Re: [fpc-devel] rdtscp

2017-10-23 Thread Nikolay Nikolov
On 10/23/2017 02:21 AM, Wolf wrote: On 23/10/17 02:53, Nikolay Nikolov wrote: FPC trunk supports rdtscp. And if you're using a FPC version that doesn't support an instruction, you can always hardcode it with 'db' (make sure you add a comment with the real instruction to keep your code re

Re: [fpc-devel] rdtscp

2017-10-22 Thread Marco van de Voort
In our previous episode, Martok said: > Tangent: On Windows, RDTSC is wrapped by the QueryPerformanceCounter() call. > QPC > incidentally is complicated enough that it is very likely no out-of-order > instructions are pending by the time it gets to actually executing RDTSC, but > with less jitter

Re: [fpc-devel] rdtscp

2017-10-22 Thread Martok
Hi, Am 21.10.2017 um 21:41 schrieb Wolf: > rdtsc cannot do it either. You need to have a CPU capable of > understanding rdtscp. From what I understood, that doesn't give you cycles either, but only the same timestamp intervals RDTSC returns. Tangent: On Windows, RDTSC is wrapped by the QueryPerfo

Re: [fpc-devel] rdtscp

2017-10-22 Thread Nikolay Nikolov
On 10/21/2017 10:41 PM, Wolf wrote: Hi, How do you measure time with a one cycle resolution? EpicTimer clearly does not cut it, and from what I gather , rdtsc cannot do it either. You