Intel Penryn

[Matt2]

No matter how revolutionary anything Intel brings to the table, AMD will always be right there. Have been since the K6, finally took over with K7 and has held Intel down throughout K8.

Instead of hearing about all these new and fancy innovations Intel is implementing, how about doing so at a reasonable price, ala AMD???

When that happens, I will take Intel seriously.

 

[Viditor]

Excellent posts...many thanks PM!!

:thumbsup:

 

[AMDrulZ]

Have you guy's forgot AMD has been developing The K9 or K10 or whatever they decide on calling it. For some time now and know what intel is doing long before any of us do so WTF makes you think they are not prepared for thease new chip's intel have been designing and will produce in the future????

don't forget about pacifica and DDR2 Memory controller, And Interegrated PCIe Controller. AND the quad core chip's i don't care what you say with all of that technology on one chip that will be impresive???

AMD is not VIA or Transmeta that some intel fanboy's might think and they will have a response to these new intel chip's and beat them down like they do with the prescott's the more intel tries to make something good they more they screw it up !!!!!!!

 

[Intelia]

Well I don't no if Tecs are as you say Inefficient or not( David says not). I know he uses them to cool the water only and has perfect temp control of the water. AS for desk cases I am only aware of 1 company that makes 1 and thats Lian Li. He will offer a system that doesn't include the $1500 dollar chiller system. That is 100% passive (NON O/C).
Yes he will not bring it to market till its the way he wants with Intel and ATI inside.
We already know that they well be a hard sell and very low volume.
But there performance in gaming should be unrivaled. Than the Freeupgrade that will be already figured in the price is very nice.

 

[Intelia]

Originally posted by: pm
Some fab terminology (at Intel anyway, but most of these are industry-wide):

tape-in : the layout database is frozen and begins the check-out process looking for issues (such as metal density issues among many others). This is done by the team who designed the chip.
tape-out : the layout database has been checked the team and is ready for manufacturing. In the old days, the tape reel would be shipped to the mask shop. Nowadays, the files are transferred. This is also done by the team who designed the chip.
fracture : the layout database is turned into mask layers. This is done by a mask team, mask shop, or fab company
first silicon/A0 silicon/post-silicon : the very first revision of a chip
sampling : an early "beta" chip that is shipped to OEM customers for early team and system check-out
product-shipping/product ready : in theory, this means that you can buy it on the street.
stepping : a revision of a mask-set. Could be thought of as something akin to a new version of software. Steppings at Intel are designated, letter/number, such as A0, B2, C1, etc. The letter indicates a computer mask revision (all, or nearly all, layers changed), a number indicates only a few layers changed - typically metal layers. A design could go from A0 -> B0 -> C0, but more commonly goes A0 -> A1 -> A2 -> B0 or something similar. Mask sets are expensive, and the more layers changed the more time it takes to get the silicon through the fab.

So, it's not possible for anyone to have a chip without having taped it out. The mask set is required to manufacture it.

As far as comments on 45nm, etc. It is too early for anyone to conclude much of anything about 45nm. Charlie is a smart guy but he's stretching in this article. No matter who is source is, no one knows what 45nm is going to look like yet. The switch to "3D gates" will be a one-shot massive improvement in leakage, but this will just reset the leakage back to the days of 0.18um silicon in terms of leakage. Similarly a switch to "high-K" gates would be a one-time massive improvement in leakage. Either one will be a huge change to the semiconductor design, manufacturing, and - in the case of "3D gates" - the semiconductor CAD industry. It is almost certain that one of these two will occur in the 45nm or 30nm timeframe, but neither one is a "sure thing" at this point. Once the change has been made, future process steps will result in further increases in leakage... the clock will be reset back a bit, but it will start ticking down again. Neither is a permanent fix for the leakage problem, and both introduce a whole new level of complexity in and of themselves.

PM I am assuming that this post was not meant for me as I was already aware of all this which I am quite sure you knew.
Now that everyone is on the same page here,s a link

Gee Dave's only been gone 2 days and I am so lonely.I hope there's no earthquakes in San Francisco while he's there.6 more days till he's home bummer. It wouldn't be so bad but I just got home from our yearly sisters vac. To top it off there"s no really good articles to read . Oh! my what to do what to do.

http://www.tomshardware.com/hardnews/20050816_163912.html

http://www.neoseeker.com/news/story/4896/

 

[pm]

Originally posted by: Intelia
PM I am assuming that this post was not meant for me as I was already aware of all this which I am quite sure you knew.

No. It wasn't meant for you... although my comments about 45nm were in response to the Inquirer article that you linked. The definition of terms was in response to an earlier comment that there were chips available but it hadn't taped-out yet. I started a post to mention that you need to tape-out to have chips, and then turned it into a list of terms because some of the explanation lead to other terms...

 

[Intelia]

Originally posted by: AMDrulZ
Have you guy's forgot AMD has been developing The K9 or K10 or whatever they decide on calling it. For some time now and know what intel is doing long before any of us do so WTF makes you think they are not prepared for thease new chip's intel have been designing and will produce in the future????

don't forget about pacifica and DDR2 Memory controller, And Interegrated PCIe Controller. AND the quad core chip's i don't care what you say with all of that technology on one chip that will be impresive???

AMD is not VIA or Transmeta that some intel fanboy's might think and they will have a response to these new intel chip's and beat them down like they do with the prescott's the more intel tries to make something good they more they screw it up !!!!!!!

Start a thread with links could be interesting reading. Even though Intel amd have a tech agreement I dought Intel will share the compiler stuff they got with the Russian purchase and To me if this is True its a really really big deal.

 

[Intelia]

Originally posted by: Acanthus
I dont think you understand what i am trying to say.

Under supercooled conditions, you cannot in any way reliably predict how far a chip will scale, based on the results of the supercooling.

Supercooling allows clockspeeds that are not possible on air cooling, because air cooling can never go below ambient temps.

Exotic cooling systems, in your case, the waterchiller on the Dothan, do not in any way represent how far the CPU can or will scale in clockspeed.

Iwouldn't call 20C summer 10c winter super cooling would you.

 

[Vegitto]

Originally posted by: Intelia

Originally posted by: Acanthus
I dont think you understand what i am trying to say.

Under supercooled conditions, you cannot in any way reliably predict how far a chip will scale, based on the results of the supercooling.

Supercooling allows clockspeeds that are not possible on air cooling, because air cooling can never go below ambient temps.

Exotic cooling systems, in your case, the waterchiller on the Dothan, do not in any way represent how far the CPU can or will scale in clockspeed.

Iwouldn't call 20C summer 10c winter super cooling would you.

Well, that'd mean that it's not fan nor water cooling, seen that they can never reach any temperature under the room temperature. Otherwise, the air in the room would heat up the processor, instead of cooling it down.

 

[AMDrulZ]

intelia im not saying that the new intel chip's are going to be bad chip's but don't forget that AMD knows about intel chips long before the we do. Spies/insider's and so forth so they know what they are up to and intel know's what AMD is up to. in the end it its the better architecture/design that matter's. The chip's features are just as important as a chip's seed. Not to mention how well the cpu talks to the rest of the system. intel will eventually stop using the front side bus system. and AMD has a very good alternative with the hyper transport. and i bet if intel want's hypertransport AMD will want something back in return. maybe compilers ?????

 

[Intelia]

I honest to god don't care what amd does .I am very interested in what intel is up to. This is a thread about Intel AMD should have never been mentioned.

Start a thread about future AMD plains I will read it but won't post.

 

[Intelia]

Originally posted by: AMDrulZ
intelia im not saying that the new intel chip's are going to be bad chip's but don't forget that AMD knows about intel chips long before the we do. Spies/insider's and so forth so they know what they are up to and intel know's what AMD is up to. in the end it its the better architecture/design that matter's. The chip's features are just as important as a chip's seed. Not to mention how well the cpu talks to the rest of the system. intel will eventually stop using the front side bus system. and AMD has a very good alternative with the hyper transport. and i bet if intel want's hypertransport AMD will want something back in return. maybe compilers ?????

AMD can use any intel tech available but they have to develop it . They can use the tech but not intels tech. Intel will develop their own ondie controller they don't need AMD. Iam sure intel enginners can create hypo. tech. Fact is Ramdus well sell a lic. to anyone that wants their very good memory controler just ask ATI

NDA'S are so cool

 

[AMDrulZ]

then AMD will do what they do best and make a better type of intels same technology and the thing's continue like normal. nothing new!!!!

 

[Intelia]

That might be true but THEY HAVE TO DEVELOP THE TECH . Intel is not going to say here amd use this.

 

[RichUK]

Intelia - was you aware that AMD created hyperthreading.

Thats AMD tech

 

[AMDrulZ]

isn't that what AMD said to intel whent they gave them the information intel needed to make EM64T compatible with AMD64 ????????

oop's i mean fully compatible with AMD64 !!!!!!

 

[pm]

Intelia - was you aware that AMD created hyperthreading.

Come again? The original work on simultaneous multithreading was done at Cray based on research performed at the University of Washington. The first implementation of SMT was a Cray supercomputer. Regardless of the original work, Intel's Hyperthreading has some unique traits - specifically with the ways that it interacts with chipsets.

 

[Intelia]

Very good Pm .Impressive

 

[Acanthus]

cooling below ambient increases the clockspeed ceiling of the chip.

once again you argue in affairs you dont even begin to understand.

keep tossing around random speculation news links and tossing random sentences youve seen others post though.

Its amsuing.

 

[Intelia]

Ya Iam LOL

 

[RichUK]

Originally posted by: pm

Intelia - was you aware that AMD created hyperthreading.

Come again? The original work on simultaneous multithreading was done at Cray based on research performed at the University of Washington. The first implementation of SMT was a Cray supercomputer. Regardless of the original work, Intel's Hyperthreading has some unique traits - specifically with the ways that it interacts with chipsets.

what i meant to say is that AMD had patented the technology, although this is what i have heard on the forums, i dont know accurate this claim is.

 

[clarkey01]

Hyperthreading is an elegant fix to a complicated and market drive architecture, netburst. It's importance will decrease as years pass by with higher IPC designs and shorter pipeline architectures becoming the focus of Intel?s .

AMD will be mixing in a few years time by adding more pipelines for scaling. Webber said this in a an interview not too long ago.

I?d like to paste something from a thread about speculation and claims from a resurgent Intel following on ths board:

I don?t pay attention to the hype. itanic was suppose to take over the world and kill X86, Nehalem (netburst) was to hit 10.25 Ghz in 2005 and prescott was suppose to be the final nail in AMD's coffin after the poor showing of the 3200 AXP.

Itanic didn?t take over the world. It didnt kill x86. Nehalem and the long terms of plans of netburst were ditched. 10 Ghz or even 4Ghz was not seen in 2005. Prescott was delayed and became preshott and handed the performance crown over to AMD for being a backwards step interms of performance over northwood. One thing I dont get is this second coming of christ with Dothans offspring. No numbers or reviews are out. You cant just go into forums saying "Oh you AMD fanboys watch out, your goona die and fab 36 will fall". That hasn?t been the tone of this thread but we see it all the time in pentium M related posts

I remember 2 years ago an Intel worker telling me that prescott was the final nail in AMD's coffin. I mean if Intel responds well and offers, a cheaper, faster, cooler running chip than AMD which is all rounded (no weak FPU) then I have no reason to stay with AMD.

RnD and work in boston/DD/East fishkill continues. AMD are working constantly, something some of you like to pretend doesn?t happen.

 

[IntelUser2000]

What I see is that the design team for Pentium M is better than the one for desktops. At least what their products say. The desktop design team didn't manage to make a satisfying product ever since... Pentium II. Even the Northwood P4 was a disappointment. I couldn't see how less than 10% increase in performance per clock could ever make P4 competitive. It did, but because the competitor screwed up, not because Northwood was good, it was OK.

Hype for Conroe spread by FALSELY made up rumors and speculations by I-know-nothing-but-I-pretend-I-do writers.
-30% faster than Yonah per clock
-Its based on EPIC or some form of VLIW and uses translation software for 32-bit


The second one is definitely wrong, and I can confidently say that. First one is also in doubt because Yonah improves upon already impressive Dothan. I would expect average of 10-15% per clock over Yonah at BEST.

 

[IntelUser2000]

Not only Yonah which is 65nm, is taped-out, I heard its even on A0 silicon. Conroe was taped out only few weeks ago...

I don't know about Presler, but considering its shipping date of Q1 2006, I think its safe to say its on A0 silicon too.

 

[stratman]

Yeah didn't they have a demo Yonah machine up and running at some con?