AMD: R7xx Speculation

Status
Not open for further replies.
I've cleaned up the worst bits from the back end of this thread, to give it some fresh impetus. Some of the OT still remains though for some useful visibility, and if people want to pursue it there's the New Thread button.

Back to the scheduled R7xx programming.
 
vertex_shader said:
Fruitzilla think R700 is two RV770.

I call this as highly possible, no same dies package multicore architecture coming :cry:

I think RV770 was originally R700 but ATi not want another R600 fiasco so they ranamed it to a value part and 2 of them HD3870X2 style coming in highend against NV single core GPU G100 (Fuad think G100 renamed to GT200 :) )
Click to expand...

As I said before, I haven't the vaguest idea where Fudo got that G100 codename from and why he was chewing over it several times recently. I don't think something with a former codename "G100" was renamed to something else; I'd rather believe that what is called GT200 today (if that's even accurate) has only one minor difference to the codename on older roadmaps.

As for AMD's next big thing I'm not so sure whether the first digit should be 7 or 6 in the end. Such a detail though would lighten up the fire even more for the ongoing ridiculous soap-opera above and I can already picture Rys hunting me with Wavey's frying pan <img>
 
That sounds good.

Once again, the R600 AA needing to be fixed meme has popped up, and according to Kyle it is AMD's engineers saying so.
Just what do they mean by "fixed" when we've had multiple AMD statements that AA "is not broken"?

Does this mean R700's AA is "more not broken"?
 
3dilettante said:
That sounds good.

Once again, the R600 AA needing to be fixed meme has popped up, and according to Kyle it is AMD's engineers saying so.
Just what do they mean by "fixed" when we've had multiple AMD statements that AA "is not broken"?

Does this mean R700's AA is "more not broken"?
Click to expand...

They undoubtedly just mean that AA performance is designed to be higher than it was on R600. The "fixed" comment is just in response to the mistaken belief that AA on R600 was "broken" in the first place. Much easier to say "fixed" than to try and explain R600 AA performed as expected but was underspecified in comparison to the competition!
 
Mariner said:
Much easier to say "fixed" than to try and explain R600 AA performed as expected but was underspecified in comparison to the competition!
Click to expand...

Much more true as well. It's not like they ever thought that half the speed of the last-gen implementation would be "great".
 
Ailuros said:
As for AMD's next big thing I'm not so sure whether the first digit should be 7 or 6 in the end. Such a detail though would lighten up the fire even more for the ongoing ridiculous soap-opera above and I can already picture Rys hunting me with Wavey's frying pan <img>
Click to expand...
Rather than come hit you with it, I made an awesome bacon sandwich using it instead. And as I moved the bacon around in the pan with the wooden poking device thing in the utensils pot that I haven't the foggiest clue about, I felt a strange force overcome me, as if Wavey himself were reaching out from his ex-pan to control my movements. When Wavey was finished with me, the seven rashers of bacon (I'm a fat man) were arranged like a number 6. Weird.
 
Rys said:
Rather than come hit you with it, I made an awesome bacon sandwich using it instead. And as I moved the bacon around in the pan with the wooden poking device thing in the utensils pot that I haven't the foggiest clue about, I felt a strange force overcome me, as if Wavey himself were reaching out from his ex-pan to control my movements. When Wavey was finished with me, the seven rashers of bacon (I'm a fat man) were arranged like a number 6. Weird.
Click to expand...

Got it ;)

Side note : Bacon!
 
Probably ATi is on a new dogma where single chip solutions will/should all fall under RV* class of products and R* would be saved for multi-chip flavours.
Yes, HD4000 will be Tasty
Click to expand...
Hope they will stop some time around 6000, otherwise there is a danger of brand "re-spin" embarrassment, echoing from the far past. :LOL:
 
Rys said:
Rather than come hit you with it, I made an awesome bacon sandwich using it instead. And as I moved the bacon around in the pan with the wooden poking device thing in the utensils pot that I haven't the foggiest clue about, I felt a strange force overcome me, as if Wavey himself were reaching out from his ex-pan to control my movements. When Wavey was finished with me, the seven rashers of bacon (I'm a fat man) were arranged like a number 6. Weird.
Click to expand...

I love numerical riddles. We knew though that you're a 2in1 type of guy (at heart too :p) so there's nothing new in the above either :p
 
Digitimes:
With the increasing demand for AMD's Radeon HD 3800 series (RV670) graphics cards, the company is planning to bring forward the launch schedule of its next generation RV770 GPU. This has triggered Nvidia to also accelerate the launch of its G100 (D9x) GPU, according to a Chinese-language Commercial Times report, citing sources at graphics card makers.

AMD has already released samples of the 55nm RV770 GPU to its partners for certification and cards are expected to launch at late second quarter, added the paper.
Click to expand...
 
Status
Not open for further replies.

Similar threads

F
RDNA5 Speculation
Replies
2
Views
1K
Erinyes
E
S
Apple Dynamic Caching on M3 GPU
Replies
5
Views
3K
Lurkmass
L
hoom
AMD: Zen 4, Speculation, Rumours and Discussion
8 9 10
Replies
199
Views
39K
MfA
M
xpea
Nvidia Hopper Speculation, Rumours and Discussion
7 8 9
Replies
177
Views
38K
Deleted member 2197
D
A
AMD: Zen 3 Announced [2020-10-08]
10 11 12
Replies
220
Views
91K
davis.anthony
D
Back
Top