软错误上的硬数据：GPGPU中真实世界出错率的大规模评估
Hard Data on Soft Errors: A Large-Scale Assessment of Real-World Error Rates in GPGPU
摘要：
图形处理单元（GPU）在计算化学和其他科学模拟环境中得到了广泛的使用，因为它们相对于传统CPU具有巨大的性能优势。然而，GPU在容错应用中的可靠性在很大程度上尚未得到证实。特别地，图形卡的存储器子系统中缺乏错误检查和校正（ECC）能力已经被引用为GPU被接受为高性能协处理器的障碍，但是这种设计的影响先前没有被量化。在本文中，我们提出MemtestG 80，我们的软件评估内存出错率的NVIDIA G80和GT 200架构的图形卡。此外，我们还展示了通过在Folding@home分布式计算网络上的20，000多台主机上运行MemtestG 80对GPU出错率进行大规模评估的结果。我们在受控环境中对消费级和专用GPGPU硬件进行的控制实验没有发现错误。然而，我们对Folding@home上的显卡的调查发现，在其安装环境中，三分之二的测试GPU显示出可检测的、模式敏感的内存软错误率。我们证明，这些错误持续控制超频和环境代理温度后，但强烈依赖于电路板架构。
英文摘要：
Graphics processing units (GPUs) are gaining widespread use in computational chemistry and other scientific simulation contexts because of their huge performance advantages relative to conventional CPUs. However, the reliability of GPUs in error-intolerant applications is largely unproven. In particular, a lack of error checking and correcting (ECC) capability in the memory subsystems of graphics cards has been cited as a hindrance to the acceptance of GPUs as high-performance coprocessors, but the impact of this design has not been previously quantified. In this article we present MemtestG80, our software for assessing memory error rates on NVIDIA G80 and GT200-architecture-based graphics cards. Furthermore, we present the results of a large-scale assessment of GPU error rate, conducted by running MemtestG80 on over 20,000 hosts on the Folding@home distributed computing network. Our control experiments on consumer-grade and dedicated-GPGPU hardware in a controlled environment found no errors. However, our survey over cards on Folding@home finds that, in their installed environments, two-thirds of tested GPUs exhibit a detectable, pattern-sensitive rate of memory soft errors. We demonstrate that these errors persist after controlling for overclocking and environmental proxies for temperature, but depend strongly on board architecture.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
