Название: Towards Heterogeneous Multi-core Systems-on-Chip for Edge Machine Learning: Journey from Single-core Acceleration to Multi-core Heterogeneous Systems
Автор: Vikram Jain, Marian Verhelst
Издательство: Springer
Год: 2024
Страниц: 199
Язык: английский
Формат: pdf (true)
Размер: 10.4 MB
This book explores and motivates the need for building homogeneous and heterogeneous multi-core systems for Machine Learning to enable flexibility and energy-efficiency. Coverage focuses on a key aspect of the challenges of (extreme-)edge-computing, i.e., design of energy-efficient and flexible hardware architectures, and hardware-software co-optimization strategies to enable early design space exploration of hardware architectures. The authors investigate possible design solutions for building single-core specialized hardware accelerators for machine learning and motivates the need for building homogeneous and heterogeneous multi-core systems to enable flexibility and energy-efficiency. The advantages of scaling to heterogeneous multi-core systems are shown through the implementation of multiple test chips and architectural optimizations. Machine Learning (ML), specifically Deep Learning (DL), has become the workhorse for emerging applications in vision, audio, sensing, and data analytics. State-of-the-art DL models are incredibly costly regarding model size, computational resources required, and the energy consumption of running the models. Owing to their size and complexity, they can only be deployed on large devices like GPUs typically used in cloud servers or data centers. This book focuses on the first aspect of the abovementioned challenges of (extreme-)edge-computing, i.e., the design of energy-efficient and flexible hardware architectures and hardware-software co-optimization strategies to enable early design space exploration of hardware architectures.
