It happened last time so....
Also, hardly anyone will buy a £ 500+ mid range pascal that is only 10-15% better than a 980ti as anyone willing to spend that sort of noney on 980ti performance will have already bought.....a 980ti.
-
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 **
- Thread starter Boomstick777
- Start date
It happened last time so....
Also, hardly anyone will buy a £ 500+ mid range pascal that is only 10-15% better than a 980ti as anyone willing to spend that sort of noney on 980ti performance will have already bought.....a 980ti.
Soldato
Oh I don't know. Dropping 500 quid on a card puts you firmly in the proper enthusiast end of the market and rarely are those guys concerned about cost.
Soldato
- Joined
- 30 Nov 2011
- Posts
- 11,358
I've bought £500 graphics cards fir the last 5 years, but no way am I upgrading for 10%, it will have to be at least 50%
Associate
- Joined
- 12 Jul 2015
- Posts
- 1,694
I doubt even Volta will touch that 50% mark :/ maybe the one after that as compared to the current generation?
Um, which is my point
Nvidia arent going to release a card with same performance as a 980ti for £500+ a year after the 980ti release.
And I never said they would, people are claiming 980Ti performance will cost ~£300 with whatever the 2nd tier Nvidia Pascal GPU will be. I believe (my opinion) that Nvidia will release a Pascal GPU for £500+ and ~30% extra performance. The 2nd tier will cost ~£400 and the 3rd tier ~£300. I expect similar price/perf ratio from Polaris.
No they aren't adamant, they are guessing just like you and me. IMHO a more realistic estimate would put initial medium fat Pascal at around ~30% faster than 980Ti. This would be enough for Nvidia to charge £500+
Medium Pascal does not need to be monstrous it just needs the usual 30% increase over previous top end GPUs. Titan was ~30% faster than GTX770 and 7970GE yet was priced at ~£900. GTX780 was ~30% faster than GTX770 and 7970GE yet was priced at £550. 7970 was ~30% faster (on a new node) than GTX580 and cost ~£550. GTX970 and 980 released at a lower price point because the market was already saturated with similar performance GPUs.
No we didn't, the last jump in performance with a new node was GTX580 to HD7970 and that was ~25-30%. Or 40% if we go from 6970 - 7970. GTX580 - GTX680 was a similar jump in performance. That's the usual performance jump when we go from full fat on old node to mid fat on a new node. Next gen Pascal and Polaris will start at mid sizes as is the new norm in this industry. These mid sized GPUs on a new node will bring the usual ~30%-40% performance increase and marginal power savings. It will be 2017 before we start to see full fat Pascal or Polaris. The only way I see a significant performance increase of ~50%+ would be if Nvidia release a large mm2 HPC pascal chip and salvage/harvest parts for a cut down consumer version. If that happens expect it to release at ~£900
Last edited:
Associate
- Joined
- 4 Aug 2014
- Posts
- 1,111
Hmmm... Just got £500 extra to play with as an unexpected bonus... Was planning on sticking with the 970 for a while but now....
Soldato
- Joined
- 11 Mar 2013
- Posts
- 5,469
Agree, but damn Nvidia are taking forever to release. My 500+ is burning a hole in my pocket.
Caporegime
- Joined
- 18 Oct 2002
- Posts
- 30,337
1080p? Stick with the 970 tbh
If he wants to push those 144Hz then 970 is not enough.
Full fat kepler to full fat maxwell ( 780Ti to 980Ti) was more like 40-50% though and that was on the same process
I fully expect full fat pascal to be more than 30% faster than full fat maxwell! Don't you?
Whatever you say, you won't chang my mind that there will be a card that has 980Ti performance for around £300 ....because that is what is going to happen.
It will be a truly unspectacular release if we don't.
Last edited:
Full fat kepler to full fat maxwell ( 780Ti to 980Ti) was more like 40-50% though and that was on the same process
I fully expect full fat pascal to be more than 30% faster than full fat maxwell! Don't you?
Whatever you say, you won't changed my mind that there will be a card that has 980Ti performance for around £300....because that is what is going to happen.
ofcourse....one day!
can you say which day so i know if to call u crazy or not
like um Soon?
Associate
- Joined
- 4 Aug 2014
- Posts
- 1,111
I get the feeling that the newest Tomb Raider for example won't let me even hit 60 all maxed out...
I'll see what happens. Maybe the 1070 will be another sweet spot for me... Just need some self control!
Full fat kepler to full fat maxwell ( 780Ti to 980Ti) was more like 40-50% though and that was on the same process
I fully expect full fat pascal to be more than 30% faster than full fat maxwell! Don't you?
Yes but we aren't talking about a full fat Pascal being released any time soon, we are talking about a mid level Pascal.
Whatever you say, you won't chang my mind that there will be a card that has 980Ti performance for around £300 ....because that is what is going to happen.
There very well may be a GPU close to 980Ti for ~£300. After all Fury non X is ~£400 and is only 10% slower than reference 980Ti stock for stock (OC potential aside). If new Polaris replaces Fiji then expect a ~£300 GPU with Fury performance which would be close to 980Ti. In fact if I was being pedantic I could claim there has already been a GPU in 980Ti performance range released for ~£330 (Nano).
R9 Nano ~£350
Fury ~£400
Fury X ~£450
980Ti ~£530
Try to remember top tier GPUs are only separated by 10-15% performance delta but the price from Nano to 980Ti can be in the region of 70% higher. There are clear advantages for a 9080Ti with better OC potential and an extra 2GB VRAM. I will leave you do decide if those features are worth the premium. My own experience with owning all of those GPUs at one point or another is no, it isn't but I game at 4K where Fiji is even closer, or even exceeds Maxwell in performance.
Last edited:
Caporegime
I genuinely don't feel anybody other than NVidia know what will be released in the guise of Pascal first. It could well be something big on GDDR5 or even HBM (doubtful) or it could be a 256bit memory GPU that takes the spot of the 750Ti/950.
Also, worth noting is the selling power of a brand and whilst the Fury X was higher than the 980Ti at launch and the Nano had a price to match, the prices dropped when stock was sat on shelves. I paid £550 for a Fury X at launch and it massively under performed compared to a 980Ti/Titan X. The card I feel worth a purchase for those that game over 1080P resolutions is a 390. Other than that, you are either buying a 980Ti or even a Titan X and then maybe a couple of them to throw around the pretties. Of course if you are not fussed about having all the pretties, there is sensible choice cards like a 380/960 but top end requires some VRAM, albeit it needs some GPU grunt to cope.
Lol that's some pessimism there.
You'll be pleasantly surprised then, GPUs are not CPUs, they still scale fantasticly with die shrinks.
Caporegime
- Joined
- 18 Oct 2002
- Posts
- 33,188
Everything about this is wrong. 30-40% isn't the 'usual performance increase' at all.
5870 was 2.15billion transistors and 334mm^2, 6970 was 2.64billion transistors and 389mm^2 and 7970 was 4.3 billion transistors and 352mm^2.
So first off 5870 to 7970 was full fat to full fat. Second, the increase was around 60% for around a 1.9x more dense transistor part. IE 7970 literally doubled the transistor count and because of not being quite 2x transistor density it grew very slightly. It was around 60% faster but to a very new architecture which took time to bed in and the gains became much higher.
http://www.techspot.com/article/942-five-generations-amd-radeon-graphics-compared/page4.html
look here, today the 7970 offers over twice the performance of a 6970 and more than that compared to a 5870, much more.
http://ht4u.net/reviews/2013/xfx_r7970_double_dissipation_ghz-edition_im_test/index18.php
this review from 2013 shows the 7970 to be on average 92% faster than a 2GB 7970. So much of that performance gain was over the first year of it being available rather than the last couple of years.
On a given process node the density and performance(including clock speeds) you can achieve improve over time, what you can achieve even a year let alone 2-3 years later(think Kepler to Maxwell or compare Fiji to 7970 power efficiency) on the same process is very different.
The normal comparison is 4870 to 5870, to 7970, and you'd compare that with a circa 8.5billion maybe 320-340mm^2 14nm chip.
7970 at double the transistor count offered 60+% performance right out of the box for games that weren't designed or optimised for it, over the next year that increased significantly.
Full fat to half the size is not 'normal' at all. It's happened precisely once so far with a 520mm^2 gtx 580 to a 300mm^2 gtx 680. I mean you could say AMD did it with the 3870.... but not really. The 2900xt was never meant to be 80nm to begin with, the it was always supposed to be 65nm and had to be pushed back to 80nm which made it way bigger than they wanted.
For a given chip size, a new node offering near enough 2x transistor density has every chance of offering 60-70% more performance out of the gate without optimisation in games or drivers and 85-95% more performance within a year. That is what 'normal' is.
What is also normal is that huge chips are incredibly different to make on new nodes, Nvidia struggled with big chips at 65/55nm(only a little but the first nodes the yields weren't great at that size), at 40nm they had a disaster and at 28nm they gave up on making a big chip out of the gate which is why we had the medium chip first. 14/16nm should again see big cores out of reach and a likely longer delay between medium and large chips.
ofcourse....one day!
can you say which day so i know if to call u crazy or not
like um Soon?
Well obviously in the context of this thread, when the pascal range x70 and x80 cards get released. So hopefully by autumn at the very latest
My performance estimates are not full fat to full fat or 1st GPU on old node compared to 1st GPU on new node. 7970 to new Polaris or GTX680 to new Pascal performance increase is irrelevant because that's not how reviews and consumers compare. The comparison will be Fury X vs Polaris, or 980Ti vs Pascal.
HD 6970 to 7970 (last new node increase) gave a ~40% performance increase stock vs stock.
http://www.hardwarecanucks.com/foru...s/49646-amd-radeon-hd-7970-3gb-review-25.html
GTX580 to GTX680 gave ~36% performance increase.
http://www.hardwarecanucks.com/foru...616-nvidia-geforce-gtx-680-2gb-review-29.html
Pretty much everyone here is only interested on the performance increase compared to current top end GPUs, not compared to new 28nm GPUs release 4-4.5 years ago.
so you think by september?
i guess thats likelyyou dont think it depends on what AMD do too?
if there is no competition they could just release at the same price and sell it on new features
AMD havent said anything about high end i seen, all their talking been about small cards, power saving
Soldato
- Joined
- 11 Mar 2013
- Posts
- 5,469
I'm hoping by June at least.