When Climate Meets Machine Learning: Edge to Cloud ML Energy Efficiency

A large portion of current cloud and edge workloads feature Machine Learning (ML) tasks, thereby requiring a deep understanding of their energy efficiency. While the holy grail for judging the quality of a ML model has largely been testing accuracy, and only recently its resource usage, neither of t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2021 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED) s. 1
Hlavní autor: Marculescu, Diana
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 26.07.2021
Témata:
Clouds
Energy efficiency
Hardware
hardware-aware ML
Machine learning
Measurement
Mobile handsets
model compression
neural architecture search
quantization
Runtime
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:A large portion of current cloud and edge workloads feature Machine Learning (ML) tasks, thereby requiring a deep understanding of their energy efficiency. While the holy grail for judging the quality of a ML model has largely been testing accuracy, and only recently its resource usage, neither of these metrics translate directly to energy efficiency, runtime, or mobile device battery lifetime. This work uncovers the need for building accurate, platform-specific power and latency models for ML and efficient hardware-aware ML design methodologies, thus allowing machine learners and hardware designers to identify not just the best accuracy ML model configuration, but also those that satisfy given hardware constraints.
DOI:10.1109/ISLPED52811.2021.9502472