28 Dec
2017
28 Dec
'17
2:05 p.m.
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
28 Dec
28 Dec
3:59 p.m.
New subject: Why did PDPs become so popular?
On 12/28/17, Noel Chiappa <jnc(a)mercury.lcs.mit.edu> 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. 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.
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? 
4:08 p.m.
New subject: Why did PDPs become so popular?
On Thu, Dec 28, 2017 at 10:59:29AM -0500, Paul Winalski wrote:
On 12/28/17, Noel Chiappa
<jnc(a)mercury.lcs.mit.edu> 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
--
---
Larry McVoy lm at mcvoy.com http://www.mcvoy.com/lm
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? 
11:28 p.m.
New subject: Why did PDPs become so popular?
On Thu, Dec 28, 2017 at 08:08:11AM -0800, Larry McVoy wrote:
"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
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 
29 Dec
29 Dec
11:04 a.m.
New subject: Why did PDPs become so popular?
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…
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(a)mit.edu> wrote:
On Thu, Dec 28, 2017 at 08:08:11AM -0800, Larry McVoy
wrote:
"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
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 
11:35 p.m.
New subject: Why did PDPs become so popular?
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…
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
11:58 p.m.
New subject: Why did PDPs become so popular?
On Fri, Dec 29, 2017 at 03:35:27PM -0800, Jon Forrest wrote:
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
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…
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.
2303
days inactive
2304
days old
6 comments
6 participants
participants (6)
-
jnc＠mercury.lcs.mit.edu -
Jon Forrest -
Kevin Bowling -
Larry McVoy -
Paul Winalski -
Theodore Ts'o