Am 01.05.2014 05:51, schrieb Thomas Bohl:
Am 01.05.2014 03:56, schrieb Jonathan Gray:
It wouldn't hurt to check with md5 -tt and/or a power meter
to see if there is actually a difference between
hw.setperf=0 and hw.setperf=100.
hw.setperf=100
16.5 Watt
# md5 -tt
MD5 time trial. Processing 100000 10000-byte blocks...
Digest = 766a2bb5d24bddae466c572bcabca3ee
Time = 39.389348 seconds
Speed = 25387574.325932 bytes/second
hw.setperf=0
16.9 Watt
# md5 -tt
MD5 time trial. Processing 100000 10000-byte blocks...
Digest = 766a2bb5d24bddae466c572bcabca3ee
Time = 4.672665 seconds
Speed = 214010634.188413 bytes/second
So the CPU actually gets slowed down quite heavily (apm shows 224 MHz).
But the system has a greater power consumption while doing so. (Now
that happens if you buy stuff in a hurry. I was aiming for a 10 Watt
system. My bad!)
Sorry, I mixed up the md5 results.
hw.setperf=100
16.5 Watt
# md5 -tt
MD5 time trial. Processing 100000 10000-byte blocks...
Digest = 766a2bb5d24bddae466c572bcabca3ee
Time = 4.672665 seconds
Speed = 214010634.188413 bytes/second
hw.setperf=0
16.9 Watt
# md5 -tt
MD5 time trial. Processing 100000 10000-byte blocks...
Digest = 766a2bb5d24bddae466c572bcabca3ee
Time = 39.389348 seconds
Speed = 25387574.325932 bytes/second
