☆ 3.8 Proceedings Paper

A 3 TOPS/W RISC-V Parallel Cluster for Inference of Fine-Grain Mixed-Precision Quantized Neural Networks

2023 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI, ISVLSI (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Electrical & Electronic

Vega: A Ten-Core SoC for IoT Endnodes With DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode

Davide Rossi et al.

Summary: Vega is an IoT endnode SoC chip that features ultra-low power consumption, high performance, and flexibility to achieve efficiency in handling complex NSAAs algorithms.

IEEE JOURNAL OF SOLID-STATE CIRCUITS (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs

Alessio Burrello et al.

Summary: This work introduces an automatic tool DORY for deploying DNNs on low-cost MCUs, aiming to maximize memory utilization and improve performance through additional heuristics. A case study demonstrates that DORY outperforms other devices in the market on GreenWaves Technologies GAP8.

IEEE TRANSACTIONS ON COMPUTERS (2021)

Add to Collection

Article Computer Science, Information Systems

XpulpNN: Enabling Energy Efficient and Flexible Inference of Quantized Neural Networks on RISC-V Based IoT End Nodes

Angelo Garofalo et al.

Summary: This paper presents a multi-precision arithmetic unit integrated into a RISC-V processor to boost the efficiency of heavily quantized neural network inference on microcontroller-class cores. By extending ISA and utilizing a custom SIMD execution paradigm, high-efficiency computation is achieved. Integrating the extended core in a parallel cluster further enhances efficiency.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING (2021)

Add to Collection

Article Engineering, Electrical & Electronic