Em Thu, Feb 26, 2015 at 12:34:04PM -0800, Andi Kleen escreveu: > > Having a nice explanation of the problem helps, as my first reaction to > > this patch was: "What? This is what this tool is supposed to do, to > > compare two versions of a binary, one that is being developed from the > > same source, the other with slight modifications, etc", while the > > description of the patch made it look as this was a feature that was now > > being introduced. > > AFAIK it was actually to compare multiple runs of the same binary > with different setups: e.g. varying number of threads. > > However in the Linux kernel development world it turns out comparing > multiple similar binaries is much more useful.
Surely I am getting old and forgetting things, but when I wrote it, my intent was to do: vi a.c build it perf record a vi a.c # change it build it perf record a perf diff And see if what I did while vi'ing it matched what I thought it would. - Arnaldo -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
