Blender 3.3 AMD Radeon HIP vs. NVIDIA CUDA/OptiX Performance

[JEBjames]

Michael

Typo

"modeling" "modelling"

Grammatical errors are innumerable.

Copy-paste here:

https://quillbot.com/grammar-check

[[email protected]]

Interesting that the 6800 and 3070 tend to have similar perf, but the 6800 consumes less. Better perf/watt on red side?

Given that the 6800 doesn't look near max TDP, there's some growth potential.

[Anux]

https://www.phoronix.com/review/radeon-rx6600-linux

Ah sorry mixed that up with the 6700 non XT, sure the 6600 was already there previously.

[Michael]

Baby steps in the correct direction for AMD.!!

Michael, did you ever got a 6900 XT from AMD?

I am nobody but I sent a couple of tweets to some of their accounts pointing that out.

Nope never received any 6900/6950 from AMD, hence why it wasn't tested in this or any other articles... :/

[NeoMorpheus]

Baby steps in the correct direction for AMD.!!

Michael, did you ever got a 6900 XT from AMD?

I am nobody but I sent a couple of tweets to some of their accounts pointing that out.

[Michael]

Yeah but it's slowly getting better.

Michael has a Radeon RX 6600? Haven't seen that in previous benchmarks.

https://www.phoronix.com/review/radeon-rx6600-linux

[Anux]

Wow, AMD looks really bad!

Yeah but it's slowly getting better.

Michael has a Radeon RX 6600? Haven't seen that in previous benchmarks.

[Danny3]

Wow, AMD looks really bad!

[phoronix]

Phoronix: Blender 3.3 AMD Radeon HIP vs. NVIDIA CUDA/OptiX Performance

Earlier this month Blender 3.3 released and in addition to introducing an Intel oneAPI back-end, it's notable for bringing improvements to the AMD HIP back-end for Radeon GPUs. Significant on the AMD side is extending GPU support back to GFX9/Vega. Thus it's a good time for a fresh round of benchmarking for showing how the AMD Radeon HIP performance against that of NVIDIA's existing CUDA and OptiX back-ends.

https://www.phoronix.com/review/blender-33-nvidia-amd