Please note: We are aware of an issue affecting replies on the Arm Community forums, which may not be loading as expected.
We apologize for any inconvenience and appreciate your patience while we investigate and work to resolve the issue.
Thank you for your understanding.
Hi,
I've tried doing some single-buffered benchmarking to avoid VSYNC issues.
So instead of 1)-3), I only want to perform 1) and 2).
Unfortunately, I saw a significant performance drop, and I have the suspicion that glFinish() is not recognized as a frame delimiter by the driver. Do I explicitly need to discard the framebuffer contents, or could this just be an "incomplete glClear()" issue? Also, it would be nice if MGD would also be able to recognize glFinish() as a frame delimiter, is that possible?
thanks!
Ok, doing an explicit glClear() of depth/color/stencil did help, so apparently an incomplete glClear() was responsible for the performance degradation.