AMD: R9xx Speculation

How could I possibly, not knowing what Anand's actually testing there.

 

"Performance placements are estimates" is what the slide says.

 

And not a peep from any leaks

Gives neliz a wedgie.

 

That sounds like right on schedule... oh noes!

 

Pretty terrible rebuttal. Nothing you said had anything to do with his point.

He wasn't talking about yields or power consumption. He was talking about measured performance relative to available resources - i.e. efficiency. And yes, you can count aggregate bandwidth since the 5970 is working on multiple frames in parallel.

 

http://www.chiphell.com/thread-137198-1-1.html

translation

 

No, he's just saying that he may be able to share the date before the end of the month

 

Ha! I beat chiphell by hours!

Yeah sorry .. I didn't properly reply that, right on schedule it is (and not the 22nd I believe)

 

Didnt Charlie beat ya'll by weeks?

 

True

 

Official conference this week? Is that an actual launch or just a press event?

 

So if Cayman XT is actually a 30 SIMD part, what about Cayman Pro? 24 SIMDs? Would explain the previous 1536 SP rumors...

 

send out cayman pro but tell reviewers, etc.. it is a cayman xt.
simple smokescreen

 

That would be 71.4% more computational units than Barts. We don't know clock frequencies, VLIW architecture, memory bandwidth, et cetera, but this offers some nice performance potential.

 

We know it's VLIW4

On another news, VR-Zone says the cards are indeed delayed, and according to Sampsa one of his non-AMD sources says the same
http://vr-zone.com/articles/amd-rad...age-launch-date-to-be-re-confirmed/10276.html

However, the issue is not yields or such, but just too low availability of one specific driver-MOSFET from Texas Instruments, which is "so new there's no info about it available, not even from TI"
HD6800 uses the same, and apparently there just isn't enough of them at the moment

 

Uhhh ... let's hope at TI they at least know they are producing the darned thing

 

Its probable, but AMD in this case would relocate some of those DrMOS from 6800 to 6900. Initial shortages (which are inevitable in any case) are better than postponement of the launch IMO.

 

Apparently AMD is well known for initially sending out engineering samples that are underclocked and without all units enabled.

 

Hmm so back to 30 SIMD again. I wonder how credible it is this time...

 

Come on, it almost been a 'known' thing that XT would be 1920SP with 30 SIMDs and Pro 1536SP and 24 SIMDs. Rumours have been speculating for ages. Also, it's VLIW4

My speculation:

XT specs:
900Mhz
5Ghz
VLIW4
1920SP
30SIMD

Pro Specs:
850Mhz
4.8Ghz
VLIW4
1536SP
24SIMD

They both end up with 64 which is required for Wavefront.