To satisfy prohibitively massive computational requirements of current deep Convolutional Neural Networks (CNNs), CNN-specific accelerators are widely deployed in large-scale systems. Caused by high-energy neutrons and α-particle strikes, soft error may lead to catastrophic failures when CNN is deployed on high integration density accelerators. As CNNs become ubiquitous in mission-critical domains, ensuring the reliable execution of CNN accelerators in the presence of soft errors is increasingly essential. In this article, we propose to Re cycle I dle P rocessing E lements (PEs) in the CNN accelerator for vulnerable filters soft error detection (ReIPE). Considering the error-sensitivity of filters, ReIPE first carries out a filter-level gradient analysis process to replace fault injection for fast filter-wise error resilience estimation. Then, to achieve maximal reliability benefits, combining the hardware-level systolic array idleness and software-level CNN filter-wise error resilience profile, ReIPE preferentially duplicated loads the most vulnerable filters onto systolic array to recycle idle-column PEs for opportunistically redundant execution (error detection). Exploiting the data reuse properties of accelerators, ReIPE incorporates the error detection process into the original computation flow of accelerators to perform real-time error detection. Once the error is detected, ReIPE will trigger a correction round to rectify the erroneous output. Experimental results performed on LeNet-5, Cifar-10-CNN, AlexNet, ResNet-20, VGG-16, and ResNet-50 exhibit that ReIPE can cover 96.40% of errors while reducing 75.06% performance degradation and 67.79% energy consumption of baseline dual modular redundancy on average. Moreover, to satisfy the reliability requirements of various application scenarios, ReIPE is also applicable for pruned, quantized, and Transformer-based models, as well as portable to other accelerator architectures.

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 article proposes an approximate instruction duplication (ApproxDup) mechanism for efficient SDC detection in GPGPUs. First, to replace the expensive FI-based duplication-candidate instructions identified method, we drive out a machine learning (ML)-based model (SDC-predictor) for instructionwise SDC proneness and severity estimation. Our key insight is that instruction type/functionality and instruction dependency set can efficaciously characterize the instructionwise SDC proneness in GPGPUs. In contrast, the instruction’s original data magnitude, fault propagation range, and error detected features can distinguish its SDC severity. Second, 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.

As GPUs become ubiquitous in large-scale general purpose HPC systems (GPGPUs), ensuring the reliable execution of such systems in the presence of soft errors is increasingly essential. To provide insights into how resilient GPU programs are toward soft errors, researchers typically rely on random Fault Injection (FI) to evaluate the tolerance of programs. However, it is expensive to obtain a statistically significant resilience profile and not suitable to identify all the error-critical fault sites of GPU programs.