Performance Evaluation of Data Race Detection Based on Thread Sharing Analysis With Different Granularities: An Empirical Study

Abstract

Thread Sharing Analysis (TSA) plays an important role in concurrent program testing. Providing a TSA to a data race detector may speed up the runtime logging and improve the performance of data race detection. In this paper, we focus on the empirical study of the performance of data race detection based on TSA with different granularities. First, three granularities are considered, including object, field and ''field + array element''. Then, an empirical study is conducted to evaluate the performance of data race detection based on three dynamic TSA approaches. The results show that data race detection based on the TSA with ''field + array element'' granularity outperforms those with object and field granularities. INDEX TERMS Software testing, concurrent program testing, thread sharing analysis (TSA), data race detection, dynamic analysis

Optimization of static data race detection algorithm based on out-of-order parallel SystemC simulation with array element granularity

“…Although OoO PDES has achieved a more obvious performance improvement compared to the previous simulation methods, there are still many shortcomings. According to different detection methods, it can be divided into three types: static detection, dynamic detection and combination of dynamic and static [8,9] . The static conflict detection algorithm currently applied to OoO PDES is based on field granularity and has a high false positive rate.…”