Re: [fedora-arm] Performance test of X64 compared to arm
On Fri, 30 May 2014, Gordan Bobic wrote:
That'll be very dependant on the exact application, and compiler.
If
you just want a very rough data point I guess you could benchmark a
sha512sum loop on a large file on tmpfs generated from /dev/urandom.
It's as meaningless a number as most, but a lot less meaningless than
BogoMIPS - all that measures is how fast the CPU can idle, which in
most cases nowdays is going to be the same as the CPU clock speed.
Actually the bogomips is now calibrated with a timer, regardless of the
CPU clock speed. The printing of the bogomips value has therefore been
removed since it is even more meaningless than it used to be.
See https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?i...
Nicolas