It seems wise to me to test my code before calling it slow. I assure you I'm not in the habit of writing slow code.
Besides text mode at 80x50x2 is only 800 bytes. You won't see any shearing - I doubt at full speed you will be able to see much.
800 bytes is only 200 DWORDs. This would go fast on a 386 machine let alone a modern CPU.Code:mov edi,[screen_selector] mov esi,[buffer_selector] mov ecx,200d rep movsd