A Unified Formalization of

Abshuct-This paper presents a shared-memory model, datarace-free-l, that unifies four earlier models: weak ordering, IX+ lease consistency (with sequentially consistent special operations), the VAX memory model, and data-race-free-o. The most intuitive and commonly assumed shared-memory model, sequential consistency, limits performance. The models of weak ordering, release consistency, the VAX, and data-race-free-0 are based on the common intuition that if programs synchronize explicitly and correctly, then sequential consistency can be guaranteed with high performance. However, each model formalizes this intuition differently and has different advantages and disadvantages with respect to the other models. Data-race-free-l unifies the models of weak ordering, release consistency, the VAX, and data-race-free-0 by formalizing the above intuition in a manner that retains the advantages of each of the four models. A multiprocessor is data-race-free-l if it guarantees sequential consistency to data-race-free programs. Data-race-free-l unifies the four models by providing a programmer’s interface similar to the four models, and by allowing all implementations allowed by the four models. Additionally, datarace-free-l expresses the programmer’s interface more explicitly and formally than weak ordering and the VAX, and allows an implementation not allowed by weak ordering, release consistency, or data-race-free-o. The new implementation proposal for data-race-free-l differs from earlier implementations mainly by permitting the execution of all synchronization operations of a processor even while previous data operations of the processor are in progress. To ensure sequential consistency, two synchronizing processors exchange information to delay later operations of the second processor that conflict with an incomplete data operation of the first processor.