On Sat, Aug 31, 2019 at 02:13:05AM -0700, Stephane Eranian wrote: > With PERF_METRICS, the delta is always since previous read. If you read > frequently enough you do not lose precision.
You always loose precision, the whole fraction of 255 looses the fractional part; consider: 255 * 1 / 8 31.87500000000000000000 255 * 7 / 8 223.12500000000000000000 31 * 8 / 255 .97254901960784313725 223 * 8 / 255 6.99607843137254901960 Now, we can make reconstruction use normal 'round-nearest' and then we'd get 1 and 7 back, but there's always cases where you loose things. Also, with 255 being an odd number, round-nearest is actually 'hard' :/
