An Improved Template for Approximate Computing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916954252509184 |
|---|---|
| author | Rezaalipour, Morteza Costa, Francesco Biasion, Marco Otoni, Rodrigo Constantinides, George A. Pozzi, Laura |
| author_facet | Rezaalipour, Morteza Costa, Francesco Biasion, Marco Otoni, Rodrigo Constantinides, George A. Pozzi, Laura |
| contents | Deploying neural networks on edge devices entails a careful balance between the energy required for inference and the accuracy of the resulting classification. One technique for navigating this tradeoff is approximate computing: the process of reducing energy consumption by slightly reducing the accuracy of arithmetic operators. In this context, we propose a methodology to reduce the area of the small arithmetic operators used in neural networks - i.e., adders and multipliers - via a small loss in accuracy, and show that we improve area savings for the same accuracy loss w.r.t. the state of the art. To achieve our goal, we improve on a boolean rewriting technique recently proposed, called XPAT, where the use of a parametrisable template to rewrite circuits has proved to be highly beneficial. In particular, XPAT was able to produce smaller circuits than comparable approaches while utilising a naive sum of products template structure. In this work, we show that template parameters can act as proxies for chosen metrics and we propose a novel template based on parametrisable product sharing that acts as a close proxy to synthesised area. We demonstrate experimentally that our methodology converges better to low-area solutions and that it can find better approximations than both the original XPAT and two other state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06162 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Improved Template for Approximate Computing Rezaalipour, Morteza Costa, Francesco Biasion, Marco Otoni, Rodrigo Constantinides, George A. Pozzi, Laura Machine Learning Hardware Architecture B.2.1; B.6.3 Deploying neural networks on edge devices entails a careful balance between the energy required for inference and the accuracy of the resulting classification. One technique for navigating this tradeoff is approximate computing: the process of reducing energy consumption by slightly reducing the accuracy of arithmetic operators. In this context, we propose a methodology to reduce the area of the small arithmetic operators used in neural networks - i.e., adders and multipliers - via a small loss in accuracy, and show that we improve area savings for the same accuracy loss w.r.t. the state of the art. To achieve our goal, we improve on a boolean rewriting technique recently proposed, called XPAT, where the use of a parametrisable template to rewrite circuits has proved to be highly beneficial. In particular, XPAT was able to produce smaller circuits than comparable approaches while utilising a naive sum of products template structure. In this work, we show that template parameters can act as proxies for chosen metrics and we propose a novel template based on parametrisable product sharing that acts as a close proxy to synthesised area. We demonstrate experimentally that our methodology converges better to low-area solutions and that it can find better approximations than both the original XPAT and two other state-of-the-art approaches. |
| title | An Improved Template for Approximate Computing |
| topic | Machine Learning Hardware Architecture B.2.1; B.6.3 |
| url | https://arxiv.org/abs/2509.06162 |