Joint precision optimization and high level synthesis for approximate computing

Approximate computing has been recognized as an effective low power technique for applications with intrinsic error tolerance, such as image processing and machine learning. Existing efforts on this front are mostly focused on approximate circuit design, approximate logic synthesis or processor arch...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings - ACM IEEE Design Automation Conference s. 1 - 6
Hlavní autoři: Chaofan Li, Wei Luo, Sapatnekar, Sachin S., Jiang Hu
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 07.06.2015
Témata:
Adders
approximate computing
Approximation algorithms
Approximation methods
Computational modeling
High level synthesis
Mathematical model
Optimization
Resource management
ISSN:0738-100X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Approximate computing has been recognized as an effective low power technique for applications with intrinsic error tolerance, such as image processing and machine learning. Existing efforts on this front are mostly focused on approximate circuit design, approximate logic synthesis or processor architecture approximation techniques. This work aims at how to make good use of approximate circuits at system and block level. In particular, approximation aware scheduling, functional unit allocation and binding algorithms are developed for data intensive applications. Simple yet credible error models, which are essential for precision control in the optimizations, are investigated. The algorithms are further extended to include bitwidth optimization in fixed point computations. Experimental results, including those from Verilog simulations, indicate that the proposed techniques facilitate desired energy savings under latency and accuracy constraints.
ISSN:0738-100X
DOI:10.1145/2744769.2744863