Pith. sign in

Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Analog in-memory computing (AIMC) -- a promising approach for energy-efficient acceleration of deep learning workloads -- computes matrix-vector multiplications (MVMs) but only approximately, due to nonidealities that often are non-deterministic or nonlinear. This can adversely impact the achievable deep neural network (DNN) inference accuracy as compared to a conventional floating point (FP) implementation. While retraining has previously been suggested to improve robustness, prior work has explored only a few DNN topologies, using disparate and overly simplified AIMC hardware models. Here, we use hardware-aware (HWA) training to systematically examine the accuracy of AIMC for multiple common artificial intelligence (AI) workloads across multiple DNN topologies, and investigate sensitivity and robustness to a broad set of nonidealities. By introducing a new and highly realistic AIMC crossbar-model, we improve significantly on earlier retraining approaches. We show that many large-scale DNNs of various topologies, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers, can in fact be successfully retrained to show iso-accuracy on AIMC. Our results further suggest that AIMC nonidealities that add noise to the inputs or outputs, not the weights, have the largest impact on DNN accuracy, and that RNNs are particularly robust to all nonidealities.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing

cs.LG · 2025-06-23 · conditional · novelty 6.0

AnalogNAS-Bench extends NAS-Bench-201 with analog in-memory computing metrics, revealing that architecture rankings under quantization do not transfer to analog noise, and that 3x3 convolutions, pooling, and skip connections aid robustness.

citing papers explorer

Showing 1 of 1 citing paper.

  • AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing cs.LG · 2025-06-23 · conditional · none · ref 18 · internal anchor

    AnalogNAS-Bench extends NAS-Bench-201 with analog in-memory computing metrics, revealing that architecture rankings under quantization do not transfer to analog noise, and that 3x3 convolutions, pooling, and skip connections aid robustness.