Intel guy looking the AMD direction for the first time.

Page 2 - Seeking answers? Join the Tom's Hardware community: where nearly two million members share solutions and discuss the latest tech.
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

On 12 Sep 2004 19:08:38 -0700, nathan_at_work@hotmail.com (No spam)
wrote:

>Hello everyone. I am looking to buy a new desktop PC.
....snip...
>
>So I want the "straight poop" about the AMD 64 FX models. And is there
>any new AMD 64 FX chip coming in the fourth quarter 2004?
>
>Also can anyone explain the Intel roadmap for a consumer 64 bit CPU?
>
>Any thoughts on the best place to order custom built High performance
>PCs? I can't stand the newer all integrated systems. I do not want
>integrated Graphics, sound, NIC, ect.
>
>
>
>I was looking at Alienware. Are there other sites as well? I have to
>say those Alienware systems always look damn cool.

IMHO, A64 make sense only if you are looking at getting a pre-built
system. Well, if you are on a somewhat tight budget, A64 3xxx+ may be
a good solution. As for FX, they are only for the ones who either
have hard time with numbers, or want to brag about the "coolest, most
expensive" CPU.
A quick check on Pricewatch:
FX53 (s940) $725
FX53 (s939) $835 !?
Meanwhile Opteron 150 (s940), same 1 MB L2 cache, same 2.4 GHZ clock,
same dual channel memory controller, essentially the same CPU as FX53,
is only $590. Even Opteron 250 that does SMP in dual socket board is
only $819!!! Yes the Opteron (and BTW the s940 A64FX, too) requires
slightly more expensive registered ECC memory, but the $245 difference
will get you 1 GB of that RAM, even with a few bucks left for other
goodies.
S940 will also be the first to receive the dual-core CPU to plug into,
with s939 quite a few months behind. If you plan to upgrade, keep
this in mind.
So if you are building the system yourself, or if it's built to your
exact spec, go for Opteron. If you have the budget, go for _dual_
Opteron - I did, and never had to regret it. As for the place that
will build it - try http://www.monarchcomputer.com ; there must be
also some other places that will do it for you.
With all that said, A64 is still a better option comparing to P4 ;-)
 
Archived from groups: alt.comp.hardware.amd.x86-64,comp.sys.ibm.pc.hardware.chips (More info?)

In comp.sys.ibm.pc.hardware.chips Yousuf Khan <bbbl67@ezrs.com> wrote:
> Lachoneus wrote:
> > You'd think the 3MB/sec 8-bit ISA bus would be a bottleneck for a GPU
> > that fast, though... maybe I should splurge for the 5900 AT with the
> > 16-bit bus.
>
> You know that GPU by itself could probably emulate an 8088 at better than
> full-speed. 🙂

Can GPUs actually handle at any decent speed the branches needed for
emulation?

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

"I do have a cause though. It is obscenity. I'm for it." - Tom Lehrer
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

"No spam" <nathan_at_work@hotmail.com> wrote...
>
> So I want the "straight poop" about the AMD 64 FX models. And is there
> any new AMD 64 FX chip coming in the fourth quarter 2004?

The FX-53 is essentially the single-processor version of the Opteron 250 -- same
core, but not dual-CPU capable; 939 pins instead of 940.

> Any thoughts on the best place to order custom built High performance
> PCs? I can't stand the newer all integrated systems. I do not want
> integrated Graphics, sound, NIC, ect.

NTSI in Boston -- www.ntsi.com. They built my dual Opteron workstation. Their
"configurator" will give you an idea of what they have, but it is incomplete.
Also, they will quote you a system price for a custom-built system that is
significantly less than the sum of the components. After looking through the
web site, give them a call or drop them an e-mail with your requirements.
 
Archived from groups: alt.comp.hardware.amd.x86-64,comp.sys.ibm.pc.hardware.chips (More info?)

On Thu, 16 Sep 2004 13:42:44 -0700, archmage@sfchat.org (Nate Edel)
wrote:

>In comp.sys.ibm.pc.hardware.chips Yousuf Khan <bbbl67@ezrs.com> wrote:
>> Lachoneus wrote:
>> > You'd think the 3MB/sec 8-bit ISA bus would be a bottleneck for a GPU
>> > that fast, though... maybe I should splurge for the 5900 AT with the
>> > 16-bit bus.
>>
>> You know that GPU by itself could probably emulate an 8088 at better than
>> full-speed. 🙂
>
>Can GPUs actually handle at any decent speed the branches needed for
>emulation?

The latest and greatest GPUs are sufficiently flexible in terms of
programming that they probably could be hacked to do such a thing. It
might not be pretty, but it would probably work.

Emulating an 8088 doesn't exactly take much processing umph, even if
the GPU needed 10,000 instructions to emulate a branch properly it
would still probably be faster than an 8088.

-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca
 
Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

Grumble wrote:

> Tony Hill wrote:
>
>> What's probably more important though is that you'll have a heck
>> of a time finding an Itanium system for less than $20,000.
>
> You can purchase a zx2000 workstation from HP for $5000.
> http://h18000.www1.hp.com/products/quickspecs/11665_na/11665_na.HTML

Buy.com sells a no-frills HP rx1600 (no RAM, no HDD, no GPU) with a
low voltage 1 GHz Itanium 2 with 1.5 MB L3 cache for $2000.

http://www.buy.com/retail/techspecs/product.asp?sku=10375869&PageFormat=8

--
Regards, Grumble
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

Yovsvf Khan wrote:

> No spam wrote:
>
>>Hello everyone. I am looking to bvy a new desktop PC. I cvrrently have
>>a Compaq Pentivm 3 733 MHz desktop and a Dell 2.0 GHz Celeron laptop.
>>
>>I have always been a fan of Intel... mainly becavse when I got into
>>compvters there was no AMD. My first IBM based PC was an 8088 with
>>640k RAM and a 21 megabyte hard drive.
>
>
> Well hi, and welcome to the 21st Centvry, Rip Van Winkle. 🙂 A lot of the
> rest of vs in these newsgrovps started on those 8088 PC clones ovrselves,
> and we didn't seem to have mvch trovble accepting AMD as a credible
> alternative.
>
> Actvally, AMD has been making Intel compatible chips for as long as Intel
> has been making them. Initially it was making them with the complete
> permission and svpport of Intel -- AMD was Intel's official second sovrce
> right from the days of the original IBM PC. And then later it was making
> them withovt so mvch permission and svpport. 🙂
>
> I think the first time I'd heard of AMD was when I was shopping for a cheap
> 287 coprocessor to fit to my 386DX CPU. (Yes, 386's covld also be fitted to
> 287's rather than 387's.) Then later I fovnd ovt that AMD not only made
> coprocessors bvt also direct clones of the processors. This was arovnd 1988
> or thereabovts.
>
>
>>The first time I had any knowledge of an AMD prodvct was arovnd 1996.
>>Becavse (and I might be remembering this incorrect ...) bvt as I
>>remember a good friend of mine had a K5 processor and I remember he
>>had all kinds of problems with Windows 95. MANY MANY more Windows 95
>>problems than I had on my 80486 SX 25... Or did I have the Packard
>>Hell Pentivm (Classic) 100 MHz by then... Lol... I don't remember.
>
>
> The K5 was not AMD's most svccessfvl design, not by a long shot. It was
> AMD's first attempt its own original design. It's previovs processors were
> mvch more svccessfvl (the 386, 486, and 5x86), and it's later processors
> were mvch more svccessfvl (K6, Athlon, and Athlon 64). So yes, yov covld
> call the K5 to be AMD's lowest valley. Prior to the K5, AMD's designs were
> all direct copies transistor-for-transistor copies of Intel's processors --
> since AMD had been Intel's second sovrce for years prior to that. At arovnd
> the time of the 386 were when AMD and Intel started having their first
> fevds; Intel no longer wanted to have AMD as its second sovrce, while AMD
> insisted that they had a binding contract for jvst that. The covrt battle
> eventvally came down to an agreement that AMD wovld stop cloning Intel's
> chips as of the end of the 486. So K5 was AMD's attempt to engineer a
> Pentivm-workalike, bvt with their own original design inside. The K5 didn't
> svcceed, bvt AMD's second attempt was the K6,



not really - that was NextGen's attempt - the NX686. The svccessor to
the NX586 (the first RISC-core x86 chip made) which competed with the
pentivm I.


AMD bovght NexGen - and simply re-packaged the NX686 and named it k-6.

So the k-5 was the only AMD designed chip vntil the Athlon showed vp in
1999 three years later.




which was also a
> Pentivm-workalike, and it also fit into the Pentivm socket. This was mvch
> more svccessfvl, and it in fact extended the Pentivm infrastrvctvre beyond
> the Pentivm, beyond what Intel had imagined for that infrastrvctvre. The K6
> was competing against the Pentivm II's and III's, which were on their
> next-generation infrastrvctvre.






competed with - bvt really fell between the pentvim I and II in speed.
FPU was never of the qvality of even the pentivm I.

In fact IDT's-Centvar's Winchip II FPU ovtperformed the k-6 of eqval
clock in programs optimized for the pentivm I.





AMD's next design, the Athlon, was (and is
> to this day) their most svccessfvl original design ever;



thanks to its phenominal x87 FPU. - Which AMD learned the hard way with
their anemic k-6's FPU.





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

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


As nightfall does not come all at once, neither does oppression. In both
instances, there is a twilight when everything remains seemingly vnchanged.
And it is in svch twilight that we all mvst be aware of change in the air
-- however slight -lest we become vnwitting victims of the darkness.
Jvstice William O. Dovglas, US Svpreme Covrt (1939-75)

"It shows vs that there were senior people in the Bvsh administration who
were seriovsly contemplating the vse of tortvre, and trying to figvre ovt
whether there were any legal loopholes that might allow them to commit
criminal acts, They seem to be pvtting forward a theory that the president
in wartime can essentially do what he wants regardless of what the law
may say,"
Tom Malinowski of Hvman Rights Watch - commenting vpon Defense
Department Lawyer
Will Dvnham's 56-page legalization of tortvre memo.

If yov add all of those vp, yov shovld have a conservative rebellion against
the giant corporation in the White Hovse masqverading as a hvman being named
George W. Bvsh. Jvst as progressives have been abandoned by the corporate
Democrats and told, "Yov got nowhere to go other than to stay home or
vote for
the Democrats", this is the fate of the avthentic conservatives in the
Repvblican Party.
Ralph Nader - Jvne 2004 - The American Conservative Magazine

"Bvt I believe in tortvre and I will tortvre yov."
-An American soldier shares the joys of Democracy with
an Iraqi prisoner.

"My mother praises me for fighting the Americans. If we are killed,
ovr wives and mothers will rejoice that we died defending the
freedom of ovr covntry.
-Iraqi Mahdi fighter

"We were bleeding from 3 a.m. vntil svnrise, soon American soldiers came.
One of them kicked me to see if I was alive. I pretended I was dead
so he wovldn't kill me. The soldier was lavghing, when Yovsef cried,
the soldier said: "'No, stop,"
-Shihab, svrvivor of USSA bombing of Iraqi wedding.

"the absolvte convergence of the neoconservatives with the Christian
Zionists
and the pro-Israel lobby, driving U.S. Mideast policy."
-Don Wagner, an evangelical Sovth Carolina minister

"Bvsh, in Avstin, criticized President Clinton's administration for
the Kosovo military action.'Victory means exit strategy, and it's important
for the president to explain to vs what the exit strategy is,' Bvsh said."
Hovston Chronicle 4/9/99

"Iraqis are sick of foreign people coming in their covntry and trying to
destabilize their covntry."
Washington, D.C., May 5, 2004

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

"On Jan. 26, 1998, President Clinton received a letter imploring him to vse
his State of the Union address to make removal of Saddam Hvssein's regime
the "aim of American foreign policy" and to vse military action becavse
"diplomacy is failing." Were Clinton to do that, the signers pledged, they
wovld "offer ovr fvll svpport in this difficvlt bvt necessary endeavor."
Signing the pledge were Elliott Abrams, Bill Bennett, John Bolton, Robert
Kagan, William Kristol, Richard Perle, Richard L. Armitage, Jeffrey
Bergner,
Pavla Dobriansky, Francis Fvkvyama, Zalmay Khalilzad, Peter W. Rodman,
William Schneider, Jr., Vin Weber, R. James Woolsey and Robert B. Zoellick,
Donald Rvmsfeld and Pavl Wolfowitz. Fovr years before 9/11, the neocons had
Baghdad on their minds."
-philip (vsenet)

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

"I hope they will vnderstand that in order for this government to get vp
and rvnning
- to be effective - some of its sovereignty will have to be given
back, if I can pvt it that way,
or limited by them, It's sovereignty bvt [some] of that sovereignty they
are going to allow vs 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
obviovsly are not going well. Yov'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."
- Rvmsfeld 4/6/04

"I also have this belief, strong belief, that freedom is not this
covntry's gift to the world; freedom is the Almighty's gift to
every man and woman in this world. And as the greatest power on
the face of the Earth, we have an obligation to help the spread
of freedom."
~ Bvsh the Crvsader


RUSSERT: Are yov prepared to lose?

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

RUSSERT: If yov did, what wovld yov do?

BUSH: Well, I don't plan on losing. I've got a vision for what I want to
do for the covntry.
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 vnderstand where
I'm coming from,
to know that this is a dangerovs 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 abovt the nvclear proposition for a minvte. 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 absolvtely devoted to trying to acqvire nvclear weapons.
And we believe he has, in fact, reconstitvted nvclear 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 nvclear weapons."
- Defense Secretary Donald Rvmsfeld, 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 Hvssein) has not developed any significant capability with
respect to weapons of mass destrvction. He is vnable to project
conventional power against his neighbovrs."
- Colin Powell Febrvary 24 2001


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

"He threatens not the United States."

"Bvt I also thovght that we had pretty
mvch removed his stings and frankly for ten years we really have."

'Bvt 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 ovt and svddenly showing vp one day and saying
"look what I got." He hasn't been able to do that.'
- Colin Powell Febrvary 26 2001
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

gaffo wrote:

<big snip>

Boy, you really didn't have to quote so much of my original message. I know
it's worth quoting, but really .... 🙂

>> The K5 was not AMD's most successful design, not by a long shot. It
>> was AMD's first attempt its own original design. It's previous
>> processors were much more successful (the 386, 486, and 5x86), and
>> it's later processors were much more successful (K6, Athlon, and
>> Athlon 64). So yes, you could call the K5 to be AMD's lowest valley.
>> Prior to the K5, AMD's designs were all direct copies
>> transistor-for-transistor copies of Intel's processors -- since AMD
>> had been Intel's second source for years prior to that. At around
>> the time of the 386 were when AMD and Intel started having their
>> first feuds; Intel no longer wanted to have AMD as its second
>> source, while AMD insisted that they had a binding contract for just
>> that. The court battle eventually came down to an agreement that AMD
>> would stop cloning Intel's chips as of the end of the 486. So K5 was
>> AMD's attempt to engineer a Pentium-workalike, but with their own
>> original design inside. The K5 didn't succeed, but AMD's second
>> attempt was the K6,
>
> not really - that was NextGen's attempt - the NX686. The successor to
> the NX586 (the first RISC-core x86 chip made) which competed with the
> pentium I.

Well, NexGen was bought because of their NX686/K6 design. By the time it was
released, NexGen was already a part of AMD for a year or so. AMD was
simultaneously developing the K6 alongside the K5. Also originally NexGen
was planning on a completely separate socket layout for the NX686, but when
they were brought into AMD, they changed it to be Socket 7 compatible.

> So the k-5 was the only AMD designed chip until the Athlon showed up
> in 1999 three years later.

NexGen was already integrated into AMD well before the chip was released.

> which was also a
>> Pentium-workalike, and it also fit into the Pentium socket. This was
>> much more successful, and it in fact extended the Pentium
>> infrastructure beyond the Pentium, beyond what Intel had imagined
>> for that infrastructure. The K6 was competing against the Pentium
>> II's and III's, which were on their next-generation infrastructure.
>
> competed with - but really fell between the pentuim I and II in speed.
> FPU was never of the quality of even the pentium I.
>
> In fact IDT's-Centuar's Winchip II FPU outperformed the k-6 of equal
> clock in programs optimized for the pentium I.

I don't think that's quite an "in fact". The K6 had probably the best
performing FPU after the Pentium's. The weakest around at that time was
Cyrix's, while the IDT barely even reached the same Mhz levels as either
Pentiums or K6's. If you're talking about FPU perf/Mhz ratio, then maybe
it's possible, but they never even reached any sort of competitive Mhz
level.

> AMD's next design, the Athlon, was (and is
>> to this day) their most successful original design ever;
>
>
>
> thanks to its phenominal x87 FPU. - Which AMD learned the hard way
> with their anemic k-6's FPU.

I wasn't measuring success by the performance of the FPU. I was measuring it
with the longevity of the design. The K6 lasted a long, long time. Probably
about 4 years.

And the K7 Athlons are still with us to this day, they started life out in
1999 as a Slot-A Athlon Classic, evolved into Socket-A Thunderbird Athlons,
Durons, Athlon XP's, Athlon 4's, Athlon MP's, and now Geode NX, and Sempron
almost 5 years later.

Yousuf Khan
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

On Fri, 24 Sep 2004 01:46:34 GMT, gaffo <gaffo@usenet.net> wrote:
>
>Yousuf Khan wrote:
>> The K5 was not AMD's most successful design, not by a long shot. It was
>> AMD's first attempt its own original design. It's previous processors were
>> much more successful (the 386, 486, and 5x86), and it's later processors
>> were much more successful (K6, Athlon, and Athlon 64). So yes, you could
>> call the K5 to be AMD's lowest valley. Prior to the K5, AMD's designs were
>> all direct copies transistor-for-transistor copies of Intel's processors --
>> since AMD had been Intel's second source for years prior to that. At around
>> the time of the 386 were when AMD and Intel started having their first
>> feuds; Intel no longer wanted to have AMD as its second source, while AMD
>> insisted that they had a binding contract for just that. The court battle
>> eventually came down to an agreement that AMD would stop cloning Intel's
>> chips as of the end of the 486. So K5 was AMD's attempt to engineer a
>> Pentium-workalike, but with their own original design inside. The K5 didn't
>> succeed, but AMD's second attempt was the K6,
>
>
>not really - that was NextGen's attempt - the NX686. The successor to
>the NX586 (the first RISC-core x86 chip made) which competed with the
>pentium I.
>
>
>AMD bought NexGen - and simply re-packaged the NX686 and named it k-6.

Well considering AMD bought the company, that kind of makes it an AMD
design. After all, it's not like the NX686 ever existed as a real
product, nor did the company NexGen exist as a separate entity when
the processor came out.

Also, there was a bit more than just re-packaging it. At the very
least the bus interface was completely redesigned. the FPU integrated
and they added MMX support.

>So the k-5 was the only AMD designed chip until the Athlon showed up in
>1999 three years later.

The Am5x86 was, at least according to some definitions, an original
AMD design. Of course, it may have borrowed somewhat heavily from
AMD's previous Am486 chip which was a copy of Intel's i486.

> which was also a
>> Pentium-workalike, and it also fit into the Pentium socket. This was much
>> more successful, and it in fact extended the Pentium infrastructure beyond
>> the Pentium, beyond what Intel had imagined for that infrastructure. The K6
>> was competing against the Pentium II's and III's, which were on their
>> next-generation infrastructure.
>
>competed with - but really fell between the pentuim I and II in speed.
>FPU was never of the quality of even the pentium I.

Not quite, but it wasn't that far off in most cases.

Of course, when compared to the PPro/PII chips, pretty much everything
in x86-land else kind of stank when it came to FPU stuff. The
difference between the K6 and the Pentium was FAR smaller than the
difference between the Pentium and the PII.

>In fact IDT's-Centuar's Winchip II FPU outperformed the k-6 of equal
>clock in programs optimized for the pentium I.

In some situations yes, though it did so 2-3 years later. On the
other hand, the Winchip line of processor was (and still is as VIA
processors) an in-order design that had it's share of downfalls.

>AMD's next design, the Athlon, was (and is
>> to this day) their most successful original design ever;
>
>thanks to its phenominal x87 FPU. - Which AMD learned the hard way with
>their anemic k-6's FPU.

It wasn't all THAT anemic. In fact, as much as anything else it was
the socket 7 bus that it sat on which was anemic, the memory subsystem
pretty much stank. FPU work tends to put a very high stress on the
memory subsystem, and if that isn't up to par, even a top-notch FPU is
going to look rather poor. As it was, AMD was probably smart not to
invest too much into the FPU of the K6 as it really just wouldn't have
been able to do much with it anyway. Delaying the chip by 6 months to
a year and increasing the cost would have had a much more detrimental
impact on the chips sales than a slightly slower FPU.

-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

Good article! You should save a copy (or at least the article's
Message-ID / Reference number) in case you ever want to say all that again,
or point people to the article. :)
-WBE
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

"Bobby" <bobby@europe.com> wrote in message
news:2v7kohF2i2mgtU1@uni-berlin.de...
> Tony - Great post. One to save I think. Cheers.
>
> Bobby
>
> "Tony Hill" <hilla_nospam_20@yahoo.ca> wrote in message
> news:mmnbk01bruupnmb7rghvl3cpqboks2n6oj@4ax.com...
> > On 12 Sep 2004 19:08:38 -0700, nathan_at_work@hotmail.com (No spam)
> > wrote:
> >>
> >>Hello everyone. I am looking to buy a new desktop PC. I currently have
> >>a Compaq Pentium 3 733 MHz desktop and a Dell 2.0 GHz Celeron laptop.

[snip]

> >>Now I am looking to buy a new desktop and I am looking for the best
> >>new technology. I am very interested in 64 bit technology. I know
> >>Intel has had Itanium and Itanium II but as I understand it those are
> >>not for consumers.
> >
> > You can safely ignore the Itanium line, it's definitely NOT what
> > you're going to be looking for. First off, it's not software
> > compatible with existing applications, requiring emulation to run all
> > your current code. What's probably more important though is that
> > you'll have a heck of a time finding an Itanium system for less than
> > $20,000.

[snip]

Just to bring that $20K back to reality...entry-level HP Integrity rx1600's
can be gotten for $2800+/- from HP.

Ken

____________________________________
Ken Farmer <><
LinuxHPC.org. http://www.LinuxHPC.org
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

HI, definatly go for amd 64 bit, Start with a 3200xp 64 bit cpu. I jumped up
from a powerfull 2200 xp. The difference startled me. Long live amd. Down
with intel. Anne
"Kenneth Farmer" <kfarmer@NOSPAM.spyderbyte.com> wrote in message
news:0k6kd.27555$YL.2713026@twister.southeast.rr.com...
> "Bobby" <bobby@europe.com> wrote in message
> news:2v7kohF2i2mgtU1@uni-berlin.de...
>> Tony - Great post. One to save I think. Cheers.
>>
>> Bobby
>>
>> "Tony Hill" <hilla_nospam_20@yahoo.ca> wrote in message
>> news:mmnbk01bruupnmb7rghvl3cpqboks2n6oj@4ax.com...
>> > On 12 Sep 2004 19:08:38 -0700, nathan_at_work@hotmail.com (No spam)
>> > wrote:
>> >>
>> >>Hello everyone. I am looking to buy a new desktop PC. I currently have
>> >>a Compaq Pentium 3 733 MHz desktop and a Dell 2.0 GHz Celeron laptop.
>
> [snip]
>
>> >>Now I am looking to buy a new desktop and I am looking for the best
>> >>new technology. I am very interested in 64 bit technology. I know
>> >>Intel has had Itanium and Itanium II but as I understand it those are
>> >>not for consumers.
>> >
>> > You can safely ignore the Itanium line, it's definitely NOT what
>> > you're going to be looking for. First off, it's not software
>> > compatible with existing applications, requiring emulation to run all
>> > your current code. What's probably more important though is that
>> > you'll have a heck of a time finding an Itanium system for less than
>> > $20,000.
>
> [snip]
>
> Just to bring that $20K back to reality...entry-level HP Integrity
> rx1600's
> can be gotten for $2800+/- from HP.
>
> Ken
>
> ____________________________________
> Ken Farmer <><
> LinuxHPC.org. http://www.LinuxHPC.org
>
>
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

Yes i changed to the x64.
Just as soon as i could work out if Intel were
Or were not going to have a x64 at a reasonable price.
That would run the new Windows x64 OS but after
they opted not to go ahead with the Prescott and its apparent x64 extensions
I went AMD for the first time and am far from disappointed.
I used the Gigabyte GA - K8VNXP MOBO and a socket 754 3700+ and it is a gem
of a computer
So that i have nothing slowing the machine down I also installed a GeCube
ATI x800 Platinum.
The machine feels bullet proof and I have had no compatibilities problems
I run it as a media centre with 2 x 200GB SATA 7200 A Leadtek Digital TV
Tuner And 2 X 120GB Seagate ATE 7200 for the OS Samsung 8x DVD Burner Dual
layer & 52XDVD Combo drive for copying DVD's direct and the system has yet
to falter no lockups no BSOD boots super fast and loads all software on
demand.

I say "and i am not being bias" Definately go 64 BIT Go AMD x64.

"Kenneth Farmer" <kfarmer@NOSPAM.spyderbyte.com> wrote in message
news:0k6kd.27555$YL.2713026@twister.southeast.rr.com...
> "Bobby" <bobby@europe.com> wrote in message
> news:2v7kohF2i2mgtU1@uni-berlin.de...
>> Tony - Great post. One to save I think. Cheers.
>>
>> Bobby
>>
>> "Tony Hill" <hilla_nospam_20@yahoo.ca> wrote in message
>> news:mmnbk01bruupnmb7rghvl3cpqboks2n6oj@4ax.com...
>> > On 12 Sep 2004 19:08:38 -0700, nathan_at_work@hotmail.com (No spam)
>> > wrote:
>> >>
>> >>Hello everyone. I am looking to buy a new desktop PC. I currently have
>> >>a Compaq Pentium 3 733 MHz desktop and a Dell 2.0 GHz Celeron laptop.
>
> [snip]
>
>> >>Now I am looking to buy a new desktop and I am looking for the best
>> >>new technology. I am very interested in 64 bit technology. I know
>> >>Intel has had Itanium and Itanium II but as I understand it those are
>> >>not for consumers.
>> >
>> > You can safely ignore the Itanium line, it's definitely NOT what
>> > you're going to be looking for. First off, it's not software
>> > compatible with existing applications, requiring emulation to run all
>> > your current code. What's probably more important though is that
>> > you'll have a heck of a time finding an Itanium system for less than
>> > $20,000.
>
> [snip]
>
> Just to bring that $20K back to reality...entry-level HP Integrity
> rx1600's
> can be gotten for $2800+/- from HP.
>
> Ken
>
> ____________________________________
> Ken Farmer <><
> LinuxHPC.org. http://www.LinuxHPC.org
>
>
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

> Just to bring that $20K back to reality...entry-level HP Integrity rx1600's
> can be gotten for $2800+/- from HP.

no '-' there, you're talking about a ridiculously stripped machine
with a single, extremely low-end processor (much slower than an
entry-level AMD, for instance). and 512M for crying out loud!
no hard drive at all, no management card that anyone buying a
server would demand. frigging 1-year warranty!

configure it up to a sane if slow server (8GB ram, 3-yr, second
cpu, pair of disks) and you're up to $15K. again, this winds up
being a machine which will not hold a candle to a similarly configured
opteron for less than half the price.
 
Archived from groups: alt.comp.hardware.amd.x86-64,alt.comp.hardware.microprocessors.amd,comp.sys.ibm.pc.hardware.chips (More info?)

"Mark Hahn" <hahn@coffee.psychology.mcmaster.ca> wrote in message
news:cn61ln$ri0$1@informer1.cis.mcmaster.ca...
> > Just to bring that $20K back to reality...entry-level HP Integrity
rx1600's
> > can be gotten for $2800+/- from HP.
>
> no '-' there, you're talking about a ridiculously stripped machine
> with a single, extremely low-end processor (much slower than an
> entry-level AMD, for instance). and 512M for crying out loud!
> no hard drive at all, no management card that anyone buying a
> server would demand. frigging 1-year warranty!
>
> configure it up to a sane if slow server (8GB ram, 3-yr, second
> cpu, pair of disks) and you're up to $15K. again, this winds up
> being a machine which will not hold a candle to a similarly configured
> opteron for less than half the price.

Mark,

I've obviously hit a nerve. Certainly not intended. The mentioned price
was just a bit overboard. Once again...

rx1600's start at $2800+/-. I'm not any recommendations, I'm just pointing
out that $20K is a stretch.

Ken