Hal Murray via devel writes:
> Please play with it and let me know if you find anything interesting.
Asus TinkerBoard:
--8<---------------cut here---------------start------------->8---
tinkerboard1:~/ntpsec$ ./build/main/attic/clocks
res avg min dups CLOCK
1 526 291 CLOCK_REALTIME
10000000 442 10000097 -48 CLOCK_REALTIME_COARSE
1 518 291 CLOCK_MONOTONIC
1 526 291 CLOCK_MONOTONIC_RAW
1 728 583 CLOCK_BOOTTIME
Histogram: CLOCK_REALTIME, 5 ns per bucket, 1000000 samples.
ns hits
291 23140
581 976804
871 3
53 samples were bigger than 1541.
--8<---------------cut here---------------end--------------->8---
The timer is reported to run at the 24Mhz system base clock frequency by
dmesg, so there seems to be an access or tick possible only every 7
clocks, perhaps in order to synchronize between all consumers.
rasPi 3B+:
--8<---------------cut here---------------start------------->8---
raspberrypi5:~/ntpsec $ ./build/main/attic/clocks
res avg min dups CLOCK
1 107 104 CLOCK_REALTIME
10000000 62 9999948 -5 CLOCK_REALTIME_COARSE
1 96 52 CLOCK_MONOTONIC
1 411 364 CLOCK_MONOTONIC_RAW
1 588 572 CLOCK_BOOTTIME
Histogram: CLOCK_REALTIME, 5 ns per bucket, 1000000 samples.
ns hits
104 793559
154 206422
204 1
259 1
17 samples were bigger than 1354.
--8<---------------cut here---------------end--------------->8---
The usual 52ns granularity we know from all multicore rasPi.
Regards,
Achim.
--
+<[Q+ Matrix-12 WAVE#46+305 Neuron microQkb Andromeda XTk Blofeld]>+
SD adaptations for Waldorf Q V3.00R3 and Q+ V3.54R2:
http://Synth.Stromeko.net/Downloads.html#WaldorfSDada
_______________________________________________
devel mailing list
devel@ntpsec.org
http://lists.ntpsec.org/mailman/listinfo/devel
