Evolve (GPU Benchmark)

[Jasper Bekkers]

If API reported % really is based some threshold determined by the manufacturer (as your quote suggests), this is useful information to me. For instance I'd like to know if my fan is running at or above what NVIDIA considers to be 100%.

Most of these things are useful to someone, and I think part of a what makes a benchmark nice to use is getting all the geeky low-level stats that folks care about. I won't promise to add it, but I'll bring up with the team that at least one person asked about it ;-).

 

[homerdog]

Most of these things are useful to someone, and I think part of a what makes a benchmark nice to use is getting all the geeky low-level stats that folks care about. I won't promise to add it, but I'll bring up with the team that at least one person asked about it ;-).

Oh it's not a big deal. I was just throwing in my 2 cents. Not trying to add to your workload

 

[vjPiedPiper]

I'd love to see some comparison of TAA upscalers.
Obviously FSR3 and XeSS dp4? have a pathway that will run on any hardware and should generate comparable outputs across all systems.
But also i'd like to see the impact of upscalers too.
frametime for rendering @ 1080, vs 1080 + FSR/XeSS/DLSS upscale to 1440/4K etc.
If you want to get really advanced you could potentially do comparison of the different TAA methods too.

But it would be great to know the time in ms. impact of FSR3 1440-4k updcale on RDNA4 vs RDNA3 GPU, or even a NV 5x, and 4x.
As we move towards more tensor operations in the rendering workflow, ie. neural shaders,
This should be an easy way to provide some kind of performance numbers for this parts of modern chips.

 

[Jasper Bekkers]

I'd love to see some comparison of TAA upscalers.
Obviously FSR3 and XeSS dp4? have a pathway that will run on any hardware and should generate comparable outputs across all systems.
But also i'd like to see the impact of upscalers too.
frametime for rendering @ 1080, vs 1080 + FSR/XeSS/DLSS upscale to 1440/4K etc.
If you want to get really advanced you could potentially do comparison of the different TAA methods too.

We would also love to see this and it's something we have on our list as well. The big issue with it is that in practice it's quite difficult to test properly since not all obvious metrics make sense. Stay tuned!

We did submit our first post launch patch which to contains some of the fixes discussed above! If you got a copy through the app stores they should have updated already!

Evolve

www.evolvebenchmark.com