… | |
… | |
4618 | different cpus (or different cpu cores). This reduces dependencies |
4618 | different cpus (or different cpu cores). This reduces dependencies |
4619 | and makes libev faster. |
4619 | and makes libev faster. |
4620 | |
4620 | |
4621 | =item EV_NO_THREADS |
4621 | =item EV_NO_THREADS |
4622 | |
4622 | |
4623 | If defined to be C<1>, libev will assume that it will never be called |
4623 | If defined to be C<1>, libev will assume that it will never be called from |
4624 | from different threads, which is a stronger assumption than C<EV_NO_SMP>, |
4624 | different threads (that includes signal handlers), which is a stronger |
4625 | above. This reduces dependencies and makes libev faster. |
4625 | assumption than C<EV_NO_SMP>, above. This reduces dependencies and makes |
|
|
4626 | libev faster. |
4626 | |
4627 | |
4627 | =item EV_ATOMIC_T |
4628 | =item EV_ATOMIC_T |
4628 | |
4629 | |
4629 | Libev requires an integer type (suitable for storing C<0> or C<1>) whose |
4630 | Libev requires an integer type (suitable for storing C<0> or C<1>) whose |
4630 | access is atomic with respect to other threads or signal contexts. No |
4631 | access is atomic with respect to other threads or signal contexts. No |