Late Breaking Results: Leveraging Approximate Computing for Carbon-Aware DNN Accelerators
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912214751903744 |
|---|---|
| author | Panteleaki, Aikaterini Maria Balaskas, Konstantinos Zervakis, Georgios Amrouch, Hussam Anagnostopoulos, Iraklis |
| author_facet | Panteleaki, Aikaterini Maria Balaskas, Konstantinos Zervakis, Georgios Amrouch, Hussam Anagnostopoulos, Iraklis |
| contents | The rapid growth of Machine Learning (ML) has increased demand for DNN hardware accelerators, but their embodied carbon footprint poses significant environmental challenges. This paper leverages approximate computing to design sustainable accelerators by minimizing the Carbon Delay Product (CDP). Using gate-level pruning and precision scaling, we generate area-aware approximate multipliers and optimize the accelerator design with a genetic algorithm. Results demonstrate reduced embodied carbon while meeting performance and accuracy requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Late Breaking Results: Leveraging Approximate Computing for Carbon-Aware DNN Accelerators Panteleaki, Aikaterini Maria Balaskas, Konstantinos Zervakis, Georgios Amrouch, Hussam Anagnostopoulos, Iraklis Hardware Architecture The rapid growth of Machine Learning (ML) has increased demand for DNN hardware accelerators, but their embodied carbon footprint poses significant environmental challenges. This paper leverages approximate computing to design sustainable accelerators by minimizing the Carbon Delay Product (CDP). Using gate-level pruning and precision scaling, we generate area-aware approximate multipliers and optimize the accelerator design with a genetic algorithm. Results demonstrate reduced embodied carbon while meeting performance and accuracy requirements. |
| title | Late Breaking Results: Leveraging Approximate Computing for Carbon-Aware DNN Accelerators |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2502.00286 |