[
Date Prev][
Date Next][
Thread Prev][
Thread Next][
Date Index][
Thread Index]
[
List Home]
Re: [ptp-dev] How does SDM do the scalability problem
|
I agree that supporting dyninst would be desirable. I don't think
MRNet is needed for this though, is it?
Greg
On Jan 16, 2007, at 4:43 PM, Craig Rasmussen wrote:
Yes, it was a heavy sells job. However, there may be synergy with
dyninst. It would be a lot easier to track down hot-spots in code
if you were able to do dynamic instrumentation, rather that
static. The user doesn't really want to stop and recompile code to
add loop level instrumentation, for example. It would be much
cleaner to stop at a break point in the debugger, dynamically
modify the binary to change instrumentation, and continue execution.
Craig
On Jan 16, 2007, at 3:14 PM, Greg Watson wrote:
They've been hawking this stuff for years.
Greg
On Jan 16, 2007, at 3:00 PM, Craig Rasmussen wrote:
On Jan 16, 2007, at 2:49 PM, Craig Rasmussen wrote:
I'm talking with Bart Miller and he asked how the debugger
scales. He wonders if MRNet (multicast reduction network might
be applicable).
There are several papers in the middleware section from the
address below that sound interesting in relation to debugging.
http://www.paradyn.org/html/publications-by-category.html#middleware
Craig
_______________________________________________
ptp-dev mailing list
ptp-dev@xxxxxxxxxxx
https://dev.eclipse.org/mailman/listinfo/ptp-dev
_______________________________________________
ptp-dev mailing list
ptp-dev@xxxxxxxxxxx
https://dev.eclipse.org/mailman/listinfo/ptp-dev
_______________________________________________
ptp-dev mailing list
ptp-dev@xxxxxxxxxxx
https://dev.eclipse.org/mailman/listinfo/ptp-dev