start typing sort of parallels it.

I think Linux broke into traditionally non-Unix shops as play things on 
old retired machines.  Then as time moved on and things evolved, Linux 
started doing more to carry less-critical production load.  More time 
passes with more evolution and Linux often picks up a non-trivial 
portion of the production work load from non-Linux systems.

The other similar thing that I have seen, and think I will see more of, 
is that people play with Linux at home, learn some things, and realize 
that it can do things at work too.  In which case it will likely more 
overtly take on production loads more directly.

As for virtualization, I think that's evolution and people trying to 
avoid physical server sprawl.  I think AWS (et al) are simply additional 
forms of virtualization.

> now reflected in companies explaining to ISO27001 auditors that "well, 
> we don't actually possess any physical servers..."

Okay.  How does (the lack of) physical servers actually impact ISO 27001 
compliance?  -  From my read of the Wikipedia article I don't see how 
(the lack of) physical on premise servers changes anything.

I feel like ISO 27001 is more a business plan / policy / procedure type 
check than a technical to-do list.  As such, I feel like such plans / 
policies / procedures would still apply to the infrastructure that 
people are using, be it physical on prem or virtual in the cloud. 
Someone still owns the equipment and is responsible for it.  Further, 
businesses outsourcing to the cloud still have a responsibility to 
ensure that said infrastructure is secured / updated / managed to the 
same standards.

Granted, virtual ~> AWS does make it a LOT simpler for people to start 
projects and do things that may be against company policy.  But that's a 
matter of initial economics.  For the project to continue, it will need 
to fall back in line with stated policies, be it physical on prem or 
virtual in the cloud.



-- 
Grant. . . .
unix || die

-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 3982 bytes
Desc: S/MIME Cryptographic Signature
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171227/c78fbced/attachment.bin>

[TUHS] Why did PDPs become so popular?

[Alec Muffett]

If there's any followup then Grant and I can take it off-thread, but for
clarity:

On 27 December 2017 at 21:50, Grant Taylor via TUHS <tuhs at minnie.tuhs.org>
wrote:
>
> now reflected in companies explaining to ISO27001 auditors that "well, we
>> don't actually possess any physical servers..."
>>
>
> Okay.  How does (the lack of) physical servers actually impact ISO 27001
> compliance?  -  From my read of the Wikipedia article I don't see how (the
> lack of) physical on premise servers changes anything.
>

There is none; but the preconceptions which are exposed when <crusty old
auditor or consultant> meets his/her first <tiny agile startup suddenly
needing certification in order to meet $govt_sales_requirement> - are
hilarious to experience.

Q: "Where are the servers?"

A: "Well, that depends..."

...etc.

    -a

-- 
http://dropsafe.crypticide.com/aboutalecm
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171228/9bb6edf0/attachment.html>

[TUHS] Why did PDPs become so popular?

[Clem Cole]

You are mixing a couple of different stories I fear...

If you want the full story get a copy of:   Computer Engineering: A DEC
View of Hardware Systems Design
<https://www.amazon.com/Computer-Engineering-Hardware-Systems-Design/dp/1483207676>

But a snap shot for this mailing list is this ...  The PDP term was used by
KO when he was funding Digital because the VC's the 60s did not believe
that a computer company would succeed.   But making things for the
instrumentation market (Lincoln Labs, Livermore, *etc*.).   This is how
PDP-1 came to be.  The PDP term was keep for the first 25 years (until the
Vax and renaming of the PDP-10/PDP-20 to DECSystem 10/20). [The 1 begat the
6, 9, 15 an 10 families].

The concept of purchasing smaller system, was indeed true.   This was the
idea behind the >>mini-computer<< or *minimal computer* that Gordon Bell
who lad left DEC temporarily to be a CMU Prof for a time began to explore.
 He took the idea and commercialized and the PDP-8 line was the first in
that line.  The 11 & 15 were full computer systems.  DEC also made
something called the PDP-16 'Register Transfer Modules' (RTMs) which was an
attempt to make the small controller idea even more accessible, but the
Intel microprocessor would eclipse them (I think I was the last group at
CMU was talk a course using them.   Another factoid, the predecessor to
VHDL/Verilog and the like, ISPL and ISPS actually spit out 'code' for DEC
RTM modules instead of gates).

But the key point is that in 1975 dollars, a PDP-11/40 system that was good
enough to run something like Sixth Edition of UNIX cost somewhere between
$50k-$150k.   This would have been much, much cheaper than say a PDP-10, or
a equivilent IBM 'mainframe' size system which would have started above $1M.

Clem

On Wed, Dec 27, 2017 at 4:02 PM, Alec Muffett <alec.muffett at gmail.com>
wrote:

> I apologise if this is too far from the main topic, but I wanted to check
> an urban legend.
>
> There is a story - as I have heard it told - that PDPs established their
> place (and popularity) in the marketplace by pointedly *not* advertising
> themselves as "computers", but instead as "programmed data processors".
>
> This was because - so the story goes - that everyone in corporations of
> the time simply *knew* that "computers" came only from IBM, lived in big
> datacentres, had million-dollar price-tags, and required extensive project
> management to purchase; whereas nobody cared enough about a thing called a
> "programmed data processor" to bother bikeshedding the
> few-tens-or-hundreds-of-thousands-of-dollars purchase proposal to an
> inevitable death. Thus, they flitted under the purchasing radar, and sold
> like hotcakes.
>
> I wonder: does this story have substance, please?
>
> Aside from anything else: I draw parallels to the adoption of Linux by
> Wall St, and the subsequent adoption of virtualisation / AWS by business -
> now reflected in companies explaining to ISO27001 auditors that "well, we
> don't actually possess any physical servers..."
>
>     - alec
>
> --
> http://dropsafe.crypticide.com/aboutalecm
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171227/bf04c042/attachment-0001.html>

[TUHS] Why did PDPs become so popular?

[Clem Cole]

Typo -- funding in the 50s -- sorry...

On Wed, Dec 27, 2017 at 4:51 PM, Clem Cole <clemc at ccc.com> wrote:

> You are mixing a couple of different stories I fear...
>
> If you want the full story get a copy of:   Computer Engineering: A DEC
> View of Hardware Systems Design
> <https://www.amazon.com/Computer-Engineering-Hardware-Systems-Design/dp/1483207676>
>
> But a snap shot for this mailing list is this ...  The PDP term was used
> by KO when he was funding Digital because the VC's the 60s did not believe
> that a computer company would succeed.   But making things for the
> instrumentation market (Lincoln Labs, Livermore, *etc*.).   This is how
> PDP-1 came to be.  The PDP term was keep for the first 25 years (until the
> Vax and renaming of the PDP-10/PDP-20 to DECSystem 10/20). [The 1 begat the
> 6, 9, 15 an 10 families].
>
> The concept of purchasing smaller system, was indeed true.   This was the
> idea behind the >>mini-computer<< or *minimal computer* that Gordon Bell
> who lad left DEC temporarily to be a CMU Prof for a time began to explore.
>  He took the idea and commercialized and the PDP-8 line was the first in
> that line.  The 11 & 15 were full computer systems.  DEC also made
> something called the PDP-16 'Register Transfer Modules' (RTMs) which was an
> attempt to make the small controller idea even more accessible, but the
> Intel microprocessor would eclipse them (I think I was the last group at
> CMU was talk a course using them.   Another factoid, the predecessor to
> VHDL/Verilog and the like, ISPL and ISPS actually spit out 'code' for DEC
> RTM modules instead of gates).
>
> But the key point is that in 1975 dollars, a PDP-11/40 system that was
> good enough to run something like Sixth Edition of UNIX cost somewhere
> between $50k-$150k.   This would have been much, much cheaper than say a
> PDP-10, or a equivilent IBM 'mainframe' size system which would have
> started above $1M.
>
> Clem
>
> On Wed, Dec 27, 2017 at 4:02 PM, Alec Muffett <alec.muffett at gmail.com>
> wrote:
>
>> I apologise if this is too far from the main topic, but I wanted to check
>> an urban legend.
>>
>> There is a story - as I have heard it told - that PDPs established their
>> place (and popularity) in the marketplace by pointedly *not* advertising
>> themselves as "computers", but instead as "programmed data processors".
>>
>> This was because - so the story goes - that everyone in corporations of
>> the time simply *knew* that "computers" came only from IBM, lived in big
>> datacentres, had million-dollar price-tags, and required extensive project
>> management to purchase; whereas nobody cared enough about a thing called a
>> "programmed data processor" to bother bikeshedding the
>> few-tens-or-hundreds-of-thousands-of-dollars purchase proposal to an
>> inevitable death. Thus, they flitted under the purchasing radar, and sold
>> like hotcakes.
>>
>> I wonder: does this story have substance, please?
>>
>> Aside from anything else: I draw parallels to the adoption of Linux by
>> Wall St, and the subsequent adoption of virtualisation / AWS by business -
>> now reflected in companies explaining to ISO27001 auditors that "well, we
>> don't actually possess any physical servers..."
>>
>>     - alec
>>
>> --
>> http://dropsafe.crypticide.com/aboutalecm
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171227/3b3ee8bb/attachment.html>

[TUHS] Why did PDPs become so popular?

[Greg 'groggy' Lehey]

On Wednesday, 27 December 2017 at 16:51:54 -0500, Clem Cole wrote:
>
> The concept of purchasing smaller system, was indeed true.   This was the
> idea behind the >>mini-computer<< or *minimal computer* that Gordon Bell
> who lad left DEC temporarily to be a CMU Prof for a time began to explore.

This ties in very much with what I recall from the late 1960s.  My
very first computer was a PDP-8/I, and we certainly called it a
computer, not a data processor.

> He took the idea and commercialized and the PDP-8 line was the first
> in that line.

Not the PDP-5?  I thought there was little difference.  If there was,
it would be interesting to know.

Greg
--
Sent from my desktop computer.
Finger grog at lemis.com for PGP public key.
See complete headers for address and phone numbers.
This message is digitally signed.  If your Microsoft mail program
reports problems, please read http://lemis.com/broken-MUA
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 163 bytes
Desc: not available
URL: <http://minnie.tuhs.org/pipermail/tuhs/attachments/20171228/b9e17e68/attachment.sig>