Leveraging Highly Approximated Multipliers in DNN Inference
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_ | 1866913622801776640 |
|---|---|
| author | Zervakis, Georgios Frustaci, Fabio Spantidi, Ourania Anagnostopoulos, Iraklis Amrouch, Hussam Henkel, Jörg |
| author_facet | Zervakis, Georgios Frustaci, Fabio Spantidi, Ourania Anagnostopoulos, Iraklis Amrouch, Hussam Henkel, Jörg |
| contents | In this work, we present a control variate approximation technique that enables the exploitation of highly approximate multipliers in Deep Neural Network (DNN) accelerators. Our approach does not require retraining and significantly decreases the induced error due to approximate multiplications, improving the overall inference accuracy. As a result, our approach enables satisfying tight accuracy loss constraints while boosting the power savings. Our experimental evaluation, across six different DNNs and several approximate multipliers, demonstrates the versatility of our approach and shows that compared to the accurate design, our control variate approximation achieves the same performance, 45% power reduction, and less than 1% average accuracy loss. Compared to the corresponding approximate designs without using our technique, our approach improves the accuracy by 1.9x on average. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16757 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Highly Approximated Multipliers in DNN Inference Zervakis, Georgios Frustaci, Fabio Spantidi, Ourania Anagnostopoulos, Iraklis Amrouch, Hussam Henkel, Jörg Hardware Architecture Machine Learning In this work, we present a control variate approximation technique that enables the exploitation of highly approximate multipliers in Deep Neural Network (DNN) accelerators. Our approach does not require retraining and significantly decreases the induced error due to approximate multiplications, improving the overall inference accuracy. As a result, our approach enables satisfying tight accuracy loss constraints while boosting the power savings. Our experimental evaluation, across six different DNNs and several approximate multipliers, demonstrates the versatility of our approach and shows that compared to the accurate design, our control variate approximation achieves the same performance, 45% power reduction, and less than 1% average accuracy loss. Compared to the corresponding approximate designs without using our technique, our approach improves the accuracy by 1.9x on average. |
| title | Leveraging Highly Approximated Multipliers in DNN Inference |
| topic | Hardware Architecture Machine Learning |
| url | https://arxiv.org/abs/2412.16757 |