[Psycho]

Originally Posted by ECH

Looks like the Wii U will use an AMD graphics card. I've not seen any other reports on this though...

That has been official from day one: http://www.amd.com/us/press-releases...011june07.aspx

[Pressure]

Originally Posted by ECH

Looks like the Wii U will use an AMD graphics card. I've not seen any other reports on this though...
link

I wonder if it will be one of the 8000 series or this E6760 as rumored?

I'm pretty sure that has been the rumor all the time. We just don't know which GPU. Some said R700, like the Radeon HD 4870.

EDIT: And even official, as Psycho posted above.

[ECH]

Originally Posted by Pressure

I'm pretty sure that has been the rumor all the time. We just don't know which GPU. Some said R700, like the Radeon HD 4870.

EDIT: And even official, as Psycho posted above.

Which GPU though? This E6760 that's been talked out or something from the 8000 series. To me, that may determine how well future PC games will be developed and how they compare vs the same game on consoles. Consoles already have a pretty big advantage when it comes to draw calls. So I wonder what next gen AMD cards will do for PC games in this aspect. I guess Stuff on Screen is a pretty good way of putting it.

Can we get a PC game that showcases HD 8000 series card using higher draw calls then what current or next gen consoles games offer? That's what I would like to know.

[iMacmatician]

From KitGuru: "AMD Radeon HD 8970 and 8950 launch plans revealed."

They have a screenshot of the (unsourced) Wikipedia page in the report, so I'm taking this with a few grains of salt, but they say a June 2013 launch is likely.

We’ve learned that, right now, partners are planning to show off the Radeon HD 8970 XT at CeBIT in March – with a full launch at Computex in June.
However, the products are actually ahead of schedule, giving AMD the option to launch early if something new comes along from nVidia. If AMD is as far down the line as we suspect with its development, there will be some ‘behind closed doors’ displays for key customers in a secret hotel room in Vegas come the first week in January.

Videocardz, in their "AMD Radeon HD 8970 Rumored Specification Analysis" report, claims that ESes will arrive in Nov/Dec with release in February.

[Alexko]

A March launch would be very late considering that all of AMD's recent launches happened in a September-January window.

[lanek]

Cebit, Computex ? what they have got is just AIB who have told them their cards will present on Cebit of March .. Nothing about the AMD release , who will surely occur betwen January and March for the early models ( 8970- 8950 first, followed by the 8870-8850) ..

Each year some sites like Kitguru are pusing the 8930 ( 7930 - 6930 ).. If a card like this is released this will not be decided before the "standard " one are pushed on release.

[UniversalTruth]

We’ve learned that, right now, partners are planning to show off the Radeon HD 8970 XT at CeBIT in March – with a full launch at Computex in June.
However, the products are actually ahead of schedule, giving AMD the option to launch early if something new comes along from nVidia. If AMD is as far down the line as we suspect with its development, there will be some ‘behind closed doors’ displays for key customers in a secret hotel room in Vegas come the first week in January.

This is simply plain ridiculously late. After this, please, don't ask why people have the impression that something happens late. Probably even too little too late...

[Kaotik]

Originally Posted by iMacmatician

From KitGuru: "AMD Radeon HD 8970 and 8950 launch plans revealed."

They have a screenshot of the (unsourced) Wikipedia page in the report, so I'm taking this with a few grains of salt, but they say a June 2013 launch is likely.



Videocardz, in their "AMD Radeon HD 8970 Rumored Specification Analysis" report, claims that ESes will arrive in Nov/Dec with release in February.

Few grains of salt? Obvious fake is obvious when you mix desktop (oland, island in a sea) and mobile (mars, venus, planets and other things in space (since sun is supposed to be there too)) in the same chart

edit:
Not to mention it says that 8950 is Venus Pro, 8970 Venus XT and dualchip 8990 would be Venus XTX, which is obviously false

[Ryan Smith]

Originally Posted by Alexko

A March launch would be very late considering that all of AMD's recent launches happened in a September-January window.

When it comes to GPU launches it's ultimately TSMC who controls when something launches. Even though Sea Islands is 28nm, AMD has to be sure to pace themselves so that they don't have too much of a gap between that and their 20nm GPUs.

I think it's safe to say we're off the yearly GPU cadence right now, at least in the two generations per node scenario.

[liolio]

How about a launch of the 87xx and 88xx first, some "bartized" 79xx and 78xx and the 89xx launching later with a significantly revamp architecture. A bit like what happenend from 5xxx to the 6xxxx series?

[jimbo75]

Originally Posted by Ryan Smith

When it comes to GPU launches it's ultimately TSMC who controls when something launches. Even though Sea Islands is 28nm, AMD has to be sure to pace themselves so that they don't have too much of a gap between that and their 20nm GPUs.

I think it's safe to say we're off the yearly GPU cadence right now, at least in the two generations per node scenario.

It would make more sense to have a year of the older generation and 20+ months of the later, faster cards instead of say 16 months of the older gen and 16 months of the newer gen.

[Silent_Buddha]

Originally Posted by Ryan Smith

When it comes to GPU launches it's ultimately TSMC who controls when something launches. Even though Sea Islands is 28nm, AMD has to be sure to pace themselves so that they don't have too much of a gap between that and their 20nm GPUs.

I think it's safe to say we're off the yearly GPU cadence right now, at least in the two generations per node scenario.

Nvidia has been off the yearly cadence for quite a while now, but AMD has thus far been ~1 year per GPU series. It'll be interesting to see if they also fall off the 1 year cadence with this upcoming gen.

Regards,
SB

[Alexko]

Originally Posted by Ryan Smith

When it comes to GPU launches it's ultimately TSMC who controls when something launches. Even though Sea Islands is 28nm, AMD has to be sure to pace themselves so that they don't have too much of a gap between that and their 20nm GPUs.

I think it's safe to say we're off the yearly GPU cadence right now, at least in the two generations per node scenario.

Maybe, but AMD could always go for a mid-life refresh to their Sea Islands lineup, much like the 7970 GHz Edition (although with better marketing, hopefully) or the 4890, a few years ago.

It seems to me that when competition is tough, it's always best to release improved products as soon as possible.

[ECH]

Is there anything that either future drivers/gpu can do to free up hardware threads so that a game restrained to just one thread could play more efficiently? For example (look at the 'update' portion towards the end):
http://www.pcper.com/reviews/Graphic...d-HD-7970/GPU-

Which indicates that BL2 is waiting for a single thread to finish which results in lower performance.

[lanek]

I dont know. At the same time, i dont think it is in the Nivida interest to do it.. Imagine what will happend with close performance with gpu physx and cpu physx in a case like Borderland2.

[ECH]

Originally Posted by lanek

I dont know. At the same time, i dont think it is in the Nivida interest to do it.. Imagine what will happend with close performance with gpu physx and cpu physx in a case like Borderland2.

I wonder if using a ramdisk could elevate some of the performance issues using a single HW thread.
I read something not long ago that AMD might be using a ramdisk. At what capacity would this be available? Would GPU users have access?
http://news.softpedia.com/news/AMD-R...r-295452.shtml.

Edit:
I found more information but they are talking about it's use with memory products...
http://corporate.dataram.com/company...radeon-ramdisk

[CRoland]

Originally Posted by ECH

I wonder if using a ramdisk could elevate some of the performance issues using a single HW thread.

I doubt the PhysX code is blocking on disk loads.

[Psycho]

The cpu fallback of physx is just some old single threaded x87 code, coded by a retarded monkey on crack (or well, probably just made by ageia 5+ years ago and therefore not suited for today).

Making the cpu implementation of an interface made for the gpu multithreaded should be pretty damn easy, if nvidia wanted to supply a serious physics middleware. But with about 1 decent title pr year I guess noone bothers..

[ECH]

Originally Posted by Psycho

The cpu fallback of physx is just some old single threaded x87 code, coded by a retarded monkey on crack (or well, probably just made by ageia 5+ years ago and therefore not suited for today).

Making the cpu implementation of an interface made for the gpu multithreaded should be pretty damn easy, if nvidia wanted to supply a serious physics middleware. But with about 1 decent title pr year I guess noone bothers..

It's disconcerting to see that BL2 used physx 2.8.4 when physx 3.0 supposedly fixed those issues was ready in May of last year. I wonder if the newer version was released if AMD could take advantage of it's CPU performance?

[lanek]

Im more concerned by the fact PCper use a benchmark provided by Nvidia ( bugged with PhysX who stay on High on 2 scene ( even if you set it at low )
saying, this is what you will see as difference when playing .. obviously, the benchmark is only made for show PhysX effects .. ( just look the video ).

I like the article.. " as a new good game is release, we have decided to do an article about it and PhysX"... " what an hasard, Nvidia just send us a benchmark tool for it who will be certainly included in the game soon"



I dont understand why they have not just use fraps, on a choosen Game sequences, knowing the cpu thread problem, do it 3-4 times in a row. We dont have any information on the cpu used and at what speed.

If you want to mesure the impact it will have, you choose a typical game sequences and you go with it, not using large plans showing the additional PhysX effect in a raw sequences of 1min30

[UniversalTruth]

Originally Posted by iMacmatician

From SemiAccurate: "What is the latest on AMD’s Sea Islands?"

March 2013 release (they don't mention which variants) and a 15% speed increase over Southern Islands.

Here, because obviously the other thread is for something else.

Ok, I think about two possibilities. Either these 15% are wrong and we will be surprised.
Or they will significantly reduce pricing of current line-up and put these 15% more for the same price as it is the HD7970 now.

[iMacmatician]

Originally Posted by jimbo75 (from the 7xxx series thread)

I'd guess 30% was before the GHz edition was released. It'll be hard to justify the 8xxx name with only 15% performance gain though.

If this is the case, then maybe the 88*0s and 87*0s will have closer to 30% performance gain over their respective 7**0 cards (especially if that Oland rumor is anywhere near accurate).

Taking it a step further, maybe the 89*0s were planned to be ~30% above the 7970 GHz Edition and the 7950 Boost, but due to power they scaled them back to ~15%.

[CRoland]

Originally Posted by UniversalTruth

Here, because obviously the other thread is for something else.

Ok, I think about two possibilities. Either these 15% are wrong and we will be surprised.
Or they will significantly reduce pricing of current line-up and put these 15% more for the same price as it is the HD7970 now.

15% more than? Is it per W? Per SP? Or e.g. 8770 vs. 7770?

[caveman-jim]

I'm thinking CI is to SI what NI was to Evergreen. Tweak and tuck, bigger, more power, bit more performance.

SI is a 2012 line, CI is a 2013 line, 15 months between launches isn't too bad, especially with another 15 on the cards availability for next TSMC node. On a marketing slide that's still a yearly cadence.

[LittleJ]

Originally Posted by caveman-jim

I'm thinking CI is to SI what NI was to Evergreen. Tweak and tuck, bigger, more power, bit more performance.

SI is a 2012 line, CI is a 2013 line, 15 months between launches isn't too bad, especially with another 15 on the cards availability for next TSMC node. On a marketing slide that's still a yearly cadence.

Sounds about right. History seems to repeat itself in GPU manufacturing the last several years. The top GK110 part will probably be a smidge faster than HD 8970, albeit much larger and power hungry, similar to GF110 vs the top Cayman part.

Personally I want to see how Oland(8870) performs against GK104(114) since both will be relatively similar size...