PANDA: Accelerating Single-Source Value Flow Defect Detection Via Parallel Computing

Static value flow analysis is essential for single-source value flow defect detection (such as null pointer dereference); however, its practical application is limited by the performance overhead of high-precision analysis. Although researchers have attempted to leverage multi-core computing resources to enhance analysis efficiency, existing approaches encounter significant challenges in parallel scalability due to complex data dependencies and the indivisible nature of source points. This paper presents PANDA, a parallel high-precision method for single-source value flow defect detection. The core innovation of PANDA lies in decoupling the strong dependencies between static value flow analysis steps, transforming single-source value flow analysis into two parallelizable algorithms: function summary preprocessing and compositional query-based defect analysis. Experimental evaluation demonstrates that PANDA achieves high detection precision on the Juliet test Suite and attains up to 11.31x speedup in processing large-scale projects. Furthermore, PANDA exhibits adaptability to various defect types, including divide-by zero-error detection.