On sexta-feira, 10 de janeiro de 2014 12:04:23, Koehne Kai wrote: > And here are the results: > > PASS : CatLogBench::qWarningPrintf1() > RESULT : CatLogBench::qWarningPrintf1(): > 0.0010 msecs per iteration (total: 67, iterations: 65536) > PASS : CatLogBench::qWarningPrintf2() > RESULT : CatLogBench::qWarningPrintf2(): > 0.0013 msecs per iteration (total: 90, iterations: 65536) > PASS : CatLogBench::qWarningStream() > RESULT : CatLogBench::qWarningStream(): > 0.0016 msecs per iteration (total: 54, iterations: 32768) > PASS : CatLogBench::qCWarningStream() > RESULT : CatLogBench::qCWarningStream(): > 0.0018 msecs per iteration (total: 59, iterations: 32768) > PASS : CatLogBench::qCWarningPrintf() > RESULT : CatLogBench::qCWarningPrintf(): > 0.0010 msecs per iteration (total: 69, iterations: 65536) > PASS : CatLogBench::cleanupTestCase() > Totals: 7 passed, 0 failed, 0 skipped > > So, there is of course some measurable overhead, but I wouldn't say it > disqualifies the streaming variant per se
For more statistically-valid benchmark results:
1) make sure the total run time is at least half a second per test function
(those ran for 50 ms)
2) make sure the CPU is locked to performance mode and Turbo is disabled:
# tee <<<performance /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
# cut -f2 -d' '
/sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies | \
tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq
(doesn't work on Linux 3.12 with the new intel_idle driver)
3) you may want to run with the perf counter on Linux to get actual CPU
cycles. Pass -minimumtotal to a suitable value to get a runtime of half a
second.
4) Run it 6 to 10 times and average out. Use the -csv logger mode so you can
easily import into a spreadsheet. https://codereview.qt-project.org/74321
--
Thiago Macieira - thiago.macieira (AT) intel.com
Software Architect - Intel Open Source Technology Center
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
