If they can talk about overclocking potential, they can talk about performance potential. Of course, maybe AMD wants to get people's attention away from actual performance by focussing on clock speed numbers...it seemed to work for Intel in the P4 days.

So if Intel does get 7 GHz then AMD will start mad and rise the Phenom 2 to 8 GHz.

spearman914So if Intel does get 7 GHz then AMD will start mad and rise the Phenom 2 to 8 GHz.

i seriously doubt it. I think Phenom 2 hits a wall around 6GHz. Perhaps in later revisions they can up that somewhat but i dont think it will be a considerable increase.

MelvisMaybe in the states but not here in australia, the lowest dual core from intel over here is about the same amount as AMD's highest end dual core, and then there is the price of mobo's there even more to, i say to people i build comps for, how much you willing to spend? and its always on a budget around $1000 and ill say ok that be a AMD system, since i can get a AMD system to out perform a intel system for the same price. (Gaming Machines) But if it was over $2000 then yea i would go intel, but 99% of the time, people dont want to spend that much, so its a no brainer realy.

Just remember computer parts here are alot more expensive then over there, eg the new i7 lowest quad is $600, the high end, over $2500.

Actually, lowest is $464. Average around $500 just to be safe.
Highest is $1850. Average around $2000 just to be safe. ;)
Still expensive, but not what you were saying. :)

on topic
Kinda funny how Intel is admitting they are going to cheat because they THINK AMD cheated.

there like a big child ,, naa stupid amd cheating so im goin cheat to ,its not fair!!

my prediction is phenom 2 will out perform core 2 due cpus hopfully qx9970 but thats as good as the could hope plus if it outperformed i7 singletreaded that would be a big boost for there busness.

Disruptor4Actually, lowest is $464. Average around $500 just to be safe.
Highest is $1850. Average around $2000 just to be safe. ;)
Still expensive, but not what you were saying. :)

on topic
Kinda funny how Intel is admitting they are going to cheat because they THINK AMD cheated.

Well i guess that might be true if i typed it straight into staticice or shopbot those prices might be true, but not were i get all my computer parts from, and i was been nice.
And those prices are online and we all know its cheaper to buy online, so if you went to your local computer shop it would be even more :eek:
So trust me, when i say there at that price^ i mean thats at a cheap price compared to your local computer or electronic store :)

Sounds pretty cool, but this is exactly why you shouldn't give a rats a** about what some magazine or one show can do with a processor, they are handpicking the EE binned chips for a single demonstration to show off... That really shows what the average chip can do...

Still going to stick with my Core 2.

OnBoardIf you didn't read through the xtremesystes thread, that pictured chip does 4,8HGz on air. Sounds pretty :-o, but it was running 120C with temp chip disabled :) I don't doubt that AMD might have disabled temp sensor as well, point isn't to run the processor safe, but to OC it as high as possible and those quads push a lot of heat out.

Also there was talk to going to FUGGER's house to do it, and 5 other cherry babies were going to Las Vegas. So that first trip is how to do it and in CES '09 they'll just repeat the steps with a new chip.

the AMD chip was on LN2 i doubt it had the temp chip disabled it would make no difference it was sub-zero during all testing

TheGuruStudand 5.4 on LN2 is.... supposed to impress me? Those ES chips are probably higher quality than production chips, too.

ES chips are in no way shape or form "better" than production chips my E7200ES clocked no better than any other E7200ES they are more of a butchered together chip if anything else

tiggerMaybe if amd can run their chips at twice the speed of intels,it may make up for the performance per clock deficit.

These benches and speeds mean squat to normal people.

AMD does 3 IPC and intel does 4 IPC so it would only need to be running 25% faster ;) oh adn lets remember AMD chips scale very well with speeds while intel's do not

cdawallES chips are in no way shape or form "better" than production chips my E7200ES clocked no better than any other E7200ES they are more of a butchered together chip if anything else

I meant as in they're 100% cherry picked. They're obviously not going to send a out a half-ass pre-production chip and it always seems that the quality doesn't change from then until production. And unless intel is magically having high yields, I would expect those ES cherries doing better than a lot of the production ones.

Isn't the rumor that intel has bad yields on new stuff? I know no one ever talks about it.

MelvisWell i guess that might be true if i typed it straight into staticice or shopbot those prices might be true, but not were i get all my computer parts from, and i was been nice.
And those prices are online and we all know its cheaper to buy online, so if you went to your local computer shop it would be even more :eek:
So trust me, when i say there at that price^ i mean thats at a cheap price compared to your local computer or electronic store :)

No, really, that's how much I get my parts for. (roughly a little bit more) So trust me. What store are you going to? As in, what state? Because they are ripping off hardcore.
If I was to be stupid and buy i7, these are the prices I'd pay:
920: $519.00
940: $1,054.00
965EE: $2,109.00

Disruptor4No, really, that's how much I get my parts for. (roughly a little bit more) So trust me. What store are you going to? As in, what state? Because they are ripping off hardcore.
If I was to be stupid and buy i7, these are the prices I'd pay:
920: $519.00
940: $1,054.00
965EE: $2,109.00

NSW lol i think thats enough said there, been the most expensive state in Australia.
The store i go to is the one i showed you^ they have good service and most of the time competitive prices, and i cant fault them, and i know if i went to a computer shop like, leading edge computers it would cost a F load since there a good 30% more expensive then the place i get my parts from online. So going from what prices there showing that would be ALOT you know.
As i thought i typed the CPU into staticice and found the 920 for as low as $459.00 at PC Maniacs. So im guessing were i get my Parts from there just a bit expensive, or there supplier is charging alot for the CPU's
I agree you have to be stupid to buy this CPU now, and or have deep pockets and don't care.

cdawallthe AMD chip was on LN2 i doubt it had the temp chip disabled it would make no difference it was sub-zero during all testing



ES chips are in no way shape or form "better" than production chips my E7200ES clocked no better than any other E7200ES they are more of a butchered together chip if anything else



AMD does 3 IPC and intel does 4 IPC so it would only need to be running 25% faster ;) oh adn lets remember AMD chips scale very well with speeds while intel's do not

AMDs don't scale any better than Intels at higher speeds.

Going by your 25% performance difference, it would only take 4.5GHz out of a Core2Quad to match the 6Ghz Deneb. That doesn't even take into account i7. But at any rate, there is much more to it than how IPCs each chip can do. There's branch prediction, pipeline dumps, cache misses, and many other factors to take into account, so we still know nothing of these chips, to be honest. We have no idea how a 6GHz Deneb truely compares to the Intels. If it only matches a 5Ghz c2q, for example, it's all for naught anyway.

I am not concerned with the clock speed of these chips in the slightest. All that matters is performance. My guess is still that AMD is going to be behind in that category. Only time will tell.

Wile EAMDs don't scale any better than Intels at higher speeds.

Going by your 25% performance difference, it would only take 4.5GHz out of a Core2Quad to match the 6Ghz Deneb. That doesn't even take into account i7. But at any rate, there is much more to it than how IPCs each chip can do. There's branch prediction, pipeline dumps, cache misses, and many other factors to take into account, so we still know nothing of these chips, to be honest. We have no idea how a 6GHz Deneb truely compares to the Intels. If it only matches a 5Ghz c2q, for example, it's all for naught anyway.

I am not concerned with the clock speed of these chips in the slightest. All that matters is performance. My guess is still that AMD is going to be behind in that category. Only time will tell.

I think I'll get a hold of this guy I know that does custom bumper stickers, and have him make me one that reads "You could learn a lot from a Wile."


Seriousy, Wile has been running AMD from time to time, admittedly, and with conviction, yet he still honors the truth. Intel's whirlwind stomp-ass blitzkrieg has totally obliterated AMD for the last several years, and none of this inane nerd gossip about 6 or 7ghz is going to change that.

Besides, Intel just jacked the one technology advantage AMD had, which was Hyper Transport.

So...yes, you all could learn a lot from a Wile.

*Disclaimer, Wile E is entitled to royalties, of which amounts are not yet disclosed. A lawyer will approach Mr. E, at the appropriate time.

newconroerBesides, Intel just jacked the one technology advantage AMD had, which was Hyper Transport.

Actually Intel doesnt use Hyper Transport, what they do use is an onboard memory controller inCore i7 CPUs, and as you said, that was one of the few advantages AMD had over intel. I just wish AMD would get the f**k off their ass and implement triple, or better yet, quad channel memory controller on their CPUs.

KBDActually Intel doesnt use Hyper Transport, .....

Err, what he meant was "FSB replacement".

btarunrErr, what he meant was "FSB replacement".

yea, i think he meant Quick Path Interconnect but its not Hyper Transport just similar

KBDyea, i think he meant Quick Path Interconnect but its not Hyper Transport just similar

Well obviously he wasn't trying to say Intel uses HyperTransport, what he meant was AMD no longer holds the technology lead as far as an FSB replacement goes.

It was supposed to be mocking. But thanks for the defense BT.

AMD, while not matching in performance, offered that one bit of advanced technology for quite a long time, and for me at least, was what made me prefer their type of design.

And with Quick Path, they've lost that edge.

Sometimes, I'd start to think that HT was what caused them to fall behind, even if theory would suggest otherwise. If QuickPath only increases Intel's performance, then under that premise, I really don't know what in the heck AMD has to do to catch up.

I'd really like to see them go aggressive toward some sort of Unix/Linux platform, working alongside Sun to create desktops (or laptops) as well as server machines(for which they already have a strong foothold), and churn out something similiar to a MAC, but with obviously different instruction sets. With that kind of support behind it, and the freedom of open source, Windows might start to fade, as developers got hooked on a more friendly Unix platform.
If it was succesful, then it could also be streamlined into the "home entertainment" industry, as we see lots of large format displays using embedded operating systems. I have this notion that in the future(and we see it in the evolution of home appliances in the last twenty years)dang near everything in your home will be operated via a central box of some sorts, that has all kinds of networking, wireless and other functions, which can be programmed, timed, manipulated etc, but with a very user friendly approach, much like adjusting the settings on your Plasma television.

I'm off on a rant here, but with AMD's touts of a 'platform' approach with things like the Spyder(or is it Spider?), it just seems like the thing to do, and a way for them to get out of the rat race with Intel.

And heck, for all you anti-Intel and MS folks, if such a system worked, it would be killing two birds with one stone! :)

Wile EAMDs don't scale any better than Intels at higher speeds.

Going by your 25% performance difference, it would only take 4.5GHz out of a Core2Quad to match the 6Ghz Deneb. That doesn't even take into account i7. But at any rate, there is much more to it than how IPCs each chip can do. There's branch prediction, pipeline dumps, cache misses, and many other factors to take into account, so we still know nothing of these chips, to be honest. We have no idea how a 6GHz Deneb truely compares to the Intels. If it only matches a 5Ghz c2q, for example, it's all for naught anyway.

I am not concerned with the clock speed of these chips in the slightest. All that matters is performance. My guess is still that AMD is going to be behind in that category. Only time will tell.

i noticed better scaling amongst the AMD's i clocked vs the intel's i've clocked i could go pull benchmarks if you would like. AMD's scale very well over 3ghz while intel's don't start to push till around 4ghz and top ~5ghz before it takes huge clock to get a performance difference. this is what i have seen if you have seen different i would love to see

newconroerSometimes, I'd start to think that HT was what caused them to fall behind, even if theory would suggest otherwise. If QuickPath only increases Intel's performance, then under that premise, I really don't know what in the heck AMD has to do to catch up.

i dont HT is the reason they are behind, its more of combination factors. They got complacent when they were on top, made almost no architectural improvements. Bad timing for buying ATI and so forth. The only thing that can save them now is a totally new architecture, similar to what Intel did when they developed C2D.

cdawalli noticed better scaling amongst the AMD's i clocked vs the intel's i've clocked i could go pull benchmarks if you would like. AMD's scale very well over 3ghz while intel's don't start to push till around 4ghz and top ~5ghz before it takes huge clock to get a performance difference. this is what i have seen if you have seen different i would love to see

You have it backwards my friend. The problem is not that AMD scales better above 3Ghz, it is that AMDs scale TERRIBLY below 3GHz. Once you get above 3Ghz, scaling is linear. I've tested that up to 3.7ish Ghz.

All of the Core2 chips I have used have pretty much scaled linearly across the whole range I've tested, from 1.8Ghz all the way to 4.6Ghz. The only time scaling differs is when the FSB is a bottleneck. Once that bottleneck is gone, scaling is linear. You can check that for yourself by setting a high fsb, and using the multi only to clock. And someday I'll finally get the DICE pot up and running to check scaling above 5Ghz.

tiggerMaybe if amd can run their chips at twice the speed of intels,it may make up for the performance per clock deficit.

These benches and speeds mean squat to normal people.

if you need to OC it twice the speed of intels and on LN@ than i would love to meet the indavidual who bought AMD to OC to that level to reach intels performance.

KBDi seriously doubt it. I think Phenom 2 hits a wall around 6GHz. Perhaps in later revisions they can up that somewhat but i dont think it will be a considerable increase.

unless of course this ends up being a huge letdown for AMD fans because they pulled a P4 and increased the lenth of the pipelines to reach the clock....which means they would need to double clock cycles and that wouldnt still ONLY let them break minimum and keep up with the loss of the pipes.

OctaveanThe Phenom II will have a lower "instructions per clock cycle" then the i7 and Core 2 so it already has to clock higher.

Actually, on average (across a large suite of applications), current Phenoms are at an 8-9% disadvantage when compared with Core 2 at the same clock.

AMD has stated, at 3.0 GHz, a Phenom II will be 30-40% faster than the current fastest Phenom at 2.6 GHz. Let’s take the conservative approach. If Phenom II is only 30% faster than current Phenoms, and you eliminate the frequency advantage of Phenom II, at the very same clock Phenom II will be approximately 12.6% faster than Phenom.

In other words, as already stated by analysts and hinted by AMD, Phenom II is likely to be even with or slightly faster than Yorkfield processors, clock-for-clock.

This is also supported by very conservative documented estimates of an average 5% increase in same-clock IPC resulting from enlarging of cache and 3% from core improvements – a combined 8.1% IPC improvement.

I caution that this is only a very conservative prospect. If you consider the scenarios in which an application (or game) will benefit from 3 times the cache, the IPC improvements will be far greater than described above. (Keep in mind, K10’s average improvement was approximately 15% over K8. Yet in many single-threaded applications and games, it is not uncommon to see 24-40% gains at the same clock).

Also, even if Yorkfield and Deneb find themselves dead-even in most scenarios, Deneb will shine in memory instensive situations, with lower latencies and higher throughputs.

This tells us one thing. Intel didn’t rush to Core i7 as a luxury; it was forced to in order to maintain its leadership. In the coming months, we’ll see sub-$300 Phenom 940/945 processors that rival and beat 1000-dollar QX9650s, and with just as much overclocking headroom.

Owners of current AM2+ platforms will have the last laugh – and here’s why:

• Statistics show the vast majority of Intel Quad owners are sporting Q6600s (limited to 3.6-3.8 GHz, at best, on average while expending far more energy and outputting significantly more heat than next month’s PII 940).
• Intel owners of Yorkfield 45nm Quads either have to spend $1000+ for an unlocked processor or, otherwise, face the fact the less expensive Quads are multiplier-limited.
• AM2+ platform owners will require a mere BIOS update and CPU swap to enjoy unlocked performance (potentially to 4GHz and beyond), while spending fewer than $300.
• Intel Core 2 platform owners wishing to undo being outdone by PII 940/945 PCs will have to spend – at a minimum – $500 for a platform and CPU change and closer to $1000 if seeking a premium MB and having to purchase quality DDR3 – only to outperform PII 940/945s by an even smaller margin than Yorkfields.

The good news is that the above will cause significant downward shifts in pricing, making previously unattainable (or undesirable) purchase prospects possible for many.