Updated the patch with the suggestions by Gedare. Tests on real hardware yield the same frequency results as returned by FreeBSD on the same hardware. Also, subsequent calibrations only differ by <1 kHz.
I would like to backport this fix to RTEMS5. The corresponding ticket is here: https://devel.rtems.org/ticket/4456 Best regards, Jan Jan Sommer (1): bsps/i386: Update calibration of TSC to be more accurate bsps/i386/pc386/clock/ckinit.c | 71 ++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 33 deletions(-) -- 2.17.1 _______________________________________________ devel mailing list devel@rtems.org http://lists.rtems.org/mailman/listinfo/devel