DMP: Deterministic shared memory multiprocessing

Current shared memory multicore and multiprocessor sys-tems are nondeterministic. Each time these systems execute a multithreaded application, even if supplied with the same input, they can produce a different output. This frustrates de-bugging and limits the ability to properly test multithreaded code, becoming a major stumbling block to the much-needed widespread adoption of parallel programming. In this paper we make the case for fully deterministic shared memory multiprocessing (DMP). The behavior of an arbitrary multithreaded program on a DMP system is only a function of its inputs. The core idea is to make inter-thread communication fully deterministic. Previous approaches to coping with nondeterminism in multithreaded programs have focused on replay, a technique useful only for debugging. In contrast, while DMP systems are directly useful for debug-ging by offering repeatability by default, we argue that par-allel programs should execute deterministically in the field as well. This has the potential to make testing more assuring and increase the reliability of deployed multithreaded soft-ware. We propose a range of approaches to enforcing de-terminism and discuss their implementation trade-offs. We show that determinism can be provided with little perfor-mance cost using our architecture proposals on future hard-ware, and that software-only approaches can be utilized on existing systems