How Much Difference Does 4 Years Make in GPUs?
Or it might just be a single item, such as a new solid state drive.
Well, read on to find out how one person’s upgrade choice all panned out.
What card to get?
Stupid name aside, it’s been a veritable workhorse, chugging away at most things sent its way.
That meant sticking with Nvidia and then making another choice Ampere or Ada?
The cheapest models tend to be around 830, which is a small but annoying 4% difference.
The peak FP32 throughput, for example, is 40.3 TFLOPS.
And there’s the L2 cache.
So given what I was going to be using the card for, the choice became simple.
I just went with the cheapest one, which turned out to be aZotac RTX 4070 Ti Trinity OC.
Great expectations for the new card?
The only problem was that the 2080 Super wasn’t included in those tests.
However, it was included in Steve’s reviews for the RTX3070,3080, and3090cards.
Such a significant leap in performance may well end up showing clear signs of a benchmark being system limited.
It would all come down to the individual tests.
Not that I managed to get very far with those when the new card did arrive.
So why is my card a bit better than this?
Here, we’re seeing a peak FP32 rate of 41.4 TFLOPs, an increase of 2.7%.
The 2080 Super was doing the same thing, hence why its figures are higher than expected too.
Turing chips have an L1 cache of 96 kB that is partitioned by the driver.
In Ada Lovelace, there is 128 kB of L1 cache in total but the cache partitioning ismore complex.
It does make me wonder how many other applications aren’t being ‘read’ correctly by the drivers.
The 2080 Super was almost hitting 100%, whereas the 4070 Ti was around 92%.
Perhaps it’s just an oddity of the test itself.
No surprise, of course, but good that it’s working out as expected.
Second analysis with synthetic benchmarks
Testing GPUs is tiresome work.
Since I didn’t want to spend a huge amount of time on this aspect (i.e.
To start with, I used theBlender,V-Ray, and3DMarkbenchmarks.
All nice and simple to use, with no options to worry about or the like.
Nothing gets rendered onto the screen in these tests, it’s all behind-the-scene calculations, so to speak.
But the Monster test clearly shows just how much FP32 performance the 4070 Ti has over the 2080 Super.
TheV-Ray GPU benchmarksare designed to run on Nvidia cards only, as both tests use CUDA.
At least the data provides further confirmation of the compute performance uplift.
I’m not getting more RT features, of course, just more performance.
The benchmarks were done with no upscaling enabled, and then repeated for FSR and/or DLSS set to Balanced.
Lastly, where a game supports it, HDR was enabled.
First up is the game I’ve just mentioned, which uses Ubisoft’sAnvilengine for all of the rendering duties.
A sensible choice really, as it’s not a game that runs very rapidly.
Like Valhalla, there’s no ray tracing, but three upscaling options are provided.
So what’s going on here?
Another Ubisoft title, but this time using their Dunia engine (which began life as an updatedCryEngine).
Ray tracing and upscaling are both options, although the former is only used for shadows and reflections.
It provides a marked improvement to the visuals insome areasbut it’s not something that transforms the whole view.
However,Far Cry 6is another benchmark that can be pretty demanding on the CPU/system.
Without ray tracing, things fare a little better, but the rest of my PC is somewhat restricting.
The game is perfectly fine without having super-sharp shadows all over the place.
That means ray tracing is accessed via API extensions, which should give better performance, in theory.
Another engine, another benchmark.
This time it’s the clunky sequel to Techland’s Dying Light.
The use of RT, especially if it’s across multiple lighting systems (e.g.
Dying Light 2doesn’t really need ultra-high frame rates to be playable though, despite its parkour-n-zombies gameplay.
The 2080 Super obviously was just making pretty wallpapers, one every second or so.
And to finish with, it’s the ray tracing standard that isCyberpunk 2077.
Taking the geometric mean of all the above game benchmarks gives this final assessment.
So, we’re all done, yes?
Time for tea and biscuits?
However, over the years I’d binned the extra PCIe power cables for my Corsair RM1000 PSU.
So that 799 MSRP graphics card ended up being 860 in total (840 for the card).
It’s at least 33% higher than the 3070 Ti and 60% higher than the 2070 Super.
But it was supposed to be a ‘bottom end’ 4080, not a new Super.
One feature that I’ve not mentioned so far is DLSS Frame Generation (a.k.a.DLSS 3).
Switching to the mouse and keyboard makes it far less noticeable, though.
And with that, it’s time to end this upgrade tale.
Time to put it to work!
