AMD Fusion

Page 3 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Viditor

Diamond Member
Oct 25, 1999
3,290
0
0
Originally posted by: Phynaz

It says the same thing, you can't know how you will build something if you don't know what you're building.

"AMD has not made a final decision solidifying the future of Fusion" is a FAR cry from not knowing what you're building! He is most likely talking about the second iteration of Fusion, not Bulldozer.

The "other guys opinion" was somebody that heard Phil Hester speak at the hot chips conference. It's called reporting. Phil Hesters' talk was paraphrased in simular fashion on many web sites. I'm sure you could use Google to check it out.

Not true...in the section above your supposed quote he was paraphrasing. He clearly delineates the 2 sections...considering my own history as a TV news editor for several years, I think I can speak with some authority here.

Got link for Henri Richard's resignation yet? (that's four requests now, btw).
I thought Bryan was finding one...he said he's read the same thing and he would try to dig one up for you.
 

Phynaz

Lifer
Mar 13, 2006
10,140
819
126
Originally posted by: Viditor
Originally posted by: Phynaz

It says the same thing, you can't know how you will build something if you don't know what you're building.

"AMD has not made a final decision solidifying the future of Fusion" is a FAR cry from not knowing what you're building! He is most likely talking about the second iteration of Fusion, not Bulldozer.

The "other guys opinion" was somebody that heard Phil Hester speak at the hot chips conference. It's called reporting. Phil Hesters' talk was paraphrased in simular fashion on many web sites. I'm sure you could use Google to check it out.

Not true...in the section above your supposed quote he was paraphrasing. He clearly delineates the 2 sections...considering my own history as a TV news editor for several years, I think I can speak with some authority here.

Got link for Henri Richard's resignation yet? (that's four requests now, btw).
I thought Bryan was finding one...he said he's read the same thing and he would try to dig one up for you.


Whatever, constantly arguing with you is lame.

You're wrong, get over it.
 

intangir

Member
Jun 13, 2005
113
0
76
Originally posted by: Viditor
Originally posted by: Phynaz
Originally posted by: Viditor
Originally posted by: Phynaz

Wow, now you know more about Fusion than AMD's Europeon head of marketing.
And yet it was one of his quotes that you used to "prove" that Barcelona was K10.

Or maybe you read the quote wrong, or he was misquoted, or the interview is a reprint...
In any event, I don't see your point as this is a photo of the die...

Correction, that's the photo of a die. I see nothing that proves it's a fusion die.

And I note that you still haven't provided a link...so we are left to compare and contrast this unprovable photo vs your unprovable recollection?
Sorry mate, the photo wins in my book...


Um, 1) that is not a photograph, but a CAD plot as I mentioned above, and 2) that's being claimed as the Bulldozer core and not Fusion. Read the URL for it, c'mon. (http://laptoplogic.com/data/ne...bulldozer_dieshot.jpg)

I'm beginning to think you are purposefully spreading misinformation.
 

Viditor

Diamond Member
Oct 25, 1999
3,290
0
0
Originally posted by: intangir
Originally posted by: Viditor
Originally posted by: Phynaz
Originally posted by: Viditor
Originally posted by: Phynaz

Wow, now you know more about Fusion than AMD's Europeon head of marketing.
And yet it was one of his quotes that you used to "prove" that Barcelona was K10.

Or maybe you read the quote wrong, or he was misquoted, or the interview is a reprint...
In any event, I don't see your point as this is a photo of the die...

Correction, that's the photo of a die. I see nothing that proves it's a fusion die.

And I note that you still haven't provided a link...so we are left to compare and contrast this unprovable photo vs your unprovable recollection?
Sorry mate, the photo wins in my book...


Um, 1) that is not a photograph, but a CAD plot as I mentioned above, and 2) that's being claimed as the Bulldozer core and not Fusion. Read the URL for it, c'mon. (http://laptoplogic.com/data/ne...bulldozer_dieshot.jpg)

I'm beginning to think you are purposefully spreading misinformation.

Ummm...Bulldozer is to be the CPU portion of the core of the first Fusion chip (Falcon).
Text

BTW...the URL is broken. You need to get rid of the parentheses at the end.

Edit 2: I should also add (as I have at least twice in this thread already) that the die shot doesn't matter at all. In order for Fusion to arrive on time (or even in 2010!), it MUST already be in active development...which means it can't possibly be in just the "idea phase".
 

intangir

Member
Jun 13, 2005
113
0
76
Originally posted by: Viditor
Originally posted by: intangir
Originally posted by: Viditor
Originally posted by: Phynaz

Correction, that's the photo of a die. I see nothing that proves it's a fusion die.

And I note that you still haven't provided a link...so we are left to compare and contrast this unprovable photo vs your unprovable recollection?
Sorry mate, the photo wins in my book...


Um, 1) that is not a photograph, but a CAD plot as I mentioned above, and 2) that's being claimed as the Bulldozer core and not Fusion. Read the URL for it, c'mon. (http://laptoplogic.com/data/ne...bulldozer_dieshot.jpg)

I'm beginning to think you are purposefully spreading misinformation.

Ummm...Bulldozer is to be the CPU portion of the core of the first Fusion chip (Falcon).
Text

The die plot posted was of a pure CPU. There are cache structures on the left, two CPU cores to the right, some sort of crossbar between the cores, and I/O pads along the edges of the die, indicating a fully-floorplanned chip that is GPU-free. So this Bulldozer chip cannot be considered Fusion.

AMD may be reusing the Bulldozer core in Fusion, but that does not mean that the first Fusion design is anywhere near solidified. This is like claiming that Shanghai is done because the CPU core in it will be re-used from Barcelona, or posting Cedar Mill die shots and inferring from it the maturity of Tulsa.

Originally posted by: Viditor
BTW...the URL is broken. You need to get rid of the parentheses at the end.

Nuts, thanks. I didn't mean to post it as a link. I wanted the URL spelled out.
laptoplogic.com/data/news/images/960/bulldozer_dieshot.jpg

There!
 

intangir

Member
Jun 13, 2005
113
0
76
You know what? The more I investigate, the more I'm convinced that the die shot is of Griffin, and NOT Bulldozer.

Laptoplogic claimed that the die shot it obtained was of Bulldozer, but that seems to date from the days when it was thought that Bulldozer was a microarchitecture AMD aimed at the mobile market. This rumor was sourced from the Inquirer.

Going off a lead from The Inquirer, we have discovered that Bulldozer is actually the code name for AMD's upcoming killer mobile processor. However, this processor won't be seen for quite some time: Bulldozer will be AMD's second mobile CPU to be based off the still-in-development 45nm process (this is not a typo!) or possibly even AMD's 32nm process.

However, we now know that Griffin is the mobile-only design (AT article) that is based on the K8, built on a 65 nm process, has 2 cores, and is due for release in mid-2008. This information fits the die shot posted.

Bulldozer, on the other hand, according to the AT article, is a brand-new AMD microarchitecture due out in 2009, which in server designs (codenamed Sandtiger) will have 8-16 cores and 4 HT3 links. This does not fit the die shot posted at all!

So based on this information, I can conclude that Griffin and Bulldozer are two different things (don't believe the Inquirer when it hypothesizes that Bulldozer is a Griffin CPU plus Puma chipset! ;)), and that Griffin's specs match more closely to the die shot than Bulldozer. I do not believe Bulldozer die shots have yet materialized on the Web, and certainly not in this thread. ;)
 

Roy2001

Senior member
Jun 21, 2001
535
0
76
Originally posted by: Viditor
Originally posted by: PlasmaBomb
Originally posted by: Inspector Jihad
from what i understand its the gpu and cpu on the same die. is this a good idea, seems like it would limit upgrading potential.

Initial fusion products are likely to be a CPU and a GPU in the same socket, but on separate dies similar to Intel?s current quad core incarnation.

I don't think that's correct...
The reason Intel's quad core are on seperate dies is because they must communicate through the MCH away from the chip (that's also why Intel requires a much greater cache size)....../q]

Seems you don't understand Intel quad core structure. He is right about 1st gen Fusion.

Intel simply puts 2 dies in one CPU to gain TTM cycle and reduce cost. It is not saying put 2 dual core CPU on a single die won't work since 2 part of the native cores need to talk through MCH. For cost issue, no one will ever do that.

AMD is choosing the same approach for Fusion.