> The code is kernel mode so I do not think the memcopy routine uses uiomove > in this case(I could be wrong). Also this code is multiplatform so > that the general code uses memcopy and developers optimize the code to work > on the different platforms they are in. Speed is not my > concern right now because we can max out the speed of the device we are > copying from. Our problem lies in the CPU utilization. Will > uiomove be better than memcopy in that respect or the same?
Since the restriction is memory bandwidth for the copy, performance is unlikely to be much different. To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
