The GeForce NVLink still seems fast enough. After all the full NVLink is made to be sufficient for the top range Teslas and Quadros, some of which feature 6k+ Cuda cores, so if the GeForce has half the bandwidth, that is still more than enough for the kind of performance 2080ti might yield.
But does it have all the features in functionality ? Is the memory stacked ?
22GB of Vram is A LOT for GPU rendering.
Have no doubt - “If it’s not clearly written, then it doesn’t exist.”
(Either contracts, bills, invoices, inquiries, news, legislation, obituaries, articles, theses, … - it’s common knowledge & every person should be aware of that.)
So,
a.) for top tier gaming cards (2080/Ti) specs states: NVLink (SLI ready)
b.) while on the other hand, for whole RTX Quadro line it clearly states: “NVIDIA NVLink® to combine two GPUs with a high-speed link to scale memory capacity up to 96GB and drive higher performance with up to 100GB/s of data transfer.”
Go for a long walk and drink water. 
:- D
Here’s the updates from Vlado about the new GPU ray-tracing:
https://www.chaosgroup.com/blog/what-does-the-new-nvidia-rtx-hardware-mean-for-ray-tracing-gpu-rendering-v-ray
So Vlado hints that NVLink is identical in terms of memory pooling for all RTX cards.
This is super revolution for GPU rendering ?! Christ, I can’t even imagine what some people with 4x2080ti will do.
Maybe time to try Vray GPU once they implement support for RT cores. Ultra-speed, support for Corona materials plus all the nice things we are waiting forever for ( VR SCANS ).
Technically yes, that appears to be true. We still need to wait for the official response from Nvidia whether the Geforce NVLink = Quadro NVLink or if it is just a cutdown SLI version of some sorts. Considering that it is called NVLink, it shares the same physical connector and is known to have sufficient speed (50gbps compared to 100gbps on Quadros) I think that it is pretty much the same thing.
That being said, we do know that Nvidia currently only sells 3 and 4 slot NVLink bridges for the Geforce cards. That means you can probably NVLink a bunch of 2080ti although you’ll need to use PCI-Express risers in order to fit them on your motherboard.
I have 6 PCI-E slots ready but with the Geforce NVLink bridges I could probably only fit 2 cards in there in a standard chassis without any risers. Technically though, I could easily fit 4 dual slot cards without NVLink (4 x 1080 for example).
Quadros come with 2 slot NVLink bridges so with those you can actually easily NVLink 2 + 2 cards in your system and make it all fit much like with the current gen GPUs.
Hope that helps 
I am looking into it myself too but I will wait till the cards are actually release to see if everything is “as it should be” for rendering
Do you actually see multiple cards being connected ? I only see two cards, even in Quadro/Tesla range.
The 3-4 slot are only to accomodate wider spread between pci-e slots not to cover 3-4 cards, at least that is my understanding.
So with RTX 2080ti gen, 22GB Vram would be the current limit. Which is heck of a lot in gpu-rendering.
My bad, I totally didn’t address that properly.
You can only connect two cards (hence 2+2) which obviously gives you access to the combined VRAM of the two cards. So if you have 2x 2080 your VRAM total will be 16GB. That being said you can connect 2 + 2 + 2 … GPUs together. The combined VRAM total will still be the same but your rendering performance will be obviously higher.
So yeah, you are totally right. The 3 & 4 slots are there to create some room between the cards. Thats pretty much it afaik.
I really can’t wait for Vlado to post his benchmarks once NDA falls out. His words: You will be positively surprised :- ).
And that is yet without the RTX cores I believe.
Interesting point of view =) What do you think?
yup, aware of the Imagination tech, GPU arch in PowerVR RT cards since their demos in 2014 (later on Apple bought it, implemented in almost all their devices, optimizing code now…) why NV rush to release theirs, didn’t surprised me - am wary about their strategy - hyping the ignorant crowd…
Some more food for thought from Panos (RS dev.):
At some point I’ll be preparing a longer post than this but just wanted to quickly offer some insight on ray tracing hardware acceleration and ensure that user expectations are reasonable.
Most renderers work by executing the following three basic operations:
- They generate rays (initially from the camera),
- They shoot these rays into the scene (i.e. they do ray tracing),
- They run shaders at the intersection points of the rays.
Shading typically spawns new rays for reflection/refraction/GI/etc purposes which means going back to step 1.
This 1-2-3 process happens as many times as there are ray bounces.Hardware accelerated ray tracing primarily speeds up the second step: i.e. the ‘core’ ray tracing. If the renderer uses really simple shading, then the ray tracing step becomes the most expensive part of the renderer. For example, if you use extremely simple shaders that (say) just read a flat texture and return it, you could easily find out that the ray tracing step takes 99% of the entire render time and shading just takes 1%. In that case, accelerating ray tracing 10 times means that the frame renders 10 times faster, since ray tracing takes most of the time.
Unfortunately, production scenes do not use quite as simple shading as that.
Both us and other pro renderer vendors have found cases where shading takes a considerable chunk of the render time. I remember reading a Pixar paper (or maybe it was a presentation) where they were claiming that their (obviously complicated) shaders were actually taking more time than ray tracing! Let’s say that, in such a scenario, shading takes 50% of the entire frame time and tracing takes the other 50% (I intentionally ignore ray generation here). In that scenario, speeding up the ray tracer a hundred million times means that you make that 50% ray tracing time go away but you are still left with shading taking the other 50% of the frame! So even though your ray tracer became a hundred million times faster, your entire frame only rendered twice as fast!
All this is to say that when you read claims about a new system making rendering several times times faster, you have to ask yourself: was this with simple shading? Like the kind you see in videogames? Or was it in a scene which (for whatever reason) was spending a lot of time during tracing and not shading?
In more technical terms: the RT cores accelerate ray tracing while the CUDA cores accelerate shading and ray generation. The RT hardware cannot do volume rendering and I think no hair/curve tracing either - so these two techniques would probably also fall back to CUDA cores too - which means no benefit from the RT hardware.
All this is not to say that we’re not excited to see developments on the ray tracing front! On the contrary! But, at the same time, we wanted to ensure that everyone has a clear idea on what they’ll be getting when ray tracing hardware (and the necessary software support) arrives. We have, as explained in other forum posts, already started on supporting it by re-architecting certain parts of Redshift. In fact, this is something we’ve been doing silently (for RS 3.0) during the last few months and in-between other tasks. Hopefully, not too long from now, we’ll get this all working and will have some performance figures to share with you.
Thanks
-Panos
PS
VRay demos are running on Quadros.
nobody wants a software that needs a specific piece of hardware to run it. that piece of hardware will have a very high price look at quadro. that’s because companies like nvidia/amd will take advantage of the market need for that hardware and will jack the price up. use what’s there and keep it that way. use geforce instead of quadro or fancy RTX like fstorm does. cpu’s will have hundreds of cores soon with new materials to create smaller dies to push way deeper into moor’s law curve, we are set for great stuff in the cpu world. set tight
Well, I’m sitting here wondering… RTX utilizes the RT cores. Does DXR utilize RT cores too? Do you need to access the RT cores through the new RTX framework (I think its called Optix Ray Tracing)? What does that mean for AMD GPUs?
The biggest drawback of GPU rendering for me personally was always the closed off eco-system. You either run on Nvidia CUDA compliant GPUs or you don’t run at all. I dislike Otoy for their weird corporate crap they do but supposedly they are getting closer and closer with their Vulkan implementation that will work on pretty much any popular vendor going forward (Intel?).
I am mentioning that because if DXR doesn’t work well with RT cores and whatever AMD comes up with isn’t compatible… We are even more locked to Nvidia. And we all know how that turned out when Intel was on top. Or Apple. Or Comcast… You get the picture.
Disclaimer: I by no means am saying that nvidia produces crap hardware. On the contrary, for the past couple of years they are the performance leaders, no doubt. I do remember the fun times when the Radeon 9700 Pro made things go round and how nice it is to for there to actually be competition on the high end as well.
edit: It would appear that the RT cores can be programmed through Nvidia’s Optix library, DXR and Vulkan.
Source → https://www.chaosgroup.com/blog/what-does-the-new-nvidia-rtx-hardware-mean-for-ray-tracing-gpu-rendering-v-ray
@burnin Thank you for the quote.
GPU Ray Tracing for Film and Design: RenderMan XPU by Max Liani, Pixar Animation Studios
Elsewhere…
Cards coming in…
It was also mentioned (speculated?) that NVlink memory stacking on non-Quadro RTXs is possible, but must be coded-in-engine & VRay dev. already did it.
Well of course he did :- ). I can’t wait to see the results !
Apparently that is the case. I would be mad furious if Nvidia decided to call it NVlink but disable any kind of memory pooling options (on the Geforce cards that is). Might as well call it SLI 3.0 in that case.
There is one publication that had something to say about that though, Guru3D.com - (https://www.guru3d.com/articles_pages/nvidia_turing_geforce_2080_(ti)_architecture_review,7.html).
“Unfortunately, though, the new NVLINK bridge is just used for SLI, there will be no GPU or memory sharing as previously expected. Think of NVLINK as SLI version three. It is just an interface yet many times faster.”
I am unsure where they get that info from to be honest but they are pretty specific about it. Maybe they are just referring to gaming scenarios. From my quick glance at the Nvidia reviewers documents I couldn’t find any info about that. In any case, I kind of wouldn’t be surprised if they somehow managed to lock it at the driver level.
All that being said, only a couple of days to go and we’ll have more info
edit: Given that these graphic cards are supposed to drive 4k games that 8 GB framebuffer seems to be almost too small. Hence I can see how the NVlink implementation would help with memory pooling in that regard.
With regard to NVLink, Chaos Group have already stated on their blog that NVLink will support memory pooling on the new RTX cards, specifically the 2080 and 2080 Ti. Read the NVLink section at the following blog post by Vlado: https://www.chaosgroup.com/blog/what-does-the-new-nvidia-rtx-hardware-mean-for-ray-tracing-gpu-rendering-v-ray
He doesn’t mention directly 2080&2080ti, but given he uses them as example:
For example, if we have two GPUs with 11GB of VRAM each and connected with NVLink, V-Ray GPU can use that to render scenes that take up to 22 GB
..I guess the answer is yes :- ). This will be a big one..
So… The reviews have been out for like a day now. Any impressions? https://videocardz.com/78054/nvidia-geforce-rtx-2080-ti-rtx-2080-review-roundup