HAMSA-DI: A Low-Power Dual-Issue RISC-V Core Targeting Energy-Efficient Embedded Systems
- 23 October 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 71 (1) , 223-236
Abstract
The RISC-V architecture has recently emerged as a popular open source option for the design of general purpose cores with a wide spectrum of operating specifications. In this paper, we present HAMSA-DI, a small footprint, energy-efficient, embedded RISC-V core, featuring a dynamically scheduled, in-order, dual-issue processing pipeline, supporting the popular Xpulp extensions. The proposed cost-effective dual-issue implementation provides a significant performance boost and improved energy-efficiency over baseline low-power cores under common benchmarks. These include a CoreMark score of 3.48 CM/MHz ( $+$ 22%) and an Embench score of 1.3 ( $+$ 13%) with certain benchmarks displaying as much as 22% less energy than the baseline core. The proposed design was fabricated as part of a 16 nm test chip, running at 1 GHz with an 0.8V supply voltage. Silicon measurements demonstrate that the proposed core can improve performance by as much as 8for programs operating with full dual-issue utilization with energy-efficiency improving by as much as 6.5, as compared to compiled code on a single-issue core.Keywords
Funding Information
- Israel Innovation Authority through the GenPro Magnet Program
This publication has 14 references indexed in Scilit:
- A RISC-V-based Research Platform for Rapid Design Cycle2022
- An Analysis on the Crisis of “Chips shortage” in Automobile Industry ——Based on the Double Influence of COVID-19 and Trade FrictionJournal of Physics: Conference Series, 2021
- XpulpNN: Enabling Energy Efficient and Flexible Inference of Quantized Neural Networks on RISC-V Based IoT End NodesIEEE Transactions on Emerging Topics in Computing, 2021
- An Ultra-Low-Power Embedded Processor with Variable Micro-ArchitectureMicromachines, 2021
- PULP-NN: A Computing Library for Quantized Neural Network inference at the edge on RISC-V Based Parallel Ultra Low Power Clusters2019
- The Cost of Application-Class Processing: Energy and Performance Analysis of a Linux-Ready 1.7-GHz 64-Bit RISC-V Core in 22-nm FDSOI TechnologyIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2019
- A low-cost synthesizable RISC-V dual-issue processor core leveraging the compressed Instruction Set ExtensionMicroprocessors and Microsystems, 2018
- Near-Threshold RISC-V Core With DSP Extensions for Scalable IoT Endpoint DevicesIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017
- SHAKTI Processors: An Open-Source Hardware Initiative2016
- A 45nm 1.3GHz 16.7 double-precision GFLOPS/W RISC-V processor with vector accelerators2014