dorsal/arxiv
View SchemaDS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models
| Authors | Kunming Shao, Liang Zhao, Jiangnan Yu, Zhipeng Liao, Xiaomeng Wang, Yi Zou, Tim Kwang-Ting Cheng, Chi-Ying Tsui |
|---|---|
| Categories | |
| ArXiv ID | 2601.06724vv1 |
| URL | https://arxiv.org/abs/2601.06724 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Stochastic computing (SC) offers hardware simplicity but suffers from low throughput, while high-throughput Digital Computing-in-Memory (DCIM) is bottlenecked by costly adder logic for matrix-vector multiplication (MVM). To address this trade-off, this paper introduces a digital stochastic CIM (DS-CIM) architecture that achieves both high accuracy and efficiency. We implement signed multiply-accumulation (MAC) in a compact, unsigned OR-based circuit by modifying the data representation. Throughput is enhanced by replicating this low-cost circuit 64 times with only a 1x area increase. Our core strategy, a shared Pseudo Random Number Generator (PRNG) with 2D partitioning, enables single-cycle mutually exclusive activation to eliminate OR-gate collisions. We also resolve the 1s saturation issue via stochastic process analysis and data remapping, significantly improving accuracy and resilience to input sparsity. Our high-accuracy DS-CIM1 variant achieves 94.45% accuracy for INT8 ResNet18 on CIFAR-10 with a root-mean-squared error (RMSE) of just 0.74%. Meanwhile, our high-efficiency DS-CIM2 variant attains an energy efficiency of 3566.1 TOPS/W and an area efficiency of 363.7 TOPS/mm^2, while maintaining a low RMSE of 3.81%. The DS-CIM capability with larger models is further demonstrated through experiments with INT8 ResNet50 on ImageNet and the FP8 LLaMA-7B model.
{
"annotation_id": "28d008fc-37dd-49d2-9770-c6d0cef463ad",
"date_created": "2026-02-17T05:53:07.818000Z",
"date_modified": "2026-02-17T05:53:07.818000Z",
"file_hash": "5b34b0272636c8ae194305444218581ffe9ba8f4911cd61a63969f13ff36d183",
"private": false,
"record": {
"abstract": "Stochastic computing (SC) offers hardware simplicity but suffers from low throughput, while high-throughput Digital Computing-in-Memory (DCIM) is bottlenecked by costly adder logic for matrix-vector multiplication (MVM). To address this trade-off, this paper introduces a digital stochastic CIM (DS-CIM) architecture that achieves both high accuracy and efficiency. We implement signed multiply-accumulation (MAC) in a compact, unsigned OR-based circuit by modifying the data representation. Throughput is enhanced by replicating this low-cost circuit 64 times with only a 1x area increase. Our core strategy, a shared Pseudo Random Number Generator (PRNG) with 2D partitioning, enables single-cycle mutually exclusive activation to eliminate OR-gate collisions. We also resolve the 1s saturation issue via stochastic process analysis and data remapping, significantly improving accuracy and resilience to input sparsity. Our high-accuracy DS-CIM1 variant achieves 94.45% accuracy for INT8 ResNet18 on CIFAR-10 with a root-mean-squared error (RMSE) of just 0.74%. Meanwhile, our high-efficiency DS-CIM2 variant attains an energy efficiency of 3566.1 TOPS/W and an area efficiency of 363.7 TOPS/mm^2, while maintaining a low RMSE of 3.81%. The DS-CIM capability with larger models is further demonstrated through experiments with INT8 ResNet50 on ImageNet and the FP8 LLaMA-7B model.",
"arxiv_id": "2601.06724",
"authors": [
"Kunming Shao",
"Liang Zhao",
"Jiangnan Yu",
"Zhipeng Liao",
"Xiaomeng Wang",
"Yi Zou",
"Tim Kwang-Ting Cheng",
"Chi-Ying Tsui"
],
"categories": [
"cs.AR",
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models",
"url": "https://arxiv.org/abs/2601.06724",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "1d092006-390a-4633-afc9-3f8c9db938eb",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}