Processing preferences produce preposterous performance

Topaz Video AI Bugs and Issues
1

…on Apple Silicon Macs. Here are 3 issues which can easily be reproduced on a Mac Studio M1 Max when upscaling 720x576 x 2 using Artemis LQ:

  1. Reducing memory allocation can increase performance significantly
  2. Regardless of whether CPU or “GPU” (M1/2) is selected, it’s the memory allocation which determines if the GPU or CPU ends up being used for processing
  3. If the CPU is being used for processing (intentionally or not) then “Low Power” mode has no effect on performance

All issues are not only contrary to common sense, they are contrary to the descriptions in the Topaz support article at:

The screenshot illustrates point 2 and shows the woeful waste of processing resources.

Andy

TVAI Example
TVAI Example2560×1440 390 KB

3

Processing on M1/M2 Macs is always Neural Engine(NE) first, in almost all cases the NE has similar performance to the GPU at a fraction of power, so it is favored. On the M1/M2 Macs since everything is on a single chip, selecting CPU or M1/M2 will have the same internal selections.

  1. This seems like a bug. It would be great if you can provide more information about this problem. Can you send me logs with memory set to 100% and whatever lower number that is giving you better performance.
  2. Memory allocations do not determine the device. But lowering the memory generates smaller pieces leading to more devices being used.
  3. Running in low power mode disables the use of GPU, so this observation is correct.

All the layers cannot be run on the GPU and there are certain inter frame dependencies that restrict full utilization of hardware with lower resolution inputs. If you want higher GPU usage use a higher resolution input or run multiple processes.

1 Like