SEGA-DCIM: Design Space Exploration-Guided Automatic Digital CIM Compiler with Multiple Precision Support
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916737065156608 |
|---|---|
| author | Diao, Haikang Zhang, Haoyi Song, Jiahao Luo, Haoyang Lin, Yibo Wang, Runsheng Wang, Yuan Tang, Xiyuan |
| author_facet | Diao, Haikang Zhang, Haoyi Song, Jiahao Luo, Haoyang Lin, Yibo Wang, Runsheng Wang, Yuan Tang, Xiyuan |
| contents | Digital computing-in-memory (DCIM) has been a popular solution for addressing the memory wall problem in recent years. However, the DCIM design still heavily relies on manual efforts, and the optimization of DCIM is often based on human experience. These disadvantages limit the time to market while increasing the design difficulty of DCIMs. This work proposes a design space exploration-guided automatic DCIM compiler (SEGA-DCIM) with multiple precision support, including integer and floating-point data precision operations. SEGA-DCIM can automatically generate netlists and layouts of DCIM designs by leveraging a template-based method. With a multi-objective genetic algorithm (MOGA)-based design space explorer, SEGA-DCIM can easily select appropriate DCIM designs for a specific application considering the trade-offs among area, power, and delay. As demonstrated by the experimental results, SEGA-DCIM offers solutions with wide design space, including integer and floating-point precision designs, while maintaining competitive performance compared to state-of-the-art (SOTA) DCIMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09451 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SEGA-DCIM: Design Space Exploration-Guided Automatic Digital CIM Compiler with Multiple Precision Support Diao, Haikang Zhang, Haoyi Song, Jiahao Luo, Haoyang Lin, Yibo Wang, Runsheng Wang, Yuan Tang, Xiyuan Hardware Architecture Digital computing-in-memory (DCIM) has been a popular solution for addressing the memory wall problem in recent years. However, the DCIM design still heavily relies on manual efforts, and the optimization of DCIM is often based on human experience. These disadvantages limit the time to market while increasing the design difficulty of DCIMs. This work proposes a design space exploration-guided automatic DCIM compiler (SEGA-DCIM) with multiple precision support, including integer and floating-point data precision operations. SEGA-DCIM can automatically generate netlists and layouts of DCIM designs by leveraging a template-based method. With a multi-objective genetic algorithm (MOGA)-based design space explorer, SEGA-DCIM can easily select appropriate DCIM designs for a specific application considering the trade-offs among area, power, and delay. As demonstrated by the experimental results, SEGA-DCIM offers solutions with wide design space, including integer and floating-point precision designs, while maintaining competitive performance compared to state-of-the-art (SOTA) DCIMs. |
| title | SEGA-DCIM: Design Space Exploration-Guided Automatic Digital CIM Compiler with Multiple Precision Support |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2505.09451 |