Messages in this thread | | | Subject | Re: [RFC PATCH] posix-cpu-timers: optimize calling thread_group_cputime() | From | Peter Zijlstra <> | Date | Fri, 12 Jun 2009 13:09:46 +0200 |
| |
On Fri, 2009-06-12 at 12:39 +0200, Stanislaw Gruszka wrote: > - times->utime = cputime_add(times->utime, t->utime); > - times->stime = cputime_add(times->stime, t->stime); > - times->sum_exec_runtime += t->se.sum_exec_runtime; > + if (mask & TG_CPUCLOCK_UTIME) > + times->utime = cputime_add(times->utime, t->utime); > + if (mask & TG_CPUCLOCK_STIME) > + times->stime = cputime_add(times->stime, t->stime); > + if (mask & TG_CPUCLOCK_SCHED) > + times->sum_exec_runtime += t->se.sum_exec_runtime;
Does adding 3 branches really make it faster? Since you're bound to want at least one, I would expect the cacheline to be hot (assuming all three variables live in the same cacheline -- if not, they should be!), so all you're avoiding is the addition.
| |