parallel processing in Windows

asked 2013-04-11 21:07:09 -0600

hjf
81 ●1 ●1 ●7

updated 2013-04-11 21:07:56 -0600

I developed an application with OpenCV on Linux, using TBB there to exploit the parallel capabilities of opencv (mostly: knnsearch in FLANN and SURF detection). It uses 100% of my cpu when needed, as expected.

I then ported this application to Windows, but it's only using 25% of my quad-core there. I'm using the prebuilt openCV binaries. I read that since 2.4.3, these are compiled using the Concurrency Framework. Aren't SURF and FLANN "concurrency framework aware"?

I don't have a problem compiling from source using TBB if needed, but i'd like to know if this functionality should work outside the box.

edit retag flag offensive close merge delete

add a comment

1 answer

Sort by » oldest newest most voted

answered 2013-04-12 02:41:28 -0600

StevenPuttemans

20029 ●16 ●82 ●207 http://stevenputtemans...

Basically switch to the laters 2.4.5 version. There was an update included in 2.4.4 that does the TBB enabling for you, if the hardware is available. Also tons of functions were optimized for internal parallelization starting from version 2.4.4. So again, switch to a newer version and you won't have to bother with configuring TBB yourself.