Cedar Mill and Presler Rant - 4.2GHz+ Possible

Page 2 - Seeking answers? Join the Tom's Hardware community: where nearly two million members share solutions and discuss the latest tech.
Dothan/Yonah = FX killer in performance and TDP

Yonah is the X2 killer in performance and TDP

DDR2 is under $100 per gig and you can run 2GB/4GB without all the BS associated with AMD's compatabilty/timing issues.

http://valid.x86-secret.com/show_oc.php?id=45312

<A HREF="http://www.xtremesystems.org" target="_new">www.xtremesystems.org</A>
So your comparing AMD's current proc's which have been out for 2 years with intel's future procs? U honestly dont think AMD will fix the memory compatibility thing with Ref F and DDR2? I truly respect your o/cing abilities but u can be really pigheaded when it comes to your opinion's on AMD's proc's.

It should be noted there has been no significant technological change in the K8 line other than dual cores. Perhaps like myself he believes nothing radical is comming unless Intel comes out with it and AMD licences it (SSE SSE2 ect.)
SSE2 was a radical change designed to hide the architectural weaknesses of netburst. I wouldnt call that inovation.
 
SSE2 was a radical change designed to hide the architectural weaknesses of netburst. I wouldnt call that inovation.
I don't know if I can agree with that PoV. To me it was more like SSE2 was a crutch to lean on so that they didn't have to bother fixing one of the major weakness that they introduced into the core's design when they rushed the P4 out the door to cover up their P3>1GHz failure. :lol:
 
Perhaps like myself he believes nothing radical is comming unless Intel comes out with it and AMD licences it (SSE SSE2 ect.)
It sure is a good thing Amd licenced Intel's EM64T, and the ODMC, otherwise they would be dead in the water.
Intel's last great inovation, SSE3 was also such a great step. I sure am glad we can count on Intel to keep things moving at this great pace.

Does it always have to be a pissing match with you? You understand what I am saying why do you act like I said something I didn't.

But screw it you honestly think the ODMC and AMD64 are some sort of revolution in computing power? Both technologies have been around in one form or another for a quite a few years before AMD packaged them in a great processor, but hey you read what you want to.

Frankly don’t care too much either your opinion is just that but my statement that nothing new has come out for quite some time does hold true. Unless your a wizard and know of some remarkable technological change in the K8 that I was unaware of.

With considerations at least Intel is trying to recover but no one gives em props for that too easy to bash and stare at your dearest comrade e-penis scores, when simply put you recommend/like/purchased the better platform. Everyone knows its AMD's ball right now quite assuming I don’t think otherwise cause all you do is piss me off further with your lackluster macho responses.

SSE2 was a radical change designed to hide the architectural weaknesses of netburst. I wouldnt call that inovation.
If you have the slightest understanding about code or execution resources or really anything in regards to this topic Harlan you wouldn't be saying that. SSE2 isn’t anything special though just helping extend the junk known as x86, lost as to why any of you defend such a terrible ISA but whatever.

I don't know if I can agree with that PoV. To me it was more like SSE2 was a crutch to lean on so that they didn't have to bother fixing one of the major weakness that they introduced into the core's design when they rushed the P4 out the door to cover up their P3>1GHz failure.

More of the Intel rushed the P4 wow I can’t believe people that claim they are so educated believe such a farse. The project was in the works for nearly 7 years possibly longer how is that a rush job, oh wait Intel’s platform design teams work as one group and come out with a uber processor, No they don’t do they?

It was a evolution that’s all the net burst project was and you know what it might be sucking hardcore now but it sure made Intel a crap load of cash didn’t it? Seem like the failed technology ended up paying for itself and that in itself is impressive, but I forgot where I am right now, you guys live in whatever the fad is, and the common word even if its grossly opinioned and unsupported, is the word of the land.
 
If you have the slightest understanding about code or execution resources or really anything in regards to this topic Harlan you wouldn't be saying that. SSE2 isn’t anything special though just helping extend the junk known as x86, lost as to why any of you defend such a terrible ISA but whatever.
So the line of chips from Intel and AMD that have driven the modern day computer industry for the past 20 years are junk? As someone who always retreats and hides behind Intel's inability to get a product that actually matters to the general consumer to make money and their whole buisness principle in general, you should be able to understand that while X86 might not be the strongest architecture in technical terms, It IS the strongest processor architecture because of its market penetration. I2 will remain a niche product as long as AMD and X86 have anything so say about it. I'm sorry if that dissapoints you. I remeber the days when you were telling me about how netburst would turn into IA64 and that would be the way the industry would roll. You were wrong in the end because itanium is a dead horse for now and will not mean anything to any normal consumer within the next 10 years. The software is not there. The product is simply too expensive to produce and continually R&D. Intel has pretty much stated that netburst is dead. Netburst was their big thing for years. Can't you possibly see history repeating itself with IA64 as well? Reasonable doubt is all i'm looking for here.
 
More of the Intel rushed the P4 wow I can’t believe people that claim they are so educated believe such a farse. The project was in the works for nearly 7 years possibly longer how is that a rush job, oh wait Intel’s platform design teams work as one group and come out with a uber processor, No they don’t do they?
You seriously need to wake up. The release of the P4 was rushed. There's no way of even remotely denying that if you read anything at that time.

Yes the P4 was in development for a long time. It was in the back, away from the limelight, an engineering project just evolving and waiting for technology to make it possible to fill the engineer's dreams.

If you'd looked at the original design specs, you'd have seen that the P4 was supposed to have had much more transistors for things like a second independant FPU. Imagine what a P4 with much better x87 performance would have been like!

But to get the P4 out the door to cover up the sorry state of the P3, Intel management forced the engineers to hack useful things like that out of the core to save space, and directly to that, to save costs. They even used compression technology on their instruction cache to reduce die space. (I mean look how big Willy was even after that!)

Had Intel waited on releasing the P4 until the next process shrink, instead of rushing something to market like they did (against their own engineer's advice/complaints) then CPU industry today would be a very different place indeed.

But of course I wouldn't know anything about that because I never read those articles years ago since I'm not educated. No, I'm compeltely clueless and just making up this farce.
 
If you have the slightest understanding about code or execution resources or really anything in regards to this topic Harlan you wouldn't be saying that. SSE2 isn’t anything special though just helping extend the junk known as x86, lost as to why any of you defend such a terrible ISA but whatever.
So the line of chips from Intel and AMD that have driven the modern day computer industry for the past 20 years are junk? As someone who always retreats and hides behind Intel's inability to get a product that actually matters to the general consumer to make money and their whole buisness principle in general, you should be able to understand that while X86 might not be the strongest architecture in technical terms, It IS the strongest processor architecture because of its market penetration. I2 will remain a niche product as long as AMD and X86 have anything so say about it. I'm sorry if that dissapoints you. I remeber the days when you were telling me about how netburst would turn into IA64 and that would be the way the industry would roll. You were wrong in the end because itanium is a dead horse for now and will not mean anything to any normal consumer within the next 10 years. The software is not there. The product is simply too expensive to produce and continually R&D. Intel has pretty much stated that netburst is dead. Netburst was their big thing for years. Can't you possibly see history repeating itself with IA64 as well? Reasonable doubt is all i'm looking for here.

30+ years and any programmer with half a brain will agree x86 is junk the silicon isn’t the IA is. Retreats? Intel's inability to produce a product that matters? Market penetration? Do you hear yourself?

I don’t post here enough for you to generalize I retreat, nor will I ever. A product that sells recovers initial development costs is by definition is a successful product. As well as the several truck loads of cash net burst just produced out of no where.

IA-64? Where did I mention anything to do with it? Are we trying to get me to go yaya IA-64 roxorz your boxorz? Granted I do believe IA-64 is superior to x86 it simply does not work with the industry conditions. Nor will it ever work at least in the mainstream. But whatever feasibility and market demand go figure it cant/wont get a foot hold.

Wrong in the end? I don’t follow, ah wait I'm sure you’re attempting to rehash old conversations or something to that extent. Vague as they are too me I would have to assume I said IA-64 will become mainstream or something retarded.

Reasonable doubt? You don’t even have any real facts to support anything said since it was all opinion so you can reasonably doubt that Intel cant compete you can reasonably doubt Intel has anything in store for the industry and you can reasonably doubt I care as well. No doubt about it.
 
More of the Intel rushed the P4 wow I can’t believe people that claim they are so educated believe such a farse. The project was in the works for nearly 7 years possibly longer how is that a rush job, oh wait Intel’s platform design teams work as one group and come out with a uber processor, No they don’t do they?
You seriously need to wake up. The release of the P4 was rushed. There's no way of even remotely denying that if you read anything at that time.

Yes the P4 was in development for a long time. It was in the back, away from the limelight, an engineering project just evolving and waiting for technology to make it possible to fill the engineer's dreams.

If you'd looked at the original design specs, you'd have seen that the P4 was supposed to have had much more transistors for things like a second independant FPU. Imagine what a P4 with much better x87 performance would have been like!

But to get the P4 out the door to cover up the sorry state of the P3, Intel management forced the engineers to hack useful things like that out of the core to save space, and directly to that, to save costs. They even used compression technology on their instruction cache to reduce die space. (I mean look how big Willy was even after that!)

Had Intel waited on releasing the P4 until the next process shrink, instead of rushing something to market like they did (against their own engineer's advice/complaints) then CPU industry today would be a very different place indeed.

But of course I wouldn't know anything about that because I never read those articles years ago since I'm not educated. No, I'm compeltely clueless and just making up this farce.

So you know this because you work there Silver insider trade information? You can say the same for the I1 oh wait no one does because the Willy and the I1 had the same problem they both sucked.

Unless Intel has no real direction of intelligent staff which all couldn’t see the P3 scaling much further, which then lead to the P4 development team going hey we have a half asses POS processor that doesn’t really improve on anything but the other team has a feasible replacement at 0.13.

As well for such a rush job I do enjoy the marginal 15% core difference (cache) the Northwood had over the Willy. Just screams to be rushed.

Ya I know what they wanted and what they got which are 2 different things, doesn’t change the fact that that’s that and this is this.

Hmm another FPU ya I can imagine cooking my dinner on a 3.0 instead of using a heat sink. But I am pretty sure the second FPU would have dragged the clocking down further than its shameful 3.8 or 3.6 I don’t know how far they scale anymore since it doesn’t matter.

Hmm more theories about Willy and its terrible performance, but alas they are yours and I have no interest in discussing the finer points of technology that neither or us can claim we honestly know since neither of us are working at Intel to confirm.

Hmm if they waited to release ya I can see how that would make it AMD's market very easily.

Oh ya I figured such a comment would come from you in regards to your education and ya whatever you say we all know I called you a idiot or whatever retarded thing you want to think of doesn’t bother me your self-esteem not mine.
 
So you know this because you work there Silver insider trade information?
...
Hmm more theories about Willy and its terrible performance, but alas they are yours and I have no interest in discussing the finer points of technology that neither or us can claim we honestly know since neither of us are working at Intel to confirm.
Right. That's how I know it, I have "Silver insider trade information". Not because it wasn't widely published by sources as trustworthy as the eetimes. Not because Darrell Boggs, Intel's principal engineer for the desktop platform group, openly admitted it to press. Not because anyone could have easily found the information and read it, espeically when the admission from Intel first came out and flooded the tech sites. No, I know it because I have privileged "insider trade information" about this "farce" that "people who claim they are so educated" made up.

Xeon, maybe you'll want to shut up now before you get your head so far up your arse that you resemble a human donut. Obviously one of us actually is educated, and one of us is being schooled.

Under the original plan, the Pentium 4 was to have one slow ALU, two fast ALUs, two arithmetic address-generation units, two fully functional floating-point units, 16 kbytes of L1 cache, 12,000 instructions of execution trace cache, 128 kbytes of L2 cache, 1 Mbyte of external L3 cache, an allocator/register renamer and a bus architecture.

But with fabs costing more than $2 billion, even the world's largest, most profitable semiconductor company had to reconsider its plans when it became apparent that the chip size was growing too big.
 
Hmm what they wanted they did not get I don’t see the issue at all, other than your smart ass comments of intellectual superiority or whatever your angle is today.

With regards to what you think and I think I will look at it objectively and look how the entire project has panned out and to me it doesn’t appear that a rush was in order unless you honestly believe that the P3 out of no where stopped scaling for Intel completely flooring them since they only test for 20 min and don’t test anything that isn’t being sold.

Then there is simply the supporting fact that the P4 thermal density is currently too great let alone getting all the goodies initially slated. Cut out 1/2 of the IC and drop what’s left to the foundries and do all this in less than 6 months.

I really really really find that whole situation improbably, what’s more probable is 12-18 months before the P3 hit its clocking limits the company realized holy moly the P3 is not gonna clock any further without modification and we have the P4 guys claiming they can have something workable in 12-18 months regardless if they are gutting the original specs. 12-18 months is very much feasible for a core redesign, now silver if you call 12-18 months a rush job then OK I agree it’s a rush job.

But looking at the actual guestimated time it would take to completely change direction of the P4 and have it work correctly out of the box would/did require some time points to a more realistic option.

Now if 12-18 months to Intel is rush work then ya I would have to agree with you but 12-18 months to me is a long time difference of opinion which doesn’t need your grade school comments coming to fruition but whatever acting like adults was lost when children and morons got access to the internet
 
Mirrors on the ceiling
Pink champagne on ice
And she said
We are all just prisoners here
Of our own device
And in the master's chambers
They gathered for the feast
They stab it with their steely knives
But they just can't kill the beast</font color=green>
<pre><font color=orange> ∩_∩
Ω Ω
(=¥=)</font color=orange> - Cedrik wonders what it would be like to hear Arnold<font color=orange>
_Ū˘Ū_</font color=orange>   Schwarzenegger sing Hotel Cal i forn i a.</pre><p>
:evil: یί∫υєг ρђœŋίχ :evil:
The <b><font color=red>Devil</font color=red></b> is in my <b><font color=red>'98 Mercury Sable</font color=red></b>!
<b>@ 201K miles!</b>

Numero Uno - I like the sig!!!!!!!!!!!!!!! LMAO!!!!!!!!

Now to the important stuff.... Im curious as to what your interpretation of the Hotel Cali would be especially the lines above. [I dont suppose we can go off topic anymore?]
 
the entire project has panned out and to me it doesn’t appear that a rush was in order unless you honestly believe that the P3 out of no where stopped scaling for Intel completely flooring them
Yup, it's not like Intel new ahead, the limits of thier architecture.

It doesn't matter what your particular concept of reality is, when it's just wrong. Truth is, that Intel had trouble scaling the copermine core. Nor did they have a crystal ball to see Tuulitan coming.
I know you are still young, but most people can remember that far back.
If you want a history lesson, start here
 
Saying they didn’t know is asinine, as well no logical assumptions can say they didn’t see the scaling issues, simply put they have been selling clock speed for a long time they would need to know those envelopes way before the end of product. Now Intel does shady things as we all know, its far more feasible that released the 1.13 in hopes no one would notice to stretch the timetable for P4 delivery from the foundries.

We are talking about big business here saying they didn’t know is completely ridiculas, saying they were buying time by dropping sub par parts on the market and then acting like they didn’t know is more Intel than they just didn’t see it coming.

But like I said it’s a difference in opinion and how many links you have which doesn’t change the facts that if you take a moment and think about it, it really doesn’t look the way it used to.
 
Of course they saw it coming. The thing they really saw though, was that the Athlon would scale fast, and without putting out something, and fast, they would be behind the eightball. All the more so because of people like Thomas Pabst.
They new they needed 6 months or so, so they dumped Williamette on the market. It was a throw away, but it got people's attention. Sure, it was a pos, but it was a fast clocked pos, and it gave them a little more time to work on northwood.
Problem was, they couldn't get northwood to work on the 133 fsb. A major step backward, on a chip that really needed the band width, so they dumped the northwoodA on the market. Again with the damage control. It was a pos, but it scaled better, and it gave them time to bring out the P4b. Problem then was the quad pumped bus. They wanted to work on a 166 fsb, but quad pumped, that would be 666, the number of the beast. Cant do that in god's country. But they could scale, and so they did.
It was only the ability of the P4b to scale, that got Intel back the crown.