honestly I'm glad its black to combat the heat.. looking good for us intel mobo people! times are good when your weakest link is a 4.0Ghz q6600.
Printable View
honestly I'm glad its black to combat the heat.. looking good for us intel mobo people! times are good when your weakest link is a 4.0Ghz q6600.
This card looks to be a huge step forward! waiting for results:)
Beguining of August I think;)Quote:
Originally Posted by Hornet331
Remember the Slide from AMD? 8 weeks counting from the day of the release of HD 4850.
I think you may want to check your math.Quote:
Originally Posted by v_rr
that first pic shows what looks to be 6 empty spaces for ram ?
could be the angle. but anyways it looks like there only two on the top side & eight on the back of the PCB
the 4870 have 8 gddr5 on one side. http://www.overclockersclub.com/revi...r_hd4870/2.htm
maybe those are high capacity chips & thats why it's not coming out as soon
2 power plugs thiis thing is going to run hoooot
I heard it is going to have 3slot cooling solution
Uh?Quote:
Originally Posted by demonkevy666
We might be looking at different pictures but what i see on the X2 are 8 chips on both pcb sides, divided in groups of four next to each gpu; can't see any empty space.
I certainly hope higher density chips are gonna be available or there'll be no 1gb framebuffer on the X2 :(
Loving the black PCB.
Sooo long lol!
there is a link in the first page, shows similar cooling to the HD3870X2Quote:
Originally Posted by XS Janus
hehe I was joking :D
But it would be cool if it had 2 slot cooler that extends to the back of the card via heat pipes for an additiona single slot sized fins.
yes black pcb!!!!
this or 280gtx that is the question.
And is a 3.4ghz e6750 enough for these cards?
This and e6750 would be a little weak for these
at last! black :D
Suddenly my rig felt the need for a bigger e-penis..
You would really want to use this card with C2Q@3Ghz,at least.Quote:
Originally Posted by disruptfam
dualcore @ 3,4ghz is enough for any game out there right now (well if we ignore supreme commander).Quote:
Originally Posted by informal
Also higher clocked dualcore own slower clocked quadcore in nearly any game.
Hmm...Quote:
Originally Posted by Hornet331
You may very well be right. I guess the images on PLX's site aren't that accurate. And since they list PEX 8648 is FCBGA so it most likely features an IHS. And the size of the chip mathes spot-on.
:)
I'd go dual for gaming anyday over a quad. I love my quad but its utterly useless to me since I don't do encoding or anything. That said, a 45nm quad is still in my future just cause I can OC those closer to 4.0GHz a lot easier than my Q6600 did.
Also, black PCBs are one of the single coolest and best inventions ever for video cards.
BTW in B3d's interconnect speculation thread here. Dave Baumann suggests that the PLX chip might be a custom design in cooperation between ATI/AMD and PLX and not listed sooooooo..... who knows
He does suggest that it is not yet listed, not much on how custom the chip really is....
Here is hoping that the CrossFireX Sideport is a separate interconnect between the 2 GPUs, a (more) direct connection between the GPUs as this will cut latencies and may increase bandwidth.
True, so we don't know exactly what it will have either way.
It looks interesting though. After reading about all the changes done to RV770 from RV670, I wouldn't put anything past ATI / AMD anymore. Now if only AMD CPU's had that same turnaround...
You can sure say that, the GPU guys are making it look so easy compared to the CPU guys....Quote:
Originally Posted by zerazax
its a possibility, someone just tell the guy who has the X2 to rip off the IHS and look what chip it is. :p:Quote:
Originally Posted by zerazax
We can always hope :).They do have the brains for it,now only if they had time to do it(and balls,since Shanghai is done on a new process node,a risky move).Quote:
Originally Posted by zerazax
edit:
Got this pic from B3d forum topic on 4870X2:
http://i32.tinypic.com/156tg05.png
http://i29.tinypic.com/2mnestj.png
http://i31.tinypic.com/2qwd9c5.png
http://i30.tinypic.com/2v1suwy.png
Enjoy :)
Why post so much for a PCIe 2.0 switch chip? It could be godly and nothing changes for the texture loading and such from CPU and memory. Still 1 PCIe x16.
And at best, PCIe x16 2.0 is 8GB/sec in each direction.
Also the slides above just tells its easier to assign buffers and such if you partition the ports in a whole other faction with alot of other devices. And not just a static 3x x16. It could also be 12 x4. Thats why the buffers are as shown.
Also it has to be a 8648 chip, with another 140ns lag added.
http://www.plxtech.com/products/expresslane/pex8648.asp
http://www.plxtech.com/pdf/product_b...95_16Jun08.pdf
this :D?
what surprises me is, that the pcie 2.0 switch has a higher latency then the pcie 1.0 switch.Quote:
Originally Posted by Shintai
That would mean that it is in fact just another version of R680, just with the RV670 chips replaced with the RV770 chips and of course a different bridge chip.Quote:
Originally Posted by hollo
My guess would be that your "standard crossfire bridge in PCB" would be the "CrossFireX SidePort" which would in fact different than the normal bridge....or the CrossFireX Sideport is another parallel connection.
Just speculation though, and hoping....
Well, I think them changing the good and efficient RingBus for the hub-systemQuote:
Originally Posted by Helmore
happened for a reason... and I think that reason is shared memory between
the gpu chips.
When clocked the same the GX2 is an hair better, due to decreased latency IIRC.Quote:
Originally Posted by AriciU
I'm pretty sure that won't happen and then there is another fact and that is that this memory subsystem they are using on the RV770 cards is more efficient than the ring-bus. The Ring-bus had other reasons for it's existence.Quote:
Originally Posted by Frank M
And then of course the fact that there won't be a shared memory system between the GPU chips, there will probably be some seriously improved communication but no complete memory sharing. Not this generation at least and probably not even the next generation.
There is also the fact that R700 will be using 2 RV770 chips clocked at 4850 speeds as the cooling needed to do 2 of those at 750 MHz. is just too crazy. This will mean that R700 will be faster than 2 4870 in CFX in general, but in occasions where crossfire scales exceptionally well this will be different.Quote:
Originally Posted by Tonucci
BTW, keep in mind that I'm just speculating although I'm pretty sure on those clocks.
Ouch, is it confirmed that R700's clocks will be around 625?
you're only speculating, so.... :shrug:Quote:
that R700 might be faster than 2 4870 in CFX in general
I will buy 2 4870's anyway because i won't be able to resist. But probably i'll buy a 4870X2 later as well, and move the 2 single cards to my other PC. Then i finally will see the difference (if there is) with my own eyes. :)
Someone who posts here regularily and knows, said that, yes. It is done because of the cooling factor. so if you want to clock them higher, change the cooler to some ultra-turbo-superdidooper one.Quote:
Originally Posted by annihilat0r
definately a good idea to go with a black pcb:up:
and the difference will be marginal. takes no nostradamus to say that.Quote:
Then i finally will see the difference (if there is) with my own eyes.
Relax and take a deep breath, The AMD folks have been leaking little tidbits of info out on this for awile now that makes it fairly obvious that the GPU interconect is not Xfire dependent at all but a PCI bridg chip still is needed for both GPU's to be fed at same time by the MB. The R700 will have to outperform 2 4870's wich really completly on the pci express bus. AMD has said many times that the interconnect tech. is superior to the R680 and I have no reason to doubt it. I Dont realy understand why so many are insisting that becouse it has a PLX Switch that its exactly like the 3870x2. There is no way at this day and time for them to do this without a switch, but that dose not mean it is the only link between GPU's.
Edit: actualy Im not sure that 2 4870's really completely on pcie bus There may be advances made here as well, but it has to be more dependent on it than R700
Why? It only needs to outperform one. And as said by others. Its most like 4850 clocks with GDDR5. Else the TDP would go completely skyhigh.Quote:
Originally Posted by G0ldBr1ck
4850 is already the same TDP as 3870. An X2 with 4870 GPUs would be 50% higher TDP or so than a 3870X2...
Not many, only a few nv-fanboys (who don't feel very good lately) keep persisting, as if they know anything...Quote:
Originally Posted by G0ldBr1ck
I would speculate that the interconnect on the X2 will out way the slower clocks vs 2 4870's
Maybe they want to see AMD/ATI go under so that they can pay $2000 dollors for there Intel quad and $1500 for there NV CardQuote:
Originally Posted by Unbornchild
Why does that surprise you?Quote:
Originally Posted by Hornet331
Look at DDR...
ATI really needs to have done a good amount of improvement to its x2 setup for the 4870x2 at 4850 clocks to be faster than two 4870s in CF.
Anand says the new Crossfire Sideport (wich is suposed to enable the GPUs to share memory) isn't enable in single RV770, and will be enable in the X2.
http://anandtech.com/video/showdoc.aspx?i=3341&p=9
And unlike the 3870X2, the new one has GDDR5 memory (probably faster than on normal 4870) and PCIe Gen2 interconnect.
Add binned, higher clocked GPUs and we have real competition to the GTX 280.
And I read somewhere the 4870X2 will have a full copper + heatpipe cooler, maybe with the fan in the middle, like the 7900GTX cooler.
I hope they bring back the "wind tunnel" blower design, like the X800/X1800 cooler.
BTW, I see a lot of CPU design influence here:
http://images.anandtech.com/reviews/...I/4800/hub.png
binned chips at a lower voltage maybe? dunno, just guessing, but its the only other way I can think off how they could keep heatoutput within reasonable levels.Quote:
Originally Posted by Shintai
ok, so according to anandtech it's more like this-
That seems likeliest. The sideport probably communicates certain information to improve scaling and performance while the bridge chip is used to communicate with the PCI-E interface (which is necessary). So it won't be CF on the chip but a different method.Quote:
Originally Posted by hollo
this photo shows the card using the same cooling design as 3870x2 or very similar.Quote:
Originally Posted by doompc;
And I read somewhere the 4870X2 will have a full copper + heatpipe cooler, maybe with the fan in the middle, like the 7900GTX cooler.
I hope they bring back the "wind tunnel" blower design, like the X800/X1800 cooler.
BTW, I see a lot of CPU design influence here:
[img
http://img.hexus.net/v2/graphics_car.../R7001-big.jpg
More like this:
http://www.xtremesystems.org/forums/...1&d=1211646064
Although it has been said by some that even this cooling design has been revised to improve cooling, there may be an extra heatpipe for example.
Must be a newer design from the other pic. theres no heat pipe on the first one.
I think I just came.
Would be awesome if 3870x2 H20 blox fit on these. You'd think, with the price of fullcover blox these days, that ATI and NVidia would try to allow for that to promote upgrading.
looks big. Hope the price isnt out there.
I don't think ATI is going to place the HD4870X2 too far out. $489 it will cripple Nvidia and there would be riots over this card!Quote:
Originally Posted by strange|ife
Well, according to the cnet article, the R700 doesn't use crossfire at all to communicate between its two gpu's. "They've come up with this stellar way of doing inter-processor communications ... a new proprietary inter-processor communication technology."
The article implies that the processors communication isn't at the end of the pipeline, so it seems they would be working together in the pipeline, on the same frame, ie SFR.
Split Frame Rendering probably isn't the best way to desribe it because the GPU's are probably working on a much smaller level than half of a frame. Probably, the command processor splits commands up between GPU's. Indeed, the Command Processor has a direct link to the Hub, but it would also need a link to the other GPU. Whatever pixels are rendered by each GPU need to be sent to the other GPU to put into its own memory.
Who knows, but this 'stellar' communication link should be operating at a high frequency (core frequency) and allow for fairly high bandwidth from all the rendered pixels.
Of course the best way to do this would be to have a 115GB/s link ... maybe just connect up each GPU's memory controllers to the other GPU's memory, making it a 512 bit interface to each GPU ... but I dont think they would do this because of cost. So, it will probably be a lot less bandwidth than 115GB/s.
Anyone wants to join me on some guesses for the estimated price for release? I'll aim for $499 :)
I'll say $449.Quote:
Originally Posted by martindh2005
When does this card come out?
If its the fastest card on the block by a considerable margin and considering the amount of DDR5 on that thing...I bet it will be closer to $600 or $487.20 :p: Seriously though, I'm thinking there is going to be a shortage of these cards at release. Once things settle down though I could see this card settling at the $499 range.
The only rumors I have heard say $499, but we also had rumors of a $499 GTX280 right up to like a week before release or something. So who knows. AMD could price it at $599 if they wanted and it would still be a much better deal than the GTX280. The old ATI would definitely have priced it at something like $739 MSRP, but AMD tends to be a bit more aggressive with their pricing, especially now when they are in financial trouble. Some of you folks are truly optimists. Maybe they will just give the cards away or pay you to take one off their hands. After all AMD is making so much money they can afford to just give away their products. It's not like they have been losing millions of dollars over the past year. Too many people try to think with their emotions, believing something because they want it to be true.
Excuse me while I go change my pants...
Damn this looks like a wonderful solution for me. ATI/AMD is really looking excellent with their solutions.
I am still wondering, why many see this as a 2 x 800 SP solution, while viewing the 8800 GTX as a 128 SP and GTX 280 as a 240 SP solution. That is just flat out wrong and even GPU-Z gets these numbers wrong. If 8800 GTX is a 128 SP solution, then HD 4870 is a 160 SP solution. If HD 4870 is a 800 SP solution, then 8800 GTX is a 256 SP (and perhaps even a 384 SP) solution.
That ignored, I just love what appears to be a strong comeback by AMD/ATI for me personally. They really look strong and if I had the need for it, I would upgrade my two Ultras without question (but I don't, for now).
Looks like a R300 / R350 vs NV30 / NV35 scenario repeated, except that the prices are different.
my 4870x2 doesn't boot, but windows can detect it and install the driver. (use another PCI-card to post)
it just no screen....
Go on... :DQuote:
Originally Posted by guess2098
man I told you not to post about that other than in the XS secret section, now they'll all know we got those pre-release samples :mad: (btw mine boots fine)Quote:
Originally Posted by guess2098
how much do these use power wise!?
im hoping a 850w is enough for two
that's too bad.Quote:
Originally Posted by guess2098
I'll give you a hand, I'll try it in my machine. Heck, maybe I'll even pay shipping. :)
:D
I don't know where your numbers from or your math is seriously skewed, but that is just not right what you are saying there. It has also been know for a long long time that you just can't compare shader/pipeline (and whatever you want to call it) count between ATI and NVIDIA, if you could then the X850 cards from ATI would have been way faster than NVIDIA's 6800 cards for example and this was clearly not the case.Quote:
Originally Posted by Seraphiel
A GTX280 has 240 stream processors while a 4870 has 800, these SPs on the GTX280 can do 1 MADD and 1 MUL per cycle (1 MADD+1 MUL/clock cycle) while those SPs on the 4870 can do 1 MADD per cycle. So that means the 4870 can do 1600 FLOPs/clock cycle and the GTX280 can do 360 FLOPs/clock cycle, that's not to hard to see now is it? It's just that the SPs on the GTX280 run at a way higher clock and are a little more flexible because there is less dependency between the SPs, but if you would write code that is optimized specifically for each architecture then you can truly get 1200 GigaFLOPs out of the 4870 and only 933 GigaFLOPs out of the GTX280. But we by now know that these numbers mean nothing for in game results though.
id say $499Quote:
Originally Posted by martindh2005
and if you want the australian price; just add 50% :lol:Quote:
Originally Posted by F.stop
no, but seriously...probly much like the 3870X2 at debut...hopefully($650aud roughly),
which would basically eliminate 9800gx2.
and if more than that i'll just put it in the gtx 280 category (ie those cards i cannot afford:D)
$499 would be super fine, and if it doesn't have microstutter, it's my next card
$549 here.Quote:
Originally Posted by martindh2005
*WIEWOOWIEWOOWIEWOO* Deputy Perkam, To Protect And Serve Xtreme Overclocking CyberspaceQuote:
Originally Posted by annihilat0r
His math is actually right. Its yours thats wrong, unless you believe marketing.Quote:
Originally Posted by Helmore
Even your math is wrong, unless you count a MUL for half or something.
Its simply a simple shader vs complex shader discussion. And marketing couldnt stand being "less".
It would be like claiming a Kentsfield/Yorkfield is a 16 "something" CPU and Bloomsfield 32. And a Phenom X4 for 12. You would instantly debunk that, but for some reason you eat the same logic if applied to GPUs.
Black PCB? I'm convinced, period, nothing will change my mind.
We've had these Nvidia SP vs. ATI SP discussions before, please search before trashing the topic.
OT: Does anyone knows if ATI will release a X2 FireGL card? I know they will release a new FireGL serie based on HD4xxx, which they never did with HD3xxx.
+1!Quote:
Originally Posted by Empty_Quarter
I wonder if the reason it has a black pcb is because they going to call it the Black Edition like the amd processors
Completely random theory, if its black edition maybe they have shader domain clocks (equiv to unlocked multis?). I'm dreaming but I want it to be true :(
guys will the 4870X2 have any problems with X48 boards? i've heard the 3870X2 wasn't booting in most X48 boards.
I just hope they hurry up and get it released cause i want one. Also i hope Thermalright hurry their ass up and get a T Rad designed for the 4870X2 aswell.
Fubar? :eek:Quote:
Originally Posted by Scubar
Perkam
That would be nice but I'm not so sure how they'd do that.
It however does look like it may fit height wise so who knows.
However them makeing a dual style T rad2 for it would be sweet but highly unlikely because I don't think though it'll be popular that it'll have a big enough market.
From the looks of it so far I'm worried about it's cooling ability and performance because of the fact its down clocked from 4870 apparantly so 4870's overclocked would seemingly be faster thanks to better overclocking headroom I'd assume. Can't wait to see what it can do though.
Hopefully optimistic that this new way of communication is what it's hyped up to be, don't understand the nay sayer's who don't have a clue but criticize already.
I think that the best way to compare would be rv770 as 800 and g80 as somewhere around 300 since one of the operations didn't always work. That way people know the full capabilities of each card. Thus we have that the 4870 has 800 shaders @ 750mhz, and gtx 280 has 720 shaders @ 1300mhz, so looking at that it is understood why gt200 outperforms the 4870 but not by much.Quote:
Originally Posted by Seraphiel
But seriously, enough of this. We've gone over it a billion times, what's most important now is if those shared memory diagrams do mean that the 4870x2 will have shared memory or if they simply are diagrams of how it would be done and what it offers
My geuss is: No shared memory for R700. Better communication between the 2 but no complete memory sharing in the sense that there is no (or hardly any) penalty for a lookup in the other GPU's memory pool.
I'm not getting your numbers though, AliG.
:D me tooQuote:
Originally Posted by Empty_Quarter
Black's nice but when your gaming or useing your comp you shouldn't be staring in at your graphics card lol
It'll be saying hello through it's nice images on your screen w/e they may be ;) lol
But if they stick with black it'll go over well with those judemental based on appearance.
175W per 4870, so the X2 would be theoretically 350W, even higher if it's clocked higher like the 3870X2 (850MHz obviously thanks to added voltage) over the 3870 (770MHz).Quote:
Originally Posted by fornowagain
Please ATI. Please, please be have done something for microstutter. I want fluid movement in super-AA quality. AND I don't want to get a GTX 280. And after reading that thread I'm not too keen on buying a 4870 and OC'ing like mad, either. Please................
2x 175W?
Doubt it, most likely, as with the 3870X2, they bin high for dual GPU's, to find ones that will reduce the total load the cards pulling.
I wonder the performance of 4870x2 when coupled with a 4850 or 4870 or another 4870x2
it will be a truest supercomputer @ home
Umm does anyone remember the press release they said 250w tdp I believe.
and it doesn't take fully twice the power that one card does, don't believe the 3870x2 or 9800gx2 did either. Just look at load on some review sights and you'll see.
I doubt it'll be to great scaling of 3 and 4 GPU's is bad right now as shown by tri and quad sli and previous crossfireX. Though since they seem to be focusing more toward dual card solutions they may have improved it a bit.
I'm gonna take a guess at scaling of maybe 30% or so for a 3rd card and like 15% for a fourth.
If I remember correctly a HD4XXX based firegl will be announced around september.Quote:
OT: Does anyone knows if ATI will release a X2 FireGL card? I know they will release a new FireGL serie based on HD4xxx, which they never did with HD3xxx.
btw a HD3XXX firegl was released, the firegl7700.
The issue is the 3870 has a TDP equal to a 4850. the 4870 is some 50% more. You need more than perfect bins and so on to make a "real" 4870X2. Thats why alot bets on its actually 4850 chips just with GDDR5. The TDP would be too high and the card lag additional power connectors for that to be 4870 chips.Quote:
Originally Posted by Caveman787
That's also what w0mbat has said so far, that R700 will be two RV770 chips clocked at around 4850 speeds but with GDDR5.
well it does have additional power from the pictures that have been shown so far it had a 6 pin and an 8 pin connector. Unlike the 4870's dual 6 pin's.
and I believe it wouldn't be a massive increase over gtx 200 series?
Why would it have to be a massive increase? And as you even write yourself. Chaning 1 6pin to an 8pin would not even be near powering an extra 4870 speed GPU (Not even a 4850 or lower if one is a 4870).Quote:
Originally Posted by Caveman787
Not sure why you stick so hard to this...You _really_ want it to be 4870 GPUs, because? Everything points against you and you keep trying...
Umm why wouldnt I want it to be a faster better graphics card? wow.
You just seriously seem to want to dump on ATI's parade.
If a single 4850 can be powered by a single 6 pin, whats to say 2 couldnt make it on 2?
Your talking like it'd be impossible to hook to cards together yet it's been done before without super massive power requirements.
Who cares, even the 4850's have hit 900+. And the ones in an x2 will probably be binned for low voltage compared to a 4850. I know that if I got an x2 card I would slap a/some water block(s) on it and the whole stock clocks point would be moot. And I'm sure I'm not the only one here either. ;)