Ampere Arrives!
Here’s a side-by-side specification comparison between the RTX 3080, 2080 and 2080 Ti.
Point is, you could’t make a meaningful CUDA core count comparison between different generations.
Comparing the memory configuration is a more straightforward affair.
The RTX 2080 Ti has an 11 GB memory buffer, while the RTX 3080 offers 10 GB.
But enough about all that, it’s time to get into the blue bar graphs.
Not bad at all, but not the 80% we suspect many of you were expecting to see.
We should note the margins were identical on our Core i9-10900K test system.
We saw the same frame rates on our 10900K test system.
Those are some pretty solid gains.
Moving on to Gears 5, we see “mild” performance gains at 1440p.
An 18% boost from the 2080 Ti and 37% over the standard 2080.
And of course, they only get better at 4K.
The RTX 3080 was a whopping 43% faster than the 2080 Ti, a massive performance uplift.
It’s also 83% faster than the 2080 and 92% faster than the 1080 Ti.
WithAssassin’s Creed Odysseywe’re back to milder gains at 1440p.
Next up we haveMetro Exodusand the 3950X does become a problem in this title.
Again, 50% remains an impressive gain.
The data is accurate, but without more information can be somewhat misleading.
And here is more information.
We’ll discuss this further, but for now let’s move on to Wolfenstein: Youngblood.
Fairly typical gains there for 1440p.
Once more we can see the Ampere GPU come to life at the 4K resolution.
It’s also 58% faster than the 1080 Ti and 113% faster than the vanilla 1080.
Those are far more impressive gains and makes Ampere a tremendous replacement at the same price point.
So the RTX 3080 does suck down a lot of power to output all that raw performance.
And while that’s a lot of power, technically it is still more efficient.
After that point the GPU peaked at just 77C and maintained a core clock speed of around 1830 MHz.
The deltas are not that much different, the RTX 3080 is just faster to begin with.
Using only DLSS sees a 16% performance boost in the RTX 2080.
So let’s see if things change much at 4K.
For comparison the RTX 2080 Ti saw a 49% drop.
We’ll test more games in the weeks to come, of course.
As far as we can tell, CPU bottlenecking alone is not the explanation.
The 2x FP32 design can only be fully utilized at 4K and beyond.
This is because at 4K the portion of the render time per frame is heavier on FP32 shaders.
The fact that the RTX 3080 simply excels at 4K gaming could be seen as the cherry on top.
In the current market the GeForce RTX 3080 is an excellent value product.
We’re looking forward to that, though clearly Nvidia has upped the ante on this generation.
As for ray tracing and DLSS, our opinion on that hasn’t changed.
I personally would have not bought an RTX 2080, but I would buy an RTX 3080.
