Intel engineer discusses their dual-core design

[YKhan]

http://www.macworld.com/news/2005/08/17/dualcore/index.php

 

[Skybuck Flying]

http://www.macworld.com/news/2005/08/17/dualcore/index.php

I can see why they called it "smithfield" kinda sounds like "smutfield "

Wieeeeeeee very interesting read though... I am just half way wow

Bye,
Skybuck

(Me looks forward to next intel processor wieeeeeee)

 

[keith]

http://www.macworld.com/news/2005/08/17/dualcore/index.php

I simply found it an admission of how far (and for how long) their
technological head is (and has been) up their corporate ass. Nine months
in development isn't that big of a deal, given that the "cores" are
already there. Years? Please! They don't simulate/verify in
multi-processor environments? *Amazing*!

 

[icerq4a]

keith skrev:

I simply found it an admission of how far (and for how long) their
technological head is (and has been) up their corporate ass. Nine months
in development isn't that big of a deal, given that the "cores" are
already there. Years? Please! They don't simulate/verify in
multi-processor environments? *Amazing*!

The only amazing thing here is that you don't seem to understand the
article and appear to know nothing about microprocessor development.

 

[YKhan]

The only amazing thing here is that you don't seem to understand the
article and appear to know nothing about microprocessor development.

Now you've done it. I don't envy your position one bit.

Yousuf Khan

 

[YKhan]

I wonder if that Intel engineer was looking for a new job?

Yousuf Khan

 

[CJT]

I wonder if that Intel engineer was looking for a new job?

Yousuf Khan

.... or is now.

 

[Rob Stow]

keith skrev:




The only amazing thing here is that you don't seem to understand the
article and appear to know nothing about microprocessor development.

Better put on your flame retardant suit.

You, as a newbie to this group with no credentials established
are telling Keith, with well established creds, that he knows
nothing about microprocessor development ?

Better stand under a stream of ice cold waterfall too.

 

[Del Cecchi]

I simply found it an admission of how far (and for how long) their
technological head is (and has been) up their corporate ass. Nine
months
in development isn't that big of a deal, given that the "cores" are
already there. Years? Please! They don't simulate/verify in
multi-processor environments? *Amazing*!

When the PHB only gives you 9 months, you do what you gotta do. And
since this is a desktop thing you do something as much like a dual
processor desktop box as you can. It's a Kluge but it's a Kluge they
needed. He'll get a medal.

del

 

[Yousuf Khan]

When the PHB only gives you 9 months, you do what you gotta do. And
since this is a desktop thing you do something as much like a dual
processor desktop box as you can. It's a Kluge but it's a Kluge they
needed. He'll get a medal.

I bet the management is just now thinking, "yeah, he got our bacon out
of the fire and all with this kludge, but just wish we could train these
engineers to lie occasionally."

Yousuf Khan

 

[Grant Schoep]

I bet the management is just now thinking, "yeah, he got our bacon out
of the fire and all with this kludge, but just wish we could train these
engineers to lie occasionally."

Yousuf Khan

:> Reminds me of something Cringly wrote in Accidental Empires. Something
about why engineers just can't lie. He had a pretty good chapter or two on
this whole subject, how engineers would get all ticked off at management,
and then go tell the public. I can't remeber it exactly... I need to stop
lending my books out as I never get them back.

-grant

 

[Terje Mathisen]

I agree, this might have been a hack but it's an amazing hack.

:> Reminds me of something Cringly wrote in Accidental Empires. Something
about why engineers just can't lie. He had a pretty good chapter or two on
this whole subject, how engineers would get all ticked off at management,
and then go tell the public. I can't remeber it exactly... I need to stop
lending my books out as I never get them back.

There are several reasons why engineers are very poor at lying:

-) "I'm an engineer, my credibility is my main capital."

-) "Salesmen, layers, PHBs and several other types that I really don't
like do it, so I want to distance myself from them."

-) It is just so inelegant. :-(

If I absolutely _have_ to lie, it must be by omission: I'll still tell
the truth and nothing but the truth (as I understand it, of course), but
unless you ask me specific questions about those parts I'm skipping, I
might not tell you all of the truth.

Terje

 

[Klaus Fehrle]

I wonder if that Intel engineer was looking for a new job?

Yousuf Khan

I'd assume Jonathan presented with full blessing of Intels management.
Playing down Smithfields architecture, blaming the bus for performance
and power issues is actually not a bad idea to prepare the soil for
Paxville, no? While I doubt anybody of the auditorium in Palo Alto was
overly impressed by it, a self-critical Hotchips-presentation by Intel
guarantees press coverage without much probability of looking through an
even paper-thin line of arguments.

KF

 

[Robert Redelmeier]

There are several reasons why engineers are very poor at lying:

-) "I'm an engineer, my credibility is my main capital."

-) "Salesmen, la[w]yers, PHBs and several other types that I really
don't like do it, so I want to distance myself from them."

-) It is just so inelegant. :-(

If I absolutely _have_ to lie, it must be by omission: I'll
still tell the truth and nothing but the truth (as I understand
it, of course), but unless you ask me specific questions about
those parts I'm skipping, I might not tell you all of the truth.

So how do you answer when your wife asks: "Does this dress make
me look fat?"

The concept of a "duty of truth" is a practical justification.
One really should not lie (even by omission) when one owes information
to someone, and they may be reasonably expected to rely upon it.

For example, I have no trouble lying to a saleman saying "I'm busy"
rather than telling him "Your product is grossly overpriced,
I'm insulted you think I'm so stupid as to fall for it, and I
find you obnoxious." The latter may be entirely true, but it is
valuable information (feedback) the saleman has not earned.

A certain amount of lying also eases social interactions.
See the Jim Carrey movie "Liar, liar". Of course, you may
claim that engineers are poor at social interactions

-- Robert

 

[Bill Davidsen]

I simply found it an admission of how far (and for how long) their
technological head is (and has been) up their corporate ass. Nine months
in development isn't that big of a deal, given that the "cores" are
already there. Years? Please! They don't simulate/verify in
multi-processor environments? *Amazing*!

If these cores are the desktop versions rather than Xeon, they were not
planned to be used in SMP, much less in dual core. I'd be interested to
get your spin on why they *would* test the desktop chip SMP.

Here's a more interesting question: Intel built the D/C chips on P4
rather than P-M, presumably so they could offer the ht model at a huge
premium. Given the low power and far better performance of the P-M in
terms of work/watt and work/clock, why not a dual core Pentium-M? Then
when the better P4 D/C chip is ready they could offer that?

Just curious as to the logic for the decision if anyone has any insight.

 

[Rob Stow]

If these cores are the desktop versions rather than Xeon, they were not
planned to be used in SMP, much less in dual core. I'd be interested to
get your spin on why they *would* test the desktop chip SMP.

Here's a more interesting question: Intel built the D/C chips on P4
rather than P-M, presumably so they could offer the ht model at a huge
premium. Given the low power and far better performance of the P-M in
terms of work/watt and work/clock, why not a dual core Pentium-M? Then
when the better P4 D/C chip is ready they could offer that?

Just curious as to the logic for the decision if anyone has any insight.

Probably has something to do with the fact that AMD64 is the
hottest thing right now. Intel just tacked two AMD64-capable
cores together in a MCP, and voila: a cheap AMD64-capable
multi-chip package that they could delude the masses into
thinking of as a competitor to AMD's dual-core chips.

Doing the same thing with the P-M is supposed to eventually
happen. Sort of. Apparently the next generation will be
dual-core and redesigned from the ground up instead of evolved
from the P3. Still haven't heard if it will be AMD64-capable.

 

[CJT]

Probably has something to do with the fact that AMD64 is the hottest
thing right now. Intel just tacked two AMD64-capable cores together in
a MCP, and voila: a cheap AMD64-capable multi-chip package that they
could delude the masses into thinking of as a competitor to AMD's
dual-core chips.

Doing the same thing with the P-M is supposed to eventually happen. Sort
of. Apparently the next generation will be dual-core and redesigned
from the ground up instead of evolved from the P3. Still haven't heard
if it will be AMD64-capable.

I think AMD has finally managed to tarnish "Intel Inside."

 

[Bill Davidsen]

Probably has something to do with the fact that AMD64 is the hottest
thing right now. Intel just tacked two AMD64-capable cores together in
a MCP, and voila: a cheap AMD64-capable multi-chip package that they
could delude the masses into thinking of as a competitor to AMD's
dual-core chips.

The 64 bit is a good point. For many applications AMD dual core or Intel
dual core will be equally satisfactory, and in most cases will perform
about as well as two-way SMP. No delusion needed, they compete.

Doing the same thing with the P-M is supposed to eventually happen. Sort
of. Apparently the next generation will be dual-core and redesigned
from the ground up instead of evolved from the P3. Still haven't heard
if it will be AMD64-capable.

I had hoped for a drop-in dual core P-M for my notebook, but I wasn't
really expecting to get it :-(

 

[daytripper]

On Fri, 19 Aug 2005 15:28:58 GMT, Bill Davidsen

Here's a more interesting question: Intel built the D/C chips on P4
rather than P-M, presumably so they could offer the ht model at a huge
premium. Given the low power and far better performance of the P-M in
terms of work/watt and work/clock, why not a dual core Pentium-M? Then
when the better P4 D/C chip is ready they could offer that?

Just curious as to the logic for the decision if anyone has any insight.

So a D/C P-M DP with ES available early fall '05 (like, soon) hasn't been
publicly announced yet?

I guess I better not talk about one, then...

 

[Rob Stow]

I think AMD has finally managed to tarnish "Intel Inside."

Finally ? Where have you been hiding for the last 4 or 5 years
? AMD has had the better CPUs for desktops and 2-way servers
and workstations since the Athlon XP and MP transitioned from
0.18 to 0.13 microns. Even before then the Athlon XP and MP
outperformed the P4 and Xeon - but also ran pretty danged hot.

The only CPU market Intel has held the technological edge in for
the past 4 or 5 years has been the mobile market, where the
Pentium M has been king and looks like it will reign for a while
longer.