Towards Standardized Evaluation of GPU Memory Safety with GMSBench
GMSBench provides 149 CUDA tests covering spatial, temporal, and concurrency GPU memory errors, exposing detection gaps in Compute Sanitizer.
GMSBench is a GPU memory safety benchmark comprising 149 self-contained CUDA tests spanning spatial, temporal, and concurrency errors across different GPU memory spaces and execution scenarios. The authors evaluate NVIDIA's Compute Sanitizer across multiple GPU architectures using the suite, exposing gaps in its detection coverage. The benchmark offers a standardized foundation for comparative evaluation of GPU memory safety mechanisms.
- 149 CUDA tests cover spatial, temporal, and concurrency memory errors
- Benchmark spans different GPU memory spaces and execution scenarios
- Compute Sanitizer evaluated across multiple GPU architectures
- Suite exposes detection coverage gaps in existing tools
- Vendors
- NVIDIA
- Products
- GMSBenchCompute Sanitizer
From the original article
1 min read at arxiv.orgAs GPUs become increasingly integral to high-performance computing and machine learning, ensuring memory safety in GPU programs has become crucial for reliable and secure execution. However, evaluating GPU memory safety techniques remains challenging due to the lack of comprehensive and standardized benchmarks.
By Saurabh Singh · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.