Axeon and Infineon unveil embedded machine learning system
March 31, 2005 -- At SAE World Congress -11th April, Axeon and Infineon will launch their embedded machine learning system based on Axeon’s Vindax technology integrated with the Infineon Powertrain Starter Kit (PSK) and Triboard development platforms. This development is targeted at the Tier 1 suppliers and OEM application developers, and puts the power of a hardware neural network to work on some of the most challenging problems in the automotive industry, including classification, function approximation and change detection. Applications developed on the system can be used to realize significant cost-down benefits combined with improved solution accuracy and increased system reliability.
The integration takes the form of a daughtercard hosting a 256 processing element array and support logic interfaced directly to the external port of the Tricore on the PSK or Triboard via the system expansion connectors. A set of library calls enables application code running on the Tricore to access the Vindax hardware resources.
Working with Infineon, Axeon has been able to deploy a class-leading solution on one of the world’s most advanced embedded platforms. This integration opens up a new opportunity space for both companies.
Speaking about the teamwork between the companies, Hamish Grant, Axeon CEO, said, “I am delighted to unveil the results of our collaboration with Infineon. This is Axeon’s first embedded platform, and reinforces our commitment to drive the Vindax architecture to the heart of future automotive embedded systems. Together we will be able to address some of the most complex issues found in current and future Powertrain architectures”.
Commenting on the integration, Chris Cook, VP Automotive North America for Infineon said, "The integration of the Vindax array with the state-of-the-art TriCore TC1796 embedded processor allows the excellent real-time performance and digital signal processing capabilities of the Infineon processor to be complemented by a powerful hardware accelerator. The embedding of this technology with one of our powertrain microcontrollers allows immediate access to the measured and calculated variables within the system enabling the neural array to be incorporated into the powertrain control loop. The data throughput and quality could allow significant savings to be made on external sensors by replacing them with 'virtual sensors' derived from the complex relationships of the other measured physical signals."
Axeon will be demonstrating the integration work at SAE World Congress where the Vindax-Triboard combination will be used to implement a Virtual Sensor application, in this case a Virtual Mass Air Flow Sensor. The demonstration shows how a machine learning system can be used to replicate the output of a physical Mass Air Flow meter to a very high degree of accuracy, allowing Tier 1 suppliers and OEMs alike to realize the cost-down benefit from deletion of the physical sensor. Conversely, this Virtual Sensor provides additional functionality to a Powertrain system, and allows the Tier 1 or OEM to calibrate the output of the physical sensor via the electronics system.
The PSK/Triboard daughtercard is sampling from Axeon now.
About Axeon:
Axeon is a Semiconductor Intellectual Property (SIP) company providing products and services to the automotive and industrial markets based on our unique real-time Artificial Neural Network technology – Vindax. Vindax is a technology comprising a methodology, an algorithm and processor architecture. This enables real-time, multi-variable, non-linear problem solutions to be formulated through development tools and deployed in FPGA or IP core products. Vindax can be employed to a wide range of automotive and industrial applications that broadly fit into the groups of Change Detection, Function Approximation and Classification.
For solving complex non-linear problems Vindax tools and methods reduce development time allowing emphasis on problem understanding and solution accuracy. Applications can be implemented via a rapid and direct path through real-time prototyping into the multitasking FPGA or IP core products.
About Infineon:
Infineon Technologies AG, Munich, Germany, offers semiconductor and system solutions for automotive, industrial and multimarket sectors, for applications in communication, as well as memory products. With a global presence, Infineon operates through its subsidiaries in the US from San Jose, CA, in the Asia-Pacific region from Singapore and in Japan from Tokyo. In fiscal year 2004 (ending September), the company achieved sales of Euro 7.19 billion with about 35,600 employees worldwide. Infineon is listed on the DAX index of the Frankfurt Stock Exchange and on the New York Stock Exchange (ticker symbol: IFX). Further information is available at www.infineon.com.
|
Related News
- SiMa.ai Partners with GUC to Accelerate Time to Market for Industry's First Purpose-Built Machine Learning Platform for the Embedded Edge
- SiMa.ai Ships First Industry Leading Purpose-built Machine Learning SoC Platform to Customers for Embedded Edge Applications
- SiMa.ai Adopts Arm Technology to Deliver a Purpose-built Heterogeneous Machine Learning Compute Platform for the Embedded Edge
- Synopsys and SiMa.ai Collaborate to Bring Machine Learning Inference at Scale to the Embedded Edge
- GLOBALFOUNDRIES and Mentor Collaborate to Launch New Semiconductor Verification Solution Embedded with Advanced Machine Learning Capabilities
Breaking News
- Faraday and Kiwimoore Succeed in 2.5D Packaging Project for Mass Production
- Secure-IC unveils its Securyzr™ neo Core Platform at Embedded World North America 2024
- OPENEDGES Technology Achieves ISO 26262 ASIL-B Certification
- Xylon's Updated logiHSSL IP Core Seamlessly Connects Infineon AURIX Microcontrollers with AMD Adaptive SoCs and FPGAs
- Electronic System Design Industry Posts $4.7 Billion in Revenue in Q2 2024, ESD Alliance Reports
Most Popular
- RaiderChip brings Meta Llama 3.2 LLM HW acceleration to low cost FPGAs
- NVMe Updates Expand Discoverability, Security
- BrainChip Introduces Lowest-Power AI Acceleration Co-Processor
- Bluetooth® V6.0 Channel Sounding RF Transceiver IP Core in 22nm & 40nm for ultra-low power distance aware Bluetooth connected devices
- Boosting Efficiency and Reducing Costs: Silvaco's Approach to Semiconductor Fabrication
E-mail This Article | Printer-Friendly Page |