aetinacorporation

AI platform combines NVIDIA Jetson Xavier NX computing module and carrier board

September 8, 2020 By Aimee Kalnoskas Leave a Comment

Aetina Corporation announced the new AN810-XNX edge AI computer leveraging the capabilities of the NVIDIA Jetson Xavier NX. This edge AI computer provided various alternatives of I/O slot, nicely expand its range of edge AI systems built on the Jetson platform for robotics, drone, UAV, industrial inspection, medical imaging, and deep learning.

The AN810-XNX combines the NVIDIA Jetson Xavier NX and Aetina brand new AN810 carrier board in a Nano-ITX form factor of 120x120x47.3 mm (with fan). It supports full M.2 slot with M-key, E-key, and B-key and the interface with PCIe/SATA/USB 3.2 Gen2/USB 2.0. AN810-XNX features prospective communication capabilities. Since 5G technology has become a sensation in IoT applications, AN810-XNX integrated with the 4G/5G module beforehand for high-speed wireless connection and data transferring. Meanwhile, AN810-XNX equipped an onboard SIM slot, building seamless global connectivity for edge devices. For better management of numerous edge devices, AN810-XNX supports the Innodisk InnoAGE out-of-band management SSD solution through M.2. With this solution, it reduces the massive cost of manually repairing the edge device and primarily minimizes the equipment’s downtime, making the remote-control of the edge device more convenient.

With the widespread use of vision AI application, AN810-XNX supports the single 120-pin connector for MIPI CSI-2 interface. It can handle intensive AI workloads ultra-high-resolution cameras to more accurate image analysis. For backup support, Aetina offers BSP and DTB configuration updates for both standard and customized platforms in their service policy.

Aetina focuses on delivering edge AI computing solutions based on the Jetson platform for embedded applications. NVIDIA Jetson benefits the users by supporting cloud-native technologies across AI solutions and various SDK. Moreover, Aetina AN810-XNX got Microsoft Azure Certified for Internet of Things (IoT), ensuring the IoT solutions could fasten development and work with Microsoft Azure IoT services.

“AIoT environment is diverse and complex. Throughout the edge AI systems, GPU-based platform has the most flexibility and Azure cloud services enhance the overall performance. Benefits the customer with shorter development period.” said Joe Lo, general manager of Aetina. AN810-XNX, high compatibility platform with well-backup service from edge to cloud, could deploy high-quality, software-defined features on embedded and edge devices targeting robotics, drone, UAV, industrial IoT, healthcare, deep learning, etc.

The AN810-XNX is available now.

New CPU cards speed real-time ray tracing, AI training

August 14, 2020 By Aimee Kalnoskas Leave a Comment

GPGPU and edge AI solution provider Aetina Corp. announces the newest Quadro Turing architecture MXM GPU module. Quadro RTX provides real-time ray tracing and AI training acceleration, sending the most professional GPU to achieve the highest quality and reliability standards. Quadro, NVIDIA graphics cards intended for workstations, running professional computer-aided design (CAD), computer-generated imagery (CGI), digital content creation (DCC) applications, scientific calculations, and machine learning.

Aetina released three Quadro MXM modules, including M3T1000-PN based on Quadro T1000, M3T3000-QN based on Quadro RTX3000, and M3T5000-WN based on Quadro RTX5000. With up to 3,072 CUDA cores and 9.4 TFLOPS performance can achieve almost every needed from industrial and professional graphics design fields. Meanwhile, there are up to four display ports, support HDR video by up to 8K at 60Hz resolution, which sent the users not only fabulous visual working experience but also meets up the work requests of accurate data analysis.

This Quadro MXM series based on Turing architecture, the perfect high-performance visual computing in the data center. Particularly for NVIDIA RTX Turing, supports real-time ray tracing, showing realistic lighting, shadowing, and reflection, and immediately performs a movie-grade rendering. RTX Turing GPUs feature new advanced shading technologies that are more powerful and flexible than the previous version.

Quadro RTX Turing supports deep learning super-sampling (DLSS) technology, catch up trends with AI functions. With Tensor cores, taking 10X speedups in AI training with TF32 and 2.5X boosts for HPC with FP64, providing a revolutionary AI training and inferencing power and graphics computing abilities.

All Quadro MXM modules are available.

Edge computing platform gets SSD integration

March 27, 2020 By Aimee Kalnoskas Leave a Comment

Aetina Corporation announced its successful integration with the world’s first out-of-band management SSD solution Innodisk InnoAGE. Aetina Jetson edge computing platform equipped with InnoAGE solid-state hard drives to achieve the goal of remote out-of-band management. It can reduce the massive cost of manually repairing the edge device, and primarily reduce the downtime of the equipment, making the control of the edge device more convenient.

Aetina displayed the integrated live demo of the Jetson platform and InnoAGE last month in Embedded World 2020 in Nuremberg, Germany. The live demo showed the effortless restart and restored when the edge device is crash. Aetina Jetson edge computing platform has the advantages of small-form-factor and low power consumption that suitable for embedded edge devices. To maintain numerous edge devices, in-band management could be limited by the unpredictable issue when it happened. With the result, in-band management could cause more labor costs and last more extended downtime of edge devices. Compared to that, out-band management gets the point from the opposite way. Out-band management benefits with the more efficient repair of crashed devices and the less workforce.

The platform is integrated with Innodisk’s InnoAGE SSD, which could fulfill remote out-of-band management. InnoAGE SSD equipped with an Azure Sphere chip, which can cut a separate space in the solid-state hard disk and install a separate operating system. InnoAGE connected with Azure Cloud and the system of the device can automatically store in the solid-state hard disk. Once the operating system or software of the edge device is crash, the owner can reset or restore the system of edge devices through the management platform on Azure Cloud. Besides, the real-time status of edge devices can also monitor the cloud management platform, which facilitates remote control and management of many edge devices.

Also, to ensure the security of the most concern of out-band management, Azure Sphere provides the world’s premier data security ability. Making the inference results of edge AI computing secure uploading to the cloud database and eliminating any security risks.

Carrier board hosts Nvidia Jetson Nano module

February 18, 2020 By Aimee Kalnoskas Leave a Comment

As the speedy development of artificial intelligence, the applications have largely expended to all industries. With the results, AI processors have significantly announced to the market. However, to live up the requests from the market, GPGPU and edge computing solutions provider Aetina Corporation provides various alternative products and AI computing platforms for developers’ choices.

Aetina will be at Embedded World 2020 demonstrating the exclusive carrier board for Jetson Nano module – AN110. Potent computing power with low power consumption, and the outlook of small form factor, Jetson Nano plus AN110 have ready to show off its AI energies to all nowadays.

Aetina AN110 is an exquisite carrier board for the Nvidia Jetson Nano module, which ignites the AI potential by delivering 472 GFLOPS of computing performance and operate as low as 5W (10W max). The meanwhile, as the smallest intelligent platform for the Nvidia series, Aetina AN110 is only the size of 87 x 67 mm, will just right for the application and ideal for community uses. The edge devices in this generation, have required the ability with intelligent purposes, with Aetina AN110, this platform will be equipped multiple I/O with 1x HDMI Type A, 1x RJ-45 for GbE, 2x USB3.2 Gen1 Type-A, 5x GPIO and 1x DC-in 12V. Moreover, AN110 supported 1x 4K or 1x FHD camera for machine vision requirements. Not only for vision-critical AI, but the Aetina AN110-Jetson Nano platform also took a vital role by acting as an intellectual gateway, bring the community to AI functional.

Followed Aetina’s business vision, the announcement of AN110 combined with Jetson Nano is one of the crucial steps in Aetina’s edge AIoT ecosystem blueprint. This platform could be the perfect choice with size features and budget tools to enlighten the intelligent life in the city, and the embedded AI computing platform into edge devices to get closer to AIoT.

AI platform lets developers run AI inference economically

December 18, 2019 By Aimee Kalnoskas Leave a Comment

Through the various application in the AIoT market, there are more requests from the developers. To meet the diverse needs, Aetina announces the new Jetson TX2 4GB edge AI computing platform with Aetina Jetson TX2 series carrier board and Nvidia Jetson TX2 4GB module, which is suitable for AI vision computing applications. This embedded AI platform lets developers run AI inference with double the price-performance-ratio of Jetson TX1. Based on the varieties of connectivity demands, Aetina provides three kinds of carrier boards, which support abundant I/O function, and driver-ready extension peripheral I/O modules.

Aetina Jetson TX2 4GB platform brings 1.3 TFLOPs of AI performance and 256 Nvidia CUDA cores, providing double compute performance and power efficiency of Jetson TX1. Additionally, Jetson TX2 4GB offers a better price-performance-ratio than Jetson TX2, which reduces development expenses on the same compute performance level.

Aetina provides a complete patch file for onboard I/O function and extension peripheral module, enabling developers to train and deploy AI vision computing projects quickly.

Development kit speeds embedded AI, vision computing tasks

October 14, 2019 By Aimee Kalnoskas Leave a Comment

Stepping into AI generation, all industries are trying to intellectualize their
application into AI applications. But it always costs money and time to do so. GPGPU and edge AI computing platform provider Aetina Corporation announced its new MXM development kits. These development tools including an MXM motherboard and an MXM to PCIe carrier that can help the
developers to build a test system to confirm performance specifications and related peripheral devices
in the early stage.

In the MXM development kit, Aetina provides MXM motherboard MH110 for evaluation uses that can
shorten the development period, speed up the time of the customer’s vision application to market. MH110
supports all kinds of Aetina MXM 3.0/3.1 type A/B modules. At the same time, MH110 supports up to 7th
Gen. Core i7 CPUs and DDR4 SO-DIMM 2133 MHz dual-channel, expandable up to 32 GB; can easily
fulfill what markets needs in a general way, make a good way to start with AI solution. Also, display via a
console HDMI 1.4 and four DisplayPorts, flexibly adopting the requirements from multi-display, make
more possibility from building a starter kit. Moreover, to get ready for peripheral I/O extension, MH110
got 1x Mini-PCIe slot, 1x M.2 B-key and M-key for Wi-Fi, Bluetooth, 4G LTE, storage or capture card
options.

Aetina provides a carrier board RTM-M3C-6DP that can convert Aetina MXM 3.1 type A/B module into a PCI Express x16 Gen3 interface. The carrier sent an easier way for embedded MXM starters to test the performance and computing capability of graphics card and shorten the development period from the beginning.

This Aetina MXM development kit series can adopt with Aetina MXM modules, the compact, thinnest
graphics module solution based on the industrial standard Mobile PCI Express Module (MXM) Version
3.0/3.1 specification, power by Nvidia Quadro GPU, delivering the latest and leading-edge GPU benefits
for embedded systems. Its superior graphics performance, GPU computing and video capabilities are
the ideal solution for embedded AI and vision computing application such as medical image, defense,
gaming and deep learning applications.

Aetina’s mission to push up intelligent application to all industrial field can be accomplish by MXM
development kit and help our customers shorten their product’s time to market.