AMD: R8xx Speculation
- Thread starter Shtal
- Start date
I kinda ignored that cpu difference. You're right though could be just enough of a difference (300 or so in the P score?) that the mobility 5870 is indeed sligthly faster than the desktop 5750, so clocks are probably similar.
leoneazzurro
Regular
In a mobile system probably you are mostly limited by the CPU at those resolutions, Asus G73 has a i720QM and these results should be compared to another mobile system with the same CPU. Anyway, if 5870 mobile is on the same level as 5750/5770 desktop, it would be anyway the fastest mobile card out there and there is no hint of a response from the green team for what could be many months. Of course, Cypress should be more powerful, but maybe the TDP for such a solution is not yet there (maybe it could be there in the future).
bit-tech: -well if it is then, do you have something else up your sleeve to compete?
Richard Huddy (AMD dev rel): Let me say that I suspect that through 2010 it's possible there will be moments where we don't have the fastest graphics card, but I expect that for the majority of 2010 we'll have the fastest card you can buy. I've good reason for believing that but I can't talk about unannounced products or any of the stuff we're doing to secure that.
Linkie: http://www.bit-tech.net/bits/interviews/2010/01/06/interview-amd-on-game-development-and-dx11/5
So you see, they say they have something. Now the question of what that is rests upon our speculation abilities, leaks and their timely release of powerful hardware!
Here's looks like the ATI mobility release and a Compal NBLB2 Review:
http://www.purepc.pl/urzadzenia_mob...otebook_z_ati_mobility_radeon_hd5000?page=0,0
Lots of details in the link...
Has die shots of the three chips, first Broadway is obviously Juniper. Looking at next 2, Madison and Park they are supposed to be the same package as the RV730 and RV710...if so i measure Madison die size as 10% smaller than RV730 or 130mm2 and Cedar as 10% bigger than RV710 or 80mm2.
Transister count on Park/Cedar appears to be the same as the RV710 despite the chip appearing larger and on a smaller process. Surely must be a mistake somewhere
http://www.purepc.pl/urzadzenia_mob...otebook_z_ati_mobility_radeon_hd5000?page=0,0
Lots of details in the link...
Has die shots of the three chips, first Broadway is obviously Juniper. Looking at next 2, Madison and Park they are supposed to be the same package as the RV730 and RV710...if so i measure Madison die size as 10% smaller than RV730 or 130mm2 and Cedar as 10% bigger than RV710 or 80mm2.
Transister count on Park/Cedar appears to be the same as the RV710 despite the chip appearing larger and on a smaller process. Surely must be a mistake somewhere
Not really: http://forum.beyond3d.com/showpost.php?p=1373752&postcount=4904
Wrong transistor count for Park, which is also in marketing slides. And there were no details about SIMD configurations of Park and Madison.
And the very bad decision of a (G)DDR3-option for Mobility HD 5850 is also missing:
http://www.amd.com/us/products/notebook/graphics/ati-mobility-hd-5800/Pages/hd-5850-specs.aspx
So this notebook with probably 1/4 of desktops HD5850 BW was no writing mistake: http://www.comdeal.de/PC-Systeme/NO...re-2-Duo/Aspire-8942G-728G1280TWn::81274.html
Last edited by a moderator:
ATI Mobility Radeon™ HD 5165/5145 Graphics... looks like ATI is back to its old renaming antics
Transistor count on Park/Cedar appears to be the same as the RV710 despite the chip appearing larger and on a smaller process. Surely must be a mistake somewhere
Here is the relevant marketing slide from anandtech: http://www.anandtech.com/GalleryImage.aspx?id=7326
(They seem to have put up the whole pack)
It says 242million transistors for Park/Cedar pretty much same as RV710, whereas the AMD site now lists as 292million from Anarchx's post above. So mistake in the press pack
If someone else wants to try the die size comparison to the RV710 i used dieshots from pcgameshardware's review here: http://www.pcgameshardware.com/aid,661814/AMD-Radeon-HD-4550-reviewed/Reviews/
Just measure the % size of the chip compared to package from the anandtech(Park/Cedar) and then same operation from the pcgameshardeware(RV710)...comparing these 2 numbers i get 10% bigger for Cedar.
Edit: Just in case anyone was wondering relatively how these will sell, from anandtech:
"That of course doesn't tell the full story, and in speaking with ATI we were informed that 70% of sales have been 4300/4500 parts - the lowest performing, least expensive offerings. 15% of sales are from the 4600 series, which is where reasonable gaming can finally enter the picture. As for the 4800 series, it's still sitting at less than 5% (with the remainder of ATI's sales apparently coming from older 3000 series parts). As far as high-end laptop graphics is concerned, NVIDIA has had a clear lead for a while, for a couple of reasons."
Last edited by a moderator:
Also compared by the components on package Park/Cedar looks a bit bigger than RV710.
So it might be pad limited by GDDR5 IMC and Eyefinity (4 outputs).
Madison/Redwood seem to be around 95-100mm², if you compare it by the components on package, or here with the Lynnfield Die: http://www.notebookcheck.com/ATI-Mobility-Radeon-HD-5650-Grafikkarte-im-Test.23823.0.html
So it might be pad limited by GDDR5 IMC and Eyefinity (4 outputs).
Madison/Redwood seem to be around 95-100mm², if you compare it by the components on package, or here with the Lynnfield Die: http://www.notebookcheck.com/ATI-Mobility-Radeon-HD-5650-Grafikkarte-im-Test.23823.0.html
Last edited by a moderator:
Wow - just wow.
Maybe GDDR5 causing inflation, not sure about the display outputs - saw this post the other day and the outputs are coming out on the side of the chip that doesn't appear to have anything else much on it(pci-x is on the bottom and memory on far side and top) at least for the RV710.
For Madison/Redwood i used anandtech's gallery image here. For RV730 from it168 here. From those images i got Redwood as 10% smaller or 130mm2. The RV730 is rotated so is hard to tell if they are the same package.
ATI Mobility Radeon™ HD 5165/5145 Graphics... looks like ATI is back to its old renaming antics
Looking at the specifications 5165 = RV730 and 5145 = RV710.
At first when i saw the names i thought they might be a new chipset as they usually lag on DX revisions and process used. As usual that was too optimistic....
Interesting what will they use for chipset numbers now 5200 will be slightly weird sitting above those two.
AMD might be scared about TSMCs 40nm capacity and or wafer price as well if Cedar is too expensive or unavailable in sufficient quantities can now dress up their old stuff with nice new vests to make the sale.
Edit: AMD Ships 2 millionth DX11 GPU - these figures better not include sales of the above 2 chips....
Last edited by a moderator:
FrameBuffer
Banned
I guess ATI has decided to yield the mobile (programming) field as they will no longer offer any mobile part with DP support, if anyone want DP they instead will have to go green or try and find the older 4800 series.
While many (including ATI/AMD) may be dismissive of the demand for dp in the mobile space, I honestly think this is a key failure for ATI/AMD and one of the long standing reasons why ATI/AMD will always play 2nd fiddle to NV when it comes to what many programmers desire (a greatly expanded LCD- lowest common denominator).
While many (including ATI/AMD) may be dismissive of the demand for dp in the mobile space, I honestly think this is a key failure for ATI/AMD and one of the long standing reasons why ATI/AMD will always play 2nd fiddle to NV when it comes to what many programmers desire (a greatly expanded LCD- lowest common denominator).
Similar threads
