# Sorted Weight Sectioning for Energy-Efficient Unstructured Sparse DNNs on Compute-in-Memory Crossbars

arXiv: https://arxiv.org/abs/2410.11298 · HTML: https://mlsanity.com/paper/2410.11298/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing](https://mlsanity.com/paper/2306.12929/) (2023)
- [Post-Training Piecewise Linear Quantization for Deep Neural Networks](https://mlsanity.com/paper/2002.00104/) (2020)
- [Layer-Wise Data-Free CNN Compression](https://mlsanity.com/paper/2011.09058/) (2020)
- [CiMLoop: A Flexible, Accurate, and Fast Compute-In-Memory Modeling Tool](https://mlsanity.com/paper/2405.07259/) (2024)
- [In-memory Associative Processors: Tutorial, Potential, and Challenges](https://mlsanity.com/paper/2203.00662/) (2022)

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

- [Efficient Reprogramming of Memristive Crossbars for DNNs: Weight Sorting and Bit Stucking](https://mlsanity.com/paper/2410.21730/) (2024)
- [MDM: Manhattan Distance Mapping of DNN Weights for Parasitic-Resistance-Resilient Memristive Crossbars](https://mlsanity.com/paper/2511.04798/) (2025)

## Abstract (arXiv)

We introduce textitsorted weight sectioning (SWS): a weight allocation algorithm that places sorted deep neural network (DNN) weight sections on bit-sliced compute-in-memory (CIM) crossbars to reduce analog-to-digital converter (ADC) energy consumption. Data conversions are the most energy-intensive process in crossbar operation. SWS effectively reduces this cost leveraging (1) small weights and (2) zero weights (weight sparsity). DNN weights follow bell-shaped distributions, with most weights near zero. Using SWS, we only need low-order crossbar columns for sections with low-magnitude weights. This reduces the quantity and resolution of ADCs used, exponentially decreasing ADC energy costs without significantly degrading DNN accuracy. Unstructured sparsification further sharpens the weight distribution with small accuracy loss. However, it presents challenges in hardware tracking of zeros: we cannot switch zero rows to other layer weights in unsorted crossbars without index matching. SWS efficiently addresses unstructured sparse models using offline remapping of zeros into earlier sections, which reveals full sparsity potential and maximizes energy efficiency. Our method reduces ADC energy use by 89.5% on unstructured sparse BERT models. Overall, this paper introduces a novel algorithm to promote energy-efficient CIM crossbars for unstructured sparse DNN workloads.