Siracusa: A 16 nm Heterogenous RISC-V SoC for Extended Reality With At-MRAM Neural Engine


METADATA ONLY
Loading...

Date

2024-07

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Extended reality (XR) applications are machine learning (ML)-intensive, featuring deep neural networks (DNNs) with millions of weights, tightly latency-bound (10-20 ms end-to-end), and power-constrained (low tens of mW average power). While ML performance and efficiency can be achieved by introducing neural engines within low-power systems-on-chip (SoCs), system-level power for nontrivial DNNs depends strongly on the energy of non-volatile memory (NVM) access for network weights. This work introduces Siracusa, a near-sensor heterogeneous SoC for next-generation XR devices manufactured in 16 nm CMOS. Siracusa couples an octa-core cluster of RISC-V digital signal processing (DSP) cores with a novel tightly coupled "At-Memory" integration between a state-of-the-art digital neural engine called and an on-chip NVM based on magnetoresistive random access memory (MRAM), achieving 1.7x higher throughput and 3x better energy efficiency than XR SoCs using NVM as background memory. The fabricated SoC prototype achieves an area efficiency of 65.2 GOp/s/mm(2) and a peak energy efficiency of 8.84 TOp/J for DNN inference while supporting complex, heterogeneous application workloads, which combine ML with conventional signal processing and control.

Publication status

published

Editor

Book title

Volume

59 (7)

Pages / Article No.

2055 - 2069

Publisher

IEEE

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Artificial intelligence (AI); augmented reality (AR); deep neural network (DNN); extended reality (XR); heterogeneous architecture; magnetoresistive random access memory (MRAM); non-volatile memory (NVM); RISC-V; system-on-chip (SoC)

Organisational unit

03996 - Benini, Luca / Benini, Luca check_circle

Notes

Funding

101095947 - Together for RISc-V Technology and ApplicatioNs (SBFI)
22.00150 - Seamless design of smart edge processors (SBFI)

Related publications and datasets