HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908845774733312 |
|---|---|
| author | Nazari, Samira Almasi, Mohammad Saeed Taheri, Mahdi Azarpeyvand, Ali Mokhtari, Ali Mahani, Ali Herglotz, Christian |
| author_facet | Nazari, Samira Almasi, Mohammad Saeed Taheri, Mahdi Azarpeyvand, Ali Mokhtari, Ali Mahani, Ali Herglotz, Christian |
| contents | This work presents HAWX, a hardware-aware scalable exploration framework that employs multi-level sensitivity scoring at different DNN abstraction levels (operator, filter, layer, and model) to guide selective integration of heterogeneous AxC blocks. Supported by predictive models for accuracy, power, and area, HAWX accelerates the evaluation of candidate configurations, achieving over 23* speedup in a layer-level search with two candidate approximate blocks and more than (3*106)* speedup at the filter-level search only for LeNet-5, while maintaining accuracy comparable to exhaustive search. Experiments across state-of-the-art DNN benchmarks such as VGG-11, ResNet-18, and EfficientNetLite demonstrate that the efficiency benefits of HAWX scale exponentially with network size. The HAWX hardware-aware search algorithm supports both spatial and temporal accelerator architectures, leveraging either off-the-shelf approximate components or customized designs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16336 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs Nazari, Samira Almasi, Mohammad Saeed Taheri, Mahdi Azarpeyvand, Ali Mokhtari, Ali Mahani, Ali Herglotz, Christian Machine Learning Artificial Intelligence This work presents HAWX, a hardware-aware scalable exploration framework that employs multi-level sensitivity scoring at different DNN abstraction levels (operator, filter, layer, and model) to guide selective integration of heterogeneous AxC blocks. Supported by predictive models for accuracy, power, and area, HAWX accelerates the evaluation of candidate configurations, achieving over 23* speedup in a layer-level search with two candidate approximate blocks and more than (3*106)* speedup at the filter-level search only for LeNet-5, while maintaining accuracy comparable to exhaustive search. Experiments across state-of-the-art DNN benchmarks such as VGG-11, ResNet-18, and EfficientNetLite demonstrate that the efficiency benefits of HAWX scale exponentially with network size. The HAWX hardware-aware search algorithm supports both spatial and temporal accelerator architectures, leveraging either off-the-shelf approximate components or customized designs. |
| title | HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.16336 |