> As always, wait for the benchmarks before deciding to buy (or return).

Why would you keep a 1200$ RTX 2080 Ti or a 2500$ Titan when you can get at least the same perf for 50-75% of the price with the new products, and much better RTX perf ?

This assumes that with RTX off the new gen won't be slower than the old one, but I think that's a fair assumption, and if it isn't, you can always return the 30xx card in 2 weeks, and buy an used 2080 Ti or Titan on ebay for pennies, once the market overflows from people upgrading for the 30xx series.

People were still asking for 900$ for a used 2080 Ti on ebay this morning, and the 3080 700$ price just destroys that offer. Many owners are going to try and dump these cards for as much as they can get in the next two weeks. I wouldn't buy a used 2080 Ti for more than 250$ today. In one month, these cards are going to sell used for 100-200$. If AMD can only match the 2080 Ti perf, they are going to have a very hard time pricing against the used 2080 Ti market.

> And let's not forget the huge power draw, requiring a new power connector and a 3 slot cooler.

That's only for the 3090 IIUC. All other cards were announced as being actually much smaller than the 20xx series ones.

True, the new generation offers better price/performance vs the previous generation.

Do note that the 3080 is still 2 weeks away (17 sept), 3090 24 sept, 3070 in October.

I would consider getting a non-founders edition though, in the past other brands have had better/more silent cooling for pretty much identical pricing.

Edit: While the 3090 (350W) is the only one requiring a 3 slot cooler, all 3 use the new 12 pin power connector. The 3080 founder edition power draw is still 320W, vs 220W for the 2080.

The 12 pin connector has an adapter for two 8pin cables. This is a non issue unless the connector just bothers you for some weird reason.

> True, the new generation offers better price/performance vs the previous generation.

That's not that difficult considering the RTX cards had terrible price/perf.

Pretty bold claim that 2080TIs are going to sell for $250 in a month, lol.

Certainly the market for them will take a beating compared to new prices now. But I can't imagine it collapsing like that purely based on the supply. How many people are really going to drop their 2080 just because a new thing is out there?

I'd love to be wrong, as an original 2070 owner ;)

> How many people are really going to drop their 2080 just because a new thing is out there?

Pretty much everyone who paid for a 2080 Ti on launch and always need to have the latests bestest thing.

>Why would you keep a 1200$ RTX 2080 Ti or a 2500$ Titan when you can get at least the same perf for 50-75% of the price with the new products, and much better RTX perf

Well for one, keeping a card you already bought is free, buying a new one costs money.

Why are you all getting so excited about the prices given in a paper launch? Wait until you can actually buy one at that price, which I'm guessing isn't going to be until well into 2021.

keeping a card you already bought is only free if you ignore the opportunity cost of what you'd get from returning it

I'm not sure if I'm missing some context but I'm assuming you are outside the return period. But anyway, I'd be really beyond surprised if these cards are actually available at these prices anytime soon.

Also if find a 2080ti for 200 before the year 2022 let me know I'll buy you a beer.

Hardware Unboxed tested an RTX 3080 and it seems like the performance improvements are not just in ray tracing: https://youtu.be/cWD01yUQdVA

It looks pretty impressive.

Regarding the new power connector: All the partner cards showcased by Gamers Nexus have the regular two or three 8-pin connectors and the FE cards seem to include an adapter. Nvidia states that a 750W power supply is required, so depending on the CPU even a 650W should be fine.

That’s global foundry not hardware unboxed

I don't blame you. NVidia's numbers look loaded. But surprisingly it really is a LARGE boost in FPS for games.

- Ray tracing only is not 200% but 195% in real world tests.

- In modern games like Tomb Raider the fps increase is between 165 and 180%, averaging 175%.

This is comparing the 2080 to 3080 playing real world games.

> My guess is the performance improvements are the biggest for raytracing, which I personally don't care for.

I still don't understand the raytracing craze when it comes to games. Years ago when I wrote my first raytracer I might have got excited about it. But we have advanced so much with rasterization that I don't really understand why this is something we need.

Raytracing complexity is tricky and it is likely to prove challenging to do in a game with consistent frame rates. Soft shadows are expensive even for hardware.

I would be more excited about some other global illumination improvements, like photon mapping.

> other global illumination improvements

RTX cards don't render everything with ray tracing. They use it for light calculations, for example it can be used exactly for global illumination.

> why this is something we need.

The answer is simple. Because there is a limit to how realistic we can make the lighting and shadowing using the old models. We are almost at that limit. Using ray tracing removes that limit.

> challenging to do in a game with consistent frame rates

Try Quake II RTX. It is very consistent right off the bat, and if you turn on the resolution scaling, you can get completely consistent framerates (within 2-3 fps continuously). While it might not be a game with the most advanced graphics, it does have variety of scenes, and there is no issue with the framerates being "inconsistent".

Many newer games are designed to show off raytracing effects. Cyberpunk 2077 has lots of neon lights, shiny things, rain puddles, etc for light to bounce around, and raytracing makes it look a lot nicer than when the shadows are approximated in traditional ways. Minecraft ... ye gods. The videos I've seen look amazing. The other nice thing these cards have is the DLSS 2.0 tech, which is supposed to let it render at higher resolutions by _making things up_ (?) based on ... something buzzword-laden. The effect, though, is that you get similar or better quality at much higher framerates, because lossy techniques are still nice to look at.

"Need" is a strong word, but I'm sure someone will make a game where the shadows _matter_ for telling the story, or solving puzzles, or even just making the game world look more realistic and believable.

DLSS renders the game at a lower resolution then upscales it to a higher resolution using AI to modify the final image. The models are trained from super-resolution renders and used to be trained per-game but are now generalized. They're designed to upscale textures, denoise, fix aliasing and overall increase quality based on that high-end source data so you get the same output without having to actually run at those settings.

> "Need" is a strong word, but I'm sure someone will make a game where the shadows _matter_ for telling the story, or solving puzzles, or even just making the game world look more realistic and believable.

Or selling GFX cards..

> 8N manufacturing process is presumably Samsung

They explicitly noted that it was Samsung.

It's not mentioned in this announcement, was it confirmed somewhere in the past by Nvidia?

It was mentioned in the video.

Indeed it is. For those wondering, this (official) link has much more info (and the video), that the currently linked blog post.

[1] https://www.nvidia.com/en-us/geforce/news/introducing-rtx-30...

Yeah there is no way they sell a card that does 200% the fps of a 2080ti in "normal" (non raytracing, ultra quality) averaged over multiple titles. If a 2080ti does 100fps without raytracing and 30fps with, this might do 110fps without raytracing and 60fps with, for they'll a "100%" increase but most would consider that 10%.

I was wondering if all benchmarks use the OptiX features or only the CUDA features. In software like Blender this makes a huge difference. OptiX can be twice as fast as CUDA. So of benchmarks don't use the OptiX capabilities then they will miss a lot of available speed.

I think the new connector is only on the 3090.

The product page linked elsewhere in the thread[1] has photos of the 3070 with the 12-pin connector and mentions that all Founder Edition cards include an adapter:

> To that end, our engineers designed a much smaller PCB, shrank the NVLink and power connectors, and still managed to pack in 18-phases for improved power delivery. Don’t worry, we included an adapter that allows Founders Edition cards to work with users’ existing power supplies.

[1] https://www.nvidia.com/en-us/geforce/news/introducing-rtx-30...