# Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer

arXiv: https://arxiv.org/abs/2505.14303 · HTML: https://mlsanity.com/paper/2505.14303/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 44 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 10 of 10)

- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays](https://mlsanity.com/paper/2104.02184/) (2021)
- [On the Accuracy of Analog Neural Network Inference Accelerators](https://mlsanity.com/paper/2109.01262/) (2021)
- [Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals](https://mlsanity.com/paper/2201.12861/) (2022)
- [CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory Paradigms](https://mlsanity.com/paper/2301.07486/) (2022)
- [Mapping of CNNs on multi-core RRAM-based CIM architectures](https://mlsanity.com/paper/2309.03805/) (2023)
- [Neural Network-Hardware Co-design for Scalable RRAM-based BNN Accelerators](https://mlsanity.com/paper/1811.02187/) (2018)
- [TDO-CIM: Transparent Detection and Offloading for Computation In-memory](https://mlsanity.com/paper/2007.00060/) (2020)
- [Evaluating the Scalability of Binary and Ternary CNN Workloads on RRAM-based Compute-in-Memory Accelerators](https://mlsanity.com/paper/2505.07490/) (2025)

## Built on by (most cited first, 1 of 1)

- [Mixed-Precision Training and Compilation for RRAM-based Computing-in-Memory Accelerators](https://mlsanity.com/paper/2601.21737/) (2026)

## Abstract (arXiv)

Using Resistive Random Access Memory (RRAM) crossbars in Computing-in-Memory (CIM) architectures offers a promising solution to overcome the von Neumann bottleneck. Due to non-idealities like cell variability, RRAM crossbars are often operated in binary mode, utilizing only two states: Low Resistive State (LRS) and High Resistive State (HRS). Binary Neural Networks (BNNs) and Ternary Neural Networks (TNNs) are well-suited for this hardware due to their efficient mapping. Existing software projects for RRAM-based CIM typically focus on only one aspect: compilation, simulation, or Design Space Exploration (DSE). Moreover, they often rely on classical 8 bit quantization. To address these limitations, we introduce CIM-Explorer, a modular toolkit for optimizing BNN and TNN inference on RRAM crossbars. CIM-Explorer includes an end-to-end compiler stack, multiple mapping options, and simulators, enabling a DSE flow for accuracy estimation across different crossbar parameters and mappings. CIM-Explorer can accompany the entire design process, from early accuracy estimation for specific crossbar parameters, to selecting an appropriate mapping, and compiling BNNs and TNNs for a finalized crossbar chip. In DSE case studies, we demonstrate the expected accuracy for various mappings and crossbar parameters. CIM-Explorer can be found on GitHub.