High-density ultra-compact Inforce 6403 system-on-module engineered for intelligent display devices and smart enterprise use cases
Tempe, Ariz., November 3, 2021 — SMART Wireless Computing™, a business of SGH (Nasdaq: SGH) and a leading provider of edge computing embedded solutions, today announced the Inforce 6403, a powerful new system-on-module (“SoM”) based on the Qualcomm® QCS610 which enables advanced visual computing for AI-enabled surveillance camera and edge appliances, connected body cameras, smart displays, and other internet-of-things (IoT) wireless network edge devices. The new Inforce 6403 SoM brings on-device artificial intelligence (AI) and machine learning (ML) to cameras and displays for fast decision making, while enabling multiple connectivity options for critical data transfer, all in a compact footprint that is both power-efficient and cost-effective.
The Inforce 6403 SoM supports 4K UltraHD (HEVC) video capture and playback capability with on-device AI to enable video analytics applications integrated into smart cameras, such as face detection and object tracking. With a wide range of the latest high-bandwidth connectivity options that includes Ethernet RGMIII, 802.11nac Wi-Fi, Bluetooth 5.x, USB-C, and LTE Cat 4 via a carrier board, the Inforce 6403 SoM enables cameras to stream large files quickly. A compact LGA package measuring just 43 mm x 32.5 mm (1.69 in x 1.28 in) makes the Inforce 6403 SoM easy to integrate into camera housings and systems, particularly in applications where a soldered connection can provide a rugged solution.
“The new SMART Wireless Inforce 6403 SoM addresses the need for power-efficient, on-device compute capability with AI-enabled video analytics demanded by the fast-growing connected camera market,” said Todd Wynia, vice president, product management at SMART Wireless Computing. “Inside the compact module, which is slightly larger than a camera’s SD card, lies some incredible processing power making it ideal for dash and body cams, enterprise security, multichannel AI boxes, smart displays and video conferencing.”
“AI and edge computing have digitally transformed businesses and the new SMART Wireless module will help support a wide range of ecosystem players and businesses in enabling the adoption of next-generation connected camera and AI capabilities. The highly-integrated, low-power Qualcomm QCS610 – at the heart of SMART Wireless’ new Inforce 6403 SoM – brings premium imaging and hardware acceleration of ML to the edge, supporting leading-edge inferencing capabilities. We believe this new solution will enable faster time to commercialization and provide the capabilities to pack feature-rich services at the intelligent edge,” said Siddhartha Franco, director, business development, Qualcomm Technologies, Inc.
This latest module comes with a software package that includes integration with Google® Firebase and a sample application to upload or stream videos in real time. Google Firebase is a unified backend-as-a-service (BaaS) platform for mobile and web developers that integrates with other Google services.
Technical Specifications and Application Benefits
- The Qualcomm QCS610 SoC at the heart of the Inforce 6403 SoM integrates:
- Qualcomm® Kryo™ 460 CPU with independent efficiency and power clusters.
- Dual 14-bit Qualcomm Spectra™ 230 image signal processors support up to 24MP for simultaneous concurrent cameras capturing sharp images.
- The Qualcomm® Adreno™ 612 GPU provides efficient rendering of advanced 3D graphics.
- Qualcomm® Hexagon™ Vector eXtensions (HVX) on Hexagon 685 DSP enable accelerated machine learning through deep neural network models and with advanced Qualcomm® Neural Processing Engine SDK support and TensorFlow Lite.
- A secure processing unit enables secure boot, DRM and content protection creating a security-rich environment for the camera system.
- The Inforce 6403 SoM incorporates enhanced electromagnetic interference shielding for better radio frequency noise protection, while also improving heat dissipation to improve performance.
- A reference design based on this SoM offers functionality to help developers create and optimize their products quickly, cost-effectively and with lower risk, including integrated HDMI 2.0 output and an optional North America and Canada regions pre-certified LTE Cat 4 module.
Starting in mid-November, customer samples will be available to order at www.smartwirelesscompute.com priced at $139 for the SoM and $249 for the development kit, which includes a SoM, evaluation carrier board with IO, and a starter kit that includes a power adapter and cable.
About SMART Wireless Computing (formerly Inforce Computing, Inc.)
SMART Wireless Computing is a leading developer of high-performance, production-ready embedded computing platforms for IoT applications. Our customers create applications in medical imaging, videoconferencing/collaboration, AR/VR-based hands-free computing, industrial internet-of-everything, commercial drones, and robotics.
SMART Wireless Computing is part of the Intelligent Platform Solutions (IPS) business within SGH. IPS is accelerating digital transformation with emerging technologies and innovative platforms that create value, improve competitiveness and unify edge, core and cloud.
The stylized “S,” “SMART,” “SGH,” and “SMART Global Holdings” are registered trademarks or trademarks of SMART Global Holdings, Inc. in the United States and other jurisdictions. The stylized “S” combined with “SMART” and “Wireless Computing” are trademarks of SMART Modular Technologies, Inc. All other trademarks are the property of their respective owners. ©2021. All rights reserved.
Qualcomm, Kryo, Qualcomm Spectra, Adreno, and Hexagon are trademarks or registered trademarks of Qualcomm Incorporated. Qualcomm IoT Solutions, Qualcomm QCS610, Qualcomm Kryo, Qualcomm Spectra, Qualcomm Adreno, Qualcomm Hexagon, and Qualcomm Neural Processing Engine SDK are products of Qualcomm Technologies, Inc. and/or its subsidiaries.
Communications Director, Intelligent Platform Solutions
+1 (602) 330-6846
Sandstar Communications for SMART Wireless Computing
+44 (0) 77 86 26 32 21