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?

#102
theGryphon
RH92
One explanation might be they want to isolate the airflow between the two supposed vapor chambers . But i have to agree the airflow pattern is very hard to grasp .

The only logical airflow pattern i can come up with would be this one :



So in essence 2/3 of the heatsink area is dedicated to the core/memory cooling and will blow hot air from the sides , while the other 1/3 is dedicated to VRM cooling .

Still weird AF i have to admit !
Everything on that airflow pattern is right except for the implication of intake from the back. It will not and cannot intake from the back. It will intake from the axial fan blades and exhaust in all directions shown, as well as towards the back.

The front airflow pattern seems legit. That fan will simply blow through the fins, as in a radiator.

There is absolutely no push-pull config here, as there is no such airpath...

Overall, I think the design is very functional-oriented and to me, it looks great. Fans on either side will probably help with airflow obstruction in some cases, and it may help with case/DIMM cooling. In some other cases (mostly smaller ones) however, the case airflow will get messed up.

I wish, for the sake of compatibility, they flipped that top fan to reverse the airflow direction, so that the card acts like all cards now do: intake only from under the card...
Posted on Reply
#103
Darmok N Jalad
Interesting concept, though I can’t really make logical sense of it. The best I can see is the bottom fan moves the air back and to the sides, and the top fan will pull air up. The whole idea would be to help move the hot air up and above the card, where there is usually more air flow from case fans. The down side though, would be dumping this heat right in front of the CPU. Also, it almost looks like no air will get pushed out the back plate.
Posted on Reply
#104
Totally
theGryphon
Everything on that airflow pattern is right except for the implication of intake from the back. It will not and cannot intake from the back. It will intake from the axial fan blades and exhaust in all directions shown, as well as towards the back.

The front airflow pattern seems legit. That fan will simply blow through the fins, as in a radiator.

There is absolutely no push-pull config here, as there is no such airpath...

Overall, I think the design is very functional-oriented and to me, it looks great. Fans on either side will probably help with airflow obstruction in some cases, and it may help with case/DIMM cooling. In some other cases (mostly smaller ones) however, the case airflow will get messed up.

I wish, for the sake of compatibility, they flipped that top fan to reverse the airflow direction, so that the card acts like all cards now do: intake only from under the card...
It's no different from current to fan axial coolers, so there is no shared flow between the fans. fans are just are on opposite sides of the massive heatsink. What I think they're trying to accomplish is create a scavenging effect is the exhaust of the fan aimed top-down will pull the exhaust of the fan towards the front of the card. This wouldn't be possible with the fans on the same side because the would be able to get in some overlap.

Posted on Reply
#105
medi01
lynx29
now that AMD has officially said Big Navi will arrive in September,
Could you poke me with a link please.
Posted on Reply
#106
RH92
theGryphon
Everything on that airflow pattern is right except for the implication of intake from the back. It will not and cannot intake from the back. It will intake from the axial fan blades and exhaust in all directions shown, as well as towards the back.
This is the so called '' back '' ( read back-plate face on conventional coolers ) of the card :



So the card definitely can/will intake from the back . Both fans present on the 2 different faces are intake fans !
Posted on Reply
#107
wheresmycar
Looks like a toy. I guess an black variant will suffice.

Where i'm a little confused... with the 2 fans set on opposite sides doesn't that mean the pcb is downsized by roughly 50%? Is that even possible?
Posted on Reply
#108
QUANTUMPHYSICS
My computer doesn't have glass sides so as long as it is fast as hell, I honestly don't give a damn what kind of shroud my 3080Ti has.
Posted on Reply
#109
RH92
dicktracy
The design is fake. Why? Because why would they suddenly ditch the superior axial fans for these awful ones.
Except for the part where both fans used on this prototype are axial ............... Don't get confused :

Axial / Radial

Posted on Reply
#110
Vya Domus
cueman
erhh, when ampere are tested no1 took big navi, or any amd gpus,rtx 3060 is enough and when and if radeon viii aka big navi coming, and if it coming, same thing ,belive it...or not.

fact are, amd use still 7nm process tech without any new arch or updates and top on that hill is ,still 7nm radeon vii gpu, rx 5700 xt little brother is same gpu core with less tmus and rops but clocks maxed what is possible when hardware gadgets taken off.

so only way to get more power radeon vii(i)/big navi is put it inside more tmus and rops...thats all...but if so, except tdp 400W and watercool what i say that if happends ,its 7th wonder for 7nm gpu.
finally, lisa Su says 'we have big navi,sure, nice to ask it,yes its coming..' this she says only few month ago...i mean time,capice. so its it is radeon vii(i).


ampere leaps are process tech from 12nm to 7nm and new core arch and new cudas innovation cuda 3... any1 need more facts?

stop dream and stop took big navi.. its coming or not,but 7nm ampere coming 100%....just waiting and see.

my opinion is that desktop gpus max tdp should be 200W. if over 100-200 $ tax on it,different is science and other industrial kind using gpus.


naah,, lets joy summer and wait interesting autum with 7nm nvidia ampere (1st 7nm!), 10nm intel cpu (1st under 14nm cpu!), intel 7nm gpu (1st!) and amd erhh, ok, big navi.
Anyone who knows Sumerian here ?
cellar door
It looks like a push-pull tunnel. With enough static presure, this design could be very efficient.
Except both fans look like they are pushing air into the heatsink, the problem with such a design is that the heatsink wouldn't have enough surface area and the fans would have to run at pretty absurd speeds, >2000 rpm. It would be the least efficient design that I can think of.
Vayra86
Like a double radial blower, kind of idea.
It just doesn't work though. With radial fans the air has to be directed, so if you want both fans to blow in the same direction that means one of them would be blocked by whatever directs the air for the other one. In this case it would be just as bad, some of the air would go out the back of the card, except it goes through almost no fins so it cools down nothing and the other one would do the same. The heatsink itself would just get airflow from both sides and little place for the air to escape. No matter how you spin (pun intended) none of this makes sense.

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.
Posted on Reply
#111
Valantar
Vya Domus
Anyone who knows Sumerian here ?
My thought exactly. I think we need some sort of cryptolinguist in here to decipher that.
Vya Domus
Except both fans look like they are pushing air into the heatsink, the problem with such a design is that the heatsink wouldn't have enough surface area and the fans would have to run at pretty absurd speeds, >2000 rpm. It would be the least efficient design that I can think of.



It just doesn't work though. With radial fans the air has to be directed, so if you want both fans to blow in the same direction that means one of them would be blocked by whatever directs the air. In this case it would be the same thing, some of the air would go out the back of the card, except it goes through almost no fins so it cools down nothing and the other one would do the same. The heatsink itself would just get airflow from both sides and little place for the air to escape. No matter how you spin (pun intended) none of this makes sense.

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.
That's a very good overview. Lots of issues here, definitely. Guess the fan closest to the I/O could be directly on top of a vapor chamber and some really small fins, but the area of those would be quite tiny even if including the middle section of the card - where of course air would just dissipate out the path of least resistance out that same side of the card, close to the fan and get recirculated. The tiny amount exhausted out the back would as such perhaps make more of a difference as it's exhausting already heated air despite passing over just a tiny fin array, but... Yeah, that's not a good plan. And if the die is cooled with a vapor chamber there is no way of connecting that to the fins on the other end of the card due to the fan being on that side... unless they're using one of those kinda dumb "3D vapor chambers" or stupidly putting heat pipes onto a vapor chamber... This is weird.
Posted on Reply
#112
Totally
Vya Domus
Except both fans look like they are pushing air into the heatsink, the problem with such a design is that the heatsink wouldn't have enough surface area and the fans would have to run at pretty absurd speeds, >2000 rpm. It would be the least efficient design that I can think of.
They worked out that problem the heatsink fin arrangement is creating a tesla valve.
Posted on Reply
#113
Xzibit
Vya Domus
Anyone who knows Sumerian here ?
Where is Wonder Woman when we need her. She made quick work of Dr. Maru's book.
Posted on Reply
#114
Vya Domus
Totally
They worked out that problem the heatsink fin arrangement is creating a tesla valve.
I don't see how anything is worked out, even if the heatsink is meant to receive air from one direction what does the other fan do ?
Posted on Reply
#115
Totally
Vya Domus
I don't see how anything is worked out, even if the heatsink is meant to receive air from one direction what does the other fan do ?
see the masterpiece I sketched out in paint?
Posted on Reply
#116
Vya Domus
Totally
see the masterpiece I sketched out in paint?
It would have been brilliant if not for the fact that the other fan is also an intake.
Posted on Reply
#117
moproblems99
Ugly as sin itself.
Dazzm8
Didn't the R9 Fury X become really small due to it's use of HBM?
Hbm was one of the reasons it was small.
Posted on Reply
#118
Totally
Vya Domus
It would have been brilliant if not for the fact that the other fan is also an intake.
That's how they're drawn, the lines have arrows on them, flow of front intake is light blue, dark blue for the back intake, the red is a heatpipe
Posted on Reply
#119
Vya Domus
Totally
That's how they're drawn, the lines have arrows on them, flow of front intake is light blue, dark blue for the back intake, the red is a heatpipe
Look at the fin stack, how dense it is even a radiator is usually less dense than that , how much air do you think will go trough there ? Plus it looks like it's actually closed off, otherwise you could see the fan through it (which should be very close).

Most air coolers on GPUs are design such that the air goes through the fins around the fans not under them, because you can't fit many fins in there and there is also a dead spot under the fan.
Posted on Reply
#120
Totally
Vya Domus
Look at the fin stack, how dense it is even a radiator is usually less dense than that , how much air do you think will go trough there ? Plus it looks like it's actually closed off, otherwise you could see the fan through it (which should be very close).

Most air coolers on GPUs are design such that the air goes through the fins around the fans not under them, because you can't fit many fins in there and there is also a dead spot under the fan.
Second First picture if you look through the gap in the fan blades you can see another layer of fins that run length wise and not arrange in chevrons like the layer on top so the fans are shallow. Hence why the fans can't been seen through the other side and provides a path for air but that's from what I can see so I could be wrong.
Posted on Reply
#121
Vya Domus
Totally
Second First picture if you look through the gap in the fan blades you can see another layer of fins that run length wise and not arrange in chevrons like the layer on top so the fans are shallow. Hence why the fans can't been seen through the other side and provides a path for air but that's from what I can see so I could be wrong.
See, if the fans are shallow they wont move a lot of air and the fins are very dense as I said, end result almost no real air flow. Again no matter how you spin it this is bad.
Posted on Reply
#122
Totally
Vya Domus
See, if the fans are shallow they wont move a lot of air and the fins are very dense as I said, end result almost no real air flow. Again no matter how you spin it this is bad.
We're blind. The fan on the back-plate side has the blades reversed. Either way I was thinking that the purpose of the second fan was to create a pressure pocket the sucks air out of the fins. updated pic
Posted on Reply
#123
Caring1
Totally
We're blind. The fan on the back-plate side has the blades reversed. Either way I was thinking that the purpose of the second fan was to create a pressure pocket the sucks air out of the fins
But it still pushes air down through the fins.
Posted on Reply
#124
Totally
Caring1
But it still pushes air down through the fins.
Then I don't know, we'll have to just wait and see.
Posted on Reply
Add your own comment