Methods and Tools for Benchmarking Computer Hardware Performance with Resolume Avenue and Arena
Posted: Tue Oct 24, 2023 22:42
After much searching I am on the quest to figure out how to rate the performance of our video and projection machines.
Of course there are great tools out there for this task such as GeekBench 6 or the Blender Benchmark application.
https://www.geekbench.com/
https://opendata.blender.org/
However, these scores are sort of aggregated and I would like to find a better way to benchmark the performance of the machine when it comes to specifically Resolume Avenue.
Is there a standard way to do this?
So far I have created an 8K (7680 x 4320) Resolume comp at 30 FPS. I was able to mix 3 layers of different 30 second 8K videos in DXV 3 Codec sent out to 8 seperate screens (DataPath Fx4 x2) with various blend modes and it ran at 30 FPS. Awesome! However, this does not tell me where the limit is...
Some of my machines just don't even chop this at all so it's kind of a higher end test.
I was also thinking that I could use conversion times in Alley to benchmark the machines but that only tests conversion and not playback.
My aim is to definitely find the fastest machine of my lot and then to give it a score. That way I can be sure any given machine is the best one possible for the gig.
Has anyone else been down this path and found some good ways to do it?
Or, does the GeekBench 6 score plot close enough to performance in Resolume that it works just fine as a benchmark?
Thank you for any tips!
Of course there are great tools out there for this task such as GeekBench 6 or the Blender Benchmark application.
https://www.geekbench.com/
https://opendata.blender.org/
However, these scores are sort of aggregated and I would like to find a better way to benchmark the performance of the machine when it comes to specifically Resolume Avenue.
Is there a standard way to do this?
So far I have created an 8K (7680 x 4320) Resolume comp at 30 FPS. I was able to mix 3 layers of different 30 second 8K videos in DXV 3 Codec sent out to 8 seperate screens (DataPath Fx4 x2) with various blend modes and it ran at 30 FPS. Awesome! However, this does not tell me where the limit is...
Some of my machines just don't even chop this at all so it's kind of a higher end test.
I was also thinking that I could use conversion times in Alley to benchmark the machines but that only tests conversion and not playback.
My aim is to definitely find the fastest machine of my lot and then to give it a score. That way I can be sure any given machine is the best one possible for the gig.
Has anyone else been down this path and found some good ways to do it?
Or, does the GeekBench 6 score plot close enough to performance in Resolume that it works just fine as a benchmark?
Thank you for any tips!