NVIDIA GT216 Specifications Trickle-In

[btarunr]

The AMD RV740 has been gaining quite some attention lately. Following news of it being the first GPU to be built on the 40nm manufacturing process, there is some information trickling in about NVIDIA's offering to combat it. The GT216, unlike what most speculations talked about being a next generation high-end GPU, is supposed to be a mainstream GPU whose specifications make it a rival to the AMD RV740. This, according to specifications of the said GPU emerging from Beyond3D, part of which they are sure of, part speculation.

For starters, the GT216 will be built on the 40nm manufacturing process. It will feature a 192-bit wide GDDR3 memory bus. Graphics cards built on this would feature 768 MB of memory (with possible OEM variants having just 384 MB). The memory is clocked at 1200 MHz (2400 MHz DDR). There is speculation linked to the rest of the specs at this point in time, notably that it might have 7 ALU clusters (168 SPs). The manufacturing process will make sure the GPU is cost-effective. With this, the next round of mainstream GPU competition sounds even more exciting.

Sources: Beyond3D Forums, Expreview

[Anonimo]

that doesn't make sense for me, it has more shader power than a 9800GTX+ but has less bandwidth than it(70gb/s vs. 57gb/s)...

[btarunr]

Originally Posted by Anonimo

that doesn't make sense for me, it has more shader power than a 9800GTX+ but has less bandwidth than it(70gb/s vs. 57gb/s)...

Me neither. That's too weak a memory sub-system to go with the rest of the GPU. Now if only it turns out that that's a 192-bit GDDR5 memory bus, the bandwidth would range around that of the G80-GTX.

[Anonimo]

Yeah, with GDDR5, at 3600Mhz it would has 86,5Gb/s.
Then I think would be at least almost enough.
But if it has more shaders then the G80-GTX, probably it will request more bandwidth. (Why they would do a more powerful shader gpu that is weak because have less texture power?)

[Weer]

Originally Posted by Anonimo

Yeah, with GDDR5, at 3600Mhz it would has 86,5Gb/s.
Then I think would be at least almost enough.
But if it has more shaders then the G80-GTX, probably it will request more bandwidth. (Why they would do a more powerful shader gpu that is weak because have less texture power?)

Where are you from?

[Anonimo]

Brazil...
What can I do if I have a poor english? : P

[OnBoard]

Originally Posted by btarunr

Me neither. That's too weak a memory sub-system to go with the rest of the GPU. Now if only it turns out that that's a 192-bit GDDR5 memory bus, the bandwidth would range around that of the G80-GTX.

Hope it's GDDR5 or ATI card will crush it with AA/AF enabled. This would be the next possible upgrade for me, like the memory amount and GPU speed will likely be near 850MHz with plenty OC space.

[newtekie1]

It isn't uncommon for the mid-range card of the next generation to have more shader power with less memory bandwidth than the high-end cards of the previous generation.

The 8600GT(G84) had more shader power than the 7900GTX(G71) but only a 128-bit memory bus, about half the memory bandwidth of the 7900GTX.

The 7600GT(G73) had more shader power than the 6800Ultra(NV45) but again only a 128-bit memory bus, about half the memory bandwidth of the 6800Ultra.

The HD4670 has the same shader power as the HD3870, but again only a 128-bit memory bus, about half the memory bandwidth of the HD3870.

The HD2600XT has a lot more shader power than the X1950XTX, but again only a 128-bit memory bus, about half the memory bandwidth.

[lemonadesoda]

How very confusing to call this GT216.

Of all the letters and numbers available to them in the Western world, WHY OH WHY make it so confusing for everyone?

[DarkMatter]

Originally Posted by lemonadesoda

How very confusing to call this GT216.

Of all the letters and numbers available to them in the Western world, WHY OH WHY make it so confusing for everyone?

AFAIK that's the code name, so it's not for you, or for us. It's for internal use. Just like G94 and G96 are waker cards than G92.

On topic, I don't know how accurate and true are these numbers. It could use GDDR5 probably (earlier rumors said Nvidia would use 40nm and GDDR5 at the same time) or even have a 384 bit memory bus. The amount of memory would be the same and could have confused whoever listened the rumors first. 168 SP and only 12 ROPs just doesn't make sense to me either.

[Mussels]

i might hold off my new viddie upgrade til these are released.

listen to this about GT214

Came across this post on ABT

http://alienbabeltech.com/main/?p=2240

Looks like Nvidia will also be using GDDR5 on upcoming chips.

[DarkMatter]

Originally Posted by wolf2009

listen to this about GT214

Came across this post on ABT

http://alienbabeltech.com/main/?p=2240

Looks like Nvidia will also be using GDDR5 on upcoming chips.

I had never heard of GT214. It makes me wonder if it's not that the chip described in the OP intead of the GT216, which was suposed to be high-end...

[Anonimo]

GT216:
- More shader power than 8800GTX with the same architeture, but more SPs
- Less die size (because 40nm)
- But less bandwidht

They are using more die size to put more useless shaders?!
Even with GDDR5, it would have the SAME bandwidht as the 8800GTX, but with much more Shader Power (+SPs, probably +Clock).

[newtekie1]

Originally Posted by wolf2009

listen to this about GT214

Came across this post on ABT

http://alienbabeltech.com/main/?p=2240

Looks like Nvidia will also be using GDDR5 on upcoming chips.

No, nVidia will most likely not be using GDDR5 on any GT200 series chip, GDDR5 won't likely be used by nVidia until GT300. They just ran simulations testing the effects of GDDR5 on their GPUs, they did the same thing with G96, if you read the article, and we don't see any GDDR5 9500GTs floating around...

Originally Posted by Anonimo

GT216:
- More shader power than 8800GTX with the same architeture, but more SPs
- Less die size (because 40nm)
- But less bandwidht

They are using more die size to put more useless shaders?!
Even with GDDR5, it would have the SAME bandwidht as the 8800GTX, but with much more Shader Power (+SPs, probably +Clock).

Again, standard practice in the video game industry.

[Hayder_Master]

ohh , nvidia with 40nm