AdAM: Adaptive Fault-Tolerant Approximate Multiplier for Edge DNN Accelerators
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910354279235584 |
|---|---|
| author | Taheri, Mahdi Cherezova, Natalia Nazari, Samira Rafiq, Ahsan Azarpeyvand, Ali Ghasempouri, Tara Daneshtalab, Masoud Raik, Jaan Jenihhin, Maksim |
| author_facet | Taheri, Mahdi Cherezova, Natalia Nazari, Samira Rafiq, Ahsan Azarpeyvand, Ali Ghasempouri, Tara Daneshtalab, Masoud Raik, Jaan Jenihhin, Maksim |
| contents | In this paper, we propose an architecture of a novel adaptive fault-tolerant approximate multiplier tailored for ASIC-based DNN accelerators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02936 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AdAM: Adaptive Fault-Tolerant Approximate Multiplier for Edge DNN Accelerators Taheri, Mahdi Cherezova, Natalia Nazari, Samira Rafiq, Ahsan Azarpeyvand, Ali Ghasempouri, Tara Daneshtalab, Masoud Raik, Jaan Jenihhin, Maksim Artificial Intelligence Hardware Architecture Machine Learning In this paper, we propose an architecture of a novel adaptive fault-tolerant approximate multiplier tailored for ASIC-based DNN accelerators. |
| title | AdAM: Adaptive Fault-Tolerant Approximate Multiplier for Edge DNN Accelerators |
| topic | Artificial Intelligence Hardware Architecture Machine Learning |
| url | https://arxiv.org/abs/2403.02936 |