# PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems

arXiv: https://arxiv.org/abs/2209.08617 · HTML: https://mlsanity.com/paper/2209.08617/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 53 references that are in the map.
- First posted on arXiv 18 Sep 2022.

## Builds on (most cited first, 14 of 14)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Exponential expressivity in deep neural networks through transient chaos](https://mlsanity.com/paper/1606.05340/) (2016)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [Deep Information Propagation](https://mlsanity.com/paper/1611.01232/) (2016)
- [A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1804.03294/) (2018)
- [Mean Field Residual Networks: On the Edge of Chaos](https://mlsanity.com/paper/1712.08969/) (2017)
- [WRPN: Wide Reduced-Precision Networks](https://mlsanity.com/paper/1709.01134/) (2017)
- [Towards Efficient Training for Neural Network Quantization](https://mlsanity.com/paper/1912.10207/) (2019)
- [Progressive Weight Pruning of Deep Neural Networks using ADMM](https://mlsanity.com/paper/1810.07378/) (2018)
- [CoCoPIE: Making Mobile AI Sweet As PIE --Compression-Compilation Co-Design Goes a Long Way](https://mlsanity.com/paper/2003.06700/) (2020)

## Built on by (most cited first, 2 of 2)

- [Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions](https://mlsanity.com/paper/2502.06309/) (2025)
- [ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures](https://mlsanity.com/paper/2607.17091/) (2026)

## Abstract (arXiv)

Processing-in-memory (PIM), an increasingly studied neuromorphic hardware, promises orders of energy and throughput improvements for deep learning inference. Leveraging the massively parallel and efficient analog computing inside memories, PIM circumvents the bottlenecks of data movements in conventional digital hardware. However, an extra quantization step (i.e. PIM quantization), typically with limited resolution due to hardware constraints, is required to convert the analog computing results into digital domain. Meanwhile, non-ideal effects extensively exist in PIM quantization because of the imperfect analog-to-digital interface, which further compromises the inference accuracy. In this paper, we propose a method for training quantized networks to incorporate PIM quantization, which is ubiquitous to all PIM systems. Specifically, we propose a PIM quantization aware training (PIM-QAT) algorithm, and introduce rescaling techniques during backward and forward propagation by analyzing the training dynamics to facilitate training convergence. We also propose two techniques, namely batch normalization (BN) calibration and adjusted precision training, to suppress the adverse effects of non-ideal linearity and stochastic thermal noise involved in real PIM chips. Our method is validated on three mainstream PIM decomposition schemes, and physically on a prototype chip. Comparing with directly deploying conventionally trained quantized model on PIM systems, which does not take into account this extra quantization step and thus fails, our method provides significant improvement. It also achieves comparable inference accuracy on PIM systems as that of conventionally quantized models on digital hardware, across CIFAR10 and CIFAR100 datasets using various network depths for the most popular network topology.