Printable View
That's the point I was trying to make a while back though. Cypress has strong theoretical performance, but significantly less real performance. If efficiency can be improved, real performance could increase disproportionately to paper power.Quote:
Originally Posted by Picao84
I hate this meme so much. Mr Norris is a loser.Quote:
Originally Posted by Sn0wm@n
Yes, hence I don't get the 50% comment
Also, looks like the folks over at bbs expreview are back to commenting on the 6970
Link
Quote:
NV took the 6950 test 1536SP 10% worse than the 580 ha ha ~! ~
If true, AMD really pulled a RV770 again and sent out fake info/leaksQuote:
SIMD Core groups as less able to estimate the calculated out, CHH is also a bunch of fools for the NV to get what 1536SP data in happy, NV was a child when you (like you guys like the fool?), That he look, made several false data, NV will be believed?
ugh double post
so no new info; we already had the 1920SP rumor a month ago....
6970 is going to be at least 50% faster than 6870 or there would be no room for 6950.
480x4 vs. 320x5 SPs + 2times higher tesselation performance + more vram support the 50% claim + higher clockspeeds (6990 clock speeds are the same as 5970 at the same board power, but 6970 TDP is supposed to be higher than 5870 TDP so it should have higher stock clocks)
looks like a winner, but still 3 weeks until release....
If the slide is not fake it's going to be nice upgrade option for me. Neither GTX 580 or HD 6970 is an upgrade for me.Quote:
Originally Posted by jaredpace
Going by the limited info on the slide I estimate the HD 6990 should be about 30% faster than my HD 5970 and if the rumors are true it should be much faster in tesselation plus extra 2GB GDDR 5 is also good upgrade.
How do you know the HD 6970 is 3 TeraFLOPS. It doesn't show on this slide which somebody claimed is a fake anyway.Quote:
Originally Posted by Picao84
Quote:
Originally Posted by cold2010
6990 is 6gflops so Cayman xt is prolly at least half thatQuote:
Originally Posted by Heinz68
Fancy that... semi-concrete info.
Should be more than 3TFlops:
Teraflops:
Core frequency(higher in single core Cayman) * SP * 2
900*1920*2 --> 3.45TFlops "HD6970" (barts frequency as reference)
At least half is not neceseraly 3TeraFLOPS which Pica084 was using in his calculation.Quote:
Originally Posted by zerazax
The HD 5970 has "Processing power (single precision): 4.64 TeraFLOPS" and the HD 5870 is 2.7TeraFLOPS. LINK
In order to get within the 300W load power AMD needed to reduce the clock and voltage on the 5970. Since the HD 6990 slide shows "Load/Idle board power 300W/30W" some similar adjustment was most likely done.
HD 5970 performs about same as HD 5850 Crossfire unless overclocked to at least the HD 5870 levels.
why estimate if the 6000 series is already out and has been benched by dozens of sites? compare reviews and you will see that sp for sp the 6000 series is ~10% faster than the 5000 series.Quote:
Originally Posted by Dimitriman
i dont know how much the increase in poly/clock will help... but i doubt itll help much besides in tesselation benchmarks and new games that come out in 2011... and there itll only matter with high tesselation settings and i have yet to see a game or let alone demo where tesselation actually makes me want to upgrade :PQuote:
Originally Posted by SimBy
sure, it MIGHT be faster than the 580, but from what ive seen so far, theres nothing hinting at it... if the 1920sp number is true, it will trade blows with the 580 at best, and probably be a tad slower.
lets make a guess... OR... OOOOORRR we look at real world benchmarks :DQuote:
Originally Posted by Nintendork
go and continue doing your 4d 5d math all you want, actual performance boost of 4d over 5d is around 10%, sp for sp at the same clock :)
which means you have high expectations and think a lot of me? thanks :DQuote:
Originally Posted by Nintendork
i shant be dissapointing you :D
revolutionized? so far it sounds more like a tweaked rv800?Quote:
Originally Posted by spursindonesia
why would they only do that for the 6900 series though and not 6800? sure, 6900 might be a different arch, but... that would be a bit weird wouldnt it? would be cool, but its more wishful thinking and looking for a reason HOW the 6900 could beat the 580 if you ask me :PQuote:
Originally Posted by spursindonesia
id love it... i just dont think its very realistic :D
dual gpu card formula:Quote:
Originally Posted by zalbard
if ( perf/W perfMAX - perf/W perfMIN ) > ( perf/W SLI - perf/W single) release :D
basically, if you can get more perf out of 300W by using 2 gpus, then yeah... but sli doesnt scale that well, so using two gpus is always slower than using one gpu at higher clocks.
that Antilles board is going to run so hot, its huuuge
But Barts parts are still VLIW 5, no one knows yet how good (or bad) the VLIW 4 will perform. That 10% improvement seen on benchmarks are due to internal optimizations (Techreport states AMD resized some queue and buffers).Quote:
Originally Posted by saaya
Having twice the triangle setup rate/clock and 50% more ALU power, plus the internal optimizations seen on Barts, those improvements alone should give a nice boost over Cypress IMO.
At least, but im sure more. The 6970 will surely be clocked higher:)Quote:
Originally Posted by zerazax
Quote:
Originally Posted by Heinz68
Quote:
Originally Posted by LightSpeed
Hence the at least ;)
I don't care about your at least. I was wondering about Pica084 calculation based on 3TeraFLOPS and wanted to know from where he got the info.Quote:
Originally Posted by zerazax
At least in this case means nothing.
/sighQuote:
Originally Posted by Heinz68
He was taking it from dividing the 6 TFlops, nothing more/less - you're reading too much into it
Please show those real world tests showing 4sp config performance. All that can be said based on Barts is that performance is atleast 10% sp per sp as othwise there would be no point doing that big arch change(basically making new shaders).Quote:
Originally Posted by saaya
Maybe it has something to do with where the best efficiency lies at what core config. It could be that 5VLIW sweetspot is ~1,2k sp and after that it declines. And 4VLIW sweet spot is after that. Who knows? Im just saying that there is too much variables that are left unanswered that one could really say about beating or not beating 580GTX.Quote:
why would they only do that for the 6900 series though and not 6800? sure, 6900 might be a different arch, but... that would be a bit weird wouldnt it? would be cool, but its more wishful thinking and looking for a reason HOW the 6900 could beat the 580 if you ask me :P
.
Exactly that's what I was thinking except that 6990 is not 6970x2 same as 5970 is not 5870x2, that's why such division doesn't make a sense same like calculating performance based on the division doesn't make a sense.Quote:
Originally Posted by zerazax
I just wanted to point out his 11% is misleading info unless he knows something else than dividing the 6990 6 TeraFLOPS.
PS
I think it should be me to post the "/sigh"
You're misinterpreting what I wrote - I said it has to be at least 3 TFlops if the 6990 slide is real. He's taking the 11% based on 2.7 -> 3 TFlops, which is pointless given that going from 5-VLIW to 4D is going to affect real world performance more than theoretical throughput
Finally some real slides.
http://www.frazpc.pl/artykuly/652601...n-HD-6950.html
Thanks that explains a lot, all the ROP's have been beefed up, and so have the shaders. It's really is a totally different beast from Barts.Quote:
Originally Posted by SimBy
Hé Hé, i like this preview, it just say enough, but not too much ... anyway, this time tesselation increase is explained ..
Yep... almost always 2x faster than Cypress and up to 3x faster
edit: looks like slide 72 still needs to be filled in.
What a tease
Well, if we always simplify stuffs, then Fermi mArch can also be called a tweaked G80. But we're not simpletons, are we ? :yepp:Quote:
Originally Posted by saaya
IIRC, it was stated in B3D forum by an AMD rep there that while officially lumped into Northern Islands family, Bart & Cayman have different product development process, since both are targeting very different market. With Bart, basically a tweaked & optimised Evergreen mArch as you've mentioned, AMD try to address its glaring weakness in Evergreen line up, the sweetspot segments, while Cayman seems like the true new gen in this family, as an enthusiast products, where AMD can be more adventurous & creative without worrying about time to market too much.
It seems around Hemlock size, i don't think it's gonna be any bigger. The cooling solution & VRM design might have been changed & improved, IMHO.Quote:
Originally Posted by tbone8ty