Vectorizing posit operations on RISC-V for faster deep neural networks: experiments and comparison with ARM SVE
Open Access
- 31 July 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Neural Computing & Applications
- Vol. 33 (16), 10575-10585
- https://doi.org/10.1007/s00521-021-05814-0
Abstract
No abstract availableFunding Information
- Università di Pisa
This publication has 16 references indexed in Scilit:
- Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and OpportunitiesIEEE Signal Processing Magazine, 2020
- Fast deep neural networks for image processing using posits and ARM scalable vector extensionJournal of Real-Time Image Processing, 2020
- A Fast Approximation of the Hyperbolic Tangent When Using Posit Numbers and Its Application to Deep Neural NetworksPublished by Springer Science and Business Media LLC ,2020
- Fast Approximations of Activation Functions in Deep Neural Networks when using Posit ArithmeticSensors, 2020
- Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving ApplicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- PositNN Framework: Tapered Precision Deep Learning Inference for the EdgePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Bfloat16 Processing for Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Deep Positron: A Deep Neural Network Using the Posit Number SystemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Parameterized Posit Arithmetic Hardware GeneratorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Exploiting Posit Arithmetic for Deep Neural Networks in Autonomous Driving ApplicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018