• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

** The Official Nvidia GeForce 'Pascal' Thread - for general gossip and discussions **

I'm sitting here doing just that (Asus ROG Swift) - ok 1-2 more recent games I don't play but plenty of recent stuff I do play at ultra settings without any problems at all.

I think a lot of review sites are still testing Kepler 2.0 cards with Boost 1.0 methodologies as that is the only way the numbers make sense (I do have a 970 as well and I still use the 780 over it in most cases for a reason :S).

EDIT: Not that I'd suggest anyone went for a Kepler card over the alternatives these days - but I sit and look at many of the benchmarks coming out of major sites and scratch my head - problem is a lot of the review sites don't seem to run tests that are easily reproduced to do a direct comparison against their results.
You're clearly not playing more demanding games man.

And no, it has nothing to do with testing methodology. I follow user performance reports just as much as benchmarks and a 970 is just about *always* ahead of a 780, usually by a clear margin. Plus a 970 can be overclocked more. And I'm talking about real game performance, not artificial benchmarks.

And as a 970 owner with a decent OC, I can assure you that it's nowhere near good enough for 1440p/60fps at max settings in everything. In *most* graphics-heavy games, my card is only about good enough for 1080p/60fps at high-ultra(mostly ultra to be fair). It seriously does take a 980Ti to do what you're claiming you can do.

You're either lying, exaggerating or are mistaken. You do not have a magic GTX 780.

As 8Pack said the other day those that do know are bound by NDAs and you don't really get the leaks like used to happen any more - 90% of the rumour articles are made up.
Made up, or jumping to conclusions based on very loose evidence and passing it off as fact.
 
Last edited:
apparently prices have been leaked from an etailer in Taiwan

$620 for the mid range 1070 and $870 for the 1080

With Computex just over a month away, leaks have been popping up daily about Nvidia’s upcoming Pascal graphics cards. So far, we’ve seen a lot of leak around the physical card but nothing yet on core specifications or pricing. Today, according to Taiwanese insiders, we are getting a look at how much GP104 will set buyers back. The GTX 1070 will reportedly sell for NT $ 19990 and the GTX1080 will sell for NT $ 27990.

Converting the prices, you get around $620 and $870 for the 1070 and 1080 respectively. That seems a bit high considering that you can find the 980 at about $500 and the 980Ti at $700. However, if you only consider NT prices, that’s exactly in line with what the GTX 980 and 980Ti cost in Taiwan respectively. This suggests to me that the GP104 cards would be priced where the GTX 980 and 980Ti are right now based on the market they are selling in

These prices are in line with what we’ve come to expect from Nvidia and mirror the GTX 670/680 and GTX 970/980 launches. The GTX 1070 will significantly less and offer competitive performance and the GTX 1080 will command the extra flagship premium. While high the prices are understandable given the new process and architecture. It’s just a shame that the top end GP100 won’t be the true flagship anymore at launch.
 
apparently prices have been leaked from an etailer in Taiwan

$620 for the mid range 1070 and $870 for the 1080

Now that I would be ***** off if it was true and if I was buying nvidia.

If it is true, which I doubt it is, I hope AMD delivers with what they were saying in regards to perf/dollar, and will price the **** out of nvidia with polaris.
 
I guess it depends on performance although. Is there any chance it will be faster than two 980ti's? I thinking thats unlikely.

Still that is not an excuse to jack the prices like that? If all tech industry used such logic to price every new faster part on release higher than slower older part, then we would be needing mortgages for a simple GPU.
 
A new architecture alone should make a 1080 faster than a Ti. That's without a die shrink and hbm2.

With a shrink and HBM 2. I'd expect another 20-30% on top of that at least. That's just the 1080 never mind the Ti versions or Titan :o.

IF it is it certainly won't be cheaper than a Ti that's for sure.
 
A new architecture alone should make a 1080 faster than a Ti. That's without a die shrink and hbm2.

With a shrink and HBM 2. I'd expect another 20-30% on top of that at least. That's just the 1080 never mind the Ti versions or Titan :o.

IF it is it certainly won't be cheaper than a Ti that's for sure.

the die shrink alone don't do much. Maybe some clock speed increase. It mostly counts because you can squeeze more transistors to a given place.
 
apparently prices have been leaked from an etailer in Taiwan

$620 for the mid range 1070 and $870 for the 1080

Looking at the piece you quoted, I see that you decided to focus on the worst price in the article rather than the better ones.

With Computex just over a month away, leaks have been popping up daily about Nvidia’s upcoming Pascal graphics cards. So far, we’ve seen a lot of leak around the physical card but nothing yet on core specifications or pricing. Today, according to Taiwanese insiders, we are getting a look at how much GP104 will set buyers back. The GTX 1070 will reportedly sell for NT $ 19990 and the GTX1080 will sell for NT $ 27990.

Converting the prices, you get around $620 and $870 for the 1070 and 1080 respectively. That seems a bit high considering that you can find the 980 at about $500 and the 980Ti at $700. However, if you only consider NT prices, that’s exactly in line with what the GTX 980 and 980Ti cost in Taiwan respectively. This suggests to me that the GP104 cards would be priced where the GTX 980 and 980Ti are right now based on the market they are selling in

These prices are in line with what we’ve come to expect from Nvidia and mirror the GTX 670/680 and GTX 970/980 launches. The GTX 1070 will significantly less and offer competitive performance and the GTX 1080 will command the extra flagship premium. While high the prices are understandable given the new process and architecture. It’s just a shame that the top end GP100 won’t be the true flagship anymore at launch.

Sounds to me like they converted the prices incorrectly, if you look and see that they also say its the same prices that the existing cards are at.

Still seems a bit high to me though and if they do come in at 980 and 980ti prices I for one will be disappointed. Of course if this ties in with the three card launch rumour, then this could be the GP104 400(1080ti) and GP104 200 (1080) with a GP104 150 (1070) to follow latter.

At the end of the day, who knows, it is yet another leak, which means something is definitely getting closer. Not long to go now, well only a few more weeks anyway. :)
 
You're clearly not playing more demanding games man.

And no, it has nothing to do with testing methodology. I follow user performance reports just as much as benchmarks and a 970 is just about *always* ahead of a 780, usually by a clear margin. Plus a 970 can be overclocked more. And I'm talking about real game performance, not artificial benchmarks.

And as a 970 owner with a decent OC, I can assure you that it's nowhere near good enough for 1440p/60fps at max settings in everything. In *most* graphics-heavy games, my card is only about good enough for 1080p/60fps at high-ultra(mostly ultra to be fair). It seriously does take a 980Ti to do what you're claiming you can do.

You're either lying, exaggerating or are mistaken. You do not have a magic GTX 780.

Just to be clear I'm not making a case of the overall suitability of a 780 at 1440p these days - none the less there is a huge gulf in performance across the range on out the box performance - something like 20% from an early A1 to one of the last B1s and what might be ok with one 780 might fall flat on its face on another.

Regarding my own setup - one aspect here is that I'm running G-Sync which makes it a lot more tolerable when you are getting drops just below 60fps - otherwise the card would have been replaced by now as it is certainly stretched at 1440p.

To put a certain amount of perspective on it a quote from one review (this was soon after release so the 290X stuff isn't so true any more - though does put some perspective on just how far the 290X has come):

The GTX 780 GHz Edition has big gains over the stock card in Battlefield 4 that essentially puts it on par with the GTX 780 Ti, give or take a couple of frames. At 2,560 x 1,440 and 5,760 x 1,080 it's 13 and 17 percent quicker than the vanilla GTX 780 and surpasses the AMD R9 290X, and even Sapphire's overclocked one.

My out the box boost is a little higher than their review card - in general over a range of games I'm averaging somewhere about 18% over a "vanilla" 780 which makes quite a difference when you are talking 1440p performance - where a normal 780 would be getting say 45fps I'm looking at more like 53fps which when coupled with G-Sync is pretty much indistinguishable from 60fps. Add to that a fairly hefty overclock again and the card is still pretty much hanging in there at 1440p with all the settings turned up though in truth I generally drop the AA down to FXAA or similar to give myself more of a buffer.

I do play many recent demanding games - though there are 1-2 I've not played like The Witched 3 and Far Cry: Primal which might change my opinion at 1440p in those games maybe - but stuff like GTA V, SWBF, etc. all run fine - I gave Everybody's gone to the Rapture a whirl with max settings and sure the 970 was a couple of FPS ahead (and I couldn't really catch it up quite even with overclocking) and the 780 was dropping to 30fps in the demanding bits - but a 980ti was only at ~38fps in the same scenes heh.
 
Still that is not an excuse to jack the prices like that? If all tech industry used such logic to price every new faster part on release higher than slower older part, then we would be needing mortgages for a simple GPU.

Unless AMD has some serious competition Pascal cards aren't going to be cheap - ignoring any other overheads and development costs the cores are more than 20% more expensive to nVidia than 28nm (that isn't to say the tier for tier prices will be 20% higher).

EDIT: TSMC developed 16FFC partly to address this fact.
 
Last edited:
Care to enlighten us? What are you basing your figures on?

Or are you just a mindless troll?

The only mindless trolls around here are the shills who buy to validate their self worth.

Anyway, it's a simple case of transistor count. We are going to see huge leaps in performance gain.
 
The only mindless trolls around here are the shills who buy to validate their self worth.

Anyway, it's a simple case of transistor count. We are going to see huge leaps in performance gain.

Its more complex than just an increase in count - you need to know what they are being used for as well.

IMO performance gains are going to be a mixed story - in DX11 and older stuff I don't think the gains are going to be as significant as DX12+ where the gains over Maxwell will be larger.
 
Unless AMD has some serious competition Pascal cards aren't going to be cheap - ignoring any other overheads and development costs the cores are more than 20% more expensive to nVidia than 28nm (that isn't to say the tier for tier prices will be 20% higher).

EDIT: TSMC developed 16FFC partly to address this fact.

issue one, you see entusiast price reach 1000 euro+.
issue two cpu goes into 2000euro+
so we have a situation where you dont really want to upgrade anytime soon or ever. Most will just wait until next generation comes out and then buy a used card.cycle of selling new developed cards starts to slow down due to buyers start to wait.
 
Back
Top Bottom