Date   : Thu, 02 Feb 2017 23:03:09 +0000
From   : jgh@... (J.G.Harston)
Subject: Pi-based second processor - fast, flexible,

John Kortink wrote:
 > So you're clearly starting to measure the overhead there, not
 > the operations themselves. The length of the loops measured
 > should be increased by factors to get a more accurate result.

ClockSp does an initial test and lengthens the loops measured on faster 
systems to avoid running so fast it's trying to time a loop that happens 
in less than 100th second. Each test tends to take around about five 
seconds regardless of nominal platform speed.