Researchers at UC Irvine unveil a groundbreaking study on chiplet-based Neural Processing Units, promising to optimise AI perception in autonomous vehicles.
Researchers at the University of California, Irvine, have made significant strides in the realm of artificial intelligence within the automotive industry with the publication of a new technical paper titled “Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception.” This research focuses on the integration of chiplet-based Neural Processing Units (NPUs) to enhance vehicular AI perception capabilities, especially within the constraints of automotive environments.
The study highlights the growing importance of chiplet technology in modern vehicular architectures, as it presents a cost-effective solution that balances performance, modularity, and customisation. The necessity for such advancements is propelled by the fact that perception models used in autonomous driving are among the most computationally intensive tasks encountered in these systems.
The researchers used Tesla’s Autopilot perception pipeline as a real-world case study, meticulously breaking down its constituent models and analysing their performance when run on various chiplet accelerators. Their investigation led to the proposal of an innovative scheduling strategy, designed to optimise the deployment of perception workloads across multi-chip AI accelerators.
Through extensive experiments conducted using the DNN performance simulator known as MAESTRO, the research team reported significant enhancements in processing efficiency. According to their findings, the proposed scheduling strategy achieved an impressive 82% increase in throughput, along with a 2.8 times greater utilisation of processing engines in comparison to traditional monolithic accelerator designs.
The paper, authored by Mohanad Odema, Luke Chen, Hyoukjun Kwon, and Mohammad Abdullah Al Faruque, underscores the potential of chiplet technology to revolutionise AI applications in the automotive sector. As the industry looks to further embrace AI for improvements in safety and efficiency, the insights provided in this research may serve as a catalyst for future developments in autonomous driving technologies.
The technical paper is currently available as a preprint, with a formal publication anticipated in November 2024.
Source: Noah Wire Services
- https://www.assemblymag.com/articles/97663-new-uc-irvine-institute-focuses-on-mobility-and-connectivity – This article discusses the establishment of the Horiba Institute for Mobility and Connectivity2 (HIMaC2) at UC Irvine, focusing on autonomous, connected, and zero-emission vehicles, which aligns with the broader context of automotive AI research.
- https://scag.ca.gov/sites/main/files/file-attachments/23-3066-doe-grant-partnerships-with-uci-fs-8.5×11-final.pdf – This document details a project involving UC Irvine and AI infrastructure for transportation, highlighting the use of AI in automotive and transportation systems, which is relevant to the integration of AI in vehicles.
- https://www.irvinestandard.com/2024/uci-partners-with-karma-automotive-to-address-industry-climate-concerns/ – This article mentions UC Irvine’s partnership with Karma Automotive to address electric mobility and energy efficiency, which are key aspects of the automotive industry’s shift towards AI and autonomous vehicles.
- https://news.uci.edu/2022/05/26/uci-researchers-autonomous-vehicles-can-be-tricked-into-dangerous-driving-behavior/ – This article discusses research by UC Irvine on the vulnerabilities of autonomous vehicles, which is crucial for understanding the challenges and improvements needed in AI-driven automotive systems.
- https://www.ucop.edu/federal-governmental-relations/_files/fact-sheets/ai-fact-sheet.pdf – This fact sheet provides an overview of AI research at UC Irvine, including its applications in various fields, which supports the context of AI research in the automotive sector.
- https://apep.uci.edu/ConnectedVehicles/ – This website from UC Irvine’s Advanced Power and Energy Program discusses connected vehicles and related research, aligning with the focus on AI in automotive systems.
- https://scag.ca.gov/alternative-fuels-vehicles-projects – This page from the Southern California Association of Governments details projects related to alternative fuels and vehicles, including AI-based intersection monitoring, which is relevant to AI in transportation.
- https://www.noahwire.com – Although this link does not directly corroborate the specific claims about the technical paper, it is the source mentioned in the query and provides a general context for AI and technology news.
- https://www.ucop.edu/federal-governmental-relations/_files/fact-sheets/ai-fact-sheet.pdf – This fact sheet further details AI research at UC Irvine, including its broader applications, which supports the ongoing research in AI within the university.
- https://www.assemblymag.com/articles/97663-new-uc-irvine-institute-focuses-on-mobility-and-connectivity – This article also mentions the grid evolution laboratory and the study of electric grid demands, which is related to the efficiency and safety improvements sought through AI in autonomous vehicles.
- https://news.uci.edu/2022/05/26/uci-researchers-autonomous-vehicles-can-be-tricked-into-dangerous-driving-behavior/ – This article discusses the testing tool PlanFuzz used by UC Irvine researchers to evaluate vulnerabilities in autonomous driving systems, highlighting the need for robust AI solutions.
Automate Your Business
You are one step away from removing your bottlenecks, automating your business and getting your time back. It’s like hiring 3 staff members – minus the headache, minus the pensions, minus the sick pay!
Schedule a free automation consultation
Automate Your Business
You are one step away from removing your bottlenecks, automating your business and getting your time back. It’s like hiring 3 staff members – minus the headache, minus the pensions, minus the sick pay!
Schedule a free automation consultation
Automate Your Business
You are one step away from removing your bottlenecks, automating your business and getting your time back. It’s like hiring 3 staff members – minus the headache, minus the pensions, minus the sick pay!
