Towards an Accurate GPU Data Race Detector

TL;DR

This paper introduces HGRD, a static analysis tool that leverages host code information to accurately detect GPU data races, outperforming existing dynamic and static methods in precision and recall.

Contribution

HGRD is a novel static analysis approach that combines host and GPU code analysis to detect data races with high accuracy and minimal false alarms.

Findings

HGRD detects all true data races missed by prior methods.

HGRD raises no false alarms unlike other static techniques.

HGRD outperforms dynamic techniques like iGUARD in race detection.

Abstract

Data races in GPU programs pose a threat to the reliability of GPU-accelerated software stacks. Prior works proposed various dynamic (runtime) and static (compile-time) techniques to detect races in GPU programs. However, dynamic techniques often miss critical races, as they require the races to manifest during testing. While static ones can catch such races, they often generate numerous false alarms by conservatively assuming values of variables/parameters that cannot ever occur during any execution of the program. We make a key observation that the host (CPU) code that launches GPU kernels contains crucial semantic information about the values that the GPU kernel's parameters can take during execution. Harnessing this hitherto overlooked information helps accurately detect data races in GPU kernel code. We create HGRD, a new state-of-the-art static analysis technique that performs a holistic analysis of both CPU and GPU code to accurately detect a broad set of true races while minimizing false alarms. While SOTA dynamic techniques, such as iGUARD, miss many true races, HGRD misses none. On the other hand, static techniques such as GPUVerify and FaialAA raise tens of false alarms, where HGRD raises none.