Scholarlink

<p>The rapid proliferation of Artificial Intelligence applications necessitates scalable solutions that perform efficiently under real-world constraints. Heterogeneous accelerators combining specialized analog and digital units offer localized, energy-efficient neural network computations. However, achieving optimal performance on these platforms requires balancing energy efficiency and model accuracy through optimized neural network layer mapping. To this end, we introduce Mixed-Precision Supernetwork, a unified framework for training mixed-precision supernetworks that seamlessly integrate quantized layers with analog noise-sensitive layers. Mixed-Precision Supernetwork incorporates a mapping-aware adaptation strategy, dynamically optimizing layer assignments while refining the neural network via hardware-aware architecture search. This dual innovation establishes Mixed-Precision Supernetwork as a groundbreaking approach for deploying deep learning models efficiently on heterogeneous accelerators. On average, Mixed-Precision Supernetwork produces mappings &#xa0;~&#xa0;2.2&#xa0;× faster and achieves a &#xa0;~&#xa0;3.4% increase in model accuracy over a fully analog approach, while improving energy-efficiency by mapping up to 80% of the model’s weights to analog hardware while maintaining full-precision accuracy.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Supernetwork-based efficient mapping of deep learning applications to mixed-precision hardware using model adaptation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月27日

查看全文
  • Hadjer Benmeziane,
  • Corey Lammie,
  • Irem Boybat,
  • Malte Rasch,
  • Manuel Le Gallo,
  • Athanasios Vasilopoulos,
  • Hsinyu Tsai,
  • Geoffrey W. Burr,
  • Vijay Narayanan,
  • Kaoutar El Maghraoui,
  • Abu Sebastian

摘要

The rapid proliferation of Artificial Intelligence applications necessitates scalable solutions that perform efficiently under real-world constraints. Heterogeneous accelerators combining specialized analog and digital units offer localized, energy-efficient neural network computations. However, achieving optimal performance on these platforms requires balancing energy efficiency and model accuracy through optimized neural network layer mapping. To this end, we introduce Mixed-Precision Supernetwork, a unified framework for training mixed-precision supernetworks that seamlessly integrate quantized layers with analog noise-sensitive layers. Mixed-Precision Supernetwork incorporates a mapping-aware adaptation strategy, dynamically optimizing layer assignments while refining the neural network via hardware-aware architecture search. This dual innovation establishes Mixed-Precision Supernetwork as a groundbreaking approach for deploying deep learning models efficiently on heterogeneous accelerators. On average, Mixed-Precision Supernetwork produces mappings  ~ 2.2 × faster and achieves a  ~ 3.4% increase in model accuracy over a fully analog approach, while improving energy-efficiency by mapping up to 80% of the model’s weights to analog hardware while maintaining full-precision accuracy.