C lean

Abstract

Data races make parallel programs hard to understand. Precise race detection that stops an execution on first occurrence of a race addresses this problem, but it comes with significant overhead. In this work, we exploit the insight that precisely detecting only write-after-write (WAW) and read-afterwrite (RAW) races suffices to provide cleaner semantics for racy programs. We demonstrate that stopping an execution only when these races occur ensures that synchronizationfree-regions appear to be executed in isolation and that their writes appear atomic. Additionally, the undetected racy executions can be given certain deterministic guarantees with efficient mechanisms.We present CLEAN, a system that precisely detects WAW and RAW races and deterministically orders synchronization. We demonstrate that the combination of these two relatively inexpensive mechanisms provides cleaner semantics for racy programs. We evaluate both software-only and hardware-supported CLEAN. The software-only CLEAN runs all Pthread benchmarks from the SPLASH-2 and PARSEC suites with an average 7.8x slowdown. The overhead of precise WAW and RAW detection (5.8x) constitutes the majority of this slowdown. Simple hardware extensions reduce the slowdown of CLEAN's race detection to on average 10.4% and never more than 46.7%.

Parsnip

“…Both schemes implement precise data race detection, however, it is only needed during a short window within which instruction reordering can occur, which simplies the implementation and allows for almost-negligible performance overheads. Other hardware schemes enforce stronger memory consistency models design to preserve sequential consistency or related properties [25,30,47,51]. SC violation detectors ignore data races where at least one access occurs outside of the current detection window.…”

“…An extensive body of prior work on static, dynamic, and hybrid techniques for general data race checking with software or hardware support has yielded suitable assistants for debugging and testing programs with data races (e.g., [1,9,12,15,20,37,46,47,55,58]). Yet existing approaches remain limited by missing true data races, reporting false data races, or incurring large run-time overheads.…”