Efficiently Detecting Races in Cilk Programs That Use Reducer Hyperobjects

Abstract

A multithreaded Cilk program that is ostensibly deterministic may nevertheless behave nondeterministically due to programming errors in the code. For a Cilk program that uses reducers, a general reduction mechanism supported in various Cilk dialects, such programming errors are especially challenging to debug, because the errors can expose the nondeterminism in how the Cilk runtime system manages a reducer.We identify two unique types of races that arise from incorrect use of reducers in a Cilk program and present two algorithms to catch them. The first algorithm, called the Peer-Set algorithm, detects view-read races, which occur when the program attempts to retrieve a value out of a reducer when the read may result a nondeterministic value, such as before all previously spawned subcomputations that might update the reducer have necessarily returned. The second algorithm, called the SP+ algorithm, detects determinacy races, instances where a write to a memory location occurs logically in parallel with another access to that location, even when the raced-on memory locations relate to reducers. Both algorithms are provably correct, asymptotically efficient, and can be implemented efficiently in practice. We have implemented both algorithms in our prototype race detector, Rader. When running Peer-Set, Rader incurs a geometric-mean multiplicative overhead of 2.32 over running the benchmark without instrumentation. When running SP+, Rader incurs a geometric-mean multiplicative overhead of 16.76.

Efficient race detection with futures

“…Subsequently, Xu et al [59] propose a race detector for two-dimensional dags with asymptotically optimal parallel running time. Lee and Schardl [34] propose a sequential race detector for fork-join computations with reductions, where the computation dag is almost series-parallel except when reductions are performed.…”

“…When neither of the component SP-dags have a non-SP edge (lines [29][30][31][32] or if only one of them has a non-SP edge(lines [41][42][43][44][45][46], no new attached sets are created. The only case where (at most two) additional attached sets are created is if both subcomponents have non-SP edges (lines [33][34][35][36][37][38][39][40]. The total number of such sync nodes is O(k).…”

Processor-Oblivious Record and Replay

“…PORRidge uses the DRF assumption to allow it to track lock operations only. However, the same conceptual record and replay techniques could be applied to racy programs, by using race detection tools (e.g., [25,30,31,45]) to identify races and indicate to PORRidge additional sources of non-determinism (tools like Chimera adopt similar approaches [44]).…”