[Development] Mutex future directions

Thiago Macieira thiago.macieira at intel.com
Sat May 19 10:37:40 CEST 2012


On sábado, 19 de maio de 2012 07.30.56, lars.knoll at 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
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 190 bytes
Desc: This is a digitally signed message part.
URL: <http://lists.qt-project.org/pipermail/development/attachments/20120519/3dd98bb4/attachment.sig>


More information about the Development mailing list