CIMinus: Empowering Sparse DNN Workloads Modeling and Exploration on SRAM-based CIM Architectures

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qi, Yingjie, Yang, Jianlei, Yang, Rubing, Duan, Cenlin, He, Xiaolin, He, Ziyan, Pan, Weitao, Zhao, Weisheng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912720902684672
author Qi, Yingjie
Yang, Jianlei
Yang, Rubing
Duan, Cenlin
He, Xiaolin
He, Ziyan
Pan, Weitao
Zhao, Weisheng
author_facet Qi, Yingjie
Yang, Jianlei
Yang, Rubing
Duan, Cenlin
He, Xiaolin
He, Ziyan
Pan, Weitao
Zhao, Weisheng
contents Compute-in-memory (CIM) has emerged as a pivotal direction for accelerating workloads in the field of machine learning, such as Deep Neural Networks (DNNs). However, the effective exploitation of sparsity in CIM systems presents numerous challenges, due to the inherent limitations in their rigid array structures. Designing sparse DNN dataflows and developing efficient mapping strategies also become more complex when accounting for diverse sparsity patterns and the flexibility of a multi-macro CIM structure. Despite these complexities, there is still an absence of a unified systematic view and modeling approach for diverse sparse DNN workloads in CIM systems. In this paper, we propose CIMinus, a framework dedicated to cost modeling for sparse DNN workloads on CIM architectures. It provides an in-depth energy consumption analysis at the level of individual components and an assessment of the overall workload latency. We validate CIMinus against contemporary CIM architectures and demonstrate its applicability in two use-cases. These cases provide valuable insights into both the impact of sparsity patterns and the effectiveness of mapping strategies, bridging the gap between theoretical design and practical implementation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16368
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CIMinus: Empowering Sparse DNN Workloads Modeling and Exploration on SRAM-based CIM Architectures
Qi, Yingjie
Yang, Jianlei
Yang, Rubing
Duan, Cenlin
He, Xiaolin
He, Ziyan
Pan, Weitao
Zhao, Weisheng
Hardware Architecture
Compute-in-memory (CIM) has emerged as a pivotal direction for accelerating workloads in the field of machine learning, such as Deep Neural Networks (DNNs). However, the effective exploitation of sparsity in CIM systems presents numerous challenges, due to the inherent limitations in their rigid array structures. Designing sparse DNN dataflows and developing efficient mapping strategies also become more complex when accounting for diverse sparsity patterns and the flexibility of a multi-macro CIM structure. Despite these complexities, there is still an absence of a unified systematic view and modeling approach for diverse sparse DNN workloads in CIM systems. In this paper, we propose CIMinus, a framework dedicated to cost modeling for sparse DNN workloads on CIM architectures. It provides an in-depth energy consumption analysis at the level of individual components and an assessment of the overall workload latency. We validate CIMinus against contemporary CIM architectures and demonstrate its applicability in two use-cases. These cases provide valuable insights into both the impact of sparsity patterns and the effectiveness of mapping strategies, bridging the gap between theoretical design and practical implementation.
title CIMinus: Empowering Sparse DNN Workloads Modeling and Exploration on SRAM-based CIM Architectures
topic Hardware Architecture
url https://arxiv.org/abs/2511.16368