PCPER.com: 5 GHZ+ Phenom II Overclock on Dry Ice, 6Ghz on LN2

Printable View

Show 100 post(s) from this thread on one page

11-20-2008, 11:52 PM
clonez

oh, wonderful news

phenom 2 for me, lads :D

6ghz.... whee, didnt think ill be seeing that on an amd processor, ever... :eek:
yet breaking down the coldbug on that architecture
11-20-2008, 11:56 PM
Omastar

Quote:

Originally Posted by Newblar

so would deneb justify buying any amd stock? ive been looking for some very good and cheap technology stock, and if amd can last then id like to buy a few hundred stocks
but the problem is nehalem in the server market, we all know that the regular consumer market is nothing to the server market for cpu's. and nehalem would absolutely tear the deneb server version (forgot name ^_^) and amd a new one

I've had AMD for a while now, and at this news, I'm even more sure of hanging onto it. ;)
11-21-2008, 12:05 AM
BakerT

Hope its true.

Getting AMD back in the game would be awesome.

Faster and cheaper hardware for everyone!
11-21-2008, 12:19 AM
massman

So many sources are confirming this message .... Yeeha! :D
11-21-2008, 12:28 AM
Thallid

If this is true, I am so ready to buy a AMD-system
11-21-2008, 12:31 AM
s0lid

You're saying these don't have coldbug and they will be cheaper than bloomies?

I say: I'm getting an phenom the second!
11-21-2008, 12:32 AM
Shintai

Lets just hope the retail ones can keep the same numbers. And hope these aint another cherry picked ones like the 3Ghz Phenom that was earlier.

Also as said the 6Ghz already changed. Plus here is abit more about the rest:

Quote:

AMD took care of that itself at an event in Austin this morning, where it showcased four overclocked Phenom II systems. TR editor-in-chief Scott Wasson was on the scene, and while AMD didn't allow attendees to take pictures, he jotted down a few details.

The slowest system—cooled with a heatsink and fan—managed to reach just under 4GHz with a 1.55V core voltage. With liquid cooling, AMD successfully pushed a 45nm Phenom II in another machine just over the 4GHz mark. That required kicking up the CPU voltage to 1.6V, however. For the other two systems, AMD took out the big guns. One was strapped to a phase-change cooler and reached the mid-4GHz range at 1.7V, while the fastest system managed to well over 5GHz using liquid nitrogen (which kept the core temperature down to a chilly -185°C).

So no 4Ghz without water. And even with phase its mid 4Ghz at 1.7V. And the 5Ghz+ was 1.9V.
11-21-2008, 12:53 AM
Stukov

Quote:

Originally Posted by Shintai

Lets just hope the retail ones can keep the same numbers. And hope these aint another cherry picked ones like the 3Ghz Phenom that was earlier.

Also as said the 6Ghz already changed. Plus here is abit more about the rest:

So no 4Ghz without water. And even with phase its mid 4Ghz at 1.7V. And the 5Ghz+ was 1.9V.

There he is!

Funny thing is, that's not what most sites are saying, at least thats not the consensus. So you start off talking about cherry picking, then go cherry pick a statement/news article....:nono:
11-21-2008, 01:00 AM
duploxxx

Quote:

Originally Posted by IvanAndreevich

I bet somewhere between Kentsfield and Yorkfield in per clock performance.

Looking forward to it, if it's true. First AMD chip I am considering since S939 Opteron.

mostly NB speed will decide where the final performance ends against the intel parts.... its already shown on shanghai that cache latency and prefetch is way better, nb speed on deneb will be higher then shanghai.

Quote:

Originally Posted by Shintai

Lets just hope the retail ones can keep the same numbers. And hope these aint another cherry picked ones like the 3Ghz Phenom that was earlier.

Also as said the 6Ghz already changed. Plus here is abit more about the rest:

So no 4Ghz without water. And even with phase its mid 4Ghz at 1.7V. And the 5Ghz+ was 1.9V.

:welcome: to an AMD news thread

perhaps first make a list of all kents and york's that hit 4ghz below 1,55vcore on air playing games (no not just cpu-z) before you make such a statement...

here he goes again :rolleyes:
11-21-2008, 01:05 AM
Nedjo

Quote:

Originally Posted by informal

There are reports that some ATi people are to be "blamed" (:)) for this kind of shift in marketing and product strategy.It seems it's working,so kudos to them :)

those reports about shift in marketing are true, but real address for kudos is Dresden design center and AMD-IBM team in Fishkill ;)

Don't remember who posted this explanation about AMD's 65nm doldroms (maybe Hans)

http://www.eetimes.com/news/semi/sho...printable=true

But with 45nm tech things are complitely different, and AMD/IBM team has done some amazing job with their imersion 45nm tech, that yield all these goodies (lack of coldbug, high voltage tolerance, high clocks...)

You can read all about it here: http://www.eetimes.eu/semi/showArtic...printable=true

this part is most significant:

The new design of the PFET moves the embedded silicon-germanium source/drain regions closer to the channel to maximize the transfer of stress, thereby increasing hole mobility. Although shorter gate lengths are not driving the improvements, it is a reduction in dimensions that allows increased channel stress to provide the performance scaling. AMD 45-nm PFET design reduces the space from embedded silicon-germanium to the channel edge by half.

The transistor drive current for AMD's 45-nm devices is much lower than that of the Intel HKMG transistors. But power consumption is quickly becoming a high priority for server chips. AMD's transistors exhibit very low channel leakage.

Our transistor benchmarks indicates that leakage current is less than one-third of the value measured on AMD's 65-nm process. It's also significantly lower than the Intel 45-nm HKMG process. In fact the Ion/Ioff ratio for AMD's PFET is nearly 10 times better than that for the Intel PFET.

oh when I remember some comments on this forum that SOI is doomed with coldbug for eternety, and that is unable to produce any benefits beyond 90nm tech :rolleyes:
11-21-2008, 01:07 AM
Shintai

Quote:

Originally Posted by Stukov

There he is!

Funny thing is, that's not what most sites are saying, at least thats not the consensus. So you start off talking about cherry picking, then go cherry pick a statement/news article....:nono:

Its funny how 6Ghz reported by everyone is now 5Ghz+ by everyone :D

And not even 4Ghz on air?

I wonder what more will change.

And you seem to want a flamewar?
11-21-2008, 01:09 AM
Shintai

Quote:

Originally Posted by Nedjo

those reports about shift in marketing are true, but real address for kudos is Dresden design center and AMD-IBM team in Fishkill ;)

Don't remember who posted this explanation about AMD's 65nm doldroms (maybe Hans)

http://www.eetimes.com/news/semi/sho...printable=true

But with 45nm tech things are complitely different, and AMD/IBM team has done some amazing job with their imersion 45nm tech, that yield all these goodies (lack of coldbug, high voltage tolerance, high clocks...)

You can read all about it here: http://www.eetimes.eu/semi/showArtic...printable=true

this part is most significant:

The new design of the PFET moves the embedded silicon-germanium source/drain regions closer to the channel to maximize the transfer of stress, thereby increasing hole mobility. Although shorter gate lengths are not driving the improvements, it is a reduction in dimensions that allows increased channel stress to provide the performance scaling. AMD 45-nm PFET design reduces the space from embedded silicon-germanium to the channel edge by half.

The transistor drive current for AMD's 45-nm devices is much lower than that of the Intel HKMG transistors. But power consumption is quickly becoming a high priority for server chips. AMD's transistors exhibit very low channel leakage.

Our transistor benchmarks indicates that leakage current is less than one-third of the value measured on AMD's 65-nm process. It's also significantly lower than the Intel 45-nm HKMG process. In fact the Ion/Ioff ratio for AMD's PFET is nearly 10 times better than that for the Intel PFET.

oh when I remember some comments on this forum that SOI is doomed with coldbug for eternety, and that is unable to produce any benefits beyond 90nm tech :rolleyes:

Remember AMDs 65nm was also better than Intels 65nm in this area....
11-21-2008, 01:09 AM
Final8ty

Quote:

Originally Posted by hollo

maybe 6g post but no boot and AMD don't want to take any 'risks' right now?:D

Its more likely that they want to show enough to get the enthusiasts interested & not enough to get the attention of Intel that could lead Intel slashing prices heavily on its product range before AMD gets the P2 out the door.

It worked for ATI with NV prices being way off the mark because ATI held a little back of the 4XXX's full potential.
11-21-2008, 01:10 AM
Sly Fox

In fairness this isn't the final stepping. Could be even better come retail launch.
11-21-2008, 01:15 AM
JumpingJack

Quote:

Originally Posted by Nedjo

Our transistor benchmarks indicates that leakage current is less than one-third of the value measured on AMD's 65-nm process. It's also significantly lower than the Intel 45-nm HKMG process. In fact the Ion/Ioff ratio for AMD's PFET is nearly 10 times better than that for the Intel PFET. [/i][/b]

I am struggling to believe this statement without the IV curves and Ion/Ioff curves to assess the validity of this.... it just sounds way way to much.

here is what I mean, Intel's drive current for PMOS is about 1000 uA/um at an Ioff of 100 nA/um ... that is a ratio of 10:1, for AMD to be 10 times better would mean that at a Ion of 600ish that the EETimes article is quoting ... their Ioff would need to be 6 nA/um this is an order of manitude lower than any PMOS Ioff ever reported for a high performance high Vt proces. Ever.

It is just hard to believe.... hopefully AMD/IBM will produce some data at IEDM in a few weeks and we will be able to see if this guys claims are true... I sincerely doubt it.
11-21-2008, 01:21 AM
Nedjo

Quote:

Originally Posted by Shintai

Its funny how 6Ghz reported by everyone is now 5Ghz+ by everyone :D

And not even 4Ghz on air?

I wonder what more will change.

And you seem to want a flamewar?

I don't think that Andreas would lie:

http://www.nordichardware.com/news,8389.html

Quote:

Originally Posted by Andreas G

AMD decided to takes things in its own hands during an event in Austin, Texas. It took the unreleased Phenom II, based on the quad-core Deneb architecture, and slapped a pot suitable for exotic on it. After lowering the temperature to -185°C and raising the voltage to somewhere north of 1.9V the processor was able to move north of 6GHz. We don't know the exact frequency. At this time this is actually higher than what Nehalem can do.
11-21-2008, 01:24 AM
railer

while i'l be glad if amd is back in the game, i'l believe it when i see it. With so much hype lately and no actual delivery from amd anything is possible. Let's see retails do that.
11-21-2008, 01:26 AM
Rammsteiner

Quote:

Originally Posted by Shintai

So no 4Ghz without water. And even with phase its mid 4Ghz at 1.7V. And the 5Ghz+ was 1.9V.

Pfew, I was almost afraid you wouldnt show up anymore, but well, you prolly have the same reason as Ive anyway regarding timzone and stuff.

Anyway, how many Intel systems actually reach 4Ghz+ without water? There's a few nice chips from Intel but seriously, there ain't a lot different with those results compared to Intel:rolleyes:

But it's indeed recommendable not to have too cherry picked chips, more of pre-testing a bunch not to risk to have a lemon.
11-21-2008, 02:22 AM
saaya

Quote:

Originally Posted by RPGWiZaRD

:cheer:

This news came with a big suprise to me. What I'd really like to see is how nonhandpicked samples fare overclock wise

average 3.6 on air with 1.4v, more voltage doesnt help really...

Quote:

Originally Posted by Shintai

So no 4Ghz without water

some chips can do 4ghz on air (TRUE) with 1.4v but not that many...
11-21-2008, 02:36 AM
Solus Corvus

Quote:

Originally Posted by saaya

average 3.6 on air with 1.4v, more voltage doesnt help really...

some chips can do 4ghz on air (TRUE) with 1.4v but not that many...

Are you speaking from personal experience with these chips? Or are these your estimates?
11-21-2008, 02:39 AM
Shocker003

I hope this is for real. I haven´t seen any cpu that turned me on after the Q6600. Maybe AMD will recandle my cpu upgrading flame. Well guys don´t forget what happened with the release of HD 48XX CARDS: (lowered prices and something new to play with) On a more serious note, ain´t you guys bored with overclocking only Intel chips.
11-21-2008, 02:39 AM
dread77

Quote:

Originally Posted by massman

So many sources are confirming this message .... Yeeha! :D

AMD fanboy detected...:p:

Anyway, these are GREAT news for the consuming community. Competition = Lower Prices = Better technologies to come... etc :up:
11-21-2008, 02:39 AM
Leeghoofd

the future looks nice :) hopefully most can do 3.6-4Ghz... will this be AMD's comeback ?... nice to have some competition again...2009 will be fun
11-21-2008, 02:47 AM
Helmore

Quote:

Originally Posted by Solus Corvus

Are you speaking from personal experience with these chips? Or are these your estimates?

Saaya works for Foxconn if I remember correctly, so I guess it's from experience.

I pretty much expected these chips to be cherry picked, but that does not mean we won't be seeing any of its overclock potential. Current 65 nm. Phenoms don't always have a coldbug either, so it's not something that came out of nowhere. My guess is that we will be seeing coldbugs on Phenom II, but not on all of them (hopefully not on most of them).

The AM3 versions of Deneb will probably be even better than these stepping C2 version and 4 GHz. on air should not be a rare sight to see with those is my guess. The C3 2,8 GHz. part has a DP of 95 compared to the 125 W. of the C2 version of the same clock, that has got to account for some improvement to the process and CPU. I'm eager to know what these chips will clock like in about a year from now, as AMD has the tendency to greatly improve its manufacturing process over time.

EDIT:

BTW guys, could we stop making nasty comments (or flame baiting/trolling) to others, even if you consider that other user to do so himself (once in a while). You should not say things about others and to others that you don't like to be said about you. Or how some would say it, don't lower yourself to someone else's standards. It will only put you in bad light, so speak.
11-21-2008, 02:52 AM
Solus Corvus

Quote:

Originally Posted by Helmore

Saaya works for Foxcon if I remember correctly, so I guess it's from experience.

Well he certainly seems to have connections. But it's not necessarily a given which is why I asked.

That makes me think of another question I'd be interested to know: Does foxconn have any plans for future enthusiast AM2+/AM3 boards?
11-21-2008, 02:54 AM
Motiv

Quote:

Originally Posted by Solus Corvus

Are you speaking from personal experience with these chips? Or are these your estimates?

saaya, tony and fugger. They usually speak the truth.

These chips sound pretty good.
11-21-2008, 02:59 AM
Helmore

Quote:

Originally Posted by Solus Corvus

Well he certainly seems to have connections. But it's not necessarily a given which is why I asked.

That makes me think of another question I'd be interested to know: Does foxconn have any plans for future enthusiast AM2+/AM3 boards?

My guess would be yes, they already have AM2+ motherboard and I don't see them stopping production on those anytime soon. Whether they will attempt anything for AMD like their 'bloodrage' and similar boards, I'm not sure. I'd see they will but probably not as pricey as their Intel boards and thus not as high quality. AMD won't be the top performer and people will consider them to be a good choice when on a budget, which makes it kind of weird to make very expensive motherboards for AMD.
11-21-2008, 03:04 AM
Tony

saaya

Who told you they were hand picked samples? i read they were random picked and this is an average of what you can expect.

For those asking if I was there, i was not, lots of friends were though and we supplied hardware for the show...as such i was able to ask questions as this story was breaking.

You just have to love XS for this no CPU-Z it did not happen attitude...i still have an unreleased Intel CPU here that fools CPU-Z, so for me the reports on multiple websites all claiming the same from reporters who were at the event means a lot more.

I will restate what i stated earlier...the industry needs this, competition is not only good for the consumer it drives technology forward at a faster pace.

Now we wait to see how it benchmarks...
11-21-2008, 03:05 AM
Eson

If i see more of these clocks then i will never doubt AMD again.
11-21-2008, 03:26 AM
biohead

i myself was hinting that they fixed the coldbug before this news came to light... as with regular phenom HTT base ref. clock and temperature seem to be unrelated, and that's big in itself.

guess it's confirmed now :toast:
11-21-2008, 03:33 AM
dinos22

Quote:

Originally Posted by saaya

average 3.6 on air with 1.4v, more voltage doesnt help really...

some chips can do 4ghz on air (TRUE) with 1.4v but not that many...

thanks for the info
this is very useful to know where we are at exactly

so i assume massman is overly optimistic when he says CPC is same as core i7 :D??
11-21-2008, 03:44 AM
junior-21-

Very very interesting! :D A lot of things are starting to convince me that it might be true! :D So looking forward to own one of these 45nm AMDs! :D
11-21-2008, 03:45 AM
STaRGaZeR

Quote:

Originally Posted by Tony

No CPU-Z...it did not happen!!!...come on guys we all know this happened ;) you don't need a CPU-Z as all the press there actually saw it real time.

No, maybe you do know, not us. We are not blind believers, or at least me. I would never trust a hypothetical 8GHz Core2/i7 until I see the benches and the numbers. This is not a religion you know ;)
11-21-2008, 03:53 AM
Miss Banana

Awesome news, but question:

Up to what point is the new southbridge responsible for achieving these speeds?

I have a 790X MB now with the old SB, and kinda wonder if all these wonderful OC stories may not be for me, unless I buy a new MB.
11-21-2008, 03:54 AM
Stukov

Quote:

Originally Posted by Shintai

Its funny how 6Ghz reported by everyone is now 5Ghz+ by everyone :D

And not even 4Ghz on air?

I wonder what more will change.

And you seem to want a flamewar?

Quote:

sorry for the difference... AMD Is limiting what we can say about the processor right now... What you saw before I edited this thread was correct though.

http://forums.legitreviews.com/about...4c0729#p129466

Didn't you read the thread? (I mean XS thread this was stated earlier when someone pointed out it said 5.x Ghz not 6 anymore) Do I want a flamewar, absolutely not. Am I expecting certain indviduals to hit the ground spinning? Yes, very much so. And I wouldn't mind a good old fashion arguement/discussion, which seems some peeps are already having.
11-21-2008, 03:59 AM
T_Flight

They are probably backing off because they don't wanna have to live up to 6GHz and realize that those were exceptional chips. We've got one person that works with this stuff saying not many will do that.

If that's the case, I applaud them. It's better to be careful until you know what the release stuff is gonna do on average, not just the high end. :)
11-21-2008, 04:08 AM
herderien

good news if AMD is back for consumers !
11-21-2008, 04:12 AM
dread77

Quote:

Originally Posted by Tony

saaya

Who told you they were hand picked samples? i read they were random picked and this is an average of what you can expect.

Quote:

AMD also said that these weren't totally cherry picked samples and that these results are about average from what they are seeing with early samples. If that proves true on retail samples it will make for an interesting part!

Source

IMO there is no such thing like Totally Handpicked and Partially Handpicked.
Either you choose to test 100 out of 1000, or test the whole batch you are selecting the best possible overclocking cpu from a certain ammount.
11-21-2008, 04:14 AM
tiborrr

Congrats to AMD, waiting on more results and benchmarks. Looks like february '09 might bring me 790GX DDR3 + Deneb BE :D
11-21-2008, 04:25 AM
Stukov

Quote:

Originally Posted by dread77

Source

IMO there is no such thing like Totally Handpicked and Partially Handpicked.
Either you choose to test 100 out of 1000, or test the whole batch you are selecting the best possible overclocking cpu from a certain ammount.

Based on how AMD manufactures that actually makes sense. They will have multiple chip batches that may get tweaked mid process. What they may be saying is they didn't cherry pick the processor but, selected from a good batch.
11-21-2008, 04:31 AM
Hornet331

Quote:

Originally Posted by Eson

If i see more of these clocks then i will never doubt AMD again.

worse mistake ever. :rofl:

My approach, doubt everything form everyone, everytime. :p:
11-21-2008, 04:35 AM
STaRGaZeR

Quote:

Originally Posted by Hornet331

My approach, doubt everything form everyone, everytime. :p:

:clap:
11-21-2008, 04:46 AM
SAE

Great progress AMD was showing there. They just had to catch up... it's been said in this thread several times. The market just needed it.
I'd luv to see some benches at 4.5GHz (SS phase) now. Really looking forward to them.
11-21-2008, 04:50 AM
Hans de Vries

Quote:

Originally Posted by JumpingJack

I am struggling to believe this statement without the IV curves and Ion/Ioff curves to assess the validity of this.... it just sounds way way to much.

here is what I mean, Intel's drive current for PMOS is about 1000 uA/um at an Ioff of 100 nA/um ... that is a ratio of 10:1, for AMD to be 10 times better would mean that at a Ion of 600ish that the EETimes article is quoting ... their Ioff would need to be 6 nA/um this is an order of manitude lower than any PMOS Ioff ever reported for a high performance high Vt proces. Ever.

It is just hard to believe.... hopefully AMD/IBM will produce some data at IEDM in a few weeks and we will be able to see if this guys claims are true... I sincerely doubt it.

Thie abstract below was already a while on IEDM's technical program for
December. Not yet implemented on current Shanghai's but still to come.

Notice that a NMOS drive current of 1354μA/μm (without HKMG) is the same
as on Intel's HKMG process . The current Shanghai has been measured to
have a PMOS drive current of 660 μA/μm. Much less as the 857μA/μm
mentioned here.

Quote:

Originally Posted by IEDM-2008

27.7 Implementation and Optimization of Asymmetric Transistors in Advanced SOI CMOS
Technologies for High Performance Microprocessors,

J. Hoentschel, A. Wei, M. Wiatr, A. Gehring, T.
Scheiper, R. Mulfinger, T. Feudel, T. Lingner, A. Poock, S. Muehle, C. Krueger, T. Hermann*, W. Klix*,
R. Stenzel*, R. Stephan, P. Huebler, T. Kammler, P. Shi, M. Raab, D. Greenlaw, M. Horstmann, AMD
Fab 36 LLC & Co. KG, *University of Applied Science Dresden

Sub-40nm Lgate asymmetric halo and source/drain extension transistors have been integrated into leadingedge
65nm and 45nm PD-SOI CMOS technologies. The asymmetric NMOS and PMOS saturation drive
currents improve up to 12% and 10%, respectively, resulting in performance of NIDSAT=1354μA/μm and
PIDSAT=857μA/μm. Product-level implementation show a speed benefit of 12%.

http://www.his.com/~iedm/program/sessions/s27.html

Regards, Hans
11-21-2008, 05:20 AM
Helmore

Quote:

Originally Posted by Hans de Vries

Notice that a NMOS drive current of 1354μA/μm is the same as on Intel's HKMG process without the HKMG.

Uhm I'm not exactly getting what you are saying.
Are you saying that the NMOS driver current of 1354μA/μm on AMD's 45 nm. process is the same as on Intel's 45 nm. HKMG process, even though AMD's process does not use HKMG? Or is that NMOS driver current of AMD's 45 nm. process the same as what Intel would get if they had a 45 nm. process that did not use HK materials and metal gates? I'm guessing the former....

Could it be that their C3 revision of Shanghai and Deneb will implement these optimizations? That could explain the lower TDPs on their AM3 Deneb chips.
11-21-2008, 05:24 AM
Calmatory

Quote:

Originally Posted by STaRGaZeR

No, maybe you do know, not us. We are not blind believers, or at least me. I would never trust a hypothetical 8GHz Core2/i7 until I see the benches and the numbers. This is not a religion you know ;)

Not even if Core2 was shrunk to 32nm and there were a lot of tweaks made to enable them clock higher(E.g. AMD got rid of coldbug, higher clocks come from better process), and when there are multiple people and websites claiming the exact same? CPU-Z has it's flaws, it can be tricked. ;)
11-21-2008, 05:24 AM
v_rr

Quote:

Originally Posted by dread77

Source

IMO there is no such thing like Totally Handpicked and Partially Handpicked.
Either you choose to test 100 out of 1000, or test the whole batch you are selecting the best possible overclocking cpu from a certain ammount.

weren't totally cherry picked
11-21-2008, 05:30 AM
Calmatory

Quote:

Originally Posted by T_Flight

They are probably backing off because they don't wanna have to live up to 6GHz and realize that those were exceptional chips. We've got one person that works with this stuff saying not many will do that.

If that's the case, I applaud them. It's better to be careful until you know what the release stuff is gonna do on average, not just the high end. :)

Still AMD is not claiming that their CPUs clock to 6 GHz. If they claim something, it is that their some/at least one of their CPUs can clock to 6 GHz.

People can just use "Wheres the claimed 6 GHz chips now? :ROTF:" to troll. I'm waiting for this from Shi.. someone.
11-21-2008, 05:42 AM
dread77

Quote:

Originally Posted by v_rr

weren't totally cherry picked

I didn't say something different...:shrug:

I am just disputing the term "Partially".
11-21-2008, 05:53 AM
Hans de Vries

Quote:

Originally Posted by Helmore

Uhm I'm not exactly getting what you are saying.
Are you saying that the NMOS driver current of 1354μA/μm on AMD's 45 nm. process is the same as on Intel's 45 nm. HKMG process, even though AMD's process does not use HKMG? Or is that NMOS driver current of AMD's 45 nm. process the same as what Intel would get if they had a 45 nm. process that did not use HK materials and metal gates?

I'm guessing the former....

Indeed.

Quote:

Originally Posted by Helmore

Could it be that their C3 revision of Shanghai and Deneb will implement these optimizations?

I don't know, but I guess not. I guess it would be a later revision.

Quote:

Originally Posted by Helmore

That could explain the lower TDPs on their AM3 Deneb chips.

Is it really lower? Once you need to increase voltage to go faster you
get a 3rd power law:

95W x (3.0 GHz / 2.8 GHz)^3 = 123W

So 95W for a 2.8GHz versus 125W for a 3.0GHz seems inline with this.

Regards, Hans
11-21-2008, 05:58 AM
Helmore

Quote:

Originally Posted by Hans de Vries

Indeed.

I don't know, but I guess not. I guess it would be a later revision.

Is it really lower? Once you need to increase voltage to go faster you
get a 3rd power law:

95W x (3.0 GHz / 2.8 GHz)^3 = 123W

So 95W for a 2.8GHz versus 125W for a 3.0GHz seems inline with this.

Regards, Hans

Ah ok.

I was talking about the fact that the AM2+ Deneb chip at 2,8 GHz. has a TDP rating of 125 W., while the AM3 version of pretty much the same chip has a TDP rating of 95 W. It's not exactly a night and day difference, but at least there is some improvement.
11-21-2008, 06:02 AM
informal

INQ(referrencing CRN) disclosed the exact max. frequency of 940 under LN2,it's 6.3Ghz.That's mere 11% lower than 7Ghz.I guess that extreme benchers will have fun time conquering the 7Ghz milestone now that 6.3Ghz was done on pre-production stepping.
11-21-2008, 06:02 AM
savantu

Quote:

Originally Posted by Hans de Vries

Thie abstract below was already a while on IEDM's technical program for
December. Not yet implemented on current Shanghai's but still to come.

Notice that a NMOS drive current of 1354μA/μm is the same as on Intel's
HKMG process without the HKMG. The current Shanghai has been
measured to have a PMOS drive current of 660 μA/μm. Much less as the
857μA/μm mentioned here.

http://www.his.com/~iedm/program/sessions/s27.html

Regards, Hans

AMD/IBM is 1354/857 NMOS/PMOS at what voltage and Ioff ?

Intel is 1360/1070 at 1V and 100nA/um Ioff.
11-21-2008, 06:25 AM
biohead

Quote:

Originally Posted by informal

INQ(referrencing CRN) disclosed the exact max. frequency of 940 under LN2,it's 6.3Ghz.That's mere 11% lower than 7Ghz.I guess that extreme benchers will have fun time conquering the 7Ghz milestone now that 6.3Ghz was done on pre-production stepping.

good lord this seems so unbelievable :shocked:
11-21-2008, 06:45 AM
Shocker003

Am not shocked by the news of AMD´s new cpu. They have been playing underdog for a long time and had all the time to rectify their mistakes. Well am waiting for these cpus to hit the shelfs. God 6.3Ghz for the underdog that has recieved a lot of bashing and the cpu was not cherry picked, got me burning with upgrading fever:bows:
11-21-2008, 06:46 AM
Stukov

Quote:

Originally Posted by informal

INQ(referrencing CRN) disclosed the exact max. frequency of 940 under LN2,it's 6.3Ghz.That's mere 11% lower than 7Ghz.I guess that extreme benchers will have fun time conquering the 7Ghz milestone now that 6.3Ghz was done on pre-production stepping.

Yeah, I was just gonna quote that if someone else hadn't. 6.3ghz, even if cherry picked is still pretty darn good. Much better than the 65nm Phenoms in pre-production.

I just wonder what the bad ole...er good ole P4 on 45 or 32nm would clock like.
11-21-2008, 06:52 AM
clonez

6.3 ghz....
damn, that is really fast, even for a post screen (which i expect, win stable would be too good to be true) :eek:
thats like double clock speed than the barcelonas @ launch:clap:

how long itll take until someone gets it bench stable @ 6ghz:cool:
i guess before 8.1 2009 :up:
11-21-2008, 06:52 AM
Hornet331

Quote:

Originally Posted by Stukov

I just wonder what the bad ole...er good ole P4 on 45 or 32nm would clock like.

yeah i wonder that sometimes meyself. :D

32nm HKMG p4... maybe 10 ghz? :p:
11-21-2008, 06:56 AM
clonez

more, given that the 65 nm parts managed over 8 ghz

i would place by bet at around 15ghz
11-21-2008, 06:56 AM
Donnie27

Quote:

Originally Posted by Sly Fox

Well there it is, I'm 100% convinced. :up:

Looks like just like with ATI vs Nvidia I was right... AMD is coming back!

And the best part? i7 is good too, options people!

Odd how when the news is positive for AMD SOOOO many "certain" users don't show up at all. What's up guys? Why no posty?

Here's why I didn't. As I told you, Hornett133 and even LOE;

Quote:

Originally Posted by BE

Damn , Charles no disrespect intended but you are sounding as cynical as Shintai & Donnie

Coming from anyone but him, I'd take that as a compliment. The other side of cynicism is loyalty and fanaticism.

I have a friend who's under NDA giving me what info he can and that's why I said I believed AMDin the other thread, remember? Doesn't change folks here with grudges uh?
11-21-2008, 06:58 AM
Hans de Vries

Quote:

Originally Posted by savantu

AMD/IBM is 1354/857 NMOS/PMOS at what voltage and Ioff ?

Well, It's not from IBM . It's a paper from the AMD Dresden guys who did
manage to do this. I presume they use the (more or less) standard
reference point of 1V/100nA/um. IBM tends to use 200nA/um

Quote:

Originally Posted by savantu

Intel is 1360/1070 at 1V and 100nA/um Ioff.

Yes, The very high PMOS current is because of their gate replacement
process. By etching the whole polysilicon gate away they leave a big gap
and all the strain is released on the channel.

Intel's 32nm HKMG numbers are: Intel is 1550/1210 at 1V and 100nA/um Ioff.
http://btbmarketing.com/iedm/release...news_final.doc

There are also some HKMG numbers from IBM/Freescale/AMD
1630μA/µm and 1190μA/µm have been demonstrated at 1V and 200nA/μm off
corrected for 100nA that would be 1570/1160μA/µm or so.
http://www.his.com/~iedm/program/sessions/s27.html

All still R&D papers of course at the moment.

Regards, Hans
11-21-2008, 07:02 AM
Particle

If I were the one at AMD doing a "partial handpick" I'd be testing about 20-30 random chips and make sure to pick something fairly average--not a lemon and not a cherry. Unrelated: What makes a lemon so bad and a cherry so good? I don't like cherries, but I'll eat a lemon anytime.
11-21-2008, 07:11 AM
D-Cyph3r

I saw this on Guru3D yesterday and couldn't get these forums to load at all.

All I could think was "holy :banana::banana::banana::banana: XS must have destroyed itself in the face of such epic news".

Anyways, birthdays in jan aswell. Deneb for meeeeeee!
11-21-2008, 07:15 AM
Ozzfest05

If they start making really high performance amd boards for this release I might pick one up on release although the intel boards are looking even better then before and they always have looked better then the amd offerings IMO, Ill wait and see
11-21-2008, 07:24 AM
Calmatory

Why would one need "better" board when the current ones can already hit these results?
11-21-2008, 07:27 AM
leoy

Top end 790fx costs 170 euros....
That gx tested only costs 120 eyros...:p::p::p:
11-21-2008, 07:27 AM
Particle

Yeah, I'd rather keep boards like we have now just with better PWMs. I don't need artwork, I just want a slab of PCB with some PCIe slots on it, some RAM slots, and a CPU socket. I care not what it looks like or how "simple" or "old" the layout is. Style can bite me. Give me an affordable board that can demonstrate good performance any day!
11-21-2008, 07:27 AM
Ozzfest05

Quote:

Originally Posted by Calmatory

Why would one need "better" board when the current ones can already hit these results?

IMO the current AM2 offerings arent very impressive im not saying they wont perform but I would rather go with the feature stacked intel 1366 boards which look nice offer performance and are stacked with features
11-21-2008, 07:30 AM
Hornet331

Quote:

Originally Posted by Calmatory

Why would one need "better" board when the current ones can already hit these results?

I think he means "better" board regarding to extras/components. (more sata ports, solid state caps, better power circuit etc... )
11-21-2008, 07:39 AM
DoubleZero

This will make life easier for the ones that like to support the underdog :)

Let's hope that AMD prices Deneb like Shangai, that is cheaper then Barcelona.
11-21-2008, 07:45 AM
Rammsteiner

Quote:

Originally Posted by STaRGaZeR

No, maybe you do know, not us. We are not blind believers, or at least me. I would never trust a hypothetical 8GHz Core2/i7 until I see the benches and the numbers. This is not a religion you know ;)

Im sorry to say, well, sort off, since that post is weird.

Why wouldnt a C2/i7 be able to hit 8Ghz? I mean, I never would have thought P4 couldt hit 8Ghz, but it did. Of course I know the architecture of a P4 is different then C2/i7, but still. I didnt expect in all fairness that i7 would go straight up to 4Ghz without a lot of issues.

Also a CPU-Z validation is worth just as much as a confirmation from multiple sources and people, like Tony and saaya, who should be most of the time unbiased in their expression.

Comparing Tony's post with a religion while your CPU-Z claim tells me that you do not believe it... Although there's been multiple times someone either managed to 'hack' CPU-Z or simply CPU-Z its self made an error. It's a nice program and most of the time it's right, still it ain't anything more reliable than multiple unbiased sources admitting the whole happening.
11-21-2008, 07:57 AM
Nedjo

who asked for pictures?

http://farm4.static.flickr.com/3064/...2863740558.jpg http://farm4.static.flickr.com/3014/...e16e6bc264.jpg http://farm4.static.flickr.com/3011/...961f6107f1.jpg
http://farm4.static.flickr.com/3210/...6e802f34e9.jpg http://farm4.static.flickr.com/3252/...6c52e9771a.jpg http://farm4.static.flickr.com/3040/...a5514a491d.jpg
http://farm4.static.flickr.com/3063/...f97e877777.jpg http://farm4.static.flickr.com/3295/...aaa5749a1d.jpg http://farm4.static.flickr.com/3290/...5f3b89cffb.jpg
http://farm4.static.flickr.com/3269/...6a493d027d.jpg http://farm4.static.flickr.com/3240/...b4fe0ce330.jpg http://farm4.static.flickr.com/3282/...e7d5da92ee.jpg
http://farm4.static.flickr.com/3062/...96d185c7ac.jpg http://farm4.static.flickr.com/3183/...808e43e771.jpg http://farm4.static.flickr.com/3024/...3da4befd62.jpg
http://farm4.static.flickr.com/3048/...21481f056a.jpg http://farm4.static.flickr.com/3008/...265a19869b.jpg

Macci rides again :D
11-21-2008, 08:01 AM
JumpingJack

Quote:

Originally Posted by Hans de Vries

Thie abstract below was already a while on IEDM's technical program for
December. Not yet implemented on current Shanghai's but still to come.

Notice that a NMOS drive current of 1354μA/μm (without HKMG) is the same
as on Intel's HKMG process . The current Shanghai has been measured to
have a PMOS drive current of 660 μA/μm. Much less as the 857μA/μm
mentioned here.

http://www.his.com/~iedm/program/sessions/s27.html

Regards, Hans

Hans,

THanks for the link... this is exactly what I would like to see -- unfortunately, I will need to wait for the proceedings to show up in the library some month or two later -- unless you go to this, in which case you can probably tell us what Ioff they extracted those number from (typically, that is 100 nA/um). The lower drive current in Shangahi is not really a concern, simply depends on the conditions. Typically AMD/IBM report AC Idsat numbers, and it would not surprise me if the chop shop measured it DC.
11-21-2008, 08:03 AM
JumpingJack

Quote:

Originally Posted by Helmore

Uhm I'm not exactly getting what you are saying.
Are you saying that the NMOS driver current of 1354μA/μm on AMD's 45 nm. process is the same as on Intel's 45 nm. HKMG process, even though AMD's process does not use HKMG? Or is that NMOS driver current of AMD's 45 nm. process the same as what Intel would get if they had a 45 nm. process that did not use HK materials and metal gates? I'm guessing the former....

Could it be that their C3 revision of Shanghai and Deneb will implement these optimizations? That could explain the lower TDPs on their AM3 Deneb chips.

That is what the abstracts says, and this is what Intel's 45 nm NMOS driver current is from last year's IEDM. It is hard to compare these numbers from this statement, the abstract does not specify voltage, or Ioff. If they did this at 1.4 V and an Ioff = 200 nA/um, for example, then this is siginficantly lower than Intel's work.
11-21-2008, 08:03 AM
Rammsteiner

Quote:

Originally Posted by Ozzfest05

IMO the current AM2 offerings arent very impressive im not saying they wont perform but I would rather go with the feature stacked intel 1366 boards which look nice offer performance and are stacked with features

I hope you're not fishing at huge heatsinks, fancy colours and putting 'Xtreme' on every part of the board right?

Quote:

Originally Posted by leoy

Top end 790fx costs 170 euros....
That gx tested only costs 120 eyros...:p::p::p:

Top end 790FX is 130 Euro's or so. Besides that, 790FX is already enthusiast chipset anyway:p:

Quote:

Originally Posted by Donnie27

I have a friend who's under NDA giving me what info he can and that's why I said I believed AMDin the other thread, remember? Doesn't change folks here with grudges uh?

Why the need to explain the other side of cynicism? I mean, if he was loyal or whatever, Im sure he wouldnt have an Intel rig:confused: You do know what loyalty stands for, right? Also loyalty doesnt have to be a bad thing, but it depends a bit on what subject though:rolleyes:

Also Ive this certain issue not to believe certain people most of the time if the majority of their posts contains too much under aged context and wrong intentions. Somehow it makes me think this certain group of people are very unreliable:shrug:

Maybe more people have this issue. And in all fairness, I dont see why they should change their mind when they meet certain people who fit in this certain group:rolleyes: If a plane is considered unreliable, and this airplane compagny says it flew without issues 50Km for the first time in 1 year, I still wouldnt want to be in there.

Disclaimer, I love flying, not a rant about planes:p:
11-21-2008, 08:07 AM
GAR

Quote:

Originally Posted by saaya

average 3.6 on air with 1.4v, more voltage doesnt help really...

some chips can do 4ghz on air (TRUE) with 1.4v but not that many...

Thats a bummer. So far about 75% of i920's are hitting 4ghz with 1.4v + some only needed 1.25-1.35v. Mine does 3.8GHZ with 1.27v
11-21-2008, 08:07 AM
Sparky

Quote:

Originally Posted by Ozzfest05

IMO the current AM2 offerings arent very impressive im not saying they wont perform but I would rather go with the feature stacked intel 1366 boards which look nice offer performance and are stacked with features

Yeah, but all those features cost $$$$ and lots of it. The prices on those boards are waaay too high IMO. My old DFI 790FX-M2RS was almost perfect feature-wise, just a little beefier digital PWM is all it really needed IMO :yepp:
11-21-2008, 08:08 AM
Donnie27

Very niceeeeeeee pics. Thanks!

http://www.xtremesystems.org/forums/...6&postcount=15

Quote:

Originally Posted by Donnie27

Alright 4+GHz overclocking (water), sweet, time to move back to AMD Yes, I believe them:up:.
11-21-2008, 08:09 AM
Hornet331

Quote:

Originally Posted by Rammsteiner

Top end 790FX is 130 Euro's or so. Besides that, 790FX is already enthusiast chipset anyway:p:

Search for the Foxconn A79A-S or the ASUS M3A79-T Deluxe. ;)
11-21-2008, 08:12 AM
JumpingJack

Quote:

Originally Posted by Rammsteiner

Im sorry to say, well, sort off, since that post is weird.

Why wouldnt a C2/i7 be able to hit 8Ghz? I mean, I never would have thought P4 couldt hit 8Ghz, but it did. Of course I know the architecture of a P4 is different then C2/i7, but still. I didnt expect in all fairness that i7 would go straight up to 4Ghz without a lot of issues.

The stead march toward higher and higher clockspeed has reached a fundamental limit above and beyond the power wall. The ability to clock a device 'faster' depends on more than just the max power. A transistor can only clock as fast as it's ability to 'turn on', a group of transistors can only clock as fast as the ability for the cumulative circuit to reach the correct evaluation phase of the 'on' or 'off' state, again by flipping transistor states.

The steady march to more clock as asymptotically approached a flat line, with smaller and smaller incremental increases one lithography node to the next. This is driven in part by smaller gains in transistor performance each iteration, and also driven by added complexity of the circuit design (architecture/IPC).

Jack
11-21-2008, 08:13 AM
Slovnaft

that insulation looks insanely easy compared to x58 boards thanks for the pics.

and hans, posting on XS? wow! i love your site! ALL my backgrounds are from chiparch :D great info-we need this level of understanding.
11-21-2008, 08:14 AM
PetNorth

Quote:

Originally Posted by RPGWiZaRD

I was already assuming that, 1.45v is still a decent amount on aircooling for 45nm process. I was thinking along the lines ~1.365v Intel <-> ~1.45v AMD whereabouts I concider safe 24/7 usage. Now if AMD's Phenom II is more resistant I don't know of course but I said I was only assuming anyways. So yea some ~1.45v overclocks would be interesting.

Quote:

Originally Posted by GAR

Thats a bummer. So far about 75% of i920's are hitting 4ghz with 1.4v + some only needed 1.25-1.35v. Mine does 3.8GHZ with 1.27v

You have to keep in mind vcore default value. For reference, vcore default for Shanghai is 1.35v http://products.amd.com/en-us/Optero...il.aspx?id=494

And this is amazing, because we could think 1.35v is high for a 45nm, but it seems it isn't applicable to AMD 0.45 process, because at the same time, it has a low power consumption. So, for example, 1.50v on air (11% more than default) doesn't seem specially high for these processors. On the contrary, it is even modest :P

I don't know what in hell AMD has done with 0.45, but indeed it seems to be a fantastic work :clap:
11-21-2008, 08:15 AM
Donnie27

Quote:

Originally Posted by Hornet331

Search for the Foxconn A79A-S or the ASUS M3A79-T Deluxe. ;)

Foxconn $160 to $210 and Asus $187 to $265. In both cases, I'd NOT shop at the cheapest sites, they have low ratings. I've been shopping:up: The X58 that I'm also looking at cost $220 and Another I'm told will cost $190, stay tuned!
11-21-2008, 08:19 AM
Calmatory

Quote:

Originally Posted by PetNorth

You have to keep in mind vcore default value. For reference, vcore default for Shanghai is 1.35v http://products.amd.com/en-us/Optero...il.aspx?id=494

And this is amazing, because we could think 1.35v is high for a 45nm, but it seems it isn't applicable to AMD 0.45 process, because at the same time, it has a low power consumption. So, for example, 1.50v on air (11% more than default) doesn't seem specially high for these processors. On the contrary, it is even modest :P

I don't know what in hell AMD has done with 0.45, but indeed it seems to be a fantastic work :clap:

I've lived under assumption that the high temps by higher Vcore aren't really the reason to hesitate bumping Vcore, rather electromigration and such being feared.
11-21-2008, 08:21 AM
Gautam

Quote:

Originally Posted by Nedjo

who asked for pictures?

Macci rides again :D

I spy a Dragon Evo. :D
11-21-2008, 08:48 AM
Nedjo

Quote:

Originally Posted by Gautam

I spy a Dragon Evo. :D

the dragon is so cool! way better than spider:

http://farm4.static.flickr.com/3254/...f5936c17_b.jpg
11-21-2008, 08:49 AM
Sparky

So Nedjo, is this the kind of thing you were hinting at a few days ago? :D
11-21-2008, 08:51 AM
NH|Delph1

Quote:

Originally Posted by Nedjo

I don't think that Andreas would lie:

http://www.nordichardware.com/news,8389.html

I'm not under NDA. ;)

6.3GHz seems correct too.

It's just so sweet when you're right ;)

I still say 3.6GHz is going to be the number most people will hit on air. 4GHz is a bit much.

//Andreas
11-21-2008, 09:04 AM
G0ldBr1ck

This is great news! I realy didnt believe that Deneb was going to have so many improvements but its obvious now that its all true.
11-21-2008, 09:07 AM
Junos

Nice... wasn't expecting this at all. :)

Hopefully they'll be compatitle with my old 690G MSI board, so I can throw my 4000x2 out of the window (you can always dream, eh?).
11-21-2008, 09:12 AM
Calmatory

Quote:

Originally Posted by NH|Delph1

I'm not under NDA. ;)

6.3GHz seems correct too.

It's just so sweet when you're right ;)

I still say 3.6GHz is going to be the number most people will hit on air. 4GHz is a bit much.

//Andreas

Why not beyond 3,6 GHz? CPU just won't go further regardless of Vcore with that temperature? Or high temps due to high Vcore?
11-21-2008, 09:14 AM
G H Z

Quote:

Originally Posted by Nedjo

Macci rides again :D

He must feel really good about this, really nice to see AMD kicking up a little dust again.

Quote:

Originally Posted by Gautam

I spy a Dragon Evo. :D

Is Vince getting any royalties ;) :D
11-21-2008, 09:20 AM
informal

Quote:

Originally Posted by Calmatory

Why not beyond 3,6 GHz? CPU just won't go further regardless of Vcore with that temperature? Or high temps due to high Vcore?

He speaks of regular air cooling(ie. stock) versus higher end air cooling.
With higher end air you should hit 4Ghz+.Voltage is not an issue with Deneb and it runs fairly cool(be it stock or OC/overvolt).
11-21-2008, 09:22 AM
G0ldBr1ck

so could the rumored 4.0-4.3 FX actualy be in the future for Deneb with HighK?
11-21-2008, 09:27 AM
FlanK3r

Quote:

Originally Posted by Shintai

Lets just hope the retail ones can keep the same numbers. And hope these aint another cherry picked ones like the 3Ghz Phenom that was earlier.

Also as said the 6Ghz already changed. Plus here is abit more about the rest:

So no 4Ghz without water. And even with phase its mid 4Ghz at 1.7V. And the 5Ghz+ was 1.9V.

man, old Phenom has coldbug about -30 degrees, this not, now is 6.3GHz. Not 4GHz without water?Lol, i seen 2 Phenoms II at 4GHz with air and one with BOX cooler! U must only waiting :), OC with air Phenom II is from 3.7-4.3GHz ...
11-21-2008, 09:29 AM
Rammsteiner

Quote:

Originally Posted by Hornet331

Search for the Foxconn A79A-S or the ASUS M3A79-T Deluxe. ;)

Does a high price automatically mean a top-end board then? DFI Lanparty DK 790FXB-M2RS, very cheap and just as good:rolleyes:

Quote:

Originally Posted by JumpingJack

The stead march toward higher and higher clockspeed has reached a fundamental limit above and beyond the power wall. The ability to clock a device 'faster' depends on more than just the max power. A transistor can only clock as fast as it's ability to 'turn on', a group of transistors can only clock as fast as the ability for the cumulative circuit to reach the correct evaluation phase of the 'on' or 'off' state, again by flipping transistor states.

The steady march to more clock as asymptotically approached a flat line, with smaller and smaller incremental increases one lithography node to the next. This is driven in part by smaller gains in transistor performance each iteration, and also driven by added complexity of the circuit design (architecture/IPC).

Jack

So... due to C2's improved IPC and more complex architecture this would actually be impossible? But then again, ain't a P4 more complex than its previous Pentiums as well? I dont know, it's a question:p:

Quote:

Originally Posted by Nedjo

the dragon is so cool! way better than spider:

http://farm4.static.flickr.com/3254/...5936c17_b.jpg]

Whoa, looks damn nice! Also looks a bit like Ati Radeon pictures on the box:cool:
11-21-2008, 09:30 AM
CCUABIDExORxDIE

so that phenom II was running at full LN2 temps? woot for no measured coldbug.
11-21-2008, 09:38 AM
demonkevy666

I agree on the pwm level of Am2/Am2+ boards. the asus 790fx sb750 had the highest 8+2 phase. the rest are all 4 or five and some have a +1.
11-21-2008, 09:42 AM
Olivon

Finally ... !

Really a great newz :up:

Show 100 post(s) from this thread on one page

All times are GMT -8. The time now is 01:05 AM.

XtremeSystems