The LAST R600 Rumours & Speculation Thread

Status
Not open for further replies.
Hi I have UPDATE: It seems that tests from level505 were just confirmed link: http://www.ddworld.cz/graficke-karty/atir600-alias-ati-radeon-x2800xtx-testy-potvrzeny.html
Its in czech. BTW I know this guy and his info is most of the time very reliable - according to this info tests were done by someone from Microsoft with WEAKER:oops: :oops: version of X2800XTX on very early drivers which were modified by tester.

http://www.ddworld.cz/images/stories/grafiky/R600 2/fake.jpg

:?:
 
So he's suggesting both that nvidia has a 8950GX2 product ready to go, and that AMD will be also introducing a GX2-like product called X2800XTX2?

Well there's a big "FAKE" splattered over that particular pic so I'd be surprised if he was supporting the notion.
 
Hi I have UPDATE: It seems that tests from level505 were just confirmed link: http://www.ddworld.cz/graficke-karty/atir600-alias-ati-radeon-x2800xtx-testy-potvrzeny.html
Its in czech. BTW I know this guy and his info is most of the time very reliable - according to this info tests were done by someone from Microsoft with WEAKER:oops: :oops: version of X2800XTX on very early drivers which were modified by tester.


Does that tester have access to the source code of the drivers? I see no way or reason he would :D . Tell him to actaully get some screenshots and stop copying stuff from other sites if he wants to be a bit reliable ;) . Or does he have a overheating quadcore too:!: Must get hot enough to melt the camera lens even when its off :)
 
Well there's a big "FAKE" splattered over that particular pic so I'd be surprised if he was supporting the notion.

I can't figure out what the heck he's doing, actually. All the actual results I see seem to be explicitly marked as being from level505. And there's no language tools for Czech, so. . .
 
Hi I have UPDATE: It seems that tests from level505 were just confirmed link: http://www.ddworld.cz/graficke-karty/atir600-alias-ati-radeon-x2800xtx-testy-potvrzeny.html
Its in czech. BTW I know this guy and his info is most of the time very reliable - according to this info tests were done by someone from Microsoft with WEAKER:oops: :oops: version of X2800XTX on very early drivers which were modified by tester.
Guess what, guys? It's just as fake as it was in late December. :runaway:

let's see if I can clarify a bit: it's completely fake. meaningless. ignore it completely. it doesn't even merit discussion. it has no basis in reality. it's whoring for links. I am mildly upset at this coming back up again.
 
Guess what, guys? It's just as fake as it was in late December. :runaway:

These kind of things have beautiful defense-in-depth to them. We know now that Level505 could not have had a shipping sample, let alone the "early drivers" dodge. . . with the result that any results at all will be deemed credible/plausible in hindsight by anyone who wants to believe.
 
Just as a reminder, the Level505 guys sent our Tim Murray the following email when their site first went up:

An affiliate of ATI's business dev unit gave us two days to test the new R600 RTM-chip on a testing board for microsoft driver certification. We published the news today on our taiwan/english site
http://level505.com/2006/12/30/the-full-ati-r600-test if you are interested.

Weeks later they were claiming to be trying to remove markers for pictures and do part II results on a "RTM chip" (i.e. Released to Manufacturing) board that they'd had "for two days" before part I ever went up. What would have been known to AMD/ATI/Partners at the time (but no one else), but has since become obvious to the rest of us, is that AMD must have already gone back for another spin by then.
 
I can't figure out what the heck he's doing, actually. All the actual results I see seem to be explicitly marked as being from level505. And there's no language tools for Czech, so. . .

he is saying im text that sheet with model numbers is fake and he is just using it as example how could model numbers look like. As I said earlier his info is usualy very reliable - he said that source of this information is;) DFI.
 
he posted those benchmarks because he now believes that its true - he has to have some good reason to say that because in january he posted that its fake and none of us would change opinion without reason.
 
he posted those benchmarks because he now believes that its true - he has to have some good reason to say that because in january he posted that its fake and none of us would change opinion without reason.

Ad clicks? That's a good reason.
 
Nope, i doesn't.

They keep referring to R600 as a simple doubling of the R580, but the R580 is not unified.
In addition to the 48 Pixel Shader ALU's, there are also 8 Vertex Shaders.

In a unified architecture, those "96" ALU's would have to be doing that additional work, not to mention Geometry Shading, new for the DX10 API.

Well we are talking about a unifide arc. but 96 is very reasonable depending on clocks. I'm just about dead certain that R600 will be deploying scaler shaders which leads me to believe a high clock domain. :smile:
 
There has to be something wrong with that article.
How can 2x 8800 GTX in SLI achieve a greater than 100% increase of the frame rate compared with same setup in single GPU mode ?

In many cases, 70~90% is the most realistic gain we can expect.

While I'd love to believe that a 7900GTX is faster than a Geforce 8800 GTS...somehow I'm not convinced yet. Even better, it appears I could get a 1950pro for around $150-ish and best both of them. Yay.

I wonder if they do processor reviews, too? Perhaps they can convince the single core San Diego in my spare box to "act like a quad core"? That would be even better. I'd really appreciate that. :sly:
 
I can't figure out what the heck he's doing, actually. All the actual results I see seem to be explicitly marked as being from level505. And there's no language tools for Czech, so. . .

Bit OT, but yes, there actually are. If you use Firefox and get the Fox Lingo plugin, you can do page level translations of many languages. Transworld does the Czech -> English, and there is also a Czech -> French. It does everything from Afrikaans to Bulgarian to Ukranian.

It's very helpful when wading through the web hunting for information, though no one has created a tool yet that marks "Big Pile of BS" on erroneous data. I'm anxiously awaiting that tool, personally. Guess I'll have to use common sense for now ! :LOL:

Here is the link for the extension. I have no idea what you would do in IE since I haven't used it in years. Perhaps it has a plug-in or something too. https://addons.mozilla.org/firefox/2444/
 
Last edited by a moderator:
Based on something other than the fact G80 did?

Mintmaster said he had heard a similar rumor months back. Considering how NV shocked everyone with G80, who knows if ATI couldn't do something similar in misleading us to a degree.
 
So far I gather this together:

64 4-Way SIMD Unified Shaders “64 pixel unified processor”, 128 Shader Operations/Cycle, 32 TMUs, 16 ROPs, 512 bit Memory Controller, GDDR4 at 1.1 GHz clock speed, total bandwidth 140 GB/s on GDDR4, total video memory 1024 MB, 814MHz GPU, 32FP internal processing, over 700 million transistors, RingBus 1024bit internal, A15 silicon.

nVidia can process only one operation per clock cycle while R600 can do four.
Also nVidia 24 ROP operating and frequency of 575 MHz provides 13.4 billion:
ATI at 16 ROP operating and frequency of 814 MHz can provide very close to nVidia:

I mean what exactly we are talking here, 4 lanes of Freeway traffic driving 50MPH vs. 1 lane of Freeway traffic driving at 200MPH. “Just a question”
 
Last edited by a moderator:
Status
Not open for further replies.
Back
Top