Opteron or Athlon 64

[Mrburns2007]

I saw where the Opteron may only cost $300 to $400 which would make it reasonable priced even for desktop use.


What is the official release date anyways ?

 

[AndyHui]

Opteron, April 22. Athlon 64, September.

Opterons won't be good for desktop use yet unless you are not planning to use Windows, and don't need an AGP card.

Microsoft has not announced that they will be ready with Anvil (x86-64 Windows) and current Opteron motherboard products do not have an AGP slot.

 

[Wingznut]

I would be very surprised if the Opterons weren't priced closer to $1000.

 

[glugglug]

By the time the 2nd round of debugged mobo chipsets come out I'm sure it will be closer to $300-$400....

Andy: What do you mean "unless you don't need an AGP card"? Do the opteron mobos not have AGP slots? I mean it does make sense for a server not to have memory used on AGP aperture but isn't the slot there anyway?

And Anvil for Athlon64 should work the same on Opteron once it comes out...

 

[Wingznut]

Originally posted by: glugglug
And Anvil for Athlon64 should work the same on Opteron once it comes out...

Andy is saying that Anvil won't be out for a while.

 

[AndyHui]

The initial Opteron motherboards do not have AGP slots (as far as I have seen, anyway). We'll see in a week or two's time.

 

[galperi1]

Originally posted by: Wingznut
I would be very surprised if the Opterons weren't priced closer to $1000.

Nope

OPTERON DP Server Model 242 (PIB) - $803.95
OPTERON DP Server Model 240 (PIB) - $343.95

courtesy of pricegrabber

 

[XBoxLPU]

Prices

It appears that AMD will also offer boxed Opteron server microprocessors through its channel distributors as well. The distributor price for the Model 240 is $275, for the 242 $670, but the 244 won't be available through the channel until May. The OSA240BOX system, which AMD calls a "processor in a box", will cost $295, while the OSA242BOX will cost $690

 

[MikeMike]

Originally posted by: XBoxLPU
Prices

It appears that AMD will also offer boxed Opteron server microprocessors through its channel distributors as well. The distributor price for the Model 240 is $275, for the 242 $670, but the 244 won't be available through the channel until May. The OSA240BOX system, which AMD calls a "processor in a box", will cost $295, while the OSA242BOX will cost $690

so what speed are those at? i mean model 240 means nothing to me. what speed?

 

[AtomicDude512]

Originally posted by: nourdmrolNMT1

Originally posted by: XBoxLPU
Prices

It appears that AMD will also offer boxed Opteron server microprocessors through its channel distributors as well. The distributor price for the Model 240 is $275, for the 242 $670, but the 244 won't be available through the channel until May. The OSA240BOX system, which AMD calls a "processor in a box", will cost $295, while the OSA242BOX will cost $690

so what speed are those at? i mean model 240 means nothing to me. what speed?

I would like to know also...

 

[XBoxLPU]

The chip is expected to start at speeds of about 2GHz. But the new model numbers don't reflect clock speed. Instead, they show whether a given chip is designed for single- or multiple-processor servers and then point to its performance relative to other chips in the same family, the company said.

http://www.neowin.net/exit.php/http://news.com.com/2100-1006-992420.html?tag=fd_top

The new Opteron lines will include the 100 Series, for single-processor machines; the 200 Series, for dual-processor systems; and the 800 Series, for computers using up to eight processors. The individual chips will start their numbering at 40, so under the new nomenclature there would be a model 140, a model 240 and a model 840. As chip speed increases, so would the model number--a model 142, for instance, would be faster than a model 140, and a model 144 would be faster still.

 

[LikeLinus]

Originally posted by: XBoxLPU

The chip is expected to start at speeds of about 2GHz. But the new model numbers don't reflect clock speed. Instead, they show whether a given chip is designed for single- or multiple-processor servers and then point to its performance relative to other chips in the same family, the company said.

http://www.neowin.net/exit.php/http://news.com.com/2100-1006-992420.html?tag=fd_top

The new Opteron lines will include the 100 Series, for single-processor machines; the 200 Series, for dual-processor systems; and the 800 Series, for computers using up to eight processors. The individual chips will start their numbering at 40, so under the new nomenclature there would be a model 140, a model 240 and a model 840. As chip speed increases, so would the model number--a model 142, for instance, would be faster than a model 140, and a model 144 would be faster still.

Great. That's AMD for ya! An even more confusing sliding scale for performance based on an imaginary starting point

 

[Snoop]

Great. That's AMD for ya! An even more confusing sliding scale for performance based on an imaginary starting point

It could easily be argued that basing performance on MHz is equally as vague. Simply look at the jump from the P3 to P4; performance did not scale directly to MHz, so at least this scaling system will give values relative to its predecessors, regardless of the core design.

 

[LikeLinus]

Originally posted by: Snoop

Great. That's AMD for ya! An even more confusing sliding scale for performance based on an imaginary starting point

It could easily be argued that basing performance on MHz is equally as vague. Simply look at how the P4 has evolved; with each new stepping, performance did not scale directly to MHz, so at least this scaling system will give values relative to its predecessors.

At least theirs is a "real" number and scale that has been used for many years and many companies. AMD's scale is self sufficent and only to their needs. It's not to help the customer but to help themselves look better. Plus having 3 different numbers scale for 1 chip is confusing. Pentium as P4 and P4 Mobile or Xeon. It doesnt have P4 100 p4 200 p4 300. Ontop of that it's then done by scale of performance (i.e. p4 140 p4 240 p4 340). It's much easier just to name the chips different than to have like 20 different number names that are confusing to the end customer.

I love AMD and their chips, but the names they pick and numbering isn't helpful.

 

[Cosmic_Horror]

server market is a little different to the desktop market in that MHz isn't as big an issue. On-die cache can make a much greater impact on overall server preformance that Mhz , and wether a cpu can scale to 2-way or 4 way etc.


that said this new model number system will confuse a lot of people.

 

[mechBgon]

It's not as if the actual MHz of the Opteron is going to be kept secret or something. If you want to buy based on MHz, it should be as simple as reading the specs in the item listing.

 

[DannyBoy]

Originally posted by: mechBgon
It's not as if the actual MHz of the Opteron is going to be kept secret or something. If you want to buy based on MHz, it should be as simple as reading the specs in the item listing.

Well said

 

[drednox]

ugh

OPTERON - man that sounds liek a transformer not a CPU

Opteron Prime !

 

[LikeLinus]

Originally posted by: mechBgon
It's not as if the actual MHz of the Opteron is going to be kept secret or something. If you want to buy based on MHz, it should be as simple as reading the specs in the item listing.

Duh, yeah of course you could always check the system specs. But it'd be like GM coming up with a new name for the V6. Of course there are V6 out there that outperform V8's and It doesn't really depend on what the "number" is after the v, but it gives the buyer a good sense of reference to the assumed power that the car can output. So if GM started calling their engines 140, 242, 340 and making the people LOOK for the actual displacement, how annoying and stupid would that be?

 

[Snoop]

Duh, yeah of course you could always check the system specs. But it'd be like GM coming up with a new name for the V6. Of course there are V6 out there that outperform V8's and It doesn't really depend on what the "number" is after the v, but it gives the buyer a good sense of reference to the assumed power that the car can output. So if GM started calling their engines 140, 242, 340 and making the people LOOK for the actual displacement, how annoying and stupid would that be?

In what way is MHz a good sense of reference? MHz mean nothing to the performance of a cpu. Tommarrow, XXX company could come out with a 100mhz proccessor which could outperform ANY other proccessor whether it be 3 GHz, 2GHz or 33MHz. Is MHz in your opinion still a good "sense of reference"if this were true?
AND, last time I checked most if not all automobile mfg do go by cubic inch or Liters on the specs of their cars and deemphasize V8,V6, etc, etc. IE. Mustang 5.0L

 

[Wingznut]

Originally posted by: Snoop

Duh, yeah of course you could always check the system specs. But it'd be like GM coming up with a new name for the V6. Of course there are V6 out there that outperform V8's and It doesn't really depend on what the "number" is after the v, but it gives the buyer a good sense of reference to the assumed power that the car can output. So if GM started calling their engines 140, 242, 340 and making the people LOOK for the actual displacement, how annoying and stupid would that be?

In what way is MHz a good sense of reference? MHz mean nothing to the performance of a cpu.

So, you would have no idea how a P4-2.66ghz would compare to a P4-2.8ghz?

Using mhz as a point of reference between two completely different processes doesn't work so well, but using it amongst the same family is very relevant.

MUCH more relevant than adding a 2 to the model number.

 

[Snoop]

So, you would have no idea how a P4-2.66ghz would compare to a P4-2.8ghz?

Only if they are the same core revision, as you know the first P4's would not perform the same mhz/mhz as the later HT enabled P4. Or, look at the new AMD barton CPU's, where less mhz actually yields an increases in performance within the same processor family.

My point is not that mhz is a utterly useless measurement (even though for the most part it is), but that there is no more value in it than an arbitrary number rating scheme as AMD has proposed. At least it will avoid confusion on thing like HT enabled cpu's which make a big difference in performance but do not add any MHz.

 

[Wingznut]

I don't understand why you think that the actual speed of the cpu is "utterly useless."

If you knew the mhz of both the "240" and "242", you would be able to come to some sort of conclusion as to how much faster the "242" is... Again, it's much more relevant than some arbitrary number.

Btw... I don't know of ANYONE who is "confused" about HT.

 

[Snoop]

If you knew the mhz of both the "240" and "242", you would be able to come to some sort of conclusion as to how much faster the "242" is...

Winz, what if AMD doubled the cache, and 'borrowed' Hyperthreading, and called it the Athlon Quarterhorse, which ran 200 mhz slower than the barton, but dominated it in the majority of benchmarks. Would MHz then be an accurate guage of performance or would an arbitrary number increase be better?????

 

[Snoop]

Btw... I don't know of ANYONE who is "confused" about HT.

I was reffering to the forum threads I have read here and elsewhere discussing whether their P4 proccessors or motherboards support HT which adds a great deal of performance without adding mhz.