• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

The RTX 3080 TI isn't going to be- EDIT - No We Were All Wrong!

g67575

g67575

g67575

Soldato
Joined
30 Jun 2019
Posts
8,159
Not really hard to work out the max performance of the RTX 3080 TI, considering the 400w TDP of the already released Ampere A100 SXM4. Should be around 25% lower if the TDP is 300w so that would be approx:

Pixel rate:
169.2 GPixel/s

Texture Rate:
456.8 GTexel/s

14.6 TFLOPS

A100 SXM4 Specs:
https://www.techpowerup.com/gpu-specs/a100-sxm4.c3506

If we assume a similar boost clock to the RTX 2080 TI (1545 MHz), the figures would be:

Pixel rate:
120 ROPs x 1545mhz = 185.4 GPixel/s

Texture Rate:
324 TMUs x 1545mhz = 500.5 GTexel/s

5184 Shading Units x 1545mhz (x2) = 16.018 TFs (maybe 17TFs if GPU clock frequency is higher than the RTX 2080 TI)

So, if that ends up being correct, the raw computing performance (TFLOPS) of the RTX 3080 TI will only be about 19% higher than the RTX 2080 TI, and 31% higher than the Xbox X Series GPU.

The rumours of the RTX 3080 TI being a 20/21 TF GPU are almost certainly complete crap, Nvidia couldn't reach that with their ultra expensive Tesla / Ampere based GPU. It's not that surprisingly really, the Titan RTX and previous Tesla GPU were only 13-18% faster than the RTX 2080 TI overall, link here: https://www.techpowerup.com/gpu-specs/titan-rtx.c3311


EDIT - The PCI version of the Ampere A100 SXM4 has a lower TDP of 250w, but during a " sustained load will provide 10 to 50% lower performance than SXM4 based variant".
https://videocardz.com/newz/nvidia-announces-a100-pcie-accelerator

Let me know if you agree / disagree and why
 
Last edited:
Another fact that supports this theory is that Nvidia only increased the number of shaders by 768 from previous generations (from GTX 980 TI > GTX 1080 TI >RTX 2080 TI).

That would actually put the RTX 3080 TI at 5120‬ Shading units (slightly less than the figure I gave above).

Not sure why there would be a massive increase in clock frequency from previous generations, it's not impossible though.

Sorry, but it isn't going to be a 23 TF GPU, the super special awesome 7nm Ampere A100 SXM4 was no where near that.

I wouldn't expect it to be more than 20-30% (depends on GPU clocks) faster than the RTX 2080 TI in gaming performance, probably a big improvement in ray tracing perf. though.
 
Last edited:
I dunno, with the recent development of the chunky PSU connector and news that they require 300w I think they are having to make some ground out of nowhere so resorting to plan B rev the frig out of it.
 
g67575 said:
Another fact that supports this theory is that Nvidia only increased the number of shaders by 768 from previous generations (from GTX 980 TI > GTX 1080 TI >RTX 2080 TI).

That would actually put the RTX 3080 TI at 5120‬ Shading units (slightly less than the figure I gave above).

Not sure why there would be a massive increase in clock frequency from previous generations, it's not impossible though.

Sorry, but it isn't going to be a 23 TF GPU, the super special awesome 7nm Ampere A100 SXM4 was no where near that.

I wouldn't expect it to be more than 20-30% (depends on GPU clocks) faster than the RTX 2080 TI in gaming performance, probably a big improvement in ray tracing perf. though.
Click to expand...

Do you know what the 2080 Ti boost freq is on air & water for custom models? And do you think Ampere will see 0 improvement in clock speed? Note: I'm talking about real numbers during games, not what's on the box.
 
Yeah, I'm sure you will see some high clock custom models, with decent cooling (very expensive). the GTX 1080 TI had some impressive overclocked models...

I'm talking about the base model though, there probably will be an improvement in clock speed, but not a drastic one.
 
Kelt said:
That's pretty much just another monitor thread nowadays, full of nits!:p
Click to expand...
Tell you what, you tell me what the best 32" monitor is, and I'll summon the ghost of AdoredTV's reputation to bring you some made up Ampere rumours :p
 
Well there's a lot of rumours on twitter from people that have been 'right before', about high TDP GPUs that would be a massive performance upgrade compared to the RTX 2080 TI.

I seem to remember many of the same people predicting a Nvidia beating Navi card that would be released in 2019, only for AMD to report power usage / design problems with Navi.

Why would Nvidia release a card costing ~$10,000, only to release a more powerful / very similar GPU a bit later in the year, costing perhaps $800-$1000. Companies would never buy Tesla cards again if Nvidia did this.

The most powerful cards are always the Tesla or RTX Titan cards. I guess we might see a very high end Titan card too, perhaps released a bit later?
 
Last edited:
g67575 said:
Why would Nvidia release a card costing ~$10,000, only to release a more powerful / very similar GPU a bit later in the year, costing perhaps $800-$1000. Companies would never buy Tesla cards again if Nvidia did this.
Click to expand...
The pro cards and their price tags aren't about performance vs consumer cards. They're about being certified.
 
Th0nt said:
I dunno, with the recent development of the chunky PSU connector and news that they require 300w I think they are having to make some ground out of nowhere so resorting to plan B rev the frig out of it.
Click to expand...

Read the ampere thread and you'd realise the psu connector rumours are not true.
 
I wouldn't be surprised if this was in the ballpark considering there was that leaked benchmark of a Gpu at around 18tf which would be about right + nvidia are more interested in pushing prices these days over perf. Also going onto Samsung 8nm is not going be as big a jump as tsmc 7nm.
 
You must log in or register to reply here.
Back
Top Bottom