TEL AVIV, June 3, 2019 - SolidRun, a leading developer and manufacturer of high-performance System on Module (SOM) solutions, Single Board Computers (SBC) and network edge solutions, today introduces its i.MX 8M Mini System on Module(SOM) with robust processing power and Gyrfalcon's artificial intelligence acceleration technology. SolidRun's i.MX 8M Mini SOM combines all of the essential components necessary to quickly prototype powerful AI solutions into a compact 47mm x 30mm module, including processor and memory options, a GPU, Gyrfalcon's Lightspeeur® 2803S Neural Accelerator chip, optional flash storage, audio and video input and output and more.
"It used to be that the cloud was the best solution for neural network processing due to having virtually limitless processing power. However, with the vastly capable embedded CPUs available to edge devices today, such as the i.MX 8M series from NXP, and the efficient neural network models and AI frameworks in use today, more device manufacturers are migrating AI processing loads out of the cloud to the edge," said Atai Ziv, CEO at SolidRun. "We teamed up with Gyrfalcon to design our i.MX 8M Mini SOM to serve as the ideal building block for device manufacturers to harness the power of i.MX 8M series processors and the Lightspeeur® 2803S chip to quickly prototype and bring to market powerful new hardware solutions that unleash the true potential of edge AI."
With designs supporting low-power applications to those that require extreme processing capabilities, SolidRun's i.MX 8M Mini SOMs harness NXP's Arm Cortex A53 single/dual/quad core 1.8Ghz i.MX 8M processors with advanced 14LPC FinFET process technology. This cutting-edge building block is tailor made for a wide range of IoT and industrial applications, and features up to 4GB LPDDR4, wireless communications options including Bluetooth and WIFI, PCIe 2.0 and robust multimedia features including 20 audio channels (32bits), MIPI-DSI, and a 1080p encoder and decoder.
SolidRun's new Mini SOM also harnesses the power of Gyrfalcon's Lightspeeur® 2803S Neural Accelerator to help manufacturers quickly and cost effectively create powerful Edge AI applications based on TensorFlow, Caffe and PyTorch deep learning frameworks that benefit from a powerful dedicated AI acceleration processor. The 9 x 9mm accelerator, based on Gyrfalcon's Matrix Processing Engine architecture, offers multi-dimensional, high-speed neural network processing at very low power, rated at 24 TOPS/W per chip.
Ideal for digital assistant solutions, autonomous cars, security camera systems, video and audio analytics, digital signage and more, SolidRun's Mini SOM can be used in fan less applications. Its ability to maintain a low operating temperature without a fan reduces the potential of heat and dust-related failures, which results in reliable long-term operation and performance.
Additionally, SolidRun offers the HummingBoard Pulse carrier board, which is perfect for pairing the powerful AI processing capabilities of the i.MX 8M Mini SOM with a nearly limitless variety of external connectivity and communications features, via its integrated USB-C, Micro USB and USB 3.0 ports, mPCIe and M.2 expansion ports, 10/100/1000 ethernet jack (supports PoE), microSD slot, SIM Card holder, HDMI and DSI 2.0 display output, audio input and output and more.
"It is a great opportunity to collaborate with Solid Run, and we are looking forward to seeing many customers using this powerful combination of capabilities built into the i.MX 8M SOM offerings," said Bin Lei, VP of Sales at Gyrfalcon Technology, Inc. "These packages will accelerate a customer's time to market, and makes great use of our market leading AI accelerator for edge and edge server innovations."
The i.MX 8M Mini SOM with Gyrfalcon Lightspeeur® 2803S AI accelerator chip is available today through SolidRun or Arrow, with a starting MSRP of $56 USD. To help expedite the development process, customers will be provided access to an SDK featuring drivers and prebuilt libraries, API for easy software integration, pretrained Convolutional Neural Network models and sample source code.
For more information about the i.MX 8M Mini SOM, please visit https://www.solid-run.com/nxp-family/imx8m-mini-som. Or, for more information about SolidRun, please visit www.solid-run.com. For more information about Gyrfalcon's Lightspeeur® 2803S AI accelerator chip, please visit https://www.gyrfalcontech.ai/solutions/2803s/.