Saturday, June 6th 2020

NVIDIA GeForce RTX 3080 Pictured?

Here are what could be the very first pictures of a reference NVIDIA GeForce RTX 3080 "Ampere" graphics card revealing an unusual board design, which is the biggest departure in NVIDIA's design schemes since the original GeForce TITAN. It features a dual-fan aluminium fin-stack cooler, except that one of its fans is located on the obverse side, and the other on the reverse side of the card. The PCB of the card appears to extend only two-thirds the length of the card, ending in an inward cutout, beyond which there's only an extension of the cooling solution. The cooler shroud, rather than being a solid covering of the heatsink, is made of aluminium heatsink ridges. All in all, a very unusual design, which NVIDIA could implement on its top-tier SKUs, such as the RTX 3080, RTX 3080 Ti, and in a cosmetic form on lower SKUs. We get the feeling that "Cyberpunk 2077" has influenced this design.
Sources: ChipHell Forums, HXL (Twitter), VideoCardz
Add your own comment

225 Comments on NVIDIA GeForce RTX 3080 Pictured?

#126
Scrizz
Hopefully this lets people understand.

Blue: Intake
Red: Exhaust

Posted on Reply
#127
Xzibit
Wouldn't that cause havoc for air flow inside the case
Posted on Reply
#128
$ReaPeR$
Weird card design.. can't wait to see the tests, especially about the cooling design.
Posted on Reply
#129
theGryphon
Xzibit
Wouldn't that cause havoc for air flow inside the case
That's what I said above too... it would.
Posted on Reply
#130
Vya Domus
Scrizz
Hopefully this lets people understand.

Blue: Intake
Red: Exhaust
Here's another flaw, those kinds of fans will blow the air directly perpendicular onto the surface below, so that means little to no air reaches the middle of the heatsink.
Posted on Reply
#131
Xzibit
The rear backplate fan will be fighting with the CPU fan for fresh air if you don't have an open top case. Plus the I/O fan will feed hot air from the backplate fan due to case intake fans. Mounting the AIO in front of the case intake effect.

Its an interesting take
Posted on Reply
#132
Applewarlord
ARF
It's very possible that this front/rear fans setup is more efficient than the classic one-sided fans setup, hence they'd like to implement it for the first time.
If it's worse, why bother at all ?
Very likely, considering the new open-air fin-stack design provides more surface area for heat exchange and easier future maintenance. I love it alrdy.
Altho they could've gotten the idea of extending the heat-sink/fan-shroud over the PCB from someone else, say, Sapphire 5700xt Nitro+, Nvidia sure took it up a notch.
Another interesting thing is that the two white stripes we can see faintly from the rear of the card under the semi-seethrough plastic back.

My first guess is they are heat-interface materials usually stick on VRMs but what are they doing on the back of the board? There's no metal backplate to assist on spreading heat. Maybe it's just a habbit. Don't know they are doing it :p
Posted on Reply
#133
Caring1
People will have to rethink case fans on the bottom of the case blowing air up towards the GPU.
Posted on Reply
#134
Applewarlord
Vya Domus
Also in case no one noticed there is almost no place for the die to be on board. You can't have the fan directly over the die as that would limit the area of the coldplate and heatpipes too much.
IMO the fan on the front side of the card is NOT over the GPU but over VRM instead. It's a non-conventional board design. Notice in the rear-view picture there are two faint white stripes under the plastic see-through back plate? They could be thermal-interface materials which in recent years make contact with a metalic back plate. Truely I have no idea what they are doing here but it could be a human error. Someone just slapped it on by habbit.
Posted on Reply
#135
Chloe Price
I'd say that it's a mockup or a prototype if it's not a fake. Well, there's been interesting designs so I can't see why something like this couldn't exist.
Posted on Reply
#136
LemmingOverlord
Almost as corny as Intel's Xe renders.

So Nvidia concludes that instead of a blower reference design, it's going for a sucker reference design????? Ironic.
Posted on Reply
#137
Vayra86
thesmokingman
The aesthetic is a real departure for Nvidia. I'm not sure it's hmm, manly enough for a top end card as strange as that may sound. Maybe it'll grow on us?
Shrouded in mystery, that. But manly enough? We have waifu cards now, it will work out just fine. Manly is a Korean esports team looking badass in 2020 :)
Posted on Reply
#138
reflex75
This design will create hot air loop.
Posted on Reply
#139
efikkan
Frankly, I wouldn't care if the card were My Little Pony themed. It's going into a box, I care about performance, noise, airflow, temperature and price of course.

For those who do care about looks, rest assured there will be plenty of AiB variants.

I only wish at least one of the could go for more of a "tower cooler" design. I wouldn't mind the cooler being 6 slots as long as it pulled the air out in a silent fashion, and a such design would make much more sense in a typical computer case.
Posted on Reply
#140
Mats
Mats
Seems like the front exhaust will feed the rear fan with hot air. If the fans were on the same side then I guess the heat from the front exhaust would go directly to the CPU area..

I changed my mind. As someone pointed out, this cooler has probably a vapor chamber. If so, how can it possibly exhaust air in the underside of the card? (see pic in quote) Unlike heatpipe heatsinks, vapor chamber heatsinks doesn't let air straight through. Like someone else said, we can't see anything between those fins on the underside anyway, which is highly unlikely if that indeed was an exhaust. Maybe it's just fins on the underside of the vapor chamber, which makes this part (front, underside in case) passively cooled. (Yeah it can be a combination of VC and heatpipes, but still, we can't see anything in there anyway.)
Here's the vapor chamber of the 2080 TI FE. Pretty much no air, or light, comes through.
Posted on Reply
#141
PooPipeBoy
The design seems far too elaborate and refined to be what I would consider "fake". Knowing Nvidia, they've been trying to produce more out-of-the-box designs and move away from the standard multi-fan design. I mean hey, a radical change is a great way to justify those radical MSRPs.
Posted on Reply
#142
Vya Domus
Mats
I changed my mind. As someone pointed out, this cooler has probably a vapor chamber. If so, how can it possibly exhaust air in the underside of the card? (see pic in quote) Unlike heatpipe heatsinks, vapor chamber heatsinks doesn't let air straight through. Like someone else said, we can't see anything between those fins on the underside anyway, which is highly unlikely if that indeed was an exhaust. Maybe it's just fins on the underside of the vapor chamber, which makes this part (front, underside in case) passively cooled. (Yeah it can be a combination of VC and heatpipes, but still, we can't see anything in there anyway.)
Here's the vapor chamber of the 2080 TI FE. Pretty much no air, or light, comes through.

No open air cooler is designed such that air comes through.
Posted on Reply
#143
Mats
Vya Domus
No open air cooler is designed such that air comes through.
My post isn't based on what you've seen, or haven't seen, I'm talking about what everyone else is talking about in this thread.
This thread is 99 % speculations, and there are countless posts that suggests so.
Posted on Reply
#144
Vya Domus
Mats
My post isn't based on what you've seen, or haven't seen, I'm talking about what everyone else is talking about in this thread.
This thread is 99 % speculations, and there are countless posts that suggests so.
It doesn't matter, open air coolers are simply designed to dissipate the heat through the sides of the heatsink not directly through it, that's not a speculation it's fact.
Posted on Reply
#145
Mats
Vya Domus
It doesn't matter, open air coolers are simply designed to dissipate the heat through the sides of the heatsink not directly through it, that's not a speculation it's fact.
That doesn't stop anyone from doing different. I have no idea what you're trying to prove here. It's not like such design defies physical laws.
Posted on Reply
#146
Decryptor009
Vya Domus
It doesn't matter, open air coolers are simply designed to dissipate the heat through the sides of the heatsink not directly through it, that's not a speculation it's fact.
Anyone with 2 brain cells could tell you that air cannot move through solid metal, but upon contact it cools it depending on temperature of the air.

The flow of air once it hits though depends on which direction the gaps dictate.

Saying they are designed that way is not correct, it is physically impossible for air to dissipate any other way with such a design.
Posted on Reply
#147
Mats
Or maybe we're talking about two different things.
Posted on Reply
#148
yeeeeman
ARF
It's very weird why AMD did what they did with Navi 1st generation.
Why no Big Navi and why not competing with Vega 64/ Vega 64 derivatives in the below Big Navi segments.

They had a 256 mm2 HD 4870 but back then they had a card with 70-80% higher performance.

Now they have nothing.

And if the rumours are true, the smaller Navi 2X chips won't be out before 2021.
I can tell you why by talking to some engineers involve in its making.
rdna 1 is a new uArch with lots of changes and because the teams are small and the task is huge (nvidia is much larger than AMD), budget/timing constraints mean that navi 10 had a lot of hardware bugs that meant it is not efficient and required a lot of software tweaking (read drivers) to even make it work. You can see all these traits in the 5700xt. It eats a lot of power for a small-ish chip on 7nm, that even turing on 12nm is better. As regarding the drivers and the bugs...people are still complaining about crashes, so yeah. They were forced to sell it at a low price and create lots of subproducts from it in order to sell as many dies as possible, unfortunately for cheap. The strategy worked partially but many users got frustrated with bad drivers (in essence the drivers are OK, but you can do so much to hide hardware bugs) so they switched to nvidia. Anyway, this meant they couldn't launch a big die gpu based on rdna1 within reasonable power consumption/budget and thermal, so the focus was shifted on rdna 2 which is an improvement in many regards to rdna 1 but especially it has bug fixes for all the power/functionality related stuff.
So short answer to your question is that AMD cannot really make a great chip with new uArch from first try. If they would have succeeded to make rdna 1 what rdna 2 will be, then nvidia would have had a hard time competing with 2000 series. The 2080 ti would sell with 400-500$.
Posted on Reply
#149
Nero1024
Disappointing design if it will actually end up being the real thing. Maybe one of the prototypes?
Posted on Reply
#150
Vya Domus
Decryptor009
Anyone with 2 brain cells could tell you that air cannot move through solid metal, but upon contact it cools it depending on temperature of the air.

The flow of air once it hits though depends on which direction the gaps dictate.

Saying they are designed that way is not correct, it is physically impossible for air to dissipate any other way with such a design.
Anyone with 2 brain cells probably figured out what I said, what solid metal, what are you talking about ? The air is exhausted through the sides of the heatsinks because the PCB is in the way, so yes it's designed that way. For part of this design the air supposedly is meant to go directly perpendicularly through the heatsink, except that, like I pointed out, the that area looks closed off.
Mats
It's not like such design defies physical laws.
It doesn't, it's just severely inefficient.
Posted on Reply
Add your own comment