do we know the bitrate of caymen xt, or just assuming it?
i would think that 256bit might be enough with some really fast memory (hopefully thats why they put the cheap crappy stuff in barts)
Printable View
do we know the bitrate of caymen xt, or just assuming it?
i would think that 256bit might be enough with some really fast memory (hopefully thats why they put the cheap crappy stuff in barts)
oh snap 2gb standard popping up thats pretty cool. 32 rops though? can that be right? seems too little for cayman.
2 GB VRAM, that's cool, fits right in with its status as enthusiast level card, AMD's back in highend single GPU arena. :D
That's really sweet. Can't wait for it to come out! :up:
It looks like AMD held no brakes when it came to Cayman. The next shock for nV will proly be Cayman die size and performance.
doesnt anyne else find this 32 rops number too low?
VLIW4
New architecture anyone?
Anyone has the original source (says there expreview on all 3 photos).
By the way, there is absolutely no indication of how big Cayman is on that photo, in case someone is claiming "THAT CHIP IS HUGE!!one".
Looks almost as big as a GF100. If AMD can keep up their perf/mm^2 this thing will surpass GTX 580 easily.
If this thing is indeed VLIW4 and has 1920SP,it's game over for any GF1xx chip,no matter if it has full 512 CUDA cores and high clock. With Cayman XT on the market,Cypress is going to be lowered in mid-high class and GTX480 as well.Antilles will be uber high end,in a class of its own,in line with Chuck Norris comments we already saw.
The box shape in the middle of the PCB isn't the chip itself, but the substrate/packaging size with its corresponding pin out. The chip itself would be rotated 45 degree in orientation, just like Cypress and Bart, and if you look further behind, R600. I still believe the chip won't be bigger than 400 mm^2, with TDP no higher than 230 w.
Yeah now that I look the pcb doesn't seem that much longer than a 6870.
Rop count seems a bit low, but who knows how it works with the VLIW4 architecture. 2 GB reference is nice though.
8 phase power on stock pcb. yum!
Whooa, looks sweet!
So educate me on what VLIW4 is...
Do you remember all the 4D instead of 5D shader rumors for the HD68xx? If I'm not mistaken, it's that. Charlie wrote a bit on it here:
http://www.semiaccurate.com/2010/09/...thern-islands/
But, as we already know, it didn't turn out true for the HD68xx cards.
For people who dont know AMD used 5 way design's for most of the cards till now including the 68xx now VLIW4 is different in several ways.
The easiest way to tell the difference is that VLIW4 is suppose to use 4 medium sized units where as the old 5 way design used 1 big and 4 small units.
Hmm... haven't seen that.. mind linking me?
VLIW5 stands for "Very Long Instruction Word" 5; VLIW standing for the architecture basis, 5 for the number of execution units.
Each shader 'unit' is composed of 5 execution units, 4 of them being 'simple', with the 5th being able to handle all functions, including transcendental functions.
This is one (of many) reasons that AMD's u-arch's generally have more shaders than nvidia, yet has comparable performance; unless the developer specifically codes for this unique computing style, a game will only use some of the execution units. This is also one reason why the theoretical computation power for AMD's u-arch's are far greater than what is actually achieved in actual applications, because AMD's figures assume that all execution units are utilized.
In Cypress (and back to R600) there were 5 SPUs (Stream Processing Units) per SP (Streaming Processor).
Like in the first image here: http://www.anandtech.com/show/2841/4
Now there will be 4 SPUs per SP. And as ajaidev points out, there may be a different arrangement of simple and complex units within the SP instead of 4+1.
If they keep a grouping of 16 SPs per SIMD, and there are 1920 SPUs, then Cayman will have 30 SIMDs per chip.
The reason for such a change might be to increase utilization. It could have good results if one or two of the units in your 5 wide design are usually sitting idle. That's why RV770 and Evergreen had such a huge difference between low utilization (games) and high utilization (furmark) in terms of power-draw and heat output.
They have had a 5-wide design for a while now. Why assume that's never going to change? Especially on a generational change?
^ Evergreen had OCP so Furmark didn't use more than board power.
WXYZT turns to WXYZ with T probably done in emulation (WXYZ or T for GPGPU).
The penultimate reason for this is die size. And yet Cayman is still big. Makes you wonder.
Effectively,Cayman could have 50% more SP resources than Cypress,taking into account the grouping per SIMD. If the clocks stay in the range of Cypress,this thing will be the fastest single GPU card on the market,hands down. Now,how will they manage to put two of those monster for Antilles card and keep "reasonable" TDP is another question.
If it is indeed a 4 port VLIW architecture this will be very expensive for AMD as i speculate they will have to recoup the R&D costs for moving the SI design from it's initial 28nm target to 40nm using just one derivative. This of course will allow them to finalize the design on a well known process before they move it to the murky waters of 28nm and therefore lower risk. I suspect we will see a 5770 replacement as a 28nm test vehicle as soon as the process is ready for production.
Iirc to take advantage of all the the SPUs per SP certain scheduling conditions have to be met that makes it very difficult to even get close to the theoretical max performance with real world code
What I would like to see is an implimentation of AMD's "Turbo Core" on their dual GPU solutions. What this would mean for cards like Antilles is that on games that can use more than one GPU, the chips would clock down slightly and run in Crossfire configuration. However, in games that DON'T have a Crossfire profile or aren't optimized to run on multi-GPU solutions, one of the cores would overclock to the full speed of a Cayman XT card and run on only one GPU core while the other GPU core is essentially turned off.
This would be an intelligent solution much like the Turbo-mode that intel implements on their i3/i5/i7 CPU's, only it would apply to GPU's. This would also allow them to intelligently keep Antilles within the 300 watt PCIe spec while in dual-GPU mode and it would allow the card to perform very well on games that only utilize one GPU. They've already got the technology implemented in their cards (notice the 17watts of power consumption at idle). Now they just need to expand upon it and add intelligent power gating to the mix. It could probably be done via software.
That would be a win-win design. However, it's probably wishful thinking to hope for something like that. :(
Hm? How does logic go up? Logic should go down (minorly, 10-15% die size would be fortunate) and perf-logic ratio should get boosted just slightly less.
Unless it's WT-XT-YT-ZT which might be what you mean. That'd be quite an increase actually, but the ratio's way overdone.
I'm thinking of WXYZ + logic in the SIMD blocks that allows transcendentals to be performed through looping or such.
Which might be exactly the reason for a change from 5D. Theoretical power going unused only drags down energy efficiency. Higher real utilization of units will increase overall power usage, but will also increase performance/watt - maybe to a greater proportion.
Maybe, but we don't know if they are directly comparable to current rops anyway.
First off we are assuming that they didn't increase the size of the register file, complexity of the branch predictor, size of the texture units, size of the L1 cache, amount of shared memory, and complexity of the controlling logic - if they did then every SP and SIMD would have an increased ratio of logic to SPUs. Even if they kept it the same we are talking about 25% more SPs for the same number of SPUs (400 SPs vs 320 SPs). But they seem to be increasing the SPU count to 1920 if the rumors are true. So that's a 50% increase in the number of SPs (480 SPs vs 320 SPs). And if 16 SPs per SIMD is the same then it will be a 50% increase in texture units, L1 cache, shared memory, and controlling logic (30 SIMDs vs 20 SIMDs).
This may be a very powerful chip.
Can we have 32 SPs per SIMD with 4 Texture Units ??
Something like 16x2 SPs with 4-way VLIW 128 Shaders with 4 Texture Units
Yes, I was thinking a 16 SIMDs (32SPs) (2048 shaders) with 64 Texture Units
2x Tessellator engines (one for each Ultra-Threaded Dispatched Processor) and 256-bit memory with 32 ROPs.
so without starting a flamewar...
...is this going to be the Dogs bollox?
Sure, they don't have to stick with 16 SPs per SIMD. They would have to make fast ROP and Texture Units to keep them from being a bottleneck in this arrangement.
But 2048 shaders? This could have some serious real shader power.
AMD have shot themselves in the foot before due to low ROP's counts, i sure hope they don't do it again. with the shadder improvements and the shadder increase they will have more than enough shadding power, but if they sacrifice TMU and rop power to do that it would turn out very badly, sure the shadding performance is stupid high but games still need good TMU and ROP performance otherwise those shadders don't do jack.
That ~10-15% number was also my estimate. It's of course dependent on the actual code running. It will be possible to construct cases were Cayman will be slower than Cypress (if Cayman doesn't have significantly more than 1920 SPs). But generally, it will gain the most in situations where the VLIW5 architecture fared worst in comparison to nvidia.
Actually it is already known how the VLIW4 units will be organized. The codepath for that arch in the driver is functional since Catalyst 10.4, I've posted some stuff about that over at B3D 10 days ago.
The transcendental functions are done by the xyz units working together (just like it is done for double precision already now, only that it takes 3 slots), so 3 of the 4 slots of the VLIW unit are used to calculate a transcendental. The fourth slot (w) does not take part in that and is still free to use in the same cycle. That means a good part of the t unit got split up in three parts and is distributed to the x, y and z units.
Another function of the t unit was doing format conversions and roundings. This functionality got replicated to all subunits. That means for this kind of stuff Cayman will fly.
24bit integer arithmetics are now fully supported by Cayman and can be done in all 4 slots (Evergreen had only partial support which was not really used).
A 32Bit integer multiplication will unfortunately block all 4 slots (could be done by the t unit with the xyzw slots free for use by other instructions in Evergreen), but this is probably the price to pay to get some transistor savings from the change.
All other integer instructions can again be done in all 4 slots (as before).
Double precision instructions behave the same way as in Cypress. Everything involving a multiplication (MUL, FMA) takes 4 slots while the other stuff (like ADD and conversions) takes 2 slots. That means the DP:SP ratio is 1:4.
Hell yes.
No one can speculate the GTX 580 performance with any degree of validity or truth but Cayman will be off the wall.
Whether the 580 will be even faster than Cayman is unknown but fast is fast in subjective terms.
I'll put it this way; all these crappy fud sites are holding on to some fake 36.6 fps benchmark from 2 months ago like it has value.
What is true however is that the 6870 with 145W power draw can come close to the previous gen. Cayman will have 300W, 2G of vram, a new 4 shader system and a lot more of them.
It's more than just "30%" faster than the 6870 as fud sites say.
I don't have the link, but Gipsel posted about it underneath and was the one who posted about it in the R9xx speculation thread on b3d
As I posted here at the beginning of this thread: http://www.xtremesystems.org/forums/...55&postcount=2
Reviews on Barts have given hints that Cayman is a superset of Barts, meaning it will have more features than Barts has, and that Cayman is focused on high end GPU performance. Given that this is a break from the old AMD strategy, I bet it's a big deal
is there a release date for these yet?
Fact 16 - Two Antilles is all the graphical power a human being is ever going to need.
Fact 17 - You do not buy Antilles, Antilles selects you from a pile of lesser graphics card owners.
Fact 18 - You don't tell Antilles what resolution you want to play games at. Intead, Antilles tells you what resolution you are going to play that game at. If you attempt to change the resolution, Antilles will say no, and your head will explode.
Fact 19 - Antilles does not accelerate HD video. All HD videos are made for the sole purpose of making Antilles more awesome.
Fact 20 - If you try and take Antilles out of your computer, it will weld your case shut, and then your head will explode. After that, Antilles will steal your girlfriend and make her much happier than she was with you.
btw, after I finished writing all 3 of those facts, my nose started bleeding. It must be a sign... :lsfight:
Fact 21 - The Antilles is an aggressive feeder, and will eat anything from crickets, grasshoppers, :banana::banana::banana::banana:roaches, beetles, moths, and other flying insects, to anole lizards.
Fact 22 - Additionally to normal food, meat(for example chicken hearts) can be given on rare occasion; but because Antilles reacts to movement, it has to be moved with a tweezer or a thread.
Fact 22: On Antilles launch day there will be a human sacrafice for it. :rofl:
Fact 23 - Many sources now confirm that the Stig is in fact Antilles.
http://www.myporsche911.co.uk/blog/w...9/the-Stig.jpg
i knew it, the man behind the helmet. he's going to get you.
Do you have some benches to back up your statement that AMD HAVE ACTUALLY shot themselves in the foot yet again with low ROP number for Cayman ? They very well MIGHT have, but we have no concrete evidence yet the judgement & sentence are already given. :rolleyes:
If the past can teach us well, i remember quite fondly that my 16 ROP'ed HD 4870 were more than good enough to give 28 ROP'ed GTX 260 core 192 a very good run for its money. :clap:
6870/50 sales are weak, Im not sure how the new video cards are going to do, especially with this steady declining economy :shrug:
In the end high end video cards allways sell most people want the best and the fastest card around! I think cayman will be a real winner if its on time!
You're being sarcastic right?
http://img831.imageshack.us/img831/5913/vidms.jpg
You can't look at numbers of those below 200$ you can barely play anything on that. Not any new modern games anyways.
highoctane do you have the whole Q3 market share tables ??
if yes, please post a link
You mean you can barely game on a 5770 or a gtx 460, come on,,,, barely??? :confused:
As for playing modern games, most games have user adjustable detail and resolution, they don't only increase detail.
http://investorvillage.com/smbd.asp?...sg&mid=9688438
I disagree.
Most people are still on X1900 and 8800GT's.. most didn't jump on the dx11 bandwagon (5000 series), because their gaming cards still work fine. But now that most are switching to Win7 as bonofide dx11 games are out.
So, expect a good majority of gamers to go GPU hunting this holiday season.
@ Helix
So not reliable then...
Gents!
To get the discussion back on topic there are some new leaks which haven't been posted here AFAIK:
http://prohardver.hu/dl/upc/2010-10/26439_01110.jpg
http://prohardver.hu/dl/upc/2010-10/26439_011101.jpg
Seems we will get our 2 GB of VRAM after all :D...wonder if Antilles gets 4 then....
LOL
AMD has delivered some 25+ million hd5k chips (and that has all different chips) nVidia 10% of that of 4xx series. And you have gourage to say "most have already upgraded". Get your head out of ur arse, even if your friends have, it does not translate to everybody has.
For example, i upgraded just now, and only cos i got hd6870 for 189€. Btw I had hd3870 that i bought for some odd 150€ many years ago.
^ Wouldn't that make, in theory, 6970 only 2 times faster in tessellation than 5870? AFAIK they are claiming much higher numbers.
I swear to god i saw 2 units for pro and 3 units for xt somewhere in an amd slide. but since it was a while ago take it with a grain of salt. but imagine those same 3 units in each of antilles cores.
can we continue with the antilles fun fact of the day ??? :D
those used to be fun
I just pray that Tessellation is beefed up enough to be competitive with Nvidia's offerings. As of right now, it's not important. However, it will become important in the near future. Tessellation is the new "shader." It's a novelty that will make games look that much more impressive without a lot of extra work.
I really hope AMD sees it that way. Otherwise, the GTX 580 may win, and nvidia may gouge prices again. I seriously want a big, fat, price war so that we can't make a bad decision on which ever card we choose. I hate it when this market becomes one sided.
Here's the way I see.
First, there were vertex and texture mapping.
Next, we got pixel shaders
Then, we got enhanced lightmaps.
Then, we got self-shadowing characters and advanced lighting.
Then, we got HDR.
And NOW, we're on Tessellation.
So who's going to win this race?
Antilles will be greater than GKxxx :)
nvidia's method .. big things .. no plan b ... blame the tooth fairy if something goes wrong
i really dont see 28nm fermi refresh doing a great job .... 22nm might be something different ...
What do you guys mean about this Nordichardwa is saying?:
Quote:
GeForce GTX 580 will most likely be the most powerful single-GPU graphcis card on the market in 2010. Now that we have the complete specifications for NVIDIA's GF110 GPU it becomes clear that NVIDIA is attempting to do what it failed to with GTX 480 - going all in - to win the performance war against AMD.
do they have a gpu in hand to prove such wild claims???
Numbers we've seen so far have seemed pretty impressive... see below.
Current benchmarks we've seen have shown the GTX 580 at stock taking down a GTX 480 at over 900 mhz. They apparently did more than just kick up the clocks to 772mhz and increase the shader count... :up:
Bingo... Someone gets it. I want to see them trade blows once again, because when that happens WE win. :clap: