• 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 **

CAT-THE-FIFTH

CAT-THE-FIFTH

CAT-THE-FIFTH

Soldato
Joined
9 Nov 2009
Posts
24,986
Location
Planet Earth
Last edited:

bru

bru

bru

Soldato
Joined
21 Oct 2002
Posts
7,359
Location
kent
Depends on which side of close to the 970 it is. you could say the 980 performance is close to the 970 (only 10%).

Anyway they are just guessing the same as everyone else.
 

Jono8

Jono8

Jono8

Caporegime
Joined
20 May 2007
Posts
39,928
Location
Surrey
bru said:
Depends on which side of close to the 970 it is. you could say the 980 performance is close to the 970 (only 10%).

Anyway they are just guessing the same as everyone else.
Click to expand...

True - by close i assumed less but nearly as good but yes it could mean close as in around but maybe a bit faster.
 

D.P.

D.P.

D.P.

Caporegime
Joined
18 Oct 2002
Posts
32,624
Jono8 said:
"GP104-150 would be AIB-only version with performance close to GTX 970. "

That would be hugely dissapointing
Click to expand...

That is a misinterpretation. What they mean is the GP104-150 board would be in the same relative performance as the 970, but all GP104 will be 1 generation performance ahead.

The 1070 could 20x faster than the current TitanX and that statement still holds true. It just mean the 1080 will be 25x TitanX.


Absolute performance is not indicated.
 

CAT-THE-FIFTH

CAT-THE-FIFTH

CAT-THE-FIFTH

Soldato
Joined
9 Nov 2009
Posts
24,986
Location
Planet Earth
D.P. said:
That is a misinterpretation. What they mean is the GP104-150 board would be in the same relative performance as the 970, but all GP104 will be 1 generation performance ahead.

The 1070 could 20x faster than the current TitanX and that statement still holds true. It just mean the 1080 will be 25x TitanX.


Absolute performance is not indicated.
Click to expand...

Not it isn't - that statement was directly off the bloke on AT forums,who is a massive Nvidia fan too. If he thought it was something significantly faster he would have pretty much said it.

That would still make it much faster than the preceding GTX960.

Edit!!

On AT forums,a poster mentioned they saw the following on Chiphell forums:

1. GTX1080 GP104-400-A1 DDR5X 8G
2. GTX1070 GP104-200-A1 DDR5 8G
3. GTX1060 GP104-150-A1 DDR5 6G
 
Last edited:

CAT-THE-FIFTH

CAT-THE-FIFTH

CAT-THE-FIFTH

Soldato
Joined
9 Nov 2009
Posts
24,986
Location
Planet Earth
A GTX970 is around 55% to 60% faster than a GTX960:

https://www.techpowerup.com/reviews/ASUS/GTX_950/23.html

So that is around the upgrade if a GTX1060 is around that level.

A stock GTX980TI is around 36% faster than a GTX970 in that link.

So if Nvidia does increments of 30% performance boosts at each level.

That would put the GTX1070 at stock GTX980TI level and the GTX1080 at the purported 30% faster level.

That is around what we saw with the GTX680 and GTX670 against the GTX580 and GTX570.

The GTX660TI was nearly 50% faster than the GTX560TI.

The number seems consistent with Kepler.
 
Last edited:

TheRealDeal

TheRealDeal

TheRealDeal

Soldato
Joined
28 May 2007
Posts
10,113
CAT-THE-FIFTH said:
A GTX970 is around 55% to 60% faster than a GTX960:

https://www.techpowerup.com/reviews/ASUS/GTX_950/23.html

So that is around the upgrade if a GTX1060 is around that level.

A stock GTX980TI is around 36% faster than a GTX970 in that link.

So if Nvidia does increments of 30% performance boosts at each level.

That would put the GTX1070 at stock GTX980TI level and the GTX1080 at the purported 30% faster level.

That is around what we saw with the GTX680 and GTX670 against the GTX580 and GTX570.

The GTX660TI was nearly 50% faster than the GTX560TI.

The number seem consistent with Kepler.
Click to expand...

The difference here is those 3 cards are all based on different chips. gtx960 (gm206), gtx970 (gm204) and Gtx980ti (gm200). If they are all based on the same chip then it could be more like the gtx680/670/660ti (Gk204) and the performance gaps were not so big probably down to them all sharing the same chip. The gtx9 series all launch around 3 to 4 months after each other as well with it going gtx970/gtx970/gtx980ti. So a big difference in circumstances.

Here is tpu performance charts from the gtx660ti release. I think it will be more like this but with a little more performance in between tiers.

http://www.techpowerup.com/reviews/Palit/GeForce_GTX_660_Ti_Jet_Stream/28.html
 
Last edited:

Seanspeed

Seanspeed

Seanspeed

Soldato
Joined
7 Aug 2013
Posts
3,510
drunkenmaster said:
As for recommending 390's, seriously people need to learn about the media. Look up the issues on youtube with paid reviews on a 'normal' site and reviewers getting crap for not specifically stating they were paid for said review. A website can do 100 'normal' reviews on their own then MS comes along and says review the Surface Pro for us, we'll pay you $1000 for every 100k hits for this review, then the guy suddenly does a completely absurd pro MS piece on the surface.
Click to expand...
Jesus man, this is full on conspiracy theory, tinfoil-hat nonsense at this point.

Digital Foundry are merely going by tested results, that's all. Results that are verifiable by users and other reliable sources. There is no agenda involved.
 

drunkenmaster

drunkenmaster

drunkenmaster

Caporegime
Joined
18 Oct 2002
Posts
33,188
Seanspeed said:
Jesus man, this is full on conspiracy theory, tinfoil-hat nonsense at this point.

Digital Foundry are merely going by tested results, that's all. Results that are verifiable by users and other reliable sources. There is no agenda involved.
Click to expand...

There have been literally hundreds of paid reviews all over youtube and lots of controversy and issues with those who didn't disclaim when their reviews were paid.

See this is the problem, this is fact and you're dressing it up as conspiracy theories simply because you don't know what you are talking about. There has been so many incidents where a well known youtuber who does review videos suddenly does a stupidly biased review with a huge amount of backlash and eventually it gets admitted they took money and do some embarrassing apology video. There are many thousands more where the fact they are paid reviews was disclosed yet still a backlash because it goes against the trust a reviewer builds up... though that is exactly why companies like MS pay for such reviews, to buy the trust.

As for results, what are you on about, the video in question was about Pascal rumours and I didn't claim his other reviews were false or biased. I was simply stating the facts of journalism/you tube reviews as you seemed to believe that for someone to be biased in one article they must be for everything they do.


https://www.google.co.uk/search?q=m...&oe=utf-8&gws_rd=cr&ei=dc8jV5-PMeTYgAa_r5CoDw

first thing I could be bothered to google, dozens of results of MS admitting to paid reviews, I'm sure there are many links to threads on forums accusing reviewers of hiding payments, eventually truth coming out and how many people are paid for reviews and how many got away without disclosing it.


Suggest something that backs up his claim that every bit of information points to Nvidia launching first or you could just admit he was talking utter BS... if it's the latter(hint, it is), then I have every right to make an assumption about how biased that video is.
 
You must log in or register to reply here.
Back
Top Bottom