Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

SolidRun and Gyrfalcon Team up to Accelerate On-Device AI Performance with Powerful New I.MX 8M Mini SOM

With AI Acceleration and a Range of Connectivity Features, Solidrun’s New I.MX 8M Powered Mini SOM Is Perfect for Developing Next Generation AI Applications for the Edge

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.”

Read More: Taiwanese Startups Receive 4.5 Million Euros from Swiss & French Smart Health Industry at ICT Spring of Luxembourg

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.

Read More: The Artificial Intelligence Week

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 SolidRun, 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.”

Read More: IBM AI and Cloud Technology Helps Agriculture Industry Improve the World’s Food and Crop Supply

SolidRun’s i.MX 8M Mini SOM specifications include:

Model

i.MX 8M Mini Solo

i.MX 8M Mini Dual

i.MX 8M Mini Quad

Processor core

i.MX 8M Mini S

i.MX 8M Mini D

i.MX 8M Mini Q

General Purpose Processor

Arm Cortex-M4 core up to 400MHz

System on Chip

Single core

ARM A53

Dual core

ARM A53

Quad core

ARM A53

Processor speed

Up to 1.8GHz

Floating Point

VFPv4

SIMD

NEON

GPU

GC NanoUltra 3D + GC320 2D

3D GPU Support

OpenGL ES 2.0

HW Video Dec/Enc

Multi Format

Memory

32 bit, up to 3GB LPDDR4-3000

32 bit, up to 4GB LPDDR4-3000

Wired Network

10/100/1000 Mbps

Wireless Network

802.11 a/b/g/n (Optional)

Bluetooth

BT4.2 and BT 5.0 (Optional)

Max resolution

1080p @ 60Hz

Display Interfaces

MIPI-DSI

Dual display support

Yes

Artificial Intelligence Accelerator

Gyrfalcon Technology Lightspeeur® 2803

Supported External Storage Options

NOR-Flash, SD/microSD, PCIe SSD

Supported Internal Storage

eMMC, QSPI-NOR (Optional)

SD/MMC

1

Video Decode

1080p60 VP9, VP8, HEVC/H.265 decoder, AVC/H.264

Video Encode

1080p60 AVC/H.264 encoder, VP8 encoder

USB 2.0

2

Serial ports

2 (RTS/CTS/RX/TX) +1 (TX/RX)

Digital audio serial interface

20 channels, 32bits @384khz

DSD512

SPDIF TX&RX

8 x PDM DMIC channel

Camera interface port

1 x MIPI-CSI2 (4 Lane)

PCIe 2.0

1

I2C

2

SPI

1

PWM

4

GPIO

75

JTAG

Test Point Header

RTC

Yes

Linux Support

Yes

Android Support

Yes

Temperature range

Commercial, Industrial

Main Voltage

5V

IO Voltage

3.3V

SOM Supply

3.3V / 1A

SOM interface

Hirose DF40 connectors 1.5mm up to 4.0mm mating height

Dimensions (W x L)

47mm x 30mm

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.

Read More: Analysts Predict SaaS Revenues to Reach $85 Billion in 2019

Leave A Reply

Your email address will not be published.