[Interest] Slow event loop performance on i.MX53

[Robert Daniels]

I'm trying to understand if the performance I'm seeing with the event loop is 'normal' or 'abnormal'.  I have two embedded devices each running Qt - one is a i.MX53 and the other is a i.MX6 quadcore with all cores disabled except cpu0.

I've run the events benchmark test on both (from qtbase/tests/benchmarks/corelib/kernel/events) and these are the results:

i.MX53
---------
********* Start testing of EventsBench *********
Config: Using QtTest library 5.5.0, Qt 5.5.0 (arm-little_endian-ilp32-eabi shared (dynamic) release build; by GCC 4.8.4)
PASS   : EventsBench::initTestCase()
PASS   : EventsBench::noEvent()
RESULT : EventsBench::noEvent():
     0.000037 msecs per iteration (total: 79, iterations: 2097152)
PASS   : EventsBench::sendEvent(no eventfilter)
RESULT : EventsBench::sendEvent():"no eventfilter":
     0.00024 msecs per iteration (total: 63, iterations: 262144)
PASS   : EventsBench::sendEvent(eventfilter)
RESULT : EventsBench::sendEvent():"eventfilter":
     0.00031 msecs per iteration (total: 82, iterations: 262144)
PASS   : EventsBench::postEvent(first time, no eventfilter)
RESULT : EventsBench::postEvent():"first time, no eventfilter":
     21 msecs per iteration (total: 87, iterations: 4)
PASS   : EventsBench::postEvent(no eventfilter)
RESULT : EventsBench::postEvent():"no eventfilter":
     20 msecs per iteration (total: 83, iterations: 4)
PASS   : EventsBench::postEvent(eventfilter)
RESULT : EventsBench::postEvent():"eventfilter":
     20 msecs per iteration (total: 83, iterations: 4)
PASS   : EventsBench::cleanupTestCase()
Totals: 8 passed, 0 failed, 0 skipped, 0 blacklisted
********* Finished testing of EventsBench *********


i.MX6
---------
********* Start testing of EventsBench *********
Config: Using QtTest library 5.4.1, Qt 5.4.1 (arm-little_endian-ilp32-eabi shared (dynamic) release build; by GCC 4.8.4)
PASS   : EventsBench::initTestCase()
PASS   : EventsBench::noEvent()
RESULT : EventsBench::noEvent():
     0.000030 msecs per iteration (total: 63, iterations: 2097152)
PASS   : EventsBench::sendEvent(no eventfilter)
RESULT : EventsBench::sendEvent():"no eventfilter":
     0.00017 msecs per iteration (total: 93, iterations: 524288)
PASS   : EventsBench::sendEvent(eventfilter)
RESULT : EventsBench::sendEvent():"eventfilter":
     0.00024 msecs per iteration (total: 63, iterations: 262144)
PASS   : EventsBench::postEvent(first time, no eventfilter)
RESULT : EventsBench::postEvent():"first time, no eventfilter":
     3.0 msecs per iteration (total: 96, iterations: 32)
PASS   : EventsBench::postEvent(no eventfilter)
RESULT : EventsBench::postEvent():"no eventfilter":
     3.0 msecs per iteration (total: 97, iterations: 32)
PASS   : EventsBench::postEvent(eventfilter)
RESULT : EventsBench::postEvent():"eventfilter":
     3.0 msecs per iteration (total: 98, iterations: 32)
PASS   : EventsBench::cleanupTestCase()
Totals: 8 passed, 0 failed, 0 skipped, 0 blacklisted
********* Finished testing of EventsBench *********


>From this test it looks like sendEvent is ~1.3 times slower on the i.MX53 and postEvent is ~6.5 times slower on the i.MX53.

Is this to be expected or do I have something misconfigured somewhere?

Thanks,

Robert Daniels

________________________________

Ce message, ainsi que tous les fichiers joints à ce message, peuvent contenir des informations sensibles et/ ou confidentielles ne devant pas être divulguées. Si vous n'êtes pas le destinataire de ce message (ou que vous recevez ce message par erreur), nous vous remercions de le notifier immédiatement à son expéditeur, et de détruire ce message. Toute copie, divulgation, modification, utilisation ou diffusion, non autorisée, directe ou indirecte, de tout ou partie de ce message, est strictement interdite.
Se désabonner: Si vous souhaitez être retiré de notre liste de diffusion, s'il vous plaît envoyer vos coordonnées à CASL.unsubscribe at legrand.ca<mailto:casl.unsubscribe at legrand.ca> et indiquer quels sont les messages que vous ne souhaitez plus recevoir.


This e-mail, and any document attached hereby, may contain confidential and/or privileged information. If you are not the intended recipient (or have received this e-mail in error) please notify the sender immediately and destroy this e-mail. Any unauthorized, direct or indirect, copying, disclosure, distribution or other use of the material or parts thereof is strictly forbidden.
Unsubscribe: If you would like to be removed from our mailing list, please send your contact information to CASL.unsubscribe at legrand.ca<mailto:casl.unsubscribe at legrand.ca> and indicate what messages you no longer wish to receive.