It's all over for the P4

[Guest]

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

salfter@salfter.diespammersdie.dyndns.org (Scott Alfter) wrote:

> Intel to 'ditch' Pentium 4 core after Prescott

P4's not a bad chip in it's Northwood/.13um iteration, which is what
it was mainly designed for. (I believe that all new CPU's are
designed for one process generation ahead of what's available upon
release.)

Too bad it turned out to be a "one generation wonder"....

 

[Guest]

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

On Mon, 10 May 2004 21:29:23 GMT, "Yousuf Khan"
<news.tally.bbbl67@spamgourmet.com> wrote:

>RusH <logistyka1@pf.pl> wrote:
>> "AD." <me@privacy.net> wrote :
>>
>>> On Sat, 08 May 2004 01:50:24 +0000, gaffo wrote:
>>>
>>>> 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.
>>
>> I seem to remember the i820 chipset ... had errors and was rolled back
>> from the market
>
>Actually, no, the i820 had no problems with RDRAM, it worked fine, albeit
>just slowly. It was actually slower than the more primitive i815 chipset
>which used just single-channel SDR, but still outperformed the RDR. The 820
>had a secondary problem when using a Memory Hub Translator which converted
>SDR signals into RDR signals. The MHT had "signal integrity" problems or
>something like that. 🙂

The word from "inside Intel" was that although the problem was aggravated
by the MTH the real problem was the DRDRAM channel's "negative timing
margin":
http://www.reed-electronics.com/electronicnews/index.asp?layout=article&articleId=CA50587&rid=0&rme=0&cfd=1
This was also illustrated by the reduction in RIMM count per channel - the
mbrd recall at the 11th hour. Even 6months or so later, around the time
when the MTH was withdrawn, Dell had a 3month backlog on PC800 DRDRAM
systems and encouraged people to just take the PC600 stuff. Yes the i820
and the i840 both had problems.

Rgds, George Macdonald

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

 

[Guest]

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

On Mon, 10 May 2004 17:01:02 -0500, Ed wrote:

> Intel needs to design something to compete with AMD's K9, forget the K8.

I await the dog jokes

Cheers
Anton

 

[Guest]

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

On a sunny day (Mon, 10 May 2004 22:54:14 -0400) it happened KR Williams
<krw@att.biz> wrote in <MPG.1b0a0989658ffdfb989860@news1.news.adelphia.net>:

>In article <l83u90143416md67he4ttm0s6k3t009pv0@4ax.com>,
>fammacd=!SPAM^nothanks@tellurian.com says...
>> On Sat, 8 May 2004 12:06:00 -0400, KR Williams <krw@att.biz> wrote:
>>
>> >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.🙂
>
>Intel's P4 and Rambust woulda conquered the world, if the
>opposing "organization" of Macdonald, Kent, Hill, Kahn, Carbon,
>and Williams,
You are seriously misinformed, that last name had nothing to do with it.
JP

 

[Guest]

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

On Tue, 11 May 2004 15:02:17 GMT, Jan Panteltje <pNaonStpealmtje@yahoo.com>
wrote:

>On a sunny day (Mon, 10 May 2004 22:54:14 -0400) it happened KR Williams
><krw@att.biz> wrote in <MPG.1b0a0989658ffdfb989860@news1.news.adelphia.net>:
>
>>In article <l83u90143416md67he4ttm0s6k3t009pv0@4ax.com>,
>>fammacd=!SPAM^nothanks@tellurian.com says...
>>> On Sat, 8 May 2004 12:06:00 -0400, KR Williams <krw@att.biz> wrote:
>>>
>>> >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.🙂
>>
>>Intel's P4 and Rambust woulda conquered the world, if the
>>opposing "organization" of Macdonald, Kent, Hill, Kahn, Carbon,
>>and Williams,
>You are seriously misinformed, that last name had nothing to do with it.

Your windmill is err, tilting Jan.;-)

Rgds, George Macdonald

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

 

[Guest]

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

On Mon, 10 May 2004 22:54:14 -0400, KR Williams <krw@att.biz> wrote:

>In article <vd3u9059pan7mg744q4r4na5nqo8j3u4le@4ax.com>,
>fammacd=!SPAM^nothanks@tellurian.com says...
>> On Sun, 09 May 2004 02:51:03 GMT, daytripper <day_trippr@REMOVEyahoo.com>
>> wrote:
>>
>> >On Sat, 08 May 2004 17:43:13 -0400, George Macdonald
>> ><fammacd=!SPAM^nothanks@tellurian.com> wrote:
>>
>> >>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?
>>
>> 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.
>
>Give us a hint of the second-derivitave and we can all make some
>cash off the differentials. ;-) OTOH, I don't think I could
>touch that money. Liek M$, ...too dirty.

Call up Martha... see what Sam thinks??

Rgds, George Macdonald

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

 

[Guest]

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

On Mon, 10 May 2004 22:54:14 -0400, KR Williams <krw@att.biz> wrote:

>In article <l83u90143416md67he4ttm0s6k3t009pv0@4ax.com>,
>fammacd=!SPAM^nothanks@tellurian.com says...
>> On Sat, 8 May 2004 12:06:00 -0400, KR Williams <krw@att.biz> wrote:
>>
>> >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.🙂
>
>Intel's P4 and Rambust woulda conquered the world, if the
>opposing "organization" of Macdonald, Kent, Hill, Kahn, Carbon,
>and Williams, weren't so blasphemous. The venerable lawfirm of
>Rambust, Shambust, and Scambust could never recover. Of
>"Course" some tried, but it was by then futile. ...and it's all
>*YOUR* fault George!

Oh I'll accept some of the uhh, blame, along with the rest of you🙂 but in
here it was really mostly the work of John Corse himself. I recall telling
him he was doing more damage than good for his cause but he just kept right
on going.

>The one thing they missed was calling their uncle RICO. ...what a
>racket!

Ya don't think we're gonna all get an offer we "can't refuse"?

Rgds, George Macdonald

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

 

[Guest]

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

In article <k2o5a0dpfvjpcqdg39ji3bklo0stj2nrrg@4ax.com>,
fammacd=!SPAM^nothanks@tellurian.com says...
> On Mon, 10 May 2004 22:54:14 -0400, KR Williams <krw@att.biz> wrote:
>
> >In article <l83u90143416md67he4ttm0s6k3t009pv0@4ax.com>,
> >fammacd=!SPAM^nothanks@tellurian.com says...
> >> On Sat, 8 May 2004 12:06:00 -0400, KR Williams <krw@att.biz> wrote:
> >>
> >> >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.🙂
> >
> >Intel's P4 and Rambust woulda conquered the world, if the
> >opposing "organization" of Macdonald, Kent, Hill, Kahn, Carbon,
> >and Williams, weren't so blasphemous. The venerable lawfirm of
> >Rambust, Shambust, and Scambust could never recover. Of
> >"Course" some tried, but it was by then futile. ...and it's all
> >*YOUR* fault George!
>
> Oh I'll accept some of the uhh, blame, along with the rest of you🙂 but in
> here it was really mostly the work of John Corse himself. I recall telling
> him he was doing more damage than good for his cause but he just kept right
> on going.
>
> >The one thing they missed was calling their uncle RICO. ...what a
> >racket!
>
> Ya don't think we're gonna all get an offer we "can't refuse"?

Actually, I'd rather like "an offer that I cannot refuse". (21
calendar days 'til 30 years time served '-).

--
Keith

 

[Guest]

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

In article <dq54a0hcd3q503kjtqk7r3las7uj291tof@4ax.com>,
fammacd=!SPAM^nothanks@tellurian.com says...
> On Mon, 10 May 2004 22:54:14 -0400, KR Williams <krw@att.biz> wrote:
>
> >In article <vd3u9059pan7mg744q4r4na5nqo8j3u4le@4ax.com>,
> >fammacd=!SPAM^nothanks@tellurian.com says...
> >> On Sun, 09 May 2004 02:51:03 GMT, daytripper <day_trippr@REMOVEyahoo.com>
> >> wrote:
> >>
> >> >On Sat, 08 May 2004 17:43:13 -0400, George Macdonald
> >> ><fammacd=!SPAM^nothanks@tellurian.com> wrote:
> >>
> >> >>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?
> >>
> >> 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.
> >
> >Give us a hint of the second-derivitave and we can all make some
> >cash off the differentials. ;-) OTOH, I don't think I could
> >touch that money. Liek M$, ...too dirty.
>
> Call up Martha... see what Sam thinks??

Sam Walton? I don't think he has much on his mind anymore. Well
he has the dirt on 'em. ;-)

--
Keith

 

[Guest]

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

On Thu, 13 May 2004 00:01:52 -0400, KR Williams <krw@att.biz> wrote:

>In article <dq54a0hcd3q503kjtqk7r3las7uj291tof@4ax.com>,
>fammacd=!SPAM^nothanks@tellurian.com says...

>> Call up Martha... see what Sam thinks??
>
>Sam Walton? I don't think he has much on his mind anymore. Well
>he has the dirt on 'em. ;-)

No - Sam Waksal, the guy who was the principal at ImClone... the one who
err, didn't tell her that the stock was gonna tank the next day.🙂

Rgds, George Macdonald

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

 

[Guest]

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

On a sunny day (Wed, 12 May 2004 22:49:07 -0400) it happened George Macdonald
<fammacd=!SPAM^nothanks@tellurian.com> wrote in
<li54a0deot872bkaivoegrnsrq50mq6css@4ax.com>:

>On Tue, 11 May 2004 15:02:17 GMT, Jan Panteltje <pNaonStpealmtje@yahoo.com>
>wrote:
>
>>On a sunny day (Mon, 10 May 2004 22:54:14 -0400) it happened KR Williams
>><krw@att.biz> wrote in <MPG.1b0a0989658ffdfb989860@news1.news.adelphia.net>:
>>
>>>In article <l83u90143416md67he4ttm0s6k3t009pv0@4ax.com>,
>>>fammacd=!SPAM^nothanks@tellurian.com says...
>>>> On Sat, 8 May 2004 12:06:00 -0400, KR Williams <krw@att.biz> wrote:
>>>>
>>>> >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.🙂
>>>
>>>Intel's P4 and Rambust woulda conquered the world, if the
>>>opposing "organization" of Macdonald, Kent, Hill, Kahn, Carbon,
>>>and Williams,
>>You are seriously misinformed, that last name had nothing to do with it.
>
>Your windmill is err, tilting Jan.;-)
>
>Rgds, George Macdonald
I have changed to nuclear power.
Greetings
JP

 

[Guest]

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

In article <qt76a0h1pqbieeb4l4einedr0svj3a2d2e@4ax.com>,
fammacd=!SPAM^nothanks@tellurian.com says...
> On Thu, 13 May 2004 00:01:52 -0400, KR Williams <krw@att.biz> wrote:
>
> >In article <dq54a0hcd3q503kjtqk7r3las7uj291tof@4ax.com>,
> >fammacd=!SPAM^nothanks@tellurian.com says...
>
> >> Call up Martha... see what Sam thinks??
> >
> >Sam Walton? I don't think he has much on his mind anymore. Well
> >he has the dirt on 'em. ;-)
>
> No - Sam Waksal, the guy who was the principal at ImClone... the one who
> err, didn't tell her that the stock was gonna tank the next day.🙂

Whew! I thought for a minute you were talking about Sam
Palmisano! ;-)

--
Keith

 

[Guest]

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

On Mon, 10 May 2004 06:00:06 GMT, "Yousuf Khan"
<news.tally.bbbl67@spamgourmet.com> wrote:
>Tony Hill <hilla_nospam_20@yahoo.ca> wrote:
>> 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. 🙂

Ohh.. you noticed that too? :>

The simple fact of the matter is that AMD did a LOT of smart things
with the Athlon64/Opteron. I wouldn't say that it's an ideal design,
but I think that Intel would be smart to learn from what AMD has done.

Interesting point of note: Hector Ruiz, CEO of AMD, recently said in
an interview that they would be releasing dual-core Opteron chips next
year. These chips will have independent L2 caches, though naturally
they'll share a memory controller and the hypertransport controllers.
What is perhaps more interesting is that he said the chips would be
pin-compatible and infrastructure compatible, ie a drop-in replacement
for current Opterons!

I *want* one now! :>

-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca

 

[Guest]

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

"AD." <me@privacy.net> wrote:

>On Mon, 10 May 2004 17:01:02 -0500, Ed wrote:
>
>> Intel needs to design something to compete with AMD's K9, forget the K8.
>
>I await the dog jokes

They'll probably skip "K9", just like Intel skipped "666".

 

[Guest]

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

chrisv <chrisv@nospam.invalid> wrote:
> "AD." <me@privacy.net> wrote:
>
>> On Mon, 10 May 2004 17:01:02 -0500, Ed wrote:
>>
>>> Intel needs to design something to compete with AMD's K9, forget
>>> the K8.
>>
>> I await the dog jokes
>
> They'll probably skip "K9", just like Intel skipped "666".

I thought they skipped "Sexium"? Or maybe it was "Hexium"? Neither one
would've been an ideal marketing choice.

Yousuf Khan

 

[mygarbage2000]

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

On Thu, 13 May 2004 23:38:17 -0400, Tony Hill
<hilla_nospam_20@yahoo.ca> wrote:


>>Tony Hill <hilla_nospam_20@yahoo.ca> wrote:
....snip...
>
>Interesting point of note: Hector Ruiz, CEO of AMD, recently said in
>an interview that they would be releasing dual-core Opteron chips next
>year. These chips will have independent L2 caches, though naturally
>they'll share a memory controller and the hypertransport controllers.
>What is perhaps more interesting is that he said the chips would be
>pin-compatible and infrastructure compatible, ie a drop-in replacement
>for current Opterons!
>
>I *want* one now! :>
>
>-------------
>Tony Hill
>hilla <underscore> 20 <at> yahoo <dot> ca
Gee, looks like my humble MSI K8T (just ordered it with 2*242) will
one day proudly host a _quad_ system!!! I just pray these up and
coming puppies will not have voltages or bus or some other
requirements outside the board capabilities. Also hope MSI will
update the BIOS to accomodate them.

 

[Guest]

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

On Sat, 15 May 2004 22:22:57 GMT, "nobody@nowhere.net"
<MyGarbage2000@hotmail.com> wrote:
>On Thu, 13 May 2004 23:38:17 -0400, Tony Hill
><hilla_nospam_20@yahoo.ca> wrote:
>>Interesting point of note: Hector Ruiz, CEO of AMD, recently said in
>>an interview that they would be releasing dual-core Opteron chips next
>>year. These chips will have independent L2 caches, though naturally
>>they'll share a memory controller and the hypertransport controllers.
>>What is perhaps more interesting is that he said the chips would be
>>pin-compatible and infrastructure compatible, ie a drop-in replacement
>>for current Opterons!
>>
>>I *want* one now! :>
>>
>Gee, looks like my humble MSI K8T (just ordered it with 2*242) will
>one day proudly host a _quad_ system!!! I just pray these up and
>coming puppies will not have voltages or bus or some other
>requirements outside the board capabilities. Also hope MSI will
>update the BIOS to accomodate them.

If old Hector was telling the truth and the chips really ARE
infrastructure compatible, then yes, they should work just fine in
your system (with a BIOS update of course). That would be quite an
impressive feat if they pull it off, and probably the reason why in
the interview Hector was saying that these chips were going to "Shock
the hell out of everyone". FWIW here is the interview:

http://www.eweek.com/article2/0,1759,1574331,00.asp


-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca

 

[Guest]

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

nobody@nowhere.net <MyGarbage2000@hotmail.com> wrote:
> Gee, looks like my humble MSI K8T (just ordered it with 2*242) will
> one day proudly host a _quad_ system!!! I just pray these up and
> coming puppies will not have voltages or bus or some other
> requirements outside the board capabilities. Also hope MSI will
> update the BIOS to accomodate them.

Is that an Opteron board or an Athlon 64 board? I doubt they'll be making it
available for Athlon 64 upgrades, just Opteron upgrades.

Yousuf Khan

 

[mygarbage2000]

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

On Sat, 15 May 2004 23:44:43 GMT, "Yousuf Khan"
<news.tally.bbbl67@spamgourmet.com> wrote:

>nobody@nowhere.net <MyGarbage2000@hotmail.com> wrote:
>> Gee, looks like my humble MSI K8T (just ordered it with 2*242) will
>> one day proudly host a _quad_ system!!! I just pray these up and
>> coming puppies will not have voltages or bus or some other
>> requirements outside the board capabilities. Also hope MSI will
>> update the BIOS to accomodate them.
>
>Is that an Opteron board or an Athlon 64 board? I doubt they'll be making it
>available for Athlon 64 upgrades, just Opteron upgrades.
>
> Yousuf Khan
>
It's dual socket 940 board, MSI K8T, aka MASTER2-FAR. Supports both
Opteron and A64 FX, though the last one only in single CPU mode. The
cheapest of all dual 940 - can be had around $200 retail boxed.
No-frill board - ATX format, just one socket interfaces the memory,
only 4 32-bit PCI slots, only 2 serial ATA ports, no firewire - only
the most basic stuff. It could use a few 64-bit PCI slots, and would
be nice to connect both sockets to their own memory banks - but heck,
then it would be called K8W Thunder, sell around $450 and require
special (read - expensive!) EATX case and power supply.