Nvidia Turing Product Reviews and Previews: (Super, TI, 2080, 2070, 2060, 1660, etc)

I get that, but all in all, they can "allow" themselves to do that because of non highend competition imo.

 

2080/2080Ti review from HardwareLUXX that includes the Titan V:
https://www.hardwareluxx.de/index.p...ti-und-rtx-2080-founders-edition-im-test.html

 

First lunch of GPU and we don’t have beyond3d Suite benchmark. So said @Rys

 

Does this help?

https://www.anandtech.com/show/1334...x-2080-ti-and-2080-founders-edition-review/15

 

No it’s not beyond3d Suite but thank you.
I really miss a open benchmark tool like this. I will pay 100 dollar for it.

 

So now that Anandtech has posted their review, I though I would update the chart. Because game number 4, (Wolf2) has a much higher delta than everything else, I had Excel spit out a random number which ended up representing Total War and grabbed those results as well.



So.... unless you are huge Wolfenstein II fan, as far as games available NOW are concerned, 2080 TI is by far the worst of these transitions. Using the (Performance Δ - Power Δ - Price Δ)*100 for a composite score, 980 scores 50, 1080 39 and 2080 is ...0

 

Hmm... launch prices are correct?
You should do this type of thing for CPU's as well ....

 

I like that Anand was the only site that emulated ref clocks on the FE cards. This kind of standards are becoming rare in the media, and I honestly expected none other than Anand to adhere to them.

In the end Anand has the 2080Ti 32% faster than 1080Ti ref to ref. And has it 37% faster with the default 90MHz OC.

https://www.anandtech.com/show/1334...tx-2080-ti-and-2080-founders-edition-review/5

 

Why wouldn't you just include all the games?

 

Time constraint... I have downtime here and there while Qlikview is reloading my apps but it’s sporadic.

 

That's interesting. This 20xx series reminds me of the jump from the 7xx to 9xx series with the 970's and 980's performance straddling the 780ti. Pascal's jump in performance looks to have been something special. Great node shrink 28nm to 16FF as well as some good architecture optimization.

I think the only thing about the RTX launch that is bad is the prices. Given the same node and what Nvidia chose to do with the chips (RT enhancements) the performance gains seem ok, it's just that the price is so out of whack. I bet once Pascal is gone, they'll drop the price by a $100 bucks or so. I don't think we're going to be going back to $500 x80 series given how large these dies are and I doubt that 7nm in the future will allow for that as well even if the chip sizes shrink for the follow up series.

 

How does a mistake like this even make it into a review anymore? I can't say they were pressed for time as the process node was known for quite some time now.

"The new Turing-based GeForce RTX cards, however, consumed more power than Pascal under load, despite their use of a more advanced 7nm manufacturing process."
Read more at https://hothardware.com/reviews/nvi...e-and-overclocking?page=9#jfeyRcuqu2GoU66H.99

 

The good news is that we do have the B3D suite data. But it didn't make the cut for trying to get everything done on time. I'm thinking we're going to follow this up with a part 2, looking more at synthetics, clockspeed averages, etc.

 

A ~500mm2, 7 nm big Turing2 GPU would not be unreasonable.
On the then brand new 16 nm process, GP102 was 471mm2 (coming from 28nm for Maxwell)
(7nm SoCs like the Kirin 980 have 7B transistors on ~100mm2)
That could be ~35B transistors for TU2, twice that of the TU102.
A lot of guessing here, but 7 nm should bring a huge jump in performance, we will see soon enough with the new NV HPC GPU.

 

I agree perf wise, but my point was more about price. I don’t really see prices going back down with 7nm for such large chips.

 

Spawned off the DLSS discussion to its own thread, since it seems large enough to warrant it: https://forum.beyond3d.com/threads/nvidia-dlss-antialiasing-discussion-spawn.60896/

 

Any theories as to why Wolfenstein II loves Turing so much? Lots of int instructions perhaps?

 

It seems NVIDIA improved it's baseline performance in Vulkan games with Pascal (Doom and Wolf2). Turing just picked that up and built on it. Wolf 2 should also receive a variable shading patch that is exclusive to Turing.

 

What about rapid packed math support as well? Could that contribute to Wolf II?

 

It's possible, but I think that currently only works through AMD intrinsics extension in Vulkan. So it's only for Vega GPUs. I could be wrong though.