paper-with-me

홈 › Papers

Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs

2021-04-19 · Jack Kosaian, K. V. Rashmi

Neural networks (NNs) are increasingly employed in safety-critical domains and in environments prone to unreliability (e.g., soft errors), such as on spacecraft. Therefore, it is critical to impart fault tolerance to NN inference. Algorithm-based fault tolerance (ABFT) is emerging as an efficient approach for fault tolerance in NNs. We propose an adaptive approach to ABFT for NN inference that exploits untapped opportunities in emerging deployment scenarios. GPUs have high compute-to-memory-bandwidth ratios, while NN layers have a wide range of arithmetic intensities. This leaves some layers compute bound and others memory-bandwidth bound, but current approaches to ABFT do not consider these differences. We first investigate ABFT schemes best suited for each of these scenarios. We then propose intensity-guided ABFT, an adaptive, arithmetic-intensity-guided approach that selects the most efficient ABFT scheme for each NN layer. Intensity-guided ABFT reduces execution-time overhead by 1.09--5.3$\times$ across many NNs compared to traditional approaches to ABFT.

📄 PDF Abstract BibTeX arXiv:2104.09455

Code (1)

Thesys-lab/arithmetic-intensity-guided-abft 공식 구현

Similar Papers 제목 키워드 기반

Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles

2026-09-02 · Mingzhe Du, Anh Tuan Luu, Dong Huang, See-Kiong Ng hf

Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point tolerance, and their verdicts now feed leaderboards and reinforcement-learning rewards. Recent work agrees t…

FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention

2025-04-03 · Huangliang Dai, Shixun Wu, Hairui Zhao, Jiajun Huang 외

Transformer models leverage self-attention mechanisms to capture complex dependencies, demonstrating exceptional performance in various applications. However, the long-duration high-load computations required for model i…

From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips

2026-03-24 · Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag, Allison Seigler 외 arxiv

The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors. While empirical studies indicate that reducing numerical precision can …

Winograd Convolution: A Perspective from Fault Tolerance

2022-02-17 · Xinghua Xue, Haitong Huang, Cheng Liu, Ying Wang 외

Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation. Other than the computing efficiency, we observe it…

A Design Methodology for Fault-Tolerant Computing using Astrocyte Neural Networks

2022-04-06 · Murat Işık, Ankita Paul, M. Lakshmi Varshika, Anup Das

We propose a design methodology to facilitate fault tolerance of deep learning models. First, we implement a many-core fault-tolerant neuromorphic hardware design, where neuron and synapse circuitries in each neuromorphi…

Deep Learning