ApproxDup: Developing an Approximate Instruction Duplication Mechanism for Efficient SDC Detection in GPGPUs
- 8 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (4) , 1051-1064
Abstract
Nowadays, Selective instruction Duplication (SelDup) is the typical approach to detect Silent Data Corruption (SDC) in GPGPU. However, owing to the up-to-billions fault sites of parallel GPGPU kernel functions, it usually introduces tremendous overhead to perform Fault Injections (FIs) for obtaining the duplication-candidate instruction set (although can be conducted in parallel). Moreover, current SelDup typically considers all SDCs severe and tends to duplicate more instructions. The nontrivial duplication overhead seriously restricts the deployment of current SelDup on resource-constrained systems (e.g., embedded GPGPUs). To address the above challenges, this paper proposes an Approximate instruction Duplication mechanism (ApproxDup) for efficient SDC detection in GPGPUs. Firstly, to replace the expensive FI-based duplication-candidate instructions identified method, we drive out a Machine Learning-based model (SDC-Predictor) for instruction-wise SDC proneness and severity estimation. Our key insight is that instruction type/functionality and instruction dependency set can efficaciously characterize the instruction-wise SDC proneness in GPGPUs. In contrast, the instruction’s original data magnitude, fault propagation range, and error detected features can distinguish its SDC severity. Secondly, incorporating the concept of approximate computing, we propose ApproxDup that preferentially duplicates Severe-SDC-prone instructions while relaxing the detection of minor/detectable SDCs for traditional SelDup overhead reduction. Experimental results exhibit that ApproxDup can cover 92.51% of Severe SDCs while merely increasing 38% of dynamic instructions, which achieves a better tradeoff between reliability and performance compared with the state-of-the-art SelDup. Furthermore, we discuss the effectiveness of the proposed method on different ML models/applications/GPGPU architectures.Keywords
Funding Information
- China Postdoctoral Science Foundation (2023M733566)
- National Natural Science Foundation of China (Grants No.62272190, Grants No.62302190, Grants No.62302479, Grants No.U19A2061)
This publication has 37 references indexed in Scilit:
- Eff-ECC: Protecting GPGPUs Register File With a Unified Energy-Efficient ECC MechanismIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021
- PARIS: Predicting application resilience using machine learningJournal of Parallel and Distributed Computing, 2021
- GPU-Trident: Efficient Modeling of Error Propagation in GPU Programs2020
- G-SEAP: Analyzing and characterizing soft-error aware approximation in GPGPUsFuture Generation Computer Systems, 2020
- Characterizing Accuracy-Aware Resilience of GPGPU Applications2020
- Machine Learning Models for GPU Error Prediction in a Large Scale HPC System2018
- Fault Modeling of Extreme Scale Applications Using Machine Learning2016
- Dealing with the Unknown: Resilience to Prediction Errors2015
- Three-phase time-aware energy minimization with DVFS and unrolling for Chip MultiprocessorsJournal of Systems Architecture, 2012
- Resource allocation robustness in multi-core embedded systems with inaccurate informationJournal of Systems Architecture, 2011