Intel Penryn

[Intelia]

Quote Viditor One last note...Intel's planned quad cores are not integrated. They will be similar to Smithfield in that they will be 2 Woodcrest chips glued together. In addition, they will still be utilizing the FSB model instead of ptp...this means that the bandwidth of 4 cores will all have to fit on a 1066MHz FSB. This will be a HUGE bottleneck!
Towards 2007/2008, they will probably move it to the Whitefield's platform (with the CSI ptp), and that will be when we see it perform properly///////// ?????????????????????????????????????????????????????????????? Actuall the newcastle dual FSB is rather fast the reviewers are really impressed. Using Paxville Cpu's
These chips are going to give AMD a very hard time. They do almost everything right,
Cloverton
. It is a four core, two Woodcrest die MCM, and it is slated for Q4 2006, probably early in that quarter. There was a JAB version on the drawing board, but that would have delayed it until after the quad K8, and that is unacceptable to Intel, so they are pulling it in at the cost of performance. I still am of the opinion that AMD will pip them with a quad core K8 even if volumes are not great. We will see. Is it really going to be a woodcrest glued to gether I don't think so. Why would Intel glue together 4 cores when the P6 core was all ready 4core ready? Woodcrest is a merom correct

Also the yonah based Sossaman is also said to have a 4 core brother. why would intel do this? Research they can get the work done now and go from there.


Your also forgetting about Paxville. Here ya go it didn't come out of my hat but its a good link


http://www.theinquirer.net/?article=25439

 

[Intelia]

Wrong ans. p4e running at 7GHZ has it. Posted it on the 10th. Super pi record

 

[Intelia]

Originally posted by: jazzboy
What i dont get is that they say that leakage isnt a problem on 45nm - which is nice, but therefore surely intel couldve seen early enough that leakage would be a problem on their preshots.

The 45nm will be the first time intel will use 3D gates the tech wasn't ready till now.

 

[Duvie]

Originally posted by: Intelia

Originally posted by: jazzboy
What i dont get is that they say that leakage isnt a problem on 45nm - which is nice, but therefore surely intel couldve seen early enough that leakage would be a problem on their preshots.

The 45nm will be the first time intel will use 3D gates the tech wasn't ready till now.

You mean trigate???

 

[Intelia]

Right Duvie! I thought that was the IBM AMD version. I thought Intels was called 3D gate

 

[Keysplayr]

Originally posted by: RichUK

Originally posted by: Intelia
This post and the post to day and yesterday is just unfo i got off the web . I highly suspect your a coward hiding behind a keyboard
Hay richey intel has the Super PI record

was that aimed at me .. if so WTF ..

and yes i am aware that the Dothan holds the 1M super-pi record .. this is because it offloads it all into the 2Mb L2 cache, and the level 2 cache has a low latency, match that with high clock speed and you have a winner for just the 1M super-pi run .. and if you think i am an AMD fanboi you are very much mistaken ..

You seem to think it actually matters how it's done. Still doesn't change the outcome.

 

[RichUK]

Originally posted by: keysplayr2003

Originally posted by: RichUK

Originally posted by: Intelia
This post and the post to day and yesterday is just unfo i got off the web . I highly suspect your a coward hiding behind a keyboard
Hay richey intel has the Super PI record

was that aimed at me .. if so WTF ..

and yes i am aware that the Dothan holds the 1M super-pi record .. this is because it offloads it all into the 2Mb L2 cache, and the level 2 cache has a low latency, match that with high clock speed and you have a winner for just the 1M super-pi run .. and if you think i am an AMD fanboi you are very much mistaken ..

You seem to think it actually matters how it's done. Still doesn't change the outcome.

and whats that supposed to mean , get one of those doing a 32M test and things would be different .. what i am trying to say is the 1M record means absolute sh!t, a proper test would be the 32M.

 

[Intelia]

Originally posted by: RichUK

Originally posted by: keysplayr2003

Originally posted by: RichUK

Originally posted by: Intelia
This post and the post to day and yesterday is just unfo i got off the web . I highly suspect your a coward hiding behind a keyboard
Hay richey intel has the Super PI record

was that aimed at me .. if so WTF ..

and yes i am aware that the Dothan holds the 1M super-pi record .. this is because it offloads it all into the 2Mb L2 cache, and the level 2 cache has a low latency, match that with high clock speed and you have a winner for just the 1M super-pi run .. and if you think i am an AMD fanboi you are very much mistaken ..

You seem to think it actually matters how it's done. Still doesn't change the outcome.

and whats that supposed to mean , get one of those doing a 32M test and things would be different .. what i am trying to say is the 1M record means absolute sh!t, a proper test would be the 32M.

Who says you

 

[Duvie]

They are all legit records....The only pat I dislike is an unstable system can run 1mb and yet not run 4mb to 32mb....I could run it on a system that would have to be backed off 50mhz+ to get 32mb stable and still run 1mb....I dont put much stock in it, but the benchmark whores at extremesystems do....That is pretty much with most of their systems only do...

 

[Intelia]

Duvie you already no I agree with you but legit is legit.
Go to the orb how many don't complete the CPU test. The rules have to be changed so that only stable systems qualify.

 

[DarkKnight69]

I am not an intel Fanboy, but I am definatly impressed by their recent processor advances since they stepped out of the netburst crap. The Dothan is an awesome sincle core. The Yonah is taking 2 more powerful Dothans on one chip.

The Dothan uses a 12 stage pipe compared to AMD's 10 Stage and yet it is faster clock for clock. That would indicate that the pipeline is faster than AMD's. As well to take into account that that include no on-board memory controller.

Putting 4 amd's on one chip is going to be pointless. We are going to be sitting here comparing it to the cell going WTF is the point!!!

 

[DarkKnight69]

Originally posted by: Viditor

Originally posted by: Intelia
HAY get off AMD this is a Intel post . All the post states is that Intel has 45 nano leakage beat and this is what I got so far talk about trolls.

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

From richuk

lol .. AMD we will be right there to catch them up, or over take them with performance at that point in time so you have to look at both sides before w00ting for Intel.

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%


From Markfw
Whats wrong with "wait and see"? Its still gossip until somebody benches one.

Mark whats bench marking got to do with leakage

&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&

Clarkey 01

As if AMD dont have anything in development and are hoping an x2 in 3 years will still be enough to have the performance crown..

This Intel come back isnt the second coming of christ

Clarkey they fixed the leakage thats all.

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Viditor

1. AMD and IBM have already produced lab (hand tooled) versions of the 45nm as well at East Fishkill...they are also working on the 22nm versions


Ya lets here about the first tapout of the 65 n before you sput off about the 45n


3. AMD is shipping their quad cores at the beginning of 2007


So is Intel maybe 2006 Intels well be 65n Maybe 45n in 2007

$$$$$$$$$$$$$&&&&&&&&&&&&&&&!!!!!!!!!!!!!!!!!!!#################^^^^^^^^^^^^^

Talk about trolls you are among the people always accusing others

Ummm...AMD has been producing sample 65nm chips for months now...try google.
Both Intel and AMD will be shipping 65nm chips next year, 45nm won't be production ready till at least the end of 2007, which means that it won't ship till 2008.

BTW...please point to ANY post wherein I referred to you as a troll!

One last note...Intel's planned quad cores are not integrated. They will be similar to Smithfield in that they will be 2 Woodcrest chips glued together. In addition, they will still be utilizing the FSB model instead of ptp...this means that the bandwidth of 4 cores will all have to fit on a 1066MHz FSB. This will be a HUGE bottleneck!
Towards 2007/2008, they will probably move it to the Whitefield's platform (with the CSI ptp), and that will be when we see it perform properly.

They will be integrated, Intel itself has stated that the 8xx series was not integrated because they were too rushed...I dont think they are stupid enough to 'overlook' that bottleneck!

 

[Duvie]

Originally posted by: DarkKnight69
I am not an intel Fanboy, but I am definatly impressed by their recent processor advances since they stepped out of the netburst crap. The Dothan is an awesome sincle core. The Yonah is taking 2 more powerful Dothans on one chip.

The Dothan uses a 12 stage pipe compared to AMD's 10 Stage and yet it is faster clock for clock. That would indicate that the pipeline is faster than AMD's. As well to take into account that that include no on-board memory controller.

Putting 4 amd's on one chip is going to be pointless. We are going to be sitting here comparing it to the cell going WTF is the point!!!

I thinkyou are wrong there...A64 K8 cores are longer then 10 stage pipelines.....


To early to tell what is going to be worthless....it really depends on the software industry and where they want to go....I think Intel is prodding them into the multicore direction though....

I will be more impressed with Yonah..I have a Dothan and I am not impressed so far with my cadd performance versus my AMD systems...They have there weaknesses and yonah should help in those areas...

 

[DarkKnight69]

I apologize, K7 was 10 stage, K8 is 12 stage.

Dothan has 12 (estimate, true value unknown) as well.

 

[sonoran]

Originally posted by: Kensai
Who cares if they have the technology?

Steve Jobs? ?Our goal is to provide our customers with the best personal computers in the world, and looking ahead Intel has the strongest processor roadmap by far? - Steve Jobs, June 6, 2005.

* Not speaking for Intel Corporation *

 

[Duvie]

Originally posted by: sonoran

Originally posted by: Kensai
Who cares if they have the technology?

Steve Jobs? ?Our goal is to provide our customers with the best personal computers in the world, and looking ahead Intel has the strongest processor roadmap by far? - Steve Jobs, June 6, 2005.

* Not speaking for Intel Corporation *

That is funny since apples have not been on the forefront of new technologies of recent....


I bet you they never even considered AMD.....

We will see since none of us can see in the future...last year we were thinking 5ghz Tejas was going t happen...see where that went to....

 

[Intelia]

Originally posted by: DarkKnight69
I am not an intel Fanboy, but I am definatly impressed by their recent processor advances since they stepped out of the netburst crap. The Dothan is an awesome sincle core. The Yonah is taking 2 more powerful Dothans on one chip.

The Dothan uses a 12 stage pipe compared to AMD's 10 Stage and yet it is faster clock for clock. That would indicate that the pipeline is faster than AMD's. As well to take into account that that include no on-board memory controller.

Putting 4 amd's on one chip is going to be pointless. We are going to be sitting here comparing it to the cell going WTF is the point!!!

Ya I really don't know how cell got into this. I believe it goes back to reading comprehension again. This post was about intel getting rid of the the leakage problem with their process and Duvie was the only one that knew what was going on.

Intel 3D gates. Duvie this is correct . As IBM,AMD are flat gates

 

[Intelia]

Duvie you know what I find interesting . When these are released the GHZ race will be back.

Referring to the 45nm cpu's

 

[Duvie]

Could very well be...Both will have similar pipeline stage lengths and we can actually compare them again....

 

[Intelia]

Originally posted by: Duvie

Originally posted by: sonoran

Originally posted by: Kensai
Who cares if they have the technology?

Steve Jobs? ?Our goal is to provide our customers with the best personal computers in the world, and looking ahead Intel has the strongest processor roadmap by far? - Steve Jobs, June 6, 2005.

* Not speaking for Intel Corporation *

That is funny since apples have not been on the forefront of new technologies of recent....


I bet you they never even considered AMD.....

We will see since none of us can see in the future...last year we were thinking 5ghz Tejas was going t happen...see where that went to....

Oh so very true. But ya got to love that operating system and the ecstics of the apple products.

 

[Intelia]

I can see AMD and intel well over 6GHz by 2009

 

[RichUK]

Originally posted by: Intelia
I can see AMD and intel well over 6GHz by 2009

lol ... you make me laugh

EDIT: are you still a fool and think that Ghz mean everything, parallelism is the future

 

[Intelia]

Originally posted by: RichUK

Originally posted by: Intelia
I can see AMD and intel well over 6GHz by 2009

lol ... you make me laugh

EDIT: are you still a fool and think that Ghz mean everything, parallelism is the future

And you have know idea whats really going on

 

[fatty4ksu]

:thumbsdown:

Originally posted by: RichUK

Originally posted by: Intelia
I can see AMD and intel well over 6GHz by 2009

EDIT: are you still a fool and think that Ghz mean everything, parallelism is the future

Classless.

 

[clarkey01]

Originally posted by: Intelia
Duvie you know what I find interesting . When these are released the GHZ race will be back.

Referring to the 45nm cpu's

If there using a high IPC design like dothan there wont be a Ghz race. AMD have said (webber) that they will add pipelines and focus more on clock speed as well as tweaks to the memory controller in the future. I dont know why Intel doesnt put out higher clocked pentium M's. The seem to overclock well but everytime I see a speed bump its like 2.1 Ghz over 2 Ghz. The K8 see's 3 Ghz in Q1. People wanna argue that dothan is faster clock for clock (ever so slightly) but if AMD can get a bit of a gap in terms of Mhz then it doesnt count much.