The bug appears to be syncing to vblank, I get multiples of 30 fps for all tests.
Running glmark2 --off-screen gets the expected fps, so I do not think this is a critical performance bug. There is a bug in the way measurements are performed though, but I don't think the actual performance changed.
The bug appears to be syncing to vblank, I get multiples of 30 fps for all tests.
Running glmark2 --off-screen gets the expected fps, so I do not think this is a critical performance bug. There is a bug in the way measurements are performed though, but I don't think the actual performance changed.