Friday, July 1st 2016

NVIDIA GeForce GTX 1060 Reference Board Design and Clocks Confirmed

A leaked slide from NVIDIA press-deck for the imminent launch of the GeForce GTX 1060 confirmed the reference board design, which first surfaced in Hong Kong. The slide also reveals clock speeds, and other key specs of the card. While it doesn't reveal the GPU nominal clocks, it mentions that the GPU Boost frequency will be set as high as 1.70 GHz. The memory is clocked at 8 Gbps, which over the GPU's 192-bit GDDR5 interface, puts out 192 GB/s of memory bandwidth.

The chip features 1,280 CUDA cores based on the "Pascal" architecture. The card draws power from a single 6-pin PCIe power connector, its TDP is rated even lower than that of the AMD Radeon RX 480, at 120W (vs. 150W of the RX 480). NVIDIA has been making huge (and successful) performance claims for its "Pascal" GPUs so far. The GTX 1060 is claimed to be faster than the GeForce GTX 980 from the previous generation, and "much faster" than the RX 480, which means that NVIDIA intends to price this card competitively to the RX 480.
Source: VideoCardz
Add your own comment

117 Comments on NVIDIA GeForce GTX 1060 Reference Board Design and Clocks Confirmed

#101
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.
Posted on Reply
#102
rtwjunkie
PC Gaming Enthusiast
5DVX0130NVIDIA 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.
Posted on Reply
#103
EarthDog
I need to invest in aluminum foil, live here at this forum and sell them... o_O :roll:
Posted on Reply
#104
$ReaPeR$
GhostRyderIf 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.. :D
EarthDogI need to invest in aluminum foil, live here at this forum and sell them... o_O :roll:
LOL indeed!!
Posted on Reply
#105
RealNeil
FordGT90ConceptSo 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?
Posted on Reply
#106
ppn
Well there are GP106-400-A1 and GP106-300-A1,

1060 cant be both so the premium must be Ti?
Posted on Reply
#107
Ungari
efikkanIt 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.
Posted on Reply
#108
geon2k2
BasardNice, 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.
nem..new leak from videocarz
Nice graph. nVidia should hire you right away, before the red camp will make you an offer you cannot refuse :roll:
Posted on Reply
#109
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.
Posted on Reply
#110
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.
Posted on Reply
#111
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
Posted on Reply
#112
D007
Lol.. Destroys the 480... Not even a competition..
Posted on Reply
#114
medi01
D007Destroys the 480..
TheGuruStudCheckmate. 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):

nem..new leak from videocarz
:laugh: :laugh: :laugh:
Saturn11111How can the 4.4TFLOPS defeat 5.5TFLOPS?
Flops are just one of many aspects of GPUs, namely, number of shaders.
Posted on Reply
#116
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.
Posted on Reply
#117
medi01
Saturn11111How 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.
Posted on Reply
Add your own comment
Dec 23rd, 2024 10:12 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts