On Mon, 7 Oct 2013 12:18:51 PM Lu Mitnick wrote: > I would like to know the performance number for detection of each type of > bug, ie. the execution time when the Valgrind only > detect illegal read/write, or the execution time when the Valgrind only > detect use of uninitialised values ... etc. Is it possible to > check specified bugs? Is this some academic / theoretical exercise? The problem is that the detection of a single type of bug isn't well separated. So the cost of detecting bug type X and the cost of detecting bug type Y is going to have a lot of common factors (all the tracking work).
If its academic, I'd suggest modifying the code to extract the numbers you want to show. It probably won't be very meaningful, but it is what it is. If its not academic, please explain why you are trying to do this (not just what) - some context, so we can provide something that can help you solve your real problem. Brad ------------------------------------------------------------------------------ October Webinars: Code for Performance Free Intel webinars can help you accelerate application performance. Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from the latest Intel processors and coprocessors. See abstracts and register > http://pubads.g.doubleclick.net/gampad/clk?id=60134791&iu=/4140/ostg.clktrk _______________________________________________ Valgrind-users mailing list Valgrind-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/valgrind-users
