**Nvidia GeForce GTX 970 / 980 Review Thread**

[Chuk_Chuk]

Well Nvdia have just put me in an interesting spot.
Are there any reviews that directly compare the 970 and R9 290 at 1080P?

 

[Flying_Hellfish]

Are there any reviews floating about which compare the various custom cooled 970s?

Techpowerup have a 970 review for the EVGA SC ACX which compares a small number of OC results. Also compares this card vs ref in games, noise, power etc.



Probably have reviews for each major AIB, though I haven't read all of them

 

[Davedree]

loving that post.

Ninja edit

 

[CAT-THE-FIFTH]

I agree with this. Since the GPC are arrange in clusters of 4 SMM and since the gtx 980 is made of 4 GPC, you have 16 SMM or 128x16 = 2048 shaders. SO something scaled up should contain additional blocks up of 1 GPC or 4 SMM more. Unless they change the configuration again like they did with the gtx 750 ti(which had 5 SMM in one GPC).

So scaling up and considering the current die size(398mm2), they should be able to fit 6 GPC or 24 SMM or 3072 shaders, 96 ROPS, 384 bit bus if they tighten the transistor density a bit. They will need to do this because these large chips they focus on double precision performance, which adds a tad more to the size. So I am guessing a slightly bigger maybe 620mm2 chip, with 30-40% more performance than this chip. But of course 1200 dollar price tag or something ridiculous. It's going to be hard to get good yields from a chip like this and we are likely to see something with just 20-25% percent more performance from the cut down version meant to be sold to most people.

Yes,but you are both forgetting that the GM200 will have better DP performance which adds to the transistor budget massively.

The GK110 had twice the number of transistors as the GK104 and was nearly 90% larger in surface area. Yet it was only around 50% faster at 2560X1600 according to TPU.

 

[Akagi]

Would a single 970 be significantly better than my single 7970?

Head over to Anandtech and bench a 7970 against a 780ti (or even the 970 if they have it added already), and that should give you the information you need to answer this.

(The short answer is yes, it will be significantly better)

 

[ubersonic]

Who cares what it looks like?

Well if your paying a premium over an EVGA card + EK block and getting the exact same thing just uglier I think it should be somehting to card about.

The Swiftech blocks on the Hydro coppers don't even actively cool the VRMs.

That was just a one off on the 780 classified hydro coppers, the 780/titan/titan black/older ones actively cooled the VRM's fine.

 

[CAT-THE-FIFTH]

Head over to Anandtech and bench a 7970 against a 780ti (or even the 970 if they have it added already), and that should give you the information you need to answer this.

The drivers won't be upto date on the older cards.

Look at a newer review with a R9 280X and subtract around 10% or thereabouts.

 

[darkblueslider]

Ninja edit

haha caught out.

 

[ubersonic]

Any word on release/clocks/price?

The 780 hydro coppers were a 780 FTW with a block attached if that's any help.

 

[^JP^]

The 780 hydro coppers were a 780 FTW with a block attached if that's any help.

Yeah I think I will wait for the Classified cards and put my own blocks on.

Hope they are out next month when I am in the USA

 

[CAT-THE-FIFTH]

As I said earlier I am done with this the thread is about the 970/80 reviews.

You should not assume as much as you do

My first job was for an accountancy firm doing accounts.

Most of your facts in your last post are still wrong and I am not going to take time to correct them as this is not the place.

Yes,the funny thing is that Fermi(much bigger dies and much great power consumption) was evolved into Kepler and Maxwell is refined Kepler.

It could be quite possible AMD cannot do the same,but ultimately I don't see why they won't be doing the same thing anyway.

But this is the internet,all doom and gloom.

A bit like what we saw with Scottish independence.

Bad news is good news,no?

 

[Reaper 392]

Techpowerup have a 970 review for the EVGA SC ACX which compares a small number of OC results. Also compares this card vs ref in games, noise, power etc.



Probably have reviews for each major AIB, though I haven't read all of them

Thanks for that. There's only the Asus Strix and the EVGA so far, but already its told me to avoid the evga since they have gone for temperature over noise in a big way

 

[andybird123]

Yes,but you are both forgetting that the GM200 will have better DP performance which adds to the transistor budget massively.

The GK110 had twice the number of transistors as the GK104 and was nearly 90% larger in surface area. Yet it was only around 50% faster at 2560X1600 according to TPU.

Maxwell is already more massively more efficient at compute performance over kepler, Kepler had bad SP performance and really awful Dp performance, it will take much less work to convert small maxwell in to a DP monster than it did with GK104 to GK110

 

[Kaapstad]

Maxwell is already more massively more efficient at compute performance over kepler, Kepler had bad SP performance and really awful Dp performance, it will take much less work to convert small maxwell in to a DP monster than it did with GK104 to GK110

My bet is GM200 will be around 10 billion transistors on 20nm or better.

Allowing for lower clocks the performance increase over GM204 could be huge.

 

[CAT-THE-FIFTH]

Maxwell is already more massively more efficient at compute performance over kepler, Kepler had bad SP performance and really awful Dp performance, it will take much less work to convert small maxwell in to a DP monster than it did with GK104 to GK110

The GM204 still has poor DP performance though:

http://images.anandtech.com/graphs/graph8526/67748.png

Remember its a 33% bigger die and a 1.5 billion more transistors(42% increase) over the GK104.

With 40% transistors the GK110 is getting close to DOUBLE the DP performance of a GM204.

The GM204 only appears to have a 10% improvement in density over the GK104(or a bit higher).

It does not still change what I said though. Adding DP performance adds a HUGE amount of transistors,and ultimately Nvidia will want a BIG improvement too with the GM200.

You forget Intel is encroaching onto their turf with MIC(and AMD has even seen their pitiful marketshare in the segment grow a reasonable amount).

So if the GM200 is on 28NM it will be the biggest GPU in history. A real monster on all levels IMHO and it will be bloody fast.

Yet a GM204 is still more efficient as a gaming GPU as it does not need to do all the DP stuff as well,and hence you can optimised far better towards gaming performance and better gaming performance/mm2.

 

[Fanatic]

Tempted by the GTX970. I have a GTX780 now so I know the 970 would only be a bit faster, and so maybe a bit of a side-grade. However I do a lot of streaming so the H.265 encoder in the 970 should give a nice improvement to stream quality. Also using way less power. Anyone know if it is a full hardware H.265 encoder? I read somewhere it might not, and would be a mix of hardware/software encoding.

 

[Boomstick777]

Tempted by the GTX970. I have a GTX780 now so I know the 970 would only be a bit faster, and so maybe a bit of a side-grade. However I do a lot of streaming so the H.265 encoder in the 970 should give a nice improvement to stream quality. Also using way less power. Anyone know if it is a full hardware H.265 encoder? I read somewhere it might not, and would be a mix of hardware/software encoding.

Bit faster, extra GB or ram, cooler running and less power use. Direct X12 support (Not sure if different from older cards?), new features..

Might be worth it if you can sell your 780, 970 is great price VS performance. The best from Nvidia in a long time imho.

 

[andybird123]

I'm assuming Titan2 will be 20/16nm, they would be mental to try to do it on 28

GM204 has 1/32 DP performanceover keplers 1/24, hence the small improvement, but it wouldnt take a huge amount to improve that, so yes improving dp performance will eat in to mm2 allowance, but not by as much as it did with gk104>gk110

Ifnyou put a Titan in to full DP mode it has 1/3 dp performance, but maxwells SP performance is so good you could trim that back to 1/6 and still have a beast of a card

 

[CAT-THE-FIFTH]

I'm assuming Titan2 will be 20/16nm, they would be mental to try to do it on 28

GM204 has 1/32 DP performanceover keplers 1/24, hence the small improvement, but it wouldnt take a huge amount to improve that, so yes improving dp performance will eat in to mm2 allowance, but not by as much as it did with gk104>gk110

Ifnyou put a Titan in to full DP mode it has 1/3 dp performance, but maxwells SP performance is so good you could trim that back to 1/6 and still have a beast of a card

Even at 1/6 it would still be worse overall on 28NM. You are still not realising that the GM204 is 33% larger than a GK104 and has 42% higher transistors. Maxwell has slightly higher transistor desnity than Kepler,but overall DP performance has increased primarily down to them just using more transistors and higher clockspeeds(actually closer to 50% since I looked at the graph again).

A GK110 with 40% more transistors and 40% higher die area has nearly double the DP performance of a GM204. These are based on published figures.

Every single higher end Nvidia GPU from the GF100 onwards has shown the same thing. Adding additional DP performance eats into the transistor budget,and adds more power consumption.

The GF100,GF110 and GK110 all did not scale uniformly in gaming performance when compared to the GF104,GF114 and GK104. Yet the GPUs below the latter three did. The big difference is the "big" GPUs added functionality which is not required for gaming and this eats into power consumption,TDP,die area and transistor budget. You cannot change the laws of physics within the same uarch using the same process node.

We will have to agree to disagree.

Edit!!

On 20NM its a moot point. You get reduced power consumption and much higher transistor density anyway,so you can offset the ineffiencies of having added non-gaming relevant functionality added.

 

[almighty15]

Speaking of VRM's does anyone know if temp monitoring is supported on these as on the 780 cards you couldn't?

Gibbo?