It's all over for the P4

[Scott Alfter]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

http://www.theregister.co.uk/2004/05/07/intel_cancels_tejas/

Intel to 'ditch' Pentium 4 core after Prescott

Intel will today tear its Pentium 4 and Xeon roadmaps to shreds and
announce the cancellation of its 'Tejas' and 'Jayhawk' processors and
their successors.

Both chips represent what was to have been the next generation of 90nm
Pentium 4 and Xeon, respectively, and were scheduled to arrive in the Q2
2005 timeframe. Chips derived from them include 'Cedarmill' on the
desktop, and 'Potomac' and 'Tulsa' in the Xeon series. The future of
these chips is now also in question.

According to Reuters, Tejas and Jayhawk are now history. The report
doesn't say what Intel will offer instead, but it seems clear that the
chip giant has decided to accelerate plans to roll-out desktop processors
derived from its Pentium M architecture.

The article goes on to mention that the Xeon will also move over to this
architecture. Intel wants to do dual-core CPUs, but that just wasn't going
to happen with anything that resembles the P4.

(John Corse (or his ghost) popped up in a Rambus thread yesterday on
Slashdot. I wouldn't mind seeing him pop his ugly mug in here so we can
tell him the P4 is DEAD DEAD DEAD! )

_/_
/ v \ Scott Alfter (remove the obvious to send mail)
(IIGS( http://alfter.us/ Top-posting!
\_^_/ rm -rf /bin/laden >What's the most annoying thing on Usenet?

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (Linux)

iD8DBQFAm7GMVgTKos01OwkRAlqFAKCVwYBBkp6uU6pwIqCKCGDJewABdACeN695
Q2pf3dyxxAU+raHqFSk1l5U=
=LcOV
-----END PGP SIGNATURE-----

 

[GSV Three Minds in a Can]

http://www.theregister.co.uk/2004/05/07/intel_cancels_tejas/

Intel to 'ditch' Pentium 4 core after Prescott

Oh good, they've obviously been reading, and heeding, the comments in
the 'Pentium-M desktop' thread.

8>.

 

[Yousuf Khan]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

The article goes on to mention that the Xeon will also move over to
this architecture. Intel wants to do dual-core CPUs, but that just
wasn't going to happen with anything that resembles the P4.

Looks like the competition from AMD has now just decimated the P4. Usually
that would simply mean that the performance of one was greater than the
other. But in this case, "decimated" actually means it's destroyed its
future offsprings and all generations derived from this architecture. It's
sort of like getting your genitals cut-off so you can't have children
anymore.

(John Corse (or his ghost) popped up in a Rambus thread yesterday on
Slashdot. I wouldn't mind seeing him pop his ugly mug in here so we
can
tell him the P4 is DEAD DEAD DEAD! )

What's the point, the P4 has been exclusively DDR for the past several
years? Why would he care anymore?

Yousuf Khan
-----BEGIN PGP SIGNATURE-----
Version: PGPfreeware 6.5.8 for non-commercial use <http://www.pgp.com>

iQA/AwUBQJvhou9XnxyH0dIcEQIPkACggeID/8pU0l+FCM5oItn0dwQt2dkAniIz
rbDy2PWiPoGpo+YNEs1rE8qO
=q2jN
-----END PGP SIGNATURE-----

 

[Gary Seven]

: -----BEGIN PGP SIGNED MESSAGE-----
: Hash: SHA1
:
: http://www.theregister.co.uk/2004/05/07/intel_cancels_tejas/
:
<big snip>

: The article goes on to mention that the Xeon will also move over to this
: architecture. Intel wants to do dual-core CPUs, but that just wasn't
going
: to happen with anything that resembles the P4.

Interesting. And looky here what CNN has to say about this:
http://money.cnn.com/2004/05/07/technology/intel.reut/index.htm?cnn=yes

Intel wants to do all future CPU's as dual core??? Ya think?

: (John Corse (or his ghost) popped up in a Rambus thread yesterday on
: Slashdot. I wouldn't mind seeing him pop his ugly mug in here so we can
: tell him the P4 is DEAD DEAD DEAD! )

I thought JC litterally went to FOAD. Oh well, I can fantasize, can't I?
;-)

G7

 

[gaffo]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1




Looks like the competition from AMD has now just decimated the P4. Usually
that would simply mean that the performance of one was greater than the
other. But in this case, "decimated" actually means it's destroyed its
future offsprings and all generations derived from this architecture. It's
sort of like getting your genitals cut-off so you can't have children
anymore.




What's the point, the P4 has been exclusively DDR for the past several
years? Why would he care anymore?

"several"?...........2 yrs. maybe.


lets see:

p-4 came out in fall 2001?

did the p-3 have Rambus ram at the end of its run?? (I don't remember)


regardless, Rambus showed its ugly head around 2001 (three yrs
ago)............and hung around for two yrs.

That leaves only ONE yr, where DDR is the effective winner.

I know how the tech industry like to accelerate the timeline, but that
accelaration is subjective.

2 mor 1 yrs is "several".

"several" implies at least 4, and more likely 1/2 a decade or more.


--
http://baltimorechronicle.com/041704reTreason.shtml

http://www.truthinaction.net/iraq/illegaljayne.htm


"The new administration seems to be paying no attention to the problem
of terrorism. What they will do is stagger along until there's a major
incident and then suddenly say, 'Oh my God, shouldn't we be organized
to deal with this?'"
- Paul Bremer, speaking to a McCormick Tribune Foundation conference
on terrorism in Wheaton, Ill. on Feb. 26, 2001.

"On Jan. 26, 1998, President Clinton received a letter imploring him to use
his State of the Union address to make removal of Saddam Hussein's regime
the "aim of American foreign policy" and to use military action because
"diplomacy is failing." Were Clinton to do that, the signers pledged, they
would "offer our full support in this difficult but necessary endeavor."
Signing the pledge were Elliott Abrams, Bill Bennett, John Bolton, Robert
Kagan, William Kristol, Richard Perle, and Paul Wolfowitz. Four years before
9/11, the neocons had Baghdad on their minds."
-philip (usenet)

"I had better things to do in the 60s than fight in Vietnam,"
-Richard Cheney, Kerry critic.

"I hope they will understand that in order for this government to get up
and running
- to be effective - some of its sovereignty will have to be given
back, if I can put it that way,
or limited by them, It's sovereignty but [some] of that sovereignty they
are going to allow us to exercise
on their behalf and with their permission."
- Powell 4/27/04

"We're trying to explain how things are going, and they are going as they
are going," he said, adding: "Some things are going well and some things
obviously are not going well. You're going to have good days and bad days."
On the road to democracy, this "is one moment, and there will be other
moments. And there will be good moments and there will be less good
moments."
- Rumsfeld 4/6/04


RUSSERT: Are you prepared to lose?

BUSH: No, I'm not going to lose.

RUSSERT: If you did, what would you do?

BUSH: Well, I don't plan on losing. I've got a vision for what I want to
do for the country.
See, I know exactly where I want to lead.................And we got
changing times
here in America, too., 2/8/04


"And that's very important for, I think, the people to understand where
I'm coming from,
to know that this is a dangerous world. I wish it wasn't. I'm a war
president.
I make decisions here in the Oval Office in foreign policy matters with
war on my mind.
- pResident of the United State of America, 2/8/04


"Let's talk about the nuclear proposition for a minute. We know that
based on intelligence, that he has been very, very good at hiding
these kinds of efforts. He's had years to get good at it and we know
he has been absolutely devoted to trying to acquire nuclear weapons.
And we believe he has, in fact, reconstituted nuclear weapons."
- Vice President Dick Cheney, on "Meet the Press", 3/16/03


"I don't know anybody that I can think of who has contended that the
Iraqis had nuclear weapons."
- Defense Secretary Donald Rumsfeld, 6/24/03


"I think in this case international law
stood in the way of doing the right thing (invading Iraq)."
- Richard Perle


"He (Saddam Hussein) has not developed any significant capability with
respect to weapons of mass destruction. He is unable to project
conventional power against his neighbours."
- Colin Powell February 24 2001


"We have been successful for the last ten years in keeping
him from developing those weapons and we will continue to be successful."

"He threatens not the United States."

"But I also thought that we had pretty
much removed his stings and frankly for ten years we really have."

'But what is interesting is that with the regime that has been in place
for the past ten years, I think a pretty good job has been done of
keeping him from breaking out and suddenly showing up one day and saying
"look what I got." He hasn't been able to do that.'
- Colin Powell February 26 2001

 

[RusH]

According to Reuters, Tejas and Jayhawk are now history.

minute of silence for those two : yaaadayadayada YADADADA oops sorry,
couldn't resist

report doesn't say what Intel will offer instead, but it seems
clear that the chip giant has decided to accelerate plans to
roll-out desktop processors derived from its Pentium M
architecture.

so this explains those Vectra P-M desktops

The article goes on to mention that the Xeon will also move over to
this architecture. Intel wants to do dual-core CPUs, but that just
wasn't going to happen with anything that resembles the P4.

prescott propably convinced them, >100W would even convince a polar Bear

Pozdrawiam.

 

[KR Williams]

@twister01.bloor.is.net.cable.rogers.com>, news.tally.bbbl67
@spamgourmet.com says...

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1



Looks like the competition from AMD has now just decimated the P4. Usually
that would simply mean that the performance of one was greater than the
other. But in this case, "decimated" actually means it's destroyed its
future offsprings and all generations derived from this architecture.

Actually, decimated == reduced by one-tenth, no matter what they
tell you in school these days. ;-)

It's
sort of like getting your genitals cut-off so you can't have children
anymore.

Ow! Intel must *really* be hurting today. ;-)

What's the point, the P4 has been exclusively DDR for the past several
years? Why would he care anymore?

Because DDR killed the P4. If they'd stayed the "course" with
RamBust the P4 would have crushed, *crushed*, *CRUSHED* AMD. ;-)

 

[George Macdonald]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

http://www.theregister.co.uk/2004/05/07/intel_cancels_tejas/

Intel to 'ditch' Pentium 4 core after Prescott

Intel will today tear its Pentium 4 and Xeon roadmaps to shreds and
announce the cancellation of its 'Tejas' and 'Jayhawk' processors and
their successors.

Both chips represent what was to have been the next generation of 90nm
Pentium 4 and Xeon, respectively, and were scheduled to arrive in the Q2
2005 timeframe. Chips derived from them include 'Cedarmill' on the
desktop, and 'Potomac' and 'Tulsa' in the Xeon series. The future of
these chips is now also in question.

According to Reuters, Tejas and Jayhawk are now history. The report
doesn't say what Intel will offer instead, but it seems clear that the
chip giant has decided to accelerate plans to roll-out desktop processors
derived from its Pentium M architecture.

The article goes on to mention that the Xeon will also move over to this
architecture. Intel wants to do dual-core CPUs, but that just wasn't going
to happen with anything that resembles the P4.

Funny I thought they'd had "similar" leakage/heat problems with Dothan as
with Prescott at 90nm??... I guess not quite so bad.

(John Corse (or his ghost) popped up in a Rambus thread yesterday on
Slashdot. I wouldn't mind seeing him pop his ugly mug in here so we can
tell him the P4 is DEAD DEAD DEAD! )

Hey it's pump-n-dump time - the stock has been oscillating like a spring
the last coupla weeks.

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??

 

[Felger Carbon]

Funny I thought they'd had "similar" leakage/heat problems with Dothan as
with Prescott at 90nm??... I guess not quite so bad.

I believe the problem is die size, not heat. P4 and Prescott are both
**huge** dies with just one CPU! Dothan is much smaller IIRC.

 

[daytripper]

Funny I thought they'd had "similar" leakage/heat problems with Dothan as
with Prescott at 90nm??... I guess not quite so bad.


Hey it's pump-n-dump time - the stock has been oscillating like a spring
the last coupla weeks.

More like the last year.
Ever see a stock that looked more like a friggin' neverending saw wave?

/daytripper (RMBS: It's the Bizarro-IP play! ;-)

 

[Nate Edel]

I believe the problem is die size, not heat. P4 and Prescott are both
**huge** dies with just one CPU! Dothan is much smaller IIRC.

Dothan's got a bigger transistor count (144M, IIRC) than either Northwood
(~87M, again IIRC) or Prescott (~110M, again IIRC).

Then again, that's the 2MB cache for you.

 

[Felger Carbon]

Dothan's got a bigger transistor count (144M, IIRC) than either Northwood
(~87M, again IIRC) or Prescott (~110M, again IIRC).

Then again, that's the 2MB cache for you.

Nate, you're right. But a multi-core die only holds one cache system,
no matter how many logical cores. Dothan's logical core is much much
smaller than Prescott's. I apologize for the imprecision of my
answer.

 

[Derek Baker]

Nate, you're right. But a multi-core die only holds one cache system,
no matter how many logical cores. Dothan's logical core is much much
smaller than Prescott's. I apologize for the imprecision of my
answer.

This looks like two cores with two cache systems:
http://www.vr-zone.com/?i=734&s=1

 

[daytripper]

Nate, you're right. But a multi-core die only holds one cache system,
no matter how many logical cores.

I expect that's a little too strong a statement - if it was totally true it'd
be ugly - as mere hyperthreading has demonstrated (cache thrash).

Perhaps the nth level cache is shared, but I'd be shocked (SHOCKED, I tell's
ya!) if each core doesn't have a lower level (or two) cache(s) of its own...

/daytripper

 

[AD.]

did the p-3 have Rambus ram at the end of its run?? (I don't remember)

I seem to remember the i820 chipset (yes that one) supporting rambus
memory.

Cheers
Anton

 

[Tony Hill]

Dothan's got a bigger transistor count (144M, IIRC) than either Northwood
(~87M, again IIRC) or Prescott (~110M, again IIRC).

144M for Dothan, 55M for Northwood and 125M for Prescott according to
www.sandpile.org.

Then again, that's the 2MB cache for you.

You're hitting the nail on the head right there. Just FWIW:

2MB = 2,097,152 bytes. At 9 bits/byte (ECC adds an extra bit) and 6
transistors per bit, you're already at 113M transistors for the L2
cache, and that's without counting any extra redundancy. Chances are
that the L2 cache makes up more like 120-125M of the 144M transistors
in Dothan.

When you start to look at it this way, it suddenly makes very good
sense to make a dual-core version of the chip with shared L2. Even
with a few million extra transistors for additional control circuitry
you could probably manage to a dual-core Dothan with 175M transistors
or there-abouts. Of course, raw transistor count is only half of the
story, each of those cache transistors takes up significantly less die
space than an equivalent number of logic or control transistors.
Still, in the end a dual-core chip based off the Pentium-M probably
makes good sense. Add in an on-die memory controller and a
hypertransport-style bus and Intel could have a real winner on their
hands.

 

[George Macdonald]

Because DDR killed the P4. If they'd stayed the "course" with
RamBust the P4 would have crushed, *crushed*, *CRUSHED* AMD. ;-)

Well of course it would, because it worked so well in the umm, NetBust
architecture.

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??

 

[George Macdonald]

On Sat, 08 May 2004 17:43:13 -0400, George Macdonald


More like the last year.
Ever see a stock that looked more like a friggin' neverending saw wave?

The last few weeks has been quite striking though - even threw in a coupla
square waves. Hey, i-i-i-it's integrating..... naw, i-i-i-it's
differentiating.

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??

 

[Yousuf Khan]

When you start to look at it this way, it suddenly makes very good
sense to make a dual-core version of the chip with shared L2. Even
with a few million extra transistors for additional control circuitry
you could probably manage to a dual-core Dothan with 175M transistors
or there-abouts. Of course, raw transistor count is only half of the
story, each of those cache transistors takes up significantly less die
space than an equivalent number of logic or control transistors.
Still, in the end a dual-core chip based off the Pentium-M probably
makes good sense. Add in an on-die memory controller and a
hypertransport-style bus and Intel could have a real winner on their
hands.

Sounds like what Intel needs to design is an Athlon 64/Opteron.

Yousuf Khan

 

[Nate Edel]

Nate, you're right. But a multi-core die only holds one cache system,
no matter how many logical cores.

Well, one L2... my understanding is that you still usually want separate L1
caches... (otherwise you'd need a very large and many-ported shared L1.)

Dothan's logical core is much much smaller than Prescott's. I apologize
for the imprecision of my answer.

Prescott's, yes, but Prescott is a f___ing monster; I'm not sure it's really
that much smaller than Northwood/Willamette. IIRC, both Banias and Northwood
are on the order of 25-30M transistors for the core, while Prescott is what,
50Mish?