One thing that fascinates me is how few studies actually compare the effects of compiler flag settings. -O, -O2 and -O3 are known to most Linux users, but there are many many other flags.
Apparently the results differ if the OS and/or the compiler themselves have been compiled using them!
There are a few older tests around on the net, but I haven't seen any new tests for at least three or four years. And Ii have lost my links to the older tests.
It would be nice to have an overview of what effect these gcc compiler flags have on the newer CPUs,
While there is an immense number permutations involved in such a test I recall one which randomized the settings and had some ... Ah, I found a similar (the same?) link: http://www.coyotegulch.com/products/acovea/
Thanks for considering it!
EDIT The ACOVEA was the one I thought of, and it is published under the GNU General Public License (GPL).
Apparently the results differ if the OS and/or the compiler themselves have been compiled using them!
There are a few older tests around on the net, but I haven't seen any new tests for at least three or four years. And Ii have lost my links to the older tests.
It would be nice to have an overview of what effect these gcc compiler flags have on the newer CPUs,
While there is an immense number permutations involved in such a test I recall one which randomized the settings and had some ... Ah, I found a similar (the same?) link: http://www.coyotegulch.com/products/acovea/
Thanks for considering it!
EDIT The ACOVEA was the one I thought of, and it is published under the GNU General Public License (GPL).
Comment