On sábado, 19 de maio de 2012 07.30.56, lars.kn...@nokia.com wrote: > * it would be good to see how much of a real world (ie. not with > artificial benchmarks) difference you get due to inlining the mutex code. > Is it really relevant?
Here's a suggestion for one: the Creator C++ parser. I remember Roberto had
some benchmarks for this, though I don't remember if the benchmarks were
threaded as well. I know that the actual parser in Creator is threaded via
QtConcurrent.
Another one might be the threaded scene graph.
I recommend using the Linux perf(1) tool for benchmarking[*]. The benchlib
tickcounter mode works too, but perf provides more information in the results.
I'll be surprised if the cost of the function call shows up as more than 1%
when parsing a medium-sized project (such as a small Qt library like QtSvg or
QtDBus).
[*] I've got a perf-mode for benchlib as a pending feature for Qt 5.1
--
Thiago Macieira - thiago.macieira (AT) intel.com
Software Architect - Intel Open Source Technology Center
Intel Sweden AB - Registration Number: 556189-6027
Knarrarnäsgatan 15, 164 40 Kista, Stockholm, Sweden
signature.asc
Description: This is a digitally signed message part.
_______________________________________________ Development mailing list Development@qt-project.org http://lists.qt-project.org/mailman/listinfo/development
