arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.02520cs.DC
收藏

TurboFFT:一种在 GPU 上具备容错能力的高性能快速傅里叶变换

TurboFFT: A High-Performance Fast Fourier Transform with Fault Tolerance on GPU

Shixun Wu, Yujia Zhai, Jinyang Liu, Jiajun Huang, Zizhe Jian, Huangliang Dai, Sheng Di, Zizhong Chen, Franck Cappello

AI总结:

TurboFFT 通过双侧校验和方案及内核融合策略,在 GPU 上以平均 7%-15% 的低开销实现 FFT 的静默数据损坏检测与即时纠错,性能优于现有容错 FFT 方案。

摘要:

快速傅里叶变换(FFT)作为众多科学应用中的核心计算,正日益受到可靠性问题的威胁。本文介绍了 TurboFFT,一种高性能 FFT 实现,配备双侧校验和方案,能够高效检测并纠正计算单元中的静默数据损坏。所提出的双侧校验和通过对一批输入信号进行不同线性组合编码来解决错误传播问题,这不仅支持快速的批量错误检测,还能在运行中即时纠错,而无需重新计算。我们在内核、线程和线程块级别探索了双侧校验和设计,并提供了一种可与最先进但闭源的 cuFFT 相竞争的基线 FFT 实现。我们展示了一种内核融合策略,以减轻容错机制引入的计算/内存开销并将其与底层 FFT 计算重叠。我们提出了一种基于模板的代码生成策略,以降低开发成本并支持广泛的输入尺寸和数据类型。在 NVIDIA A100 服务器 GPU 和 Tesla Turing T4 GPU 上的实验结果表明,与闭源库 cuFFT 相比,TurboFFT 提供了具有竞争力或更优越的性能。即使在单精度和双精度下每分钟注入数百次错误,TurboFFT 相比 cuFFT 也仅产生最低限度的开销(平均 7% 至 15%)。与现有容错 FFT 方案相比,TurboFFT 实现了 23% 的性能提升。

英文摘要:

The Fast Fourier Transform (FFT), as a core computation in a wide range of scientific applications, is increasingly threatened by reliability issues. In this paper, we introduce TurboFFT, a high-performance FFT implementation equipped with a two-sided checksum scheme that detects and corrects silent data corruptions at computing units efficiently. The proposed two-sided checksum addresses the error propagation issue by encoding a batch of input signals with different linear combinations, which not only allows fast batched error detection but also enables error correction on-the-fly instead of recomputing. We explore two-sided checksum designs at the kernel, thread, and threadblock levels, and provide a baseline FFT implementation competitive to the state-of-the-art, closed-source cuFFT. We demonstrate a kernel fusion strategy to mitigate and overlap the computation/memory overhead introduced by fault tolerance with underlying FFT computation. We present a template-based code generation strategy to reduce development costs and support a wide range of input sizes and data types. Experimental results on an NVIDIA A100 server GPU and a Tesla Turing T4 GPU demonstrate TurboFFT offers a competitive or superior performance compared to the closed-source library cuFFT. TurboFFT only incurs a minimum overhead (7\% to 15\% on average) compared to cuFFT, even under hundreds of error injections per minute for both single and double precision. TurboFFT achieves a 23\% improvement compared to existing fault tolerance FFT schemes.

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。

↑