On 17 Aug 2012, at 19:35, Greg Ercolano wrote:
On 08/17/12 05:06, MacArthur, Ian (SELEX GALILEO, UK) wrote:
Just for kicks'n'giggles I ported the code to WinXP using the
QueryPerformanceCounter() API to get timings, and I get...
[..]
ian.macarthur@DESDAF599172 /d/examples/qix-win-times
$
On 08/18/12 11:56, Ian MacArthur wrote:
That first run of 109ms shows the overhead of pulling the binary off
disk,
and the subsequent runs are shaving off 100ms because they're obviously
running
from the disk cache, such that it's only 10ms.
Huh! That's odd - but makes
On 18 Aug 2012, at 20:25, Greg Ercolano wrote:
And probably need to break out strace or etc. (as I assume Matthias did!)
and see where the time is really going anyway.
Write/read caching is done at the kernel level, so I don't think you'll
see
any of that with strace(1)
On 08/18/12 13:28, Ian MacArthur wrote:
On 18 Aug 2012, at 20:25, Greg Ercolano wrote:
And probably need to break out strace or etc. (as I assume Matthias did!)
and see where the time is really going anyway.
Write/read caching is done at the kernel level, so I don't think you'll
This topic from http://www.fltk.org/str.php?L2866
I test on suse 12, and the result is:
roland@linux-8ssh:/work/fltk-1.3.0/test ./button
New control cost 0(ms)
Show window cost 341(ms)
roland@linux-8ssh:/work/fltk-1.3.0/test ./button
New control cost 0(ms)
Show window cost 250(ms)
I test on suse 12, and the result is:
roland@linux-8ssh:/work/fltk-1.3.0/test ./button
New control cost 0(ms)
Show window cost 341(ms)
roland@linux-8ssh:/work/fltk-1.3.0/test ./button
New control cost 0(ms)
Show window cost 250(ms)
roland@linux-8ssh:/work/fltk-1.3.0/test ./button
New
Just in case anyone fancies playing along at home, and did not see the original
posts in the STR, here's the version of the test code I'm currently using,
based on the OP's post but tweaked to build on my system, and a small Makefile
to build it with...
--- source (qix.cxx) ---
The show cost varies a bit, maybe as low as 30ms or as high
as 40ms, but never so long as 200ms...
The monitor refresh is 60Hz, so that possibly sets a lower bound
of about 17ms for the screen to show anyway.
Note that I'm running this in a X server on a WinXP machine,
the actual Linux box
The show cost varies a bit, maybe as low as 30ms or as high
as 40ms, but never so long as 200ms...
The monitor refresh is 60Hz, so that possibly sets a lower bound
of about 17ms for the screen to show anyway.
Note that I'm running this in a X server on a WinXP machine,
the actual
On 17.08.2012, at 14:06, MacArthur, Ian (SELEX GALILEO, UK)
ian.macart...@selexgalileo.com wrote:
Just in case anyone fancies playing along at home, and did not see the
original posts in the STR, here's the version of the test code I'm
currently using, based on the OP's post but tweaked to
On 08/17/12 05:06, MacArthur, Ian (SELEX GALILEO, UK) wrote:
Just for kicks'n'giggles I ported the code to WinXP using the
QueryPerformanceCounter() API to get timings, and I get...
[..]
ian.macarthur@DESDAF599172 /d/examples/qix-win-times
$ ./qix
New control cost 0.02(ms)
Show window cost
11 matches
Mail list logo
