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.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Logged In: NO
did the job on V3.1.1 source...
where can I poste it!!!
Djip
Logged In: YES
user_id=180260
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.