On quinta-feira, 23 de agosto de 2012 17.49.31, Thiago Macieira wrote: > Here are the partial results for Windows: > https://docs.google.com/spreadsheet/pub?key vVqQ9a3_pIudExQek1hOXRyTVVZZ0t > MN1kzQjdhNGc&gid=1 > > Just like on Linux, the new QMutex is much worse than native and than Qt 4.8 > for the contended case. Both contention cases are showing 700% worse than > Windows native. On Linux, the 1-mutex case was 100% worse but the 2-mutex > case was 1000%. > > I haven't been able to test the new code yet because tst_QMutex crashes > immediately with a failed assertion. I'll need to debug this tomorrow.
I think I've managed to fix those issues. The preliminary results indicate that the new code is now better than even the Windows native. However, I can't prove for certain because, for whatever reason, the benchmark is now taking 97.5 seconds to run -- 1.5 running the test and 96 seconds idling. I must have broken something on my Windows, so I'll do the usual Windows solution: I'll reboot it. But that's all the time I had for Windows this week without losing my sanity. Here's the latest in a series of braindamaged decisions on Windows: https://plus.google.com/photos/108138837678270193032/albums/5781390986666165185/5781390992395600994 (Of course it's something I did. But I don't know what, I don't have the tools to figure out what, and I shouldn't have been allowed to cause that much damage in the first place. My working theory, never to be proven, is that it's related to the git bash shell with colours and using of Ctrl+C in it) -- 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 [email protected] http://lists.qt-project.org/mailman/listinfo/development
