- ...Performance
- This research was supported by NSF grant CCR-9510173,
an NSF CISE Institutional Infrastructure Grant No. CDA-9401142,
and an equipment grant from Digital Equipment Corporation's External Research
Program.
Wagner Meira Jr. is supported by CNPq-Brazil, Grant 200.862/93-6
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
- ...[5].
- We
have implementations that exploit a global clock on the IBM SP2 and the SGI
Challenge. Any implementation based on logical clocks must also record
a local timestamp on each event,
so that the duration of local events can be calculated accurately.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
- ...time.
- This pair-wise approach extends easily
to barriers, which we analyze as a set of pair-wise synchronization
operations between each waiting processor and the last processor
to enter the barrier.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.