FreeBSD Foundation and iXsystems Collaborate to Further the Cause of High Performance Computing on FreeBSD

Francois Tigeot ftigeot at wolfpond.org
Mon Feb 10 01:51:46 PST 2014


On Sun, Feb 09, 2014 at 02:25:56PM -0800, Matthew Dillon wrote:
>     The cpu limit is only because we are using atomic ops to manipulate
>     the cpumask (thus 64 bits max),

Is this really a big performance gain compared to operations limited to
a single CPU cache line ?

-- 
Francois Tigeot



More information about the Kernel mailing list