NPU terminology

Luminar Neo's NPU-accelerated features show how AI is rapidly transforming creativity apps on Windows 11

Retrieved on: 
Wednesday, May 24, 2023
Hardware, Photography, Technology, Artificial Intelligence, Software, Antirrhinum, Qualcomm, Qualcomm Hexagon, Partner, Microsoft, Windows Dev Kit 2023, Creativity, Computing, NPU, Build, GAN, NPU terminology, Machine learning, Algorithm, Windows 11, Hexagon, AI, SVP, Surface Pro, BASIC Computer Games, Microsoft Store, Video game, Medical device, Skylum

At Build, Microsoft showcased Luminar Neo as an example of how AI technologies are transforming creative pursuits for creators on the Windows 11 platform.

Key Points: 
  • At Build, Microsoft showcased Luminar Neo as an example of how AI technologies are transforming creative pursuits for creators on the Windows 11 platform.
  • NPUs (neural processing units) are a class of specialized hardware accelerators that can greatly speed up AI and machine learning applications.
  • One of Luminar Neo's most complex AI models is “Supersharp AI,” capable of rescuing out-of-focus images with impressive precision.
  • “We’re excited to see the speed and user experience improvements the Luminar Neo team achieved by leveraging our latest NPU hardware on Windows 11.

Eric Schleicher, Founder and CEO of Constructive Realities Announced as Winner of OKdo's Global ROCK Engineering Challenge

Retrieved on: 
Friday, May 26, 2023
Graphics processing unit, Time of flight, Partnership, Engineering, Marketing, RS Group plc, Internet of things, Original equipment manufacturer, API, Home, CMO, Educational technology, PC, Movement, Creativity, DIY, Thermoregulation, National Association Medical Staff Services, Environmental monitoring, ROCK, Rock, Patient, Robotics, NPU terminology, RS Group, SBC, RS, Linux, Invention, Renewable energy, Entrepreneurship, AI, AR, GPU, Automation, Television, 3D printing, Health care

LONDON, May 26, 2023 /PRNewswire/ -- The ROCK Engineering Challenge invited engineers, developers, educators, inventors and entrepreneurs, to submit an idea based on the OKdo® ROCK single board computers (SBC) and compute modules. The contest attracted 160 high-quality entries from around the world, with applications and ideas spanning various verticals such as IoT, Healthcare, Smart Homes, AI, Robotics, EdTech, Renewable Energy, and Smart City initiatives.

Key Points: 
  • The grand prize winner of the ROCK Engineering challenge is Eric Schleicher and his core team at Constructive Realities .
  • Eric is developing Time of Flight (ToF) 3D cameras, capable of on-device depth data processing using the GPUs and NPUs.
  • "The ROCK Engineering Challenge has truly demonstrated the immense potential of engineers worldwide in pushing the boundaries of SBC applications.
  • "The ROCK Engineering Challenge has brought together some of the best minds to drive innovation and push the boundaries of what's possible with single board computers.

Quadric’s DevStudio Speeds Software Development with Industry’s First Integrated ML + DSP Cloud-Based Code Development Platform

Retrieved on: 
Monday, May 22, 2023
Electronic Design Automation, Semiconductor, Apps, Applications, Technology, Software, Artificial Intelligence, Hardware, Heart, NN, C, CGC, CCL, DSP, ML, CNN, Central processing unit, SOC, Organization, DSPS, CPU, NPU terminology, Machine learning, Memory, Computer program, Chimera (software library), SDK, Artificial intelligence, Architecture, Ecosystem, Silicon, API, Environment, ONNX, Quadric, ISS, Video game, Chimera

Quadric DevStudio speeds software development with the industry’s first integrated machine learning (ML) plus digital signal processing (DSP) development system.

Key Points: 
  • Quadric DevStudio speeds software development with the industry’s first integrated machine learning (ML) plus digital signal processing (DSP) development system.
  • View the full release here: https://www.businesswire.com/news/home/20230522005245/en/
    Quadric’s DevStudio speeds software development with integrated system for ML + DSP (Graphic: Quadric)
    A significant advantage of Quadric DevStudio is that neural network graphs and C++ code are merged into a single, fully programmable software application.
  • Future code changes can easily be made later as new features are added by the application developers.
  • Unlike conventional accelerators that can only run a handful of predetermined ML operators, Chimera GPNPUs can run any ML operator.

Intelligent Vehicle Cockpit-Driving Integration Research Report, 2023: Increasing Focus on Cockpit Driving Integration Attracts Major Players Such as Neta Auto, Tesla, Z-ONE & More - ResearchAndMarkets.com

Retrieved on: 
Tuesday, April 11, 2023
EV, Electric Vehicles, Automotive, Aurora, ZOS, Macan, Galaxy, Original equipment manufacturer, IVI, Porsche, Android, Premium, SOC, Tegra, Continental, Thor, MAC, DRIVE, Volkswagen, PPE, NVIDIA, NPU terminology, Socs, Algorithm, Linux, Architecture, Nvidia Drive, QNX, AI, ADAS, Tesla, SOA, L4, News, Family, Software, Mobile phone, Instrumentation, Video game, Airline, Cryptocurrency, Internet service provider, Nvidia, Qualcomm, Lenovo

are being integrated, for example, body and chassis domain integration, and cockpit and intelligent driving domain integration.

Key Points: 
  • are being integrated, for example, body and chassis domain integration, and cockpit and intelligent driving domain integration.
  • Cockpit-driving integration refers to the integration of cockpit and intelligent driving domains into a high-performance computing unit that supports both intelligent driving and intelligent cockpit functions.
  • Cockpit-driving integration falls into two types: multi-SoC integration, that is, cockpit and intelligent driving functions are deployed on different boards; single SoC integration, that is, the software and algorithms of cockpit and intelligent driving are all deployed on one board.
  • Given varying maturity and requirements of cockpit and intelligent driving technologies, cockpit-driving integration is iterating and being promoted in a gradual manner.

OStream Announces OKdo Partnership for Scalable, Edge AI Media Processing

Retrieved on: 
Thursday, April 6, 2023
Data Management, Technology, Audio, Video, Software, Artificial Intelligence, Internet, Hardware, Acceleration, Metadata, Partnership, Single-board computer, VPU, Rockchip, Sleep, SBCS, Central processing unit, NPU, CPU, Edge, NPU terminology, RS Group, NVIDIA, SBC, Object, AI, Environment, RS Group plc, Video game, Input/output

OStream , the leading innovator of Edge AI media systems, announced a global partnership with OKdo , the innovative Single Board Computer and Internet of Things arm of the RS Group PLC.

Key Points: 
  • OStream , the leading innovator of Edge AI media systems, announced a global partnership with OKdo , the innovative Single Board Computer and Internet of Things arm of the RS Group PLC.
  • The solution is deployed on the Edge and pulls media streams from already deployed cameras in the environment.
  • OKdo has licensed OStream’s PipeRunner technology that automatically delegates Edge AI operations to the most optimized hardware component available across the cluster.
  • The extended format allows customers to take real-time action at the edge and build a data lake of searchable media.

Intelligent Vehicle Cockpit-Driving Integration Research Report, 2023: Featuring Tesla, Volkswagen, Bosch, Continental & More

Retrieved on: 
Tuesday, April 11, 2023
Aurora, ZOS, Macan, Galaxy, Original equipment manufacturer, IVI, Porsche, Android, Premium, SOC, Tegra, Continental, Thor, MAC, DRIVE, Volkswagen, PPE, NVIDIA, NPU terminology, Socs, Algorithm, Linux, Architecture, Nvidia Drive, QNX, AI, ADAS, Tesla, SOA, L4, News, Family, Software, Instrumentation, Video game, Airline, Cryptocurrency, Internet service provider, Nvidia, Qualcomm, Lenovo

DUBLIN, April 11, 2023 /PRNewswire/ -- The "Intelligent Vehicle Cockpit-Driving Integration Research Report, 2023" report has been added to ResearchAndMarkets.com's offering.

Key Points: 
  • DUBLIN, April 11, 2023 /PRNewswire/ -- The "Intelligent Vehicle Cockpit-Driving Integration Research Report, 2023" report has been added to ResearchAndMarkets.com's offering.
  • are being integrated, for example, body and chassis domain integration, and cockpit and intelligent driving domain integration.
  • Cockpit-driving integration refers to the integration of cockpit and intelligent driving domains into a high-performance computing unit that supports both intelligent driving and intelligent cockpit functions.
  • Cockpit-parking integration signifies the first step of cockpit-driving integration, that is, cockpit-driving integration will be considered after the cockpit-parking integration technology matures.

Latest aiWare4+ automotive NPU brings enhanced programmability, flexibility and scalability while retaining highest efficiency

Retrieved on: 
Wednesday, December 14, 2022
SDK, Memory, NPU, Software, AImotive, NPU terminology, DSP, FP8, IP, CNN, PPA, GPU, Socs, AI, Architecture, Silicon, Video game console, Computer data storage

Together these enable higher efficiency execution of a far broader range of workloads, such as transformer networks and other emerging AI network topologies.

Key Points: 
  • Together these enable higher efficiency execution of a far broader range of workloads, such as transformer networks and other emerging AI network topologies.
  • Support for FP8, as well as INT8 computation and dedicated sparsity hardware support, are also included in aiWare4+.
  • Furthermore, aiWare4+ brings interleaved multi-tasking that optimizes performance and efficiency with multiple workloads.
  • aiWare4+ continues to deliver the automotive industry’s highest NPU efficiency of up to 98% for a wide range of AI workloads, enabling superior performance using less silicon and less power.

Kinara and Arcturus Partnership to Provide High Performance AI Solutions for Smart City and Industry 4.0 Applications

Retrieved on: 
Wednesday, September 14, 2022
Technology, Audio, Video, Professional Services, Construction & Property, Artificial Intelligence, Software, Networks, Data Analytics, Hardware, Electronic Design Automation, Semiconductor, Data Management, Security, Interior Design, Software, Safety, Algorithm, Efficiency, Industry, Innovation, NXP, Health, SOC, Partnership, Central processing unit, IP, NXP Semiconductors, Ownership, Technology, Â, Solution, Transport, NPU terminology, Ecosystem, Human, Semiconductor, Heart, Silicon, Graphics processing unit, Multimedia, AI, Classification, Original equipment manufacturer, MOT, Linux, IOT, ML, Maintenance (technical), Video game console, Medical device, Arcturus

Kinara , Inc., developer of unrivaled Edge AI solutions that accelerate and optimize real-time decision making, today announced that it has partnered with Arcturus Networks Inc., provider of edge AI analytics and enablement for smart city applications, to help customers deliver high-performance, cost-optimized AI solutions.

Key Points: 
  • Kinara , Inc., developer of unrivaled Edge AI solutions that accelerate and optimize real-time decision making, today announced that it has partnered with Arcturus Networks Inc., provider of edge AI analytics and enablement for smart city applications, to help customers deliver high-performance, cost-optimized AI solutions.
  • View the full release here: https://www.businesswire.com/news/home/20220914005082/en/
    Kinara and Arcturus Partnership to Provide High Performance AI Solutions for Smart City and Industry 4.0 Applications (Photo: Business Wire)
    The partnership combines the Kinara Ara-1 Edge AI processor with Arcturus Brinq edge AI and vision analytics software to drive leading-edge detection, tracking and characterization solutions.
  • The Ara-1 Edge AI processor delivers a ground-breaking combination of performance, power, and price for integrated cameras and edge servers.
  • Download the technical paper Practical Requirements for Mission-Critical Edge AI Applications to get additional insight into real-world AI application development.

Synaptics and WNC Partner to Bring AI Capabilities to Smart Display

Retrieved on: 
Friday, September 9, 2022
Machine learning, Synaptics, Human, NPU terminology, LCD, Artificial intelligence, Smart Display, Engineering, Central processing unit, Mark (given name), GM, SVP, IOT, LinkedIn, Multimedia, Speech, WNC, ADAS, Graphics processing unit, GLOBE, ISP, Nasdaq, Synap, Twitter, AI, Mobile phone, Sales, Facebook

AMSTERDAM, The Netherlands, Sept. 09, 2022 (GLOBE NEWSWIRE) -- Synaptics Incorporated (Nasdaq: SYNA ) today announced the availability of WNCs Smart Display platform, powered by the Synaptics VS600 series processor and the Synaptics SyNAPdevelopment framework.

Key Points: 
  • AMSTERDAM, The Netherlands, Sept. 09, 2022 (GLOBE NEWSWIRE) -- Synaptics Incorporated (Nasdaq: SYNA ) today announced the availability of WNCs Smart Display platform, powered by the Synaptics VS600 series processor and the Synaptics SyNAPdevelopment framework.
  • The Smart Display platform comprises primarily the VS600 and Synaptics SyNAP development framework, along with the LCD and wireless connectivity.
  • The SyNAP AI framework enables AI partners to quickly implement and optimize AI models to add differentiating features to their products.
  • Synaptics, and the Synaptics logo are trademarks of Synaptics in the United States and/or other countries.

Arcturus Achieves Global Recognition with Best In-Class Multiple Object Tracking Performance

Retrieved on: 
Wednesday, July 13, 2022
Method, Graphics processing unit, NPU terminology, MOTA, Solution, IOT, Do You Love Your Mom and Her Two-Hit Multi-Target Attacks?, ML, Central processing unit, Multiple-camera setup, Algorithm, Human, Linux, MOT, Acceleration, IP, AI, Vision, MTMC, Hand, Research, Efficiency, ID, Satellite navigation device, Mobile phone, Arcturus

TORONTO, July 13, 2022 /PRNewswire-PRWeb/ -- Arcturus Networks Inc., a leading provider of edge AI analytics and enablement today announced the results of its public submission to the global Multiple Object Tracking (MOT) benchmark competition where Arcturus Brinq Traq (BQTQ) achieved a MOTA benchmark score of 77.2 for MOT16 and 77.7 for MOT17 challenges. The results represent a 0.7 point gap from the top MOT16 position at 77.9 and a 2.6 point gap from the top MOT17 position at 80.3. This ranks Brinq tracking solutions in the top-10 globally when compared with all submissions (including leading research) and as the number one, commercially available edge solution.

Key Points: 
  • Multiple object tracking remains an area of highly active research among academic institutes and commercial organizations with advancements in ML enabling powerful new methods.
  • Multiple object tracking requires a unique ID to be generated for each object in the field of view.
  • This anonymized ID is maintained frame-over-frame as the object moves, ultimately describing how each unique object interacts with the space around it.
  • Accurate multiple object tracking is achieved by maintaining each unique track ID, a task referred to as reidentification.