Benchmarking of overall performance (more than one
Logged In: NO
did the job on V3.1.1 source...
where can I poste it!!!
Logged In: YES
This feature was delayed because on most SMP platform one
can just multiply the single CPU result by the number of
processors (core loop runs totally in primary cache).
Nevertheless this is not true for hi-end non-symmetric
systems like SGI Origin (supported from v3.2.3).
Now we need this feature.
Log in to post a comment.