• A Great friend to the HardForum with a great kid that he is trying to get a scholorship to continue his schooling. Please give hime a vote! Only 24 hours left! Thanks.
    If you have an VOTE FOR KEENAN!

AMD demo's native quad-core

visaris said:
More commentary on the demo:

http://www.pcworld.idg.com.au/index.php/id;1286647537
Click to expand...

Real question, no sarcasm. What did the Demo consist of besides a screen shot? Was this as PC World called it a "laboratory version"? I saw a mock up and a Screen shot, is there anything of substance other than that?

I remember you two guys (You and Duby229) being Nay-Sayers when other equipment was Demoed and folks got hands on. I remember a lot of unflattering terms used against many Webmasters who saw and ran tests on Hardware.

Before you say something Duby, that is what this is about, AMD's demo. Honestly I find it hard to call it a Demo at all. PR stunt maybe. Remember the Demo with the Console? The company used a PC to run the Demo, most of the Web was in an uproar over that. How do we know this wasn't just and 8-way dual? Did anyone verify by sight, hands on or etc..?

I remember at least 8 AMD leaning folks on this forum saying they'll wait for independent tests of Conroe. Is this just another double standard? Oh well I said Console and Conroe, sorry for going off topic although I'm talking about Demos.
 
I agree with you Donnie. It's not much of anything except a "Hey we didnt do so well with 4x4 so look at this instead"

I think this is an attempt by AMD to remove attention from 4x4. Sucks, but it is most likely true.
 
Brand loyalty=mental retardation and this thread proves it. Neither Intel nor AMD care whether or not you love them, they want your money, and that is all. If they have to make a better CPU than their competition to get this money they do so. Why do people continue to associate themselves with companies that could care less whether or not you even exist.

To Visaris: You posted about AMD demoing their cores. Scali replied that he was skeptical as to the quality of the product demonstrated. THIS IS NOT OFF TOPIC. Stop crying. This demo has no real info or numbers, so people have every right to be skeptical, including those who favor AMD.

To Scali: Visaris believes your commentary to be off topic. Although I believe if he had his way there'd be no possible way to reply to this other than by saying "Oh yeah I heard that too," or "boy I can't wait," I would encourage you to leave this thread simply because you won't make headway in this argument. It seems that Visaris merely wanted to alert people to the fact that AMD demoed native quad core rather than debate the quality or the legitimacy of this demo. Please respect his wishes on this. I would enjoy it if you started a new thread on this subjuect "(in the AMD forum, because it certainly is not off topic), because I agree with you. Intel is further along in their quad core design right now, and currently they do hold the performance crown. This however does not prevent me from considering the possibility that something better can/will be made by AMD or Intel for that matter.

To both of you: grow up.

ALSO, to avoid accusations of bias, I would like to inform those replying that I am currently using an AMD CPU which I am very happy with (although I accept that Intel has many CPUs that perform better).
 
Someone posted this on pervasive64 anonymously, and I found it to be a very humorous thought:
You got it wrong - task manager was at almost 100% only because the AMD sample was running at a clock frequency of 5 MHz :)
Click to expand...
While I don't think this is the case, it does stress that seeing more would have been nice. See, look at me go; another post about the quad-core demo.
 
Scali2 said:
Yea, but in other news:


http://www.xbitlabs.com/news/cpu/display/20061024001546.html

Somehow these articles try to make it sound like AMD is the first, while Intel already had its stuff working last month. Intel even provided benchmarks... where are AMD's benchmarks? If they demonstrate it, I want to know what they can do aswell. Intel's stuff performed excellently, like you'd expect from the finished product.
Which is also why I would find it strange if AMD would be first to market... that could only mean that AMD is rushing things, which can never be good for product quality.
Click to expand...

Amd isnt the first to 16 procs, they're the first to 4 core on one die.

who knows, maybe theyll pull an intel by sticking two of those dies on a single wafer, and introducing 32 Cores! :eek:
 
Wow... I now have a headache from reading all this tonight... I'm pretty sure that is off topic, but anyway...

I for one am impressed AMD finally managed to get to 65 nm... I've been waiting for them to accomplish this to see if now they could nudge the performance crown from Intel (but Intel has 45 nm in the works), so we'll have to see how that plays out in the long run. I'll be looking forward to this!

As far as "Native" quad-core goes, they [AMD] don't explain much of this, seeing as how they called their previous Opterons "Native" dual-core. So really we'll have to see if this "Native"-core technology will in fact produce better performance or just equal. Who knows... it is entirely possible it could be just negligible or perhaps worse.

As far as the demo goes it seems to have been more a PR stunt than anything, (as was said before - to get people away from Quad FX), since there weren't any palpable results of performance increases. In the video on AMDs site, they claimed the 40% and 70% increases from their previous products, but had no proof backing it up. I especially liked the comment on the Inquirer site about the thug willing to break fingers if someone had gotten to close to "the demo," I guess.

Anyway, I'm done ranting... personally I've been a fan of both AMD and Intel products... they've gone back and forth so many times through the years it's funny. Right now, Intel has Core2 duo's and quad's to drool over... and maybe soon the drooling with be back over to AMDs products. For the AMD fans, sit back and cross your fingers!

Mmmmmmmm processing power...
 
MrWizard6600 said:
Amd isnt the first to 16 procs, they're the first to 4 core on one die.

who knows, maybe theyll pull an intel by sticking two of those dies on a single wafer, and introducing 32 Cores! :eek:
Click to expand...

You're completely right... they can and probably will... the future is in multi-core technology, but to what point will it be absurd? I mean who would really use all that power... today anyway?

You know, in 2022 dropping in your new AM-Tel 1024 Core CPU with 4 TB of RAM... :eek:

::drool::
 
Not unless someone figures out a way to do automated threading. In order for that to work, we'd also need automated programming, and that ain't gonna happen.

I think sooner or later we will see a shift away from multi-core to something else. What that something else is, I don't know, but like I said there are some very real limitations to the number of cores that can be programmed for realistically.
 
w1retap said:
Some of you guys need to write a book on this. Everyone is an expert in unreleased products all of a sudden. :confused:
Click to expand...

No doubt. Speculation is a wonderful thing, but rumor, innuendo and extrapolation based upon incomplete information is hardly gospel.

In other words, typical day @ the forums :D
 
duby229 said:
Not unless someone figures out a way to do automated threading. In order for that to work, we'd also need automated programming, and that ain't gonna happen.

I think sooner or later we will see a shift away from multi-core to something else. What that something else is, I don't know, but like I said there are some very real limitations to the number of cores that can be programmed for realistically.
Click to expand...

Which kind of goes back to Scali2's previous comment about the x86 architecture... Who knows how much longer they're going to push it, and just create a whole new architecture like Intel tried with the IA-64 (Itanium) I mean AMD was first with their AMD64 extended memory, so who knows, maybe they'll be able to make the next architecture... especially with ATi in their pocket too... Now it gets exciting, to see what is even further down the road, and not just the brand spanking new quad-cores!

Sorry if that was off-topic... I'm a little tired.

Hooray AMD and Native quad-core! :D
 
No that was not off topic.

Like I said I don't know what the next big shift will bring, but I can say for sure it wont be massively multi-core, but it will be x86 compatible.

As far as what it will be, I don't know, but I do know that AMD has just announced a new SPU, and have even gone as far as saying that Fusion will have an integrated on die SPU. Will that be the next shift? I don't know. Not every type of code lends itself to that kind of environment. Sure the applications that will benefit will be HUGE, but still alot of other applications will see next to nothing from it.

We'll have to wait and see. At this point I'm just as clueless as the next guy.
 
OppoKaze said:
I would encourage you to leave this thread simply because you won't make headway in this argument.
Click to expand...

There are people who walk away when told, and then there are people who stand up for what they believe is their right.

It seems that Visaris merely wanted to alert people to the fact that AMD demoed native quad core rather than debate the quality or the legitimacy of this demo.
Click to expand...

Then he should not have posted it on a discussion forum.
Else you should expect people to discuss the topic at hand.
He should have put it on his personal blog...
Besides, if all he wanted to do was present the news, then I don't see the point. The news is still out there to read for everyone, whether or not people discuss it in the later posts.

I would enjoy it if you started a new thread on this subjuect "(in the AMD forum, because it certainly is not off topic), because I agree with you.
Click to expand...

I don't see the point, everything has pretty much been said in this thread already.
If you want to open an thread on the matter, you're free to do so, obviously.
 
duby229 said:
I agree with you Donnie. It's not much of anything except a "Hey we didnt do so well with 4x4 so look at this instead"

I think this is an attempt by AMD to remove attention from 4x4. Sucks, but it is most likely true.
Click to expand...

I couldn't agree more!

I can't wait for the real K8L demos to take place and look forward to them. The Geek in me is anxious to see it. I don't gamble but I'd bet more Geeks want to see it kick ass! Only some crazy folks want to see this not turn out well for AMD. Don't get me wrong here, I don't want to see X2 prices again because AMD wiped the floored with Intel but faster with good prices would be nice:)
 
Donnie27 said:
I couldn't agree more!

I can't wait for the real K8L demos to take place and look forward to them. The Geek in me is anxious to see it. I don't gamble but I'd bet more Geeks want to see it kick ass! Only some crazy folks want to see this not turn out well for AMD. Don't get me wrong here, I don't want to see X2 prices again because AMD wiped the floored with Intel but faster with good prices would be nice:)
Click to expand...
Don't hold your breath. :) Intel has no competition for it's Quad Core's right now so it's charging 800+ for them. if AMD's K8L/K10 derivatives come in more powerful, expect them to charge as much as they can.

Just like how Intel will not be dropping prices on the Core 2 Duo's as AMD hasn't brought anything more powerful to compete.

I hope K8L/K10 Quad Core do well, as that means I can get an Intel Quad Core for cheaper.
 
coldpower27 said:
Don't hold your breath. :) Intel has no competition for it's Quad Core's right now so it's charging 800+ for them. i

...
Click to expand...

That's why in Q1 Intel will offer a Q6600 for $851 , Q6400 for ~$550 and a Q6300 for $316 ?
:rolleyes:
 
savantu said:
That's why in Q1 Intel will offer a Q6600 for $851 , Q6400 for ~$550 and a Q6300 for $316 ?
:rolleyes:
Click to expand...
Really and where do you have speculation on the Q6400 or Q6300? I would like a link please.
 
Scali2 said:
http://www.theinquirer.net/default.aspx?article=34652

So basically the clockspeed is the same as on the E6x00-series dualcores...
Click to expand...
That isn't quite sufficient, as that article is 1 fairly old now, and 2 it is wrong on the Xeon DP Clovertown FSB speeds, as there are indeed 2 models with 1.33GHZ FSB as well as the lower end versions of 1.06GHZ FSB.

I am more interested in the price.

I am aware of the Xeon UP 3210 which is apparently a Server LGA775 version of the 2.13GHZ model. It will be priced at 690USD if the rumor sources are to be believed.
 
coldpower27 said:
Don't hold your breath. :) Intel has no competition for it's Quad Core's right now so it's charging 800+ for them. if AMD's K8L/K10 derivatives come in more powerful, expect them to charge as much as they can.

Just like how Intel will not be dropping prices on the Core 2 Duo's as AMD hasn't brought anything more powerful to compete.

I hope K8L/K10 Quad Core do well, as that means I can get an Intel Quad Core for cheaper.
Click to expand...

Of course! But I can still hope, can I?
 
Ok. I'd like this discussion to continue in a nice, friendly manner. I don't really appreciate namecalling and personal attacks, and I'd like to keep them off this thread.

Keep it on topic.. i.e. DISCUSSION of the demo of the native quad-core solution from AMD.
 
TechHead said:
Ok. I'd like this discussion to continue in a nice, friendly manner. I don't really appreciate namecalling and personal attacks, and I'd like to keep them off this thread.

Keep it on topic.. i.e. DISCUSSION of the demo of the native quad-core solution from AMD.
Click to expand...


Me feel good inside :D

Thank you.
 
TechHead said:
Ok. I'd like this discussion to continue in a nice, friendly manner. I don't really appreciate namecalling and personal attacks, and I'd like to keep them off this thread.

Keep it on topic.. i.e. DISCUSSION of the demo of the native quad-core solution from AMD.
Click to expand...
: )
 
Alrighty.. let's keep this on topic. No flames, namecalling etc.. just good, genuine discussion and exchange of views.
 
TechHead said:
Ok. I'd like this discussion to continue in a nice, friendly manner. I don't really appreciate namecalling and personal attacks, and I'd like to keep them off this thread.

Keep it on topic.. i.e. DISCUSSION of the demo of the native quad-core solution from AMD.
Click to expand...

Does this include comparisons against Intel's technology or not? That's what I'd like to know.
 
Scali2 said:
Does this include comparisons against Intel's technology or not? That's what I'd like to know.
Click to expand...

Why would it? More importantly, HOW would it? How do you compare a tech demo with a product already on the market? When you post the first response and it's a link to an intel tech demo, upon which you engage in rampant speculation, what purpose would that have in a discussion of an amd tech demo?

Furthermore, why is there a 2 after your name? Why is there a banned user with the same name, sans the 2? My curiosity is killing me.
 
mastercheeze said:
Why would it? More importantly, HOW would it? How do you compare a tech demo with a product already on the market? When you post the first response and it's a link to an intel tech demo, upon which you engage in rampant speculation, what purpose would that have in a discussion of an amd tech demo?
Click to expand...

Would you mind reading the thread? These questions have long been answered.
Besides, the question was directed at the moderators, please don't interfere and drag the conversation offtopic again.
 
Comparisons are fine, name calling and flaming are NOT.
I don't want any definites here.. you can't run down AMD for just showing a tech demo. COmpare and contrast to the Core 2 Quad ad infinitum, it's fine.With the above riders, of course.
 
Scali with AMD's new power saving features they are putting on the k8l ie each core being able to power up and down independantly, do you think it would have been feasible for them to use a shared cache like Intel. When I sat back and thought about your arguments I was thinking this could be the reason for the big differance in architecture here.
 
moon02 said:
Scali with AMD's new power saving features they are putting on the k8l ie each core being able to power up and down independantly, do you think it would have been feasible for them to use a shared cache like Intel. When I sat back and thought about your arguments I was thinking this could be the reason for the big differance in architecture here.
Click to expand...

Intel already has that feature on their Core2 Duo Mobile line... though not exactly the same, turning an entire core off (because they only have 2), just certain areas of the CPU that aren't being used do power down, including cache... to save battery life.

But it would seem AMD is incorporating these features in their line too, especially for those Quad cores which will probably be in a server environment, where power usage is especially important now a days. Getting most performance per watt, and most bang for your buck!
 
moon02 said:
Scali with AMD's new power saving features they are putting on the k8l ie each core being able to power up and down independantly, do you think it would have been feasible for them to use a shared cache like Intel. When I sat back and thought about your arguments I was thinking this could be the reason for the big differance in architecture here.
Click to expand...

I think that's a bit beside the point, since they do actually use a shared cache... The point is that it's an L3-cache rather than L2.
If a shared cache can't be powered down, then the point is moot anyway, because then AMD's L3 can't be powered down either. With shared L2-cache, the L3-cache wouldn't be necessary, so they could save power that way.

Other than that, I think the question is what should have the biggest priority... power saving features or performance?
For a quadcore desktop/server/workstation processor, I'd prefer performance over power saving. I think AMD would do this aswell. It won't be a big problem if they don't apply quadcores to notebooks yet, and wait until 45 nm makes them more efficient, or such.

But I think technically they could choose to clock the shared cache down as a whole, so you'd still have some powersaving. It would just take down performance of the faster cores aswell, but it might be a good compromise. I'm not sure what the power consumption balance is between cores and caches, though.
 
You can really see the 100MHz clock bumps at work there; looks like it helps out their binning quite a bit.
 
You must log in or register to reply here.
Back
Top