NVIDIA GeForce GTX 1060 Reference Board Design and Clocks Confirmed

[GhostRyder]

I was waiting to see the Fury X and read the reviews. I didn't buy a Titan X (in my budget) as I was waiting for the Fury X (recall all that hype ). Proof of that is my posting history - I was keen to see how Fury X did. But in the end the better option was the GTX980ti (Kingpin for me). I'll buy what best suits me and what I find 'coolest'. I always wanted a Kingpin and I've scratched that itch now. I'm getting bored of Nvidia though as they lock so much down it's hard for you to 'play' with the cards without going crazy hardware modding.

TBH, I have a bad feeling full stop about AMD and Nvidia with future cards. I have so many 'wishes' for Vega but I don't think that will be anything other than 'reduced expectations met'. I hope I'm wrong but the node shrinks are giving less room to play with on voltages and thermals.

If AMD doesn't do anything with vega and no overclocking, I know exactly which cards I am getting. Though I feel like we're driving towards an era where one choice is the only choice for high end unfortunately.

Guess we have to wait for something...Wish it would come sooner.

even then i think these 2 cards will be pretty evenly matched, which is a good thing, competition pushes the prices down. we dont know how good this card will oc, especially since it will ship with 1.7GHz boost clock, even if it goes above 2GHz, i think they will be close if the vendor 480s can hit the 1.6GHz mark. only time will tell..

See, that will be interesting because if vendors can make the card clock it should provide some great performance. It's all going to depend then how the 1060 compares clocked to its higher point.

 

[5DVX0130]

Instead of the fabled much faster by 15% (in best case scenario), I’m interested how much faster it will still be six months/a year after. NVIDIA has really dropped the ball in recent years with all the driver issues, and their planned obsolescence plan. I understand the reason behind it, and also why AMD can’t afford to do the same, it still leaves a bitter taste considering you always pay a premium for everything NVIDIA.

That said, I expect the prices will be 299$ for the founders and a 259$ “regular” edition, and it will still sell like hotcakes. Subtract 20$ for the 3GB version, if it’ll actually exist outside the OEM channels.

 

[rtwjunkie]

NVIDIA has really dropped the ball in recent years with all the driver issues, and their planned obsolescence plan.

I understand your driver issues point, since they started sending out bad drivers last summer.

Planned obsolescence as you are implying is mostly a fallacy. No piece of equipment, whether a car or computer equipment is meant to last forever, so you are correct.

I suspect you mean though, as many conspiracy theorists claim, that drivers deliberately worsen the performance of previous gen cards. This is a fallacy. Drivers can improve the performance of a gpu by optimizing things. Most of these imprivements come early on in a GPU life. Eventually, there is a point at which hardware limits of that design have been reached, and no further optimizatiion is possible. This is not abandonment or planned obsolescence.

 

[EarthDog]

I need to invest in aluminum foil, live here at this forum and sell them...

 

[$ReaPeR$]

If AMD doesn't do anything with vega and no overclocking, I know exactly which cards I am getting. Though I feel like we're driving towards an era where one choice is the only choice for high end unfortunately.

Guess we have to wait for something...Wish it would come sooner.


See, that will be interesting because if vendors can make the card clock it should provide some great performance. It's all going to depend then how the 1060 compares clocked to its higher point.

i like that you two are not hyped about vega, imo that how we should face every awaited release. you cant be disappointed if you expect nothing.
yes, it will depend on the clock, but what i meant was that i expect it to be clocked high by default, and that made me wander about the oc headroom that it might lack. that would be so ironic for the 10xx series..

I need to invest in aluminum foil, live here at this forum and sell them...

LOL indeed!!

 

[RealNeil]

So supply is short of GTX 1080 (2560 cores) and GTX 1070 (1920 cores) cards

Maybe low supply equals higher asking prices at a time when AMD can't compete at top tier performance levels. Could this be a controlled release of product by NVIDIA?

 

[ppn]

Well there are GP106-400-A1 and GP106-300-A1,

1060 cant be both so the premium must be Ti?

 

[Ungari]

It was a "paper launch" because the card was delayed, not rushed. The planned release window for GTX 1080 was actually April or later, but it was postponed to the end of May.

It was a Paper Launch because they had no stocks to release to the public---hence Paper Launch.

 

[geon2k2]

Nice, another graph that doesn't start at zero! Deceptive bastards.

Edit: HOLY FUUUUUUU.... that's a deceptive bastard! 1.1, 1.2, 1.3.... lol so it's not 2x faster, 15% like others said. Wow.

This was my first observation also. First time I was like WTH, this is so much faster, but it is not, its like 15%, however if the price will be ~250$ there will be reasonable competition in this price range.

new leak from videocarz

Nice graph. nVidia should hire you right away, before the red camp will make you an offer you cannot refuse

 

[Steevo]

By release do they mean they have like 1 or 2 for sale all over, of you include the test cards?

Paper knee jerk response to 480, which is seeming very mediocre as well, but perhaps it's due to AMD overvoltage to get better yields in the new process.

 

[Camm]

The problem with Nvidia's fud this time is where would it sit in the stack?

The 1070 is as fast a 980 Ti. With Nvidia marketing the 1060 as faster than a 980, the 1060 will start to eat into the 1070, especially if priced against the RX 480.

As for pricing (relative to a 480 anyway), there's the tidbit that these dies are much larger than the 480's, and from a nm perspective, is at a 13% transistor density disadvantage. Unless Nvidia is doing successful faulty die recovery from 1080\70 wafers to make the 60, I can't see this really working, unless Nvidia sells at a loss of course.

 

[ViperXTR]

Perhaps its like Titan X 1070 situation?, 1070 only matches or outperforms it by 1fps so perhaps its gonna be like that for 980 and 1060

 

[D007]

Lol.. Destroys the 480... Not even a competition..

 

[Saturn11111]

The hull is plastic or metal

 

[medi01]

Destroys the 480..

Checkmate. AMD shouldn't have even bothered to make the 480.

Neither nVidia should have bothered with 1070. Oh, and even 1080, it would be rougthly where the green bar ends (+77% of RX 480):

new leak from videocarz

How can the 4.4TFLOPS defeat 5.5TFLOPS?

Flops are just one of many aspects of GPUs, namely, number of shaders.

 

[Saturn11111]

How can the 4.4TFLOPS defeat 5.5TFLOPS?

 

[wolar]

That graph is marketing shit, look at the scale below, even if its true (which i doubt) it will be 15% at max higher performance than the RX 480(the reference which uses 1x 6pin). But of course nvidia will display it as it doubles the performance which in reality its only a 0.15 in the graph , their graph, which i do not trust after all these marketing crap they are pulling.

 

[medi01]

How can the 4.4TFLOPS defeat 5.5TFLOPS?

It is 4.4 vs 5.5 AT COMPUTE.
It doesn't defeat it at compute.
Games are more than just compute.

Leaked benches show that 15% is an overstatement.