Like Gerhard I checked the speed of lcms 1.12 and 1.13 conversions (16bit sRGB to printer output profile):
lcms 1.12 7.0 M pix/sec
lcms 1.13 9.0 M pix/sec
The computer used is equipped with an AMD XP 2800+ processor (2.1GHz Barton).
I did compile my ‘own’ lib using Borland cbuilder, version 6, optimized for Pentium Pro processor.
Another data point: on a 2.5 GHz P4 Xeon I get 1.2 and 2.2 Mpix/sec for lcms 1.12 and 1.13. My benchmark was
time tifficc -w -oprofile.icc test.tif fred.tif
where profile is an HP inkjet printer profile and test.tif is a 65 Mpix 16 bit sRGB image. Built with gcc 2.95.3, -O2.
Maybe the difference is float handling? My ancient gcc is too dumb to generate SSE2 so I guess it's using the very clunky x87 float instructions.
Again, congratulations on the impressive speed up Marti.
John
------------------------------------------------------- This SF.Net email is sponsored by: Oracle 10g Get certified on the hottest thing ever to hit the market... Oracle 10g. Take an Oracle 10g class now, and we'll give you the exam FREE. http://ads.osdn.com/?ad_id149&alloc_id?66&op=click _______________________________________________ Lcms-user mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/lcms-user
