Hi, Steve. Thank you for your reply. I am now trying to implemente such an event like TickEvent to reschedule itselt at the end of every cycle. I hope this works as the data is quite intensive and the I/O device should have a pipeline to deal with the data that may arrive in every cycle. Thank you.
在 2010年3月12日 下午10:21，Steve Reinhardt <[email protected]>写道： > The right way to do this is to have the event reschedule itself every > time it runs for the proper latency until the next clock tick of the > device you're simulating. (Note that you don't want to schedule every > 1 tick, you need to base the latency off a clock parameter.) See the > TickEvent in src/cpu/simple/atomic.{cc,hh} for an example; the event > gets rescheduled on the last line of the tick() function. > > Steve > > 2010/3/12 Veydan Wu <[email protected]>: > > I just want my I/O device to run in parallel with CPU. Does the CPUs > run > > over and over? More specifically speaking, CPU may send something to the > I/O > > device to handle, but the time is not fixed. So it is better to let the > > device keep running and when it receive data ( by the write() function ), > it > > can handle it. I do want the handling invoked within the write() > function, I > > want it to act like a real hardware device. Is there any way I can do > this? > > Thank you very much! > > > > Weidan >
_______________________________________________ m5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
