Extending the RISC-V ISA for Efficient RNN-based 5G Radio Resource Management
Authors:
Preprint
Abstract
Radio Resource Management (RRM) in 5G mobile communication is a challenging problem for which Recurrent Neural Networks (RNN) have shown promising results. Accelerating the compute-intensive RNN inference is therefore of utmost importance. Programmable solutions are desirable for effective 5G-RRM top cope with the rapidly evolving landscape of RNN variations. In this paper, we investigate RNN inference acceleration by tuning both the instruction set and micro-architecture of a micro-controller-class open-source RISC-V core. We couple HW extensions with software optimizations to achieve an overall improvement in throughput and energy efficiency of 15$\times$ and 10$\times$ w.r.t. the baseline core on a wide range of RNNs used in various RRM tasks.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- PULP-NN: accelerating quantized neural networks on parallel ultra-low-power RISC-V processorsPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2019
- Survey and Benchmarking of Machine Learning Accelerators2019
- Deep Learning for Radio Resource Allocation in Multi-Cell NetworksIEEE Network, 2019
- Artificial Intelligence Defined 5G Radio Access NetworksIEEE Communications Magazine, 2019
- Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks2018
- Deep Power Control: Transmit Power Control Scheme Based on Convolutional Neural NetworkIEEE Communications Letters, 2018
- Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless NetworksIEEE Transactions on Cognitive Communications and Networking, 2018
- Sustainable green networking: exploiting degrees of freedom towards energy-efficient 5G systemsWireless Networks, 2017
- 5G Ultra-Dense Cellular NetworksIEEE Wireless Communications, 2016
- Optimal power allocation for green cognitive radio: fractional programming approachIET Communications, 2013