Nondeterminator-3 : a provably good data-race detector that runs in parallel

Abstract

This thesis describes the implementation of a provably good data-race detector, called the Nondeterminator-3, which runs efficiently in parallel. A data race occurs in a multithreaded program when two logically parallel threads access the same location while holding no common locks and at least one of the accesses is a write. The Nondeterminator-3 checks for data races in programs coded in Cilk [3, 10], a shared-memory multithreaded programming language. A key capability of data-race detectors is in determining the series-parallel (SP) relationship between two threads. The Nondeterminator-3 is based on a provably good parallel SP-maintenance algorithm known as SP-hybrid [2]. For a program with n threads, T1 work, and critical-path length To, the SP-hybrid algorithm runs in O((T1/P + PTO) lg n) expected time when executed on P processors. A data-race detector must also maintain an access-history, which consists of, for each shared memory location, a representative subset of memory accesses to that location. The Nondeterminator-3 uses an extension of the ALL-SETS [4] access-history algorithm used by its serially running predecessor, the Nondeterminator-2. First, the ALL-SETS algorithm was extended to correctly support the inlet feature of Cilk.

(cont.) This extension increases the memory-access cost by only a constant factor. Then, this extended ALL-SETS algorithm was parallelized, so that it can be combined with the SP-hybrid algorithm to obtain a data-race detector. Assuming that the cost of locking the access-history can be ignored, this parallelization also inflates the memory-access cost by only a constant factor. I tested the Nondeterminator-3 on several programs to verify the accuracy of the implementation. I have also observed that the Nondeterminator-3 achieves good speed-up when run on a multiprocessor machine.