Powered by the NXP S32G274A vehicle network processor, the SoM based miriac AIP-S32G274A can integrate up to 2 advanced Hailo-8 AI accelerators to reach its maximum AI performance of 52 TOPS, providing best-in-class processing performance and deep learning capabilities for decentralized situational awareness. The embedded platform delivers exceptional AI computing performance across multiple standard NN benchmarks, including 2450 Frames Per Second (FPS) on Resnet-50, 2100 FPS on Mobilenet-V1 SSD, and up to 380 FPS on YOLOv5m.
Awarded “Best AI and Vision Processor 2021” by the Edge AI and Vision Alliance, the automotive grade Hailo-8 outperforms other available AI processors for edge computing with up to 26 TOPS at a typical power consumption of 2.5 W. The miriac AIP-S32G274A embedded platform, combining the Hailo-8 AI processor with MicroSys’s Arm Cortex NXP Automotive S32G platforms, provides customers with a highly efficient way to implement AI into their connected edge appliances.
The feature set at a glance
The new application-ready miriac AIP-S32G274A starter kit for AI is a highly effective springboard for cost efficient custom designs in industrial quantity, quality and long-term availability and comes complete with everything necessary for evaluation and development. It includes an IEC 61508 compliant and ASIL D safety ready miriac MPX-S32G274 SoM with quad Arm Cortex-A53 cores plus triple Arm Cortex-M7 dual-cores, 1 or 2 Hailo-8 AI processor modules, a carrier board with Ethernet with TSN, PCIe, USB, SPI, and I²C as well as standard automotive busses like Flexray (2x), LIN (4x) or CAN (16x plus 2x CAN FD) and a cable set. Developers also have access to the comprehensive AI and development tools offered in the Hailo Developer Zone. For more information about the miriac AIP-S32G274A, please visit the product page:
https://www.microsys.de/en/products/system-device/off-the-shelf/miriac-aip-S32G274A
For more information about the miriac MPX-S32G274 System-on-Module please visit this landing page:
About Hailo
Hailo, an AI-focused, Israel-based chipmaker, has developed a specialized AI processor that delivers the performance of a data center-class computer to edge devices. Hailo’s processor is the product of a rethinking of traditional computer architecture, enabling smart devices to perform sophisticated deep learning tasks such as object detection and segmentation in real-time, with minimal power consumption, size, and cost. The processor is designed to fit into a multitude of smart machines and devices, impacting a variety of sectors including automotive, Industry 4.0, smart cities, smart homes, and retail. For more information visit www.hailo.ai
MicroSys Electronics has been designing and developing embedded system solutions since 1975, is an NXP Gold Partner and widely integrates NXP’s S32 Automotive, Layerscape and QorIQ processor technology. Designs based on System-on-Modules (SoMs) are the strengths of this German company, with the portfolio ranging from application-ready SoMs and customer-specific carrier board designs to fully integrated systems. Application areas for these extremely rugged designs with long-term availability are primarily found in markets where safety standards analog to IEC 61508 are required, such as railway technology (EN 50155), aviation (DO-160), and mobile machinery (ISO 13849), as well as manufacturing robots (ISO 10218), control systems (IEC 62061), and drive systems (IEC 61800-5-2). Further application areas can be found in medical technology (60601), and in critical infrastructures, like the nuclear sector (IEC 61513) or the process industry (IEC 61511). MicroSys works closely with its customers in all these industries to ensure that the specific applicable standards are fully met. For more information, visit www.microsys.de
MicroSys Electronics GmbH
Mühlweg 1
82054 Sauerlach
Telefon: +49 (8104) 801-0
Telefax: +49 (8104) 801-110
http://www.microsys.de
Headline Media
Telefon: +1 (786) 233-7684
E-Mail: garrett@headline.media
Geschäftsführerin
E-Mail: info@microsys.de
Sales And Management Services
Telefon: +49 (2405) 4526720
E-Mail: info@sams-network.com