Sign in with
Sign up | Sign in
Your question

Intel quietly ships 64-bit Prescott

Tags:
  • CPUs
  • Hardware
  • Intel
Last response: in CPUs
Share
Anonymous
a b à CPUs
August 4, 2004 4:00:08 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Apparently the 64-bit Pentium 4's are now ready. And they're server parts!?

http://www.eetimes.com/semi/news/showArticle.jhtml?arti...

Yousuf Khan

--
Humans: contact me at ykhan at rogers dot com
Spambots: just reply to this email address ;-)

More about : intel quietly ships bit prescott

August 4, 2004 4:00:09 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Server parts? So they must be quite expensive? If they aren't very expensive,
then they will probably put tremendous downward pressure on the prices of
Intel's 32 bit processors. I wonder about the power consumption and about
the performance.

Yousuf Khan wrote:

> Apparently the 64-bit Pentium 4's are now ready. And they're server parts!?
>
> http://www.eetimes.com/semi/news/showArticle.jhtml?arti...
>
> Yousuf Khan
>
> --
> Humans: contact me at ykhan at rogers dot com
> Spambots: just reply to this email address ;-)
Anonymous
a b à CPUs
August 4, 2004 4:00:09 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Yousuf Khan wrote:

> Apparently the 64-bit Pentium 4's are now ready. And they're server parts!?

Huh ? You seem surprised ? Intel has been saying
for quite a while that only the P4-Xeons were going
to be getting the AMD64 compatibility.


>
> http://www.eetimes.com/semi/news/showArticle.jhtml?arti...
>
> Yousuf Khan
>
Related resources
Anonymous
a b à CPUs
August 4, 2004 4:00:10 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

<grumble> stupid top-posting...

On Tue, 03 Aug 2004 20:36:18 -0400, JK <JK9821@netscape.net> wrote:
>Yousuf Khan wrote:
>
>> Apparently the 64-bit Pentium 4's are now ready. And they're server parts!?
>>
>> http://www.eetimes.com/semi/news/showArticle.jhtml?arti...
>>
>Server parts? So they must be quite expensive? If they aren't very expensive,
>then they will probably put tremendous downward pressure on the prices of
>Intel's 32 bit processors.

Intel is not selling the chips at retail, only as an OEM part to IBM
and probably Dell (HPaq will probably be left out in the cold on this
one due to their loud support of the Athlon64 and Opteron). You might
see a few of them showing up in the gray market, but probably not
enough to make a serious dent in things one way or the other.

> I wonder about the power consumption and about
>the performance.

Power consumption should be more or less unchanged from the 32-bit
part. Maybe a few more watts here or there, I highly doubt that it
would be even a 5% change.

As for performance though.. well now that's the real question isn't
it. Benchmarks comparing the Xeon vs. Opteron (or this new P4 vs.
Athlon64) in both 32 and 64-bit code are still basically non-existent.

-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca
Anonymous
a b à CPUs
August 4, 2004 5:50:35 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Wed, 04 Aug 2004 00:00:08 GMT, "Yousuf Khan" <bbbl67@ezrs.com> wrote:

>Apparently the 64-bit Pentium 4's are now ready. And they're server parts!?
>
>http://www.eetimes.com/semi/news/showArticle.jhtml?arti...

Not all "server" parts are created equal - the Prescotts are more likely just
desktop parts that will be used in some blades and pizza boxen (read:
seriously cost conscious products) vs the Noconas (Xeons) that will go in less
cost-sensitive applications.

The somewhat interesting part of this is that Intel is going along with
desktop processors being used in servers. They've had a major malfunction when
we thought out loud about doing the same with earlier P4s...

/daytripper ("Nancona"? Another fine job by EE Times! ;-)
August 4, 2004 5:50:36 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Wed, 04 Aug 2004 01:50:35 +0000, daytripper wrote:

> On Wed, 04 Aug 2004 00:00:08 GMT, "Yousuf Khan" <bbbl67@ezrs.com> wrote:
>
>>Apparently the 64-bit Pentium 4's are now ready. And they're server parts!?
>>
>>http://www.eetimes.com/semi/news/showArticle.jhtml?arti...
>
> Not all "server" parts are created equal - the Prescotts are more likely just
> desktop parts that will be used in some blades and pizza boxen (read:
> seriously cost conscious products) vs the Noconas (Xeons) that will go in less
> cost-sensitive applications.
>
> The somewhat interesting part of this is that Intel is going along with
> desktop processors being used in servers. They've had a major malfunction when
> we thought out loud about doing the same with earlier P4s...

Maybe they've listened to the market speak? Naw, gotta be something else.
They've never had that particular problem before.

--
Keith
Anonymous
a b à CPUs
August 4, 2004 10:52:43 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Rob Stow wrote:
> Yousuf Khan wrote:
>
>> Apparently the 64-bit Pentium 4's are now ready. And they're server
>> parts!?
>
> Huh ? You seem surprised ? Intel has been saying
> for quite a while that only the P4-Xeons were going
> to be getting the AMD64 compatibility.

The Xeons were the only ones officially announced at that point. The P4's
were always "eventually".

Yousuf Khan
Anonymous
a b à CPUs
August 4, 2004 12:29:43 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

JK wrote:
> Server parts? So they must be quite expensive? If they aren't very expensive,
> then they will probably put tremendous downward pressure on the prices of
> Intel's 32 bit processors. I wonder about the power consumption and about
> the performance.

Not necessarily expensive. Intel's lowest Xeons have long been about
$10 more than the Pentium 4. Those are the 2-way only, no extra cache
versions. This is probably going to be priced the same + $15 or so.

Power consumption will be the same. It's the exact same chip. Since
exactly the same circuits are in use, the power will be 99.9999%
identical. Minute variation only due to greater activity factor on the
upper bits of pathways. But expect the difference to be under a watt or
two.

By performance, I assume you mean the performance on 64b code. I assume
that because there's been tons of 32b benchmarking of the 64b-capable
processors so far. I'm personally of the belief that performance of 64b
code vs Opteron will be comparable to 32b code on the same chips. Thus
if the performance of P4 vs A64 is X:Y in 32b, then it will be X:Y in
64b. Until someone can show benchmarks, that's a fair assumption.

Alex
--
My words are my own. They represent no other; they belong to no other.
Don't read anything into them or you may be required to compensate me
for violation of copyright. (I do not speak for my employer.)
Anonymous
a b à CPUs
August 4, 2004 7:36:37 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

In comp.sys.ibm.pc.hardware.chips JK <JK9821@netscape.net> wrote:
> Server parts? So they must be quite expensive? If they aren't very expensive,
> then they will probably put tremendous downward pressure on the prices of
> Intel's 32 bit processors. I wonder about the power consumption and about
> the performance.

Since it's a Xeon, the higher cost of the motherboard and PSU will count
against it, even if the chip price itself if not much higher than a
comparable-speed desktop chip.

--
Nate Edel http://www.nkedel.com/

"Wanted: One .Sig-quote. Must work cheap."
Anonymous
a b à CPUs
August 4, 2004 9:01:28 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Alex Johnson wrote:
> By performance, I assume you mean the performance on 64b code. I
> assume that because there's been tons of 32b benchmarking of the
> 64b-capable processors so far. I'm personally of the belief that
> performance of 64b code vs Opteron will be comparable to 32b code on
> the same chips. Thus if the performance of P4 vs A64 is X:Y in 32b,
> then it will be X:Y in 64b. Until someone can show benchmarks,
> that's a fair assumption.

I'd tend to agree with that assumption, but there have been some benchmarks
done by C't magazine in Germany which suggests that 64-bit performance on
Nocona (and hence Prescott) isn't as good as its 32-bit performance.

http://www.theinquirer.net/?article=15149

And here's the original article:

http://www.heise.de/ct/04/08/020/

Translated:

http://makeashorterlink.com/?D509258F8

I think whatever performance problems that they are talking about here,
might have to do with the 4GB limit of DMA for this processor.

Yousuf Khan
Anonymous
a b à CPUs
August 4, 2004 10:51:01 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Yousuf Khan wrote:
>
[...]
>
> I'd tend to agree with that assumption, but there have been some benchmarks
> done by C't magazine in Germany which suggests that 64-bit performance on
> Nocona (and hence Prescott) isn't as good as its 32-bit performance.
>
> http://www.theinquirer.net/?article=15149
>
> And here's the original article:
>
> http://www.heise.de/ct/04/08/020/
>
> Translated:
>
> http://makeashorterlink.com/?D509258F8
>
> I think whatever performance problems that they are talking about here,
> might have to do with the 4GB limit of DMA for this processor.
>
> Yousuf Khan

The machine translation of German is quite amusing. 'Processor whispers' is
of course 'Processor rumours', since whispering is sometimes the way rumours
are spread.
August 5, 2004 2:13:27 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Wed, 04 Aug 2004 18:51:01 +0000, Johannes H Andersen wrote:

>
>
> Yousuf Khan wrote:
>>
> [...]
>>
>> I'd tend to agree with that assumption, but there have been some benchmarks
>> done by C't magazine in Germany which suggests that 64-bit performance on
>> Nocona (and hence Prescott) isn't as good as its 32-bit performance.
>>
>> http://www.theinquirer.net/?article=15149
>>
>> And here's the original article:
>>
>> http://www.heise.de/ct/04/08/020/
>>
>> Translated:
>>
>> http://makeashorterlink.com/?D509258F8
>>
>> I think whatever performance problems that they are talking about here,
>> might have to do with the 4GB limit of DMA for this processor.
>>
>> Yousuf Khan
>
> The machine translation of German is quite amusing. 'Processor whispers' is
> of course 'Processor rumours', since whispering is sometimes the way rumours
> are spread.

Oh, PLease! A whisper is a physical layer issue, while a rumor is
a link layer. One is a transport mechanism and one is a message. Rather
like one doesn't scream sweet nothings into one's lover's ears.

;-)

--
Keith
Anonymous
a b à CPUs
August 5, 2004 4:35:11 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Wed, 04 Aug 2004 15:36:37 -0700, archmage@sfchat.org (Nate Edel) wrote:

>In comp.sys.ibm.pc.hardware.chips JK <JK9821@netscape.net> wrote:
>> Server parts? So they must be quite expensive? If they aren't very expensive,
>> then they will probably put tremendous downward pressure on the prices of
>> Intel's 32 bit processors. I wonder about the power consumption and about
>> the performance.
>
>Since it's a Xeon, the higher cost of the motherboard and PSU will count
>against it, even if the chip price itself if not much higher than a
>comparable-speed desktop chip.

Prescott is not a Xeon...
Anonymous
a b à CPUs
August 5, 2004 6:39:59 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

"Keith" <krw@att.bizzzz> wrote in message
news:p an.2004.08.05.02.13.25.670211@att.bizzzz...
>
> Oh, PLease! A whisper is a physical layer issue, while a rumor is
> a link layer. One is a transport mechanism and one is a message. Rather
> like one doesn't scream sweet nothings into one's lover's ears.

It all depends in the height of ecstasy. :-o
Anonymous
a b à CPUs
August 5, 2004 6:40:46 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

"Keith" <krw@att.bizzzz> wrote in message
news:p an.2004.08.05.02.13.25.670211@att.bizzzz...
> On Wed, 04 Aug 2004 18:51:01 +0000, Johannes H Andersen wrote:
>
>>
>>
>> Yousuf Khan wrote:
>>>
>> [...]
>>>
>>> I'd tend to agree with that assumption, but there have been some
>>> benchmarks
>>> done by C't magazine in Germany which suggests that 64-bit performance
>>> on
>>> Nocona (and hence Prescott) isn't as good as its 32-bit performance.
>>>
>>> http://www.theinquirer.net/?article=15149
>>>
>>> And here's the original article:
>>>
>>> http://www.heise.de/ct/04/08/020/
>>>
>>> Translated:
>>>
>>> http://makeashorterlink.com/?D509258F8
>>>
>>> I think whatever performance problems that they are talking about here,
>>> might have to do with the 4GB limit of DMA for this processor.
>>>
>>> Yousuf Khan
>>
>> The machine translation of German is quite amusing. 'Processor whispers'
>> is
>> of course 'Processor rumours', since whispering is sometimes the way
>> rumours
>> are spread.
>
> Oh, PLease! A whisper is a physical layer issue, while a rumor is
> a link layer. One is a transport mechanism and one is a message. Rather
> like one doesn't scream sweet nothings into one's lover's ears.


Um ... not into S & M then?

--

... Hank

http://horedson.home.att.net
http://w0rli.home.att.net
Anonymous
a b à CPUs
August 5, 2004 10:46:02 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

In comp.sys.intel Keith <krw@att.bizzzz> wrote:
> Oh, PLease! A whisper is a physical layer issue, while a rumor is
> a link layer. One is a transport mechanism and one is a message.

I think you have skipped a few layers and jumbled things a bit.
Whisper is indeed physical layer, but the data link layer is phonemes
(sp). Words form the network layer, sentences the transport, and the
message is application-layer specific, which is why translation at the
network layer isn't always perfect :) 

rick jones
--
firebug n, the idiot who tosses a lit cigarette out his car window
these opinions are mine, all mine; HP might not want them anyway... :) 
feel free to post, OR email to raj in cup.hp.com but NOT BOTH...
August 6, 2004 1:18:06 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Thu, 05 Aug 2004 02:40:46 +0000, Hank Oredson wrote:

> "Keith" <krw@att.bizzzz> wrote in message
> news:p an.2004.08.05.02.13.25.670211@att.bizzzz...
>> On Wed, 04 Aug 2004 18:51:01 +0000, Johannes H Andersen wrote:
>>
>>>
>>>
>>> Yousuf Khan wrote:
>>>>
>>> [...]
>>>>
>>>> I'd tend to agree with that assumption, but there have been some
>>>> benchmarks
>>>> done by C't magazine in Germany which suggests that 64-bit performance
>>>> on
>>>> Nocona (and hence Prescott) isn't as good as its 32-bit performance.
>>>>
>>>> http://www.theinquirer.net/?article=15149
>>>>
>>>> And here's the original article:
>>>>
>>>> http://www.heise.de/ct/04/08/020/
>>>>
>>>> Translated:
>>>>
>>>> http://makeashorterlink.com/?D509258F8
>>>>
>>>> I think whatever performance problems that they are talking about here,
>>>> might have to do with the 4GB limit of DMA for this processor.
>>>>
>>>> Yousuf Khan
>>>
>>> The machine translation of German is quite amusing. 'Processor whispers'
>>> is
>>> of course 'Processor rumours', since whispering is sometimes the way
>>> rumours
>>> are spread.
>>
>> Oh, PLease! A whisper is a physical layer issue, while a rumor is
>> a link layer. One is a transport mechanism and one is a message. Rather
>> like one doesn't scream sweet nothings into one's lover's ears.
>
>
> Um ... not into S & M then?

No, not on purpose. ...unless you count 33 years of marriage. ;-)

--
Keith
August 6, 2004 1:18:49 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Thu, 05 Aug 2004 02:39:59 +0000, MyndPhlyp wrote:

>
> "Keith" <krw@att.bizzzz> wrote in message
> news:p an.2004.08.05.02.13.25.670211@att.bizzzz...
>>
>> Oh, PLease! A whisper is a physical layer issue, while a rumor is
>> a link layer. One is a transport mechanism and one is a message. Rather
>> like one doesn't scream sweet nothings into one's lover's ears.
>
> It all depends in the height of ecstasy. :-o
^^^^^^

I don't do viagra either. ;-)

--
Keith
Anonymous
a b à CPUs
August 6, 2004 8:42:01 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

"Keith" <krw@att.bizzzz> wrote in message
news:p an.2004.08.06.01.18.04.401026@att.bizzzz...
> On Thu, 05 Aug 2004 02:40:46 +0000, Hank Oredson wrote:
>
>> "Keith" <krw@att.bizzzz> wrote in message
>> news:p an.2004.08.05.02.13.25.670211@att.bizzzz...
>>> On Wed, 04 Aug 2004 18:51:01 +0000, Johannes H Andersen wrote:
>>>
>>>>
>>>>
>>>> Yousuf Khan wrote:
>>>>>
>>>> [...]
>>>>>
>>>>> I'd tend to agree with that assumption, but there have been some
>>>>> benchmarks
>>>>> done by C't magazine in Germany which suggests that 64-bit performance
>>>>> on
>>>>> Nocona (and hence Prescott) isn't as good as its 32-bit performance.
>>>>>
>>>>> http://www.theinquirer.net/?article=15149
>>>>>
>>>>> And here's the original article:
>>>>>
>>>>> http://www.heise.de/ct/04/08/020/
>>>>>
>>>>> Translated:
>>>>>
>>>>> http://makeashorterlink.com/?D509258F8
>>>>>
>>>>> I think whatever performance problems that they are talking about
>>>>> here,
>>>>> might have to do with the 4GB limit of DMA for this processor.
>>>>>
>>>>> Yousuf Khan
>>>>
>>>> The machine translation of German is quite amusing. 'Processor
>>>> whispers'
>>>> is
>>>> of course 'Processor rumours', since whispering is sometimes the way
>>>> rumours
>>>> are spread.
>>>
>>> Oh, PLease! A whisper is a physical layer issue, while a rumor is
>>> a link layer. One is a transport mechanism and one is a message.
>>> Rather
>>> like one doesn't scream sweet nothings into one's lover's ears.
>>
>>
>> Um ... not into S & M then?
>
> No, not on purpose. ...unless you count 33 years of marriage. ;-)


ROTFL!

--

... Hank

http://horedson.home.att.net
http://w0rli.home.att.net
Anonymous
a b à CPUs
August 6, 2004 11:38:16 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

At our age, you have to scream for your partner to even hear you.

Hearing is the second thing to go.

Keith wrote:
>
> Rather
> like one doesn't scream sweet nothings into one's lover's ears.
Anonymous
a b à CPUs
August 6, 2004 11:39:46 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

After 33 years, you aren't deaf yet? :) 

Though, your wife has claimed you seem to be deaf for the
past 32 years.

Keith wrote:
>
> No, not on purpose. ...unless you count 33 years of marriage. ;-)
August 7, 2004 3:39:13 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Fri, 06 Aug 2004 07:38:16 -0400, Walt wrote:

> At our age, you have to scream for your partner to even hear you.

At our age, who want's that?

> Hearing is the second thing to go.

Hmmm, can't remember the first.

--
Keith

===============================
> Keith wrote:
>>
>> Rather
>> like one doesn't scream sweet nothings into one's lover's ears.
August 7, 2004 3:40:20 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Fri, 06 Aug 2004 07:39:46 -0400, Walt wrote:

> After 33 years, you aren't deaf yet? :) 

Huh? What?

> Though, your wife has claimed you seem to be deaf for the
> past 32 years.

Selectively. ...goes both ways. ;-)

--
Keith

==================

> Keith wrote:
>>
>> No, not on purpose. ...unless you count 33 years of marriage. ;-)
Anonymous
a b à CPUs
August 8, 2004 3:45:36 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

see http://developer.intel.com/design/pcn/Processors/D01041... page 3
there is processor number for Pentium 4 Presscott with EM64T

"Yousuf Khan" <bbbl67@ezrs.com> wrote in message
news:%I%Pc.61$Y5k1.34@news04.bloor.is.net.cable.rogers.com...
> Rob Stow wrote:
>> Yousuf Khan wrote:

>> Huh ? You seem surprised ? Intel has been saying
>> for quite a while that only the P4-Xeons were going
>> to be getting the AMD64 compatibility.
>
> The Xeons were the only ones officially announced at that point. The P4's
> were always "eventually".
August 8, 2004 5:26:40 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

It seems like Intel wants to stick to its theme that 64 bits is not yet needed
for the desktop pc user, but is needed in the server space. That is why the
P4s with 64 bit compatibility are being called server chips. It will be
interesting
to see how soon those chips are available for consumers to purchase, and
how they will be priced.

Gilles Vollant wrote:

> see http://developer.intel.com/design/pcn/Processors/D01041... page 3
> there is processor number for Pentium 4 Presscott with EM64T
>
> "Yousuf Khan" <bbbl67@ezrs.com> wrote in message
> news:%I%Pc.61$Y5k1.34@news04.bloor.is.net.cable.rogers.com...
> > Rob Stow wrote:
> >> Yousuf Khan wrote:
>
> >> Huh ? You seem surprised ? Intel has been saying
> >> for quite a while that only the P4-Xeons were going
> >> to be getting the AMD64 compatibility.
> >
> > The Xeons were the only ones officially announced at that point. The P4's
> > were always "eventually".
Anonymous
a b à CPUs
August 12, 2004 7:40:41 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

JK wrote:
> It seems like Intel wants to stick to its theme that 64 bits is not yet needed
> for the desktop pc user, but is needed in the server space. That is why the
> P4s with 64 bit compatibility are being called server chips. It will be
> interesting
> to see how soon those chips are available for consumers to purchase, and
> how they will be priced.

The prime use for the 64 bit Xeon is likely to be for better performance
for 32 bit applications. With more cache and faster FSB the processor
should be 10-15% faster for many CPU-bound applications. If prices are
reasonable it might be a good choice for some uses, even single CPU
applications, since the HT can provide some of the benefits of SMP.

--
bill davidsen (davidsen@darkstar.prodigy.com)
SBC/Prodigy Yorktown Heights NY data center
Project Leader, USENET news
http://newsgroups.news.prodigy.com
August 12, 2004 7:40:42 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Do you have any links to benchmarks for the 64 bit Pentium 4s?

Bill Davidsen wrote:

> JK wrote:
> > It seems like Intel wants to stick to its theme that 64 bits is not yet needed
> > for the desktop pc user, but is needed in the server space. That is why the
> > P4s with 64 bit compatibility are being called server chips. It will be
> > interesting
> > to see how soon those chips are available for consumers to purchase, and
> > how they will be priced.
>
> The prime use for the 64 bit Xeon is likely to be for better performance
> for 32 bit applications. With more cache and faster FSB the processor
> should be 10-15% faster for many CPU-bound applications. If prices are
> reasonable it might be a good choice for some uses, even single CPU
> applications, since the HT can provide some of the benefits of SMP.
>
> --
> bill davidsen (davidsen@darkstar.prodigy.com)
> SBC/Prodigy Yorktown Heights NY data center
> Project Leader, USENET news
> http://newsgroups.news.prodigy.com
Anonymous
a b à CPUs
August 12, 2004 8:08:43 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Bill Davidsen wrote:
> The prime use for the 64 bit Xeon is likely to be for better
> performance for 32 bit applications. With more cache and faster FSB
> the processor should be 10-15% faster for many CPU-bound
> applications. If prices are reasonable it might be a good choice for
> some uses, even single CPU applications, since the HT can provide
> some of the benefits of SMP.

10-15% seems a little optimistic for just an FSB and cache increase.

Yousuf Khan
Anonymous
a b à CPUs
August 13, 2004 7:56:04 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

JK wrote:
> Do you have any links to benchmarks for the 64 bit Pentium 4s?
>
> Bill Davidsen wrote:
>
>
>>JK wrote:
>>
>>>It seems like Intel wants to stick to its theme that 64 bits is not yet needed
>>>for the desktop pc user, but is needed in the server space. That is why the
>>>P4s with 64 bit compatibility are being called server chips. It will be
>>>interesting
>>>to see how soon those chips are available for consumers to purchase, and
>>>how they will be priced.
>>
>>The prime use for the 64 bit Xeon is likely to be for better performance
>>for 32 bit applications. With more cache and faster FSB the processor
>>should be 10-15% faster for many CPU-bound applications. If prices are
>>reasonable it might be a good choice for some uses, even single CPU
>>applications, since the HT can provide some of the benefits of SMP.

Just the articles in InfoWorld. I assume they are online, but I no
longer have the mag. If you can't find them I'll go look in the library.
They were around 15%.

--
bill davidsen (davidsen@darkstar.prodigy.com)
SBC/Prodigy Yorktown Heights NY data center
Project Leader, USENET news
http://newsgroups.news.prodigy.com
August 13, 2004 7:56:05 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

I found this article on the 64 bit Xeon 3.6 ghz.

http://www.anandtech.com/linux/showdoc.aspx?i=2163&p=1

The Xeon 3.6 ghz looks like a poor performer compared to the
much less expensive Opteron 150 in those 64 bit tests.

Bill Davidsen wrote:

> JK wrote:
> > Do you have any links to benchmarks for the 64 bit Pentium 4s?
> >
> > Bill Davidsen wrote:
> >
> >
> >>JK wrote:
> >>
> >>>It seems like Intel wants to stick to its theme that 64 bits is not yet needed
> >>>for the desktop pc user, but is needed in the server space. That is why the
> >>>P4s with 64 bit compatibility are being called server chips. It will be
> >>>interesting
> >>>to see how soon those chips are available for consumers to purchase, and
> >>>how they will be priced.
> >>
> >>The prime use for the 64 bit Xeon is likely to be for better performance
> >>for 32 bit applications. With more cache and faster FSB the processor
> >>should be 10-15% faster for many CPU-bound applications. If prices are
> >>reasonable it might be a good choice for some uses, even single CPU
> >>applications, since the HT can provide some of the benefits of SMP.
>
> Just the articles in InfoWorld. I assume they are online, but I no
> longer have the mag. If you can't find them I'll go look in the library.
> They were around 15%.
>
> --
> bill davidsen (davidsen@darkstar.prodigy.com)
> SBC/Prodigy Yorktown Heights NY data center
> Project Leader, USENET news
> http://newsgroups.news.prodigy.com
Anonymous
a b à CPUs
August 13, 2004 9:16:23 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Thu, 12 Aug 2004 04:08:43 GMT, "Yousuf Khan" <bbbl67@ezrs.com>
wrote:
>Bill Davidsen wrote:
>> The prime use for the 64 bit Xeon is likely to be for better
>> performance for 32 bit applications. With more cache and faster FSB
>> the processor should be 10-15% faster for many CPU-bound
>> applications. If prices are reasonable it might be a good choice for
>> some uses, even single CPU applications, since the HT can provide
>> some of the benefits of SMP.
>
>10-15% seems a little optimistic for just an FSB and cache increase.

I don't know, the P4 saw a fairly big jump when going from 533MT/s to
800MT/s bus speeds (a 10% improvement on applications was not at all
uncommon), I suspect that the Xeon will show a similar jump as well.
It should especially help even more for dual-CPU systems where the
Xeon is even more restrained by the memory subsystem.

-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca
Anonymous
a b à CPUs
August 13, 2004 8:23:19 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Tony Hill wrote:
>> 10-15% seems a little optimistic for just an FSB and cache increase.
>
> I don't know, the P4 saw a fairly big jump when going from 533MT/s to
> 800MT/s bus speeds (a 10% improvement on applications was not at all
> uncommon), I suspect that the Xeon will show a similar jump as well.
> It should especially help even more for dual-CPU systems where the
> Xeon is even more restrained by the memory subsystem.

Most of those P4's also accompanied the FSB increase with increases in
overall frequency. A 10% increase is believable if you combine the FSB
increase with the overall frequency increase together. Perhaps 5% due to
FSB, and 5% due to overall frequency?

Yousuf Khan
Anonymous
a b à CPUs
August 14, 2004 8:43:01 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Fri, 13 Aug 2004 16:23:19 GMT, "Yousuf Khan" <bbbl67@ezrs.com>
wrote:
>Tony Hill wrote:
>>> 10-15% seems a little optimistic for just an FSB and cache increase.
>>
>> I don't know, the P4 saw a fairly big jump when going from 533MT/s to
>> 800MT/s bus speeds (a 10% improvement on applications was not at all
>> uncommon), I suspect that the Xeon will show a similar jump as well.
>> It should especially help even more for dual-CPU systems where the
>> Xeon is even more restrained by the memory subsystem.
>
>Most of those P4's also accompanied the FSB increase with increases in
>overall frequency. A 10% increase is believable if you combine the FSB
>increase with the overall frequency increase together. Perhaps 5% due to
>FSB, and 5% due to overall frequency?

Not really, for example there was a 2.8GHz P4 running off a 533MT/s
bus as well as one running off an 800MT/s bus. I would guess that the
average speed-up for applications was around 5%, but there definitely
were some applications that saw a 10%+ improvement just from the
increased bus speed (same motherboard, memory, etc).

Presumably this difference would tend to grow as clock speeds went up
(the Xeons in question were running at 3.6GHz) and if you add in any
improvements in cache it could make more of a difference still. Of
course, in the case of the Xeons there are a LOT of factors involved,
not the least of which being that it's a whole new core (the
Nocona/Prescott vs. Prestonia/Northwood comparison), and a new
motherboard + chipset.

Still, when you get right down to it, the Xeon, particularly in dual
and quad CPU setups, was getting rather limited by it's bus as
compared to some of it's competitors, so this increase is bound to
help.

-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca
Anonymous
a b à CPUs
August 17, 2004 8:45:29 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

JK wrote:
> I found this article on the 64 bit Xeon 3.6 ghz.
>
> http://www.anandtech.com/linux/showdoc.aspx?i=2163&p=1
>
> The Xeon 3.6 ghz looks like a poor performer compared to the
> much less expensive Opteron 150 in those 64 bit tests.

The point I (and InfoWorld) am trying to make is that these processors
can and probably should be thought of as better 32 bit units, and the 64
bit capability as a bonus. The anandtech review is a good example of
finding something the CPU does poorly and using benchmarks to test that.

A better test would be running the 32 bit benchmarks, and since these
are most commonly used in servers testing as 32 bit servers running
server applications, preferably both for DOS and Linux, would be more
useful to the typical buyer.

I am not predicting the results, just saying the tests were not
representative of typical use for Xeon.

--
bill davidsen (davidsen@darkstar.prodigy.com)
SBC/Prodigy Yorktown Heights NY data center
Project Leader, USENET news
http://newsgroups.news.prodigy.com
August 17, 2004 8:45:30 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

The purpose of having a chip with a 64 bit mode is for a seamless
gradual transition to 64 bit software while still running 32 bit code.
If the 64 bit mode performs much worse than a competing product,
then it doesn't make sense to buy the chip, but rather to buy one that
also has great performance with 64 bit software. There have been
many articles comparing 32 bit performance. There is also this
article about 64 bit performance.

http://www.computerworld.com.sg/pcwsg.nsf/0/EAAFAE24D76...



Bill Davidsen wrote:

> JK wrote:
> > I found this article on the 64 bit Xeon 3.6 ghz.
> >
> > http://www.anandtech.com/linux/showdoc.aspx?i=2163&p=1
> >
> > The Xeon 3.6 ghz looks like a poor performer compared to the
> > much less expensive Opteron 150 in those 64 bit tests.
>
> The point I (and InfoWorld) am trying to make is that these processors
> can and probably should be thought of as better 32 bit units, and the 64
> bit capability as a bonus. The anandtech review is a good example of
> finding something the CPU does poorly and using benchmarks to test that.
>
> A better test would be running the 32 bit benchmarks, and since these
> are most commonly used in servers testing as 32 bit servers running
> server applications, preferably both for DOS and Linux, would be more
> useful to the typical buyer.
>
> I am not predicting the results, just saying the tests were not
> representative of typical use for Xeon.
>
> --
> bill davidsen (davidsen@darkstar.prodigy.com)
> SBC/Prodigy Yorktown Heights NY data center
> Project Leader, USENET news
> http://newsgroups.news.prodigy.com
August 17, 2004 5:33:16 PM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

"Yousuf Khan" <bbbl67@ezrs.com> wrote in message news:<XV5Tc.392786$rCA1.362422@news01.bloor.is.net.cable.rogers.com>...
> Tony Hill wrote:
> >> 10-15% seems a little optimistic for just an FSB and cache increase.
> >
> > I don't know, the P4 saw a fairly big jump when going from 533MT/s to
> > 800MT/s bus speeds (a 10% improvement on applications was not at all
> > uncommon), I suspect that the Xeon will show a similar jump as well.
> > It should especially help even more for dual-CPU systems where the
> > Xeon is even more restrained by the memory subsystem.
>
> Most of those P4's also accompanied the FSB increase with increases in
> overall frequency. A 10% increase is believable if you combine the FSB
> increase with the overall frequency increase together. Perhaps 5% due to
> FSB, and 5% due to overall frequency?
>
> Yousuf Khan

Actually I remember those reviews. The clock speed actually went
*down* for the top of the line CPU at the time: 3.06 down to 3.00.

A bigger culprint was (IMO) that Canterwood/Springdale were a great
chipset right out of the gate.
Anonymous
a b à CPUs
September 2, 2004 12:47:52 AM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Tony Hill wrote:
> On Fri, 13 Aug 2004 16:23:19 GMT, "Yousuf Khan" <bbbl67@ezrs.com>
> wrote:
>
>>Tony Hill wrote:
>>
>>>>10-15% seems a little optimistic for just an FSB and cache increase.
>>>
>>>I don't know, the P4 saw a fairly big jump when going from 533MT/s to
>>>800MT/s bus speeds (a 10% improvement on applications was not at all
>>>uncommon), I suspect that the Xeon will show a similar jump as well.
>>>It should especially help even more for dual-CPU systems where the
>>>Xeon is even more restrained by the memory subsystem.
>>
>>Most of those P4's also accompanied the FSB increase with increases in
>>overall frequency. A 10% increase is believable if you combine the FSB
>>increase with the overall frequency increase together. Perhaps 5% due to
>>FSB, and 5% due to overall frequency?
>
>
> Not really, for example there was a 2.8GHz P4 running off a 533MT/s
> bus as well as one running off an 800MT/s bus. I would guess that the
> average speed-up for applications was around 5%, but there definitely
> were some applications that saw a 10%+ improvement just from the
> increased bus speed (same motherboard, memory, etc).
>
> Presumably this difference would tend to grow as clock speeds went up
> (the Xeons in question were running at 3.6GHz) and if you add in any
> improvements in cache it could make more of a difference still. Of
> course, in the case of the Xeons there are a LOT of factors involved,
> not the least of which being that it's a whole new core (the
> Nocona/Prescott vs. Prestonia/Northwood comparison), and a new
> motherboard + chipset.
>
> Still, when you get right down to it, the Xeon, particularly in dual
> and quad CPU setups, was getting rather limited by it's bus as
> compared to some of it's competitors, so this increase is bound to
> help.

Running with HT on increases cache misses, larger cache and faster main
memory will give an improvement there.

--
-bill davidsen (davidsen@tmr.com)
"The secret to procrastination is to put things off until the
last possible moment - but no longer" -me
!