Reproduce “An Investigation on Numerical Bugs in GPU Programs Towards Automated Bug Detection” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ravishka Rathnasuriya, Nidhi Majoju, Zihe Song, Wei Yang
The authors study numerical bugs in GPU programs and present GPU-NBDetect, a prototype detector. They classify 397 numerical bugs among 906 GPU bug reports, then generate or mutate inputs and compare GPU outputs with CPU counterparts using checks. In evaluation across four libraries, it detected 226 bugs in 186 functions; developers confirmed 60, so detections are not all verified defects.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.