v1v2 (latest)

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

International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2021

19 April 2021

J. Kosaian

K. V. Rashmi

ArXiv (abs)PDF HTML

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

6 / 6 papers shown

Understanding Silent Data Corruption in LLM TrainingAnnual Meeting of the Association for Computational Linguistics (ACL), 2025

297

17 Feb 2025

GCN-ABFT: Low-Cost Online Error Checking for Graph Convolutional NetworksIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024

C. Peltekis

G. Dimitrakopoulos

GNN

186

24 Dec 2024

Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUsInternational Conference on Supercomputing (ICS), 2023

289

01 May 2023

Soft Error Reliability Analysis of Vision Transformers

443

21 Feb 2023

Winograd Convolution: A Perspective from Fault ToleranceDesign Automation Conference (DAC), 2022

181

17 Feb 2022

FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation FunctionsDesign, Automation and Test in Europe (DATE), 2021

227

27 Dec 2021