RISC-V Resource-Constrained Cores: A Survey and Energy Comparison
Authors:
- 13 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Resource-Constrained electronic devices targeting IoT applications need a microcontroller to control their operation, and hence this microcontroller should be energy efficient to increase battery life. One of the emerging open-source processors ISA is RISC-V; as an open-source, it provides a great opportunity for innovation and creativity in designing processor cores. This study targets to survey open-source RISC-V cores and classify them as high-performance and resource-constrained. Afterward, we shortlist the most optimized cores for resource-constrained devices. Seven shortlisted cores are implemented using an ASIC prototyping platform as a unified technology and are compared using resource utilization and energy consumption profile to find the most energy efficient core. We proposed a method to evaluate the energy consumption using power and performance values. Results showed Ibex core to have the best energy consumption characteristics with 8.7 Coremark iterations/mJ over the ASIC prototyping platform.Keywords
This publication has 13 references indexed in Scilit:
- A Catalog and In-Hardware Evaluation of Open-Source Drop-In Compatible RISC-V Softcore Processors2019
- PULP-NN: A Computing Library for Quantized Neural Network inference at the edge on RISC-V Based Parallel Ultra Low Power Clusters2019
- A PULP-based Parallel Power Controller for Future Exascale Systems2019
- A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-DronesIEEE Internet of Things Journal, 2019
- Design and Implementation of a Dynamic Information Flow Tracking Architecture to Secure a RISC-V Core for IoT Applications2018
- Mr. Wolf: A 1 GFLOP/s Energy-Proportional Parallel Ultra Low Power SoC for IOT Edge Processing2018
- GAP-8: A RISC-V SoC for AI at the Edge of the IoT2018
- Hardware accelerator for boosting convolution computation in image classification applications2017
- Slow and steady wins the race? A comparison of ultra-low-power RISC-V cores for Internet-of-Things applications2017
- Near-Threshold RISC-V Core With DSP Extensions for Scalable IoT Endpoint DevicesIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017