Edge-AI Hardware for Extended Reality

New technical paper titled “Memory-Oriented Design-Space Exploration of Edge-AI Hardware for XR Applications” from researchers at Indian Institute of Technology Delhi and Reality Labs Research, Meta.

Abstract
“Low-Power Edge-AI capabilities are essential for on-device extended reality (XR) applications to support the vision of Metaverse. In this work, we investigate two representative XR workloads: (i) Hand detection and (ii) Eye segmentation, for hardware design space exploration. For both applications, we train deep neural networks and analyze the impact of quantization and hardware specific bottlenecks. Through simulations, we evaluate a CPU and two systolic inference accelerator implementations. Next, we compare these hardware solutions with advanced technology nodes. The impact of integrating state-of-the-art emerging non-volatile memory technology (STT/SOT/VGSOT MRAM) into the XR-AI inference pipeline is evaluated. We found that significant energy benefits (>=80%) can be achieved for hand detection (IPS=40) and eye segmentation (IPS=6) by introducing non-volatile memory in the memory hierarchy for designs at 7nm node while meeting minimum IPS (inference per second). Moreover, we can realize substantial reduction in area (>=30%) owing to the small form factor of MRAM compared to traditional SRAM.”

Find the technical paper here. Published June 2022.

Authors: Vivek Parmar, Syed Shakib Sarwar, Ziyun Li, Hsien-Hsin S. Lee, Barbara De Salvo, Manan Suri.
V. Parmar and M. Suri are with the Indian Institute of Technology Delhi,
New Delhi; S. S. Sarwar, Z. Li, H. S. Lee, B. De Salvo are with Reality Labs Research, Meta.

Related Reading
Using AI To Speed Up Edge Computing
Optimizing a system’s behavior can improve PPA and extend its useful lifetime.
SOT-MRAM To Challenge SRAM
Spin-orbit torque memory adds endurance and faster write speeds, but displacing existing memories is still not easy.
Smart Glasses, Augmented Reality, And Time-Of-Flight Imaging
3D ToF can bring differentiating features to AR glasses.
A Crossbar Array Of Magnetoresistive Memory Devices For In-Memory Computing
In-memory computing technology based on MRAM (Samsung).