Sapphire to release 7970 clocked at 1325, also a 6gb variant.

[at80eighty]

can AMD put more transistors on those chips ??
i think nvidia chips is bigger than amd one's

sorry for bad English

Which are you referring to? Kepler or Fermi?

welcome to anandtech; i used to live in your country before!

 

[VulgarDisplay]

1/4 dp rate for the 7970, 1/2 for Firepro products.

The problem is that people/businesses use Teslas because CUDA is much more prominently used for compute apps than OpenCL. AMD needs to push their software before they can get a piece of that GPGPU pie.

OpenCL isn't AMD's software. It's an open standard so expect to see it's use surpassing CUDA in time.

 

[tech97]

Which are you referring to? Kepler or Fermi?

welcome to anandtech; i used to live in your country before!

Im refering to fermi
evey one Interested in tech should have an account at that great site:thumbsup:

 

[SlowSpyder]

I would love something like this, but I think it would be so under used when coupled to my Phenom. But, I've had a 4870 Toxic as well as two 5870 Vapor-X's, and I really, really like these Sapphire cards. They run cool, quiet, and stable. This will be a monster card if the rumors are true!

 

[VirtualLarry]

Would a Q9300 C2Q 2.5Ghz clocked to 3.0Ghz bottleneck a 7970? An OCed 7970?

I'd really love to get one, haven't ever owned the highest-end GPU, but if I would be too bottlenecked, then I won't get one.

I currently have a Gigabyte windforce dual-fan GTX460 1GB OC (715, but I turn it up to 820-840). Runs Skyrim on High settings @ 1920x1200, I haven't measured with Fraps, but it's probably roughly 20-30fps.

 

[Smartazz]

Would a Q9300 C2Q 2.5Ghz clocked to 3.0Ghz bottleneck a 7970? An OCed 7970?

I'd really love to get one, haven't ever owned the highest-end GPU, but if I would be too bottlenecked, then I won't get one.

I currently have a Gigabyte windforce dual-fan GTX460 1GB OC (715, but I turn it up to 820-840). Runs Skyrim on High settings @ 1920x1200, I haven't measured with Fraps, but it's probably roughly 20-30fps.

An OC'd 7970 could rival the 6990 which is an extremely powerful setup. I would guess that at 3GHz you'd likely be CPU bottnecked a lot. However, if your resolution is 1600p or 1440p, it might be a decent fit.

 

[SlowSpyder]

Would a Q9300 C2Q 2.5Ghz clocked to 3.0Ghz bottleneck a 7970? An OCed 7970?

I'd really love to get one, haven't ever owned the highest-end GPU, but if I would be too bottlenecked, then I won't get one.

I currently have a Gigabyte windforce dual-fan GTX460 1GB OC (715, but I turn it up to 820-840). Runs Skyrim on High settings @ 1920x1200, I haven't measured with Fraps, but it's probably roughly 20-30fps.

My 4GHz Phenom would likely bottleneck this card in plenty of situations, so a 3GHz Q9300 would be even worse.

 

[toyota]

Would a Q9300 C2Q 2.5Ghz clocked to 3.0Ghz bottleneck a 7970? An OCed 7970?

I'd really love to get one, haven't ever owned the highest-end GPU, but if I would be too bottlenecked, then I won't get one.

I currently have a Gigabyte windforce dual-fan GTX460 1GB OC (715, but I turn it up to 820-840). Runs Skyrim on High settings @ 1920x1200, I haven't measured with Fraps, but it's probably roughly 20-30fps.

IMO with a cpu like that it would not be very logical to spend 500 bucks or more on a top of the line gpu. your cpu is already part of the problem for Skyrim as that game needs raw cpu speed more than it needs more than two cores.

EDIT: you see the massive increase that an oced 2500k gives over a cpu like the 3.0 Phenom X4 which is similar to your Q6600 at 3.0. that's a 60% bottleneck with just a gtx570 so imagine the wasted performance using a 7970.



Uploaded with ImageShack.us

 

[LiuKangBakinPie]

6GB variant? That will throw a stone in Nvidias generator as they normally release the 6GB cards, put a ECC stamp on it, down clock a mid range consumer card and ask 4x to 5x the amount than theyre top geforce cards.

 

[Arzachel]

OpenCL isn't AMD's software. It's an open standard so expect to see it's use surpassing CUDA in time.

I know, but AMD needs to push OpenCL to become a viable alternative to CUDA, which is what most professional software currently uses.

 

[LiuKangBakinPie]

OpenCL has the support of many vendors – both within the PC ecosystem (e.g. AMD and Intel) and in the mobile world (e.g. Imagination Technologies). While CUDA is still clearly the larger ecosystem – it is equally clear that going forward the momentum is behind OpenCL and DirectCompute.

CUDA served as a starting point and Apple then incorporated their own vision and a great deal of input from AMD, Imagination Technologies (which is responsible for nearly all cell phone graphics solutions) and Intel. Once the project was in good enough shape, Apple put OpenCL into the hands of the Khronos Group, the standards body behind OpenGL.

 

[VulgarDisplay]

OpenCL has the support of many vendors – both within the PC ecosystem (e.g. AMD and Intel) and in the mobile world (e.g. Imagination Technologies). While CUDA is still clearly the larger ecosystem – it is equally clear that going forward the momentum is behind OpenCL and DirectCompute.

CUDA served as a starting point and Apple then incorporated their own vision and a great deal of input from AMD, Imagination Technologies (which is responsible for nearly all cell phone graphics solutions) and Intel. Once the project was in good enough shape, Apple put OpenCL into the hands of the Khronos Group, the standards body behind OpenGL.

Two things will happen to CUDA. Nvidia will either stop charging people for using it, or it will become extinct. You're correct that the momentum is all behind OpenCL and DC.

 

[LiuKangBakinPie]

Two things will happen to CUDA. Nvidia will either stop charging people for using it, or it will become extinct. You're correct that the momentum is all behind OpenCL and DC.

Nvidia got a good compiler as well. Maybe they will stop downclocking geforce cards as sold them for x3 the amount as "Workstation Graphics"