RaceFree

Kai Lu, Xu Zhou, Xiaoping Wang, Wenzhe Zhang, Gen Li
2013 SIGPLAN notices  
Current deterministic systems generally incur large overhead due to the difficulty of detecting and eliminating data races. This paper presents RaceFree, a novel multi-threading runtime that adopts a relaxed deterministic model to provide a data-race-free environment for parallel programs. This model cuts off unnecessary sharedmemory communication by isolating threads in separated memories, which eliminates direct data races. Meanwhile, we leverage the happen-before relation defined by
more » ... ons themselves as one-way communication pipes to perform necessary thread communication. Shared-memory communication is transparently converted to message-passing style communication by our Memory Modification Propagation (MMP) mechanism, which propagates local memory modifications to other threads through the happenbefore relation pipes. The overhead of RaceFree is 67.2% according to our tests on parallel benchmarks.
doi:10.1145/2517327.2442553 fatcat:tkpmgkm5ibahjanupd7copeqby