AMD Cayman info (or rumor)

[saaya]

http://bbs.expreview.com/viewthread....om=recommend_f

wow... thats dissapointing...
6000 is 10% more efficient/sp/clock and only has 320sps more... which is a mere 17% more than 5000...

so at the same clocks (and i doubt itll come clocked notably higher) 6970 will only be 27% faster than a 5870... and thats an UP TO... if geometry is limiting it will be more, but... when is that actually the case besides tessellation benchmarks?

6970 is definitely slower than the 580 then...
not much, but 5-10% on average i guess...

[Dimitriman]

wow... thats dissapointing...
6000 is 10% more efficient/sp/clock and only has 320sps more... which is a mere 17% more than 5000...

so at the same clocks (and i doubt itll come clocked notably higher) 6970 will only be 27% faster than a 5870... and thats an UP TO... if geometry is limiting it will be more, but... when is that actually the case besides tessellation benchmarks?

6970 is definitely slower than the 580 then...
not much, but 5-10% on average i guess...

Not really Saaya its 4d shaders therefore its 480x4 for Cayman vs 320x5 for Cypress = 50% increase.

I would estimate performance will be around 40% higher on average with even more notable differences in tesselation intensive benchmarks.

[SimBy]

wow... thats dissapointing...
6000 is 10% more efficient/sp/clock and only has 320sps more... which is a mere 17% more than 5000...

so at the same clocks (and i doubt itll come clocked notably higher) 6970 will only be 27% faster than a 5870... and thats an UP TO... if geometry is limiting it will be more, but... when is that actually the case besides tessellation benchmarks?

6970 is definitely slower than the 580 then...
not much, but 5-10% on average i guess...

Well can't say if this slide is fake or not, but I guess you completely overlooked 50% more SIMD engines than HD5870 and double poly/clock.

On paper at least it should eat GTX580 alive.

[Nintendork]

wow... thats dissapointing...
6000 is 10% more efficient/sp/clock and only has 320sps more... which is a mere 17% more than 5000...

so at the same clocks (and i doubt itll come clocked notably higher) 6970 will only be 27% faster than a 5870... and thats an UP TO... if geometry is limiting it will be more, but... when is that actually the case besides tessellation benchmarks?

6970 is definitely slower than the 580 then...
not much, but 5-10% on average i guess...

You didn't read about Barts or you're ignoring it.

Barts 6870: 1120SP with full efficiency
Cypress 5870: 1600SP but only 1280SP being used most of the time

Cayman is not a 5D thing. Let's make a guess

Cypress 5870: 1280SP effectively used
Cayman 6870: 1920SP fully used (or 2400SP if we apply Cypress SP inefficiency)


You disappoint me.

[spursindonesia]

Now your seeing what I was trying to get at before. Atleast if your not being sarcastic. If the gtx 580 was not released at all, pricing could be potentially worse too.

Not really, you were suggesting that AMD will put US$ 500 or more MSRP price tag on Cayman XT, i said US$ 479 at most, and that's on the record. What i was trying to say, the market condition (lack of supply and perhaps combined with healthy demand) will drive up the appropiate to aggressive official pricing from AMD into higher street price level, like what has been happening with Barts XT & Pro case.

Don't worry, if Cayman XT was indeed priced (MSRP) OFFICIALLY by AMD @US$ 499 or more, i'll keep my bet & stop posting for the next 6 months.

wow... thats dissapointing...
6000 is 10% more efficient/sp/clock and only has 320sps more... which is a mere 17% more than 5000...

so at the same clocks (and i doubt itll come clocked notably higher) 6970 will only be 27% faster than a 5870... and thats an UP TO... if geometry is limiting it will be more, but... when is that actually the case besides tessellation benchmarks?

6970 is definitely slower than the 580 then...
not much, but 5-10% on average i guess...

Try not just counting on SPs amount, but also the SIMDs. Not saying that AMD mArch has been limited in math calculating or shader power, but with this quite revolutionized, new mArch, it might offer better utilization & upped efficiency compared to the current one applied in Evergreen family & Barts chips.

96 TMUs

Decoupled TMUs groups from the SIMD's engine ?

I've heard rumor about AMD's version of nVidia's GPC (Graphic Processing Cluster).

Say 30 SIMDs are divided into 2 "GPC", each with its own setup & rasteriser engine, then each "GPC" with 15 SIMD will be divided into 3 arrays of 5 SIMDs. Each array has 16 TMUs totalling 48 TMUs/"GPC". As a whole, 2 "GPC" with 48 TMUs each will make a 96 TMUs chip. Just a very, very raw speculation of mine, please don't take it too seriously.

[SimBy]

Oh well it's fake. Next one please

[-=DVS=-]

No one finds it interesting how each company declares somethings ?

Shooting big claiming "Fastest"



Conservative , claiming only "most advanced".

[Aten-Ra]

http://bbs.expreview.com/viewthread....om=recommend_f

30SIMDs / 96 Texture units = 3.2

not possible, unless Texture units will not be part of the SIMD anymore

[SimBy]

30SIMDs / 96 Texture units = 3.2

not possible, unless Texture units will not be part of the SIMD anymore

That was the premise, but as it turns out it's a fake.

[Kej]

That was the premise, but as it turns out it's a fake.

Where is the confirmation of that it's a fake slide?

[SimBy]

Where is the confirmation of that it's a fake slide?

It's a fake based on the slide #72 exposed at the event in LA last month.

[japamd]

30SIMDs / 96 Texture units = 3.2

not possible, unless Texture units will not be part of the SIMD anymore

Previous rumors mentioned TMUs decoupled from SIMD units.

[Kej]

It's a fake based on the slide #72 exposed at the event in LA last month.

Thanks for the link!

Side note: Why not put up the link in the first place? Putting up statements and
not give any background can so easily be wrongfully interpreted.

[trinibwoy]

Well can't say if this slide is fake or not, but I guess you completely overlooked 50% more SIMD engines than HD5870 and double poly/clock.

On paper at least it should eat GTX580 alive.

On paper the 5870 also eats the 580 alive. But yeah it's shaping up to be sufficiently faster than Cypress to be in >= 580 territory.

[jaredpace]

[zerazax]

That was from: http://www.forum-3dcenter.org/vbulle...&postcount=114

Not sure if this is real, but it would confirm a lot of Cayman things... 1920 SP's, 4D, 2GB GDDR5

[RaZz!]

3840 SPs

so let's hope this is true and cayman has 1920 SPs

[Dimitriman]

Chuck Norris is near!

[zerazax]

That photo looks a lot more realistic

That would suggest at a baseline, Cayman is:

2GB frame buffer
1920 SP's
1550Mtri/s (775mhz x 2)
32 ROPs (32 pixels/clock)
3 TFlops (750 GFLops DP)

But given power constraints, Cayman XT is almost certainly clocked higher... so that should give a good idea what Cayman will be packing

[zalbard]

Means that 6970 will indeed only be 1.5 times faster than 5870. Does anyone have the geometrical performance data of 5870 to compare?
Also, Nvidia is apparently readying a dual GF100 card, so AMD will be facing competition.

[zerazax]

Means that 6970 will indeed only be 1.5 times faster than 5870. Does anyone have the geometrical performance data of 5870 to compare?
Also, Nvidia is apparently readying a dual GF100 card, so AMD will be facing competition.

Where's this 1.5x faster thing coming from?

[fellix_bg]

Does anyone have the geometrical performance data of 5870 to compare?

Cypress is capable of 1 triangle per clock setup rate. ~1/3 of that when tessellating.

[Picao84]

Where's this 1.5x faster thing coming from?

I ask the same, since if we are going for the only metric we can extrapolate quickly, the Flops, its nowehere near 50%.. From 2.7 Teraflops to 3.0 Teraflops is only 11%....

[Sn0wm@n]

antilles is shaping up to be a chuck norris approved gpu

[LightSpeed]

I ask the same, since if we are going for the only metric we can extrapolate quickly, the Flops, its nowehere near 50%.. From 2.7 Teraflops to 3.0 Teraflops is only 11%....

I know but the thing is that the Tglops will be utilised much more efficiently due to 4D + other improvements. Hence comparing Tflops is simply not right in this case