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

TL;DR

TurboFFT is a GPU-based FFT implementation that incorporates a two-sided checksum scheme for efficient error detection and correction, maintaining high performance with minimal overhead even under fault conditions.

Contribution

It introduces a novel fault-tolerant FFT design with two-sided checksum encoding, kernel fusion, and template-based code generation, achieving high performance and robustness.

Findings

TurboFFT achieves 23% better performance than existing fault-tolerant FFT schemes.

It incurs only 7-15% overhead compared to cuFFT under error injections.

Demonstrates effective error detection and correction on NVIDIA GPUs.

Abstract

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.