Lines Matching refs:relation
330 The most important relation between events is program order (po). You
338 This is inherently a single-CPU relation; two instructions executing
342 po-loc is a sub-relation of po. It links two memory accesses when the
421 memory model cannot assume there is a fixed program order relation
429 We say that two events are linked by a dependency relation when the
544 The reads-from relation (rf) links a write event to a read event when
556 Usage of the rf relation implicitly assumes that loads will always
722 Just like the po relation, co is inherently an ordering -- it is not
724 just like with the rf relation, we distinguish between stores that
737 The from-reads relation (fr) can be a little difficult for people to
762 As with rf, rfi, and rfe, we subdivide the fr relation into fri (when
766 Note that the fr relation is determined entirely by the rf and co
886 though smp_wmb() isn't A-cumulative. The cumul-fence relation is
1007 where the rmw relation links the read and write events making up each
1018 degenerate case). We write this relation as: Z0 ->rmw-sequence Zn.
1022 cumul-fence relation. That is, if we have:
1031 the w-post-bounded relation defined below in the PLAIN ACCESSES AND
1046 "preserved program order") relation, which links the po-earlier
1047 instruction to the po-later instruction and is thus a sub-relation of
1101 includes address dependencies to loads in the ppo relation.
1245 The happens-before relation (hb) links memory accesses that have to
1246 execute in a certain order. hb includes the ppo relation and two
1272 The third relation included in hb is like ppo, in that it only links
1275 cache coherence. The relation is called prop, and it links two events
1372 would generate a cycle in the hb relation: The fence would create a ppo
1374 prop relation would give an hb link from the second load to the first.
1379 The formal definition of the prop relation involves a coe or fre link,
1422 In summary, the fact that the hb relation links memory access events
1426 The LKMM defines yet another relation connected to times of
1435 The propagates-before (pb) relation capitalizes on the special
1507 In summary, the fact that the pb relation links events in the order
1588 rcu-link relation. rcu-link encompasses a very general notion of
1595 The formal definition of the rcu-link relation is more than a little
1597 relation, and the details don't matter unless you want to comb through
1612 that this relation is "inverted": It links the end of the
1615 If we think of the rcu-link relation as standing for an extended
1623 The LKMM goes on to define the rcu-order relation as a sequence of
1639 The rcu-order relation is important because the Grace Period Guarantee
1674 The rcu-fence relation is a simple extension of rcu-order. While
1678 the strong-fence relation links events that are separated by an
1693 Finally, the LKMM defines the RCU-before (rb) relation in terms of
1695 relation was defined in terms of strong-fence. We will omit the
1700 Guarantee by requiring that the rb relation does not contain a cycle.
1722 relation, and R is po-before the grace period S. Thus we have:
1736 discussion of the rcu-link relation earlier) that S and U are related
2128 relation (vis), where X ->vis Y is defined to hold if there is an
2498 various relation must not contain a cycle) doesn't apply to plain
2526 contribute to the ppo relation), but at the moment it seems that this
2538 definition of the prop relation makes the initial coe or fre part
2539 optional, and it doesn't require the events linked by the relation to
2578 relation, they do contribute to it indirectly. Firstly, when there is
2585 to undermine this relation if sufficient care is not taken.