- ABOUT IMC
- IoT LIBRARY
- RFP PROGRAMME
Qualcomm powers Fibocom AI smart module
- July 27, 2022
- Steve Rogerson
Chinese firm Fibocom has launched an AI smart module powered by Qualcomm’s QCS8250 system-on-chip (SoC)
The SCA825-W module is designed to meet the requirements of high-end AIoT scenarios such as HD video conferences, HD live streaming, cloud gaming, edge computing, robotics, drones, AR and VR.
The combination of AI and IoT has opened up possibilities for industries requiring automated real-time decision-making and data analysis. The demand for 5G AIoT is expected to skyrocket, according to Counterpoint Research, with shipments of 5G AIoT modules reaching a CAGR of 84% between 2022 and 2030.
Fibocom’s AI smart module has the potential to empower a massive range of compute-intensive use cases.
It integrates an octa-core Kryo 585 CPU, Adreno 650 GPU, dedicated NPU (neural processing unit) 230, and Hexagon DSP for machine learning. The module can deliver up to 15Tops (tera operations per second), enabling complex AI computing performance.
Featuring a Spectra 480 ISP (image signal processor), Adreno 995 DPU and Adreno 665 VPU, it supports up to seven concurrent cameras, triple 4K display and video encode at up to 4K resolution at 120fps, 8K at 30fps, offering image capturing, processing and displaying capabilities.
In addition, the module supports 5G, Wifi 6.0, Bluetooth 5.1 and 2×2 wifi MIMO multi-antenna technology, which allows various wireless connectivity options for industrial and commercial use cases. It also supports the Android 10 operating system and a range of interfaces including Mipi-DSI, I2S, PCIe, uart, USB, I2C and SPI, enabling flexibility and ease of integration to meet the application demands of the AIoT industry.
“With AIoT continuously transforming every industry, high-performance AI modules will become an important pillar,” said Eden Chen, general manager at Fibocom. “Our newly-launched AI smart module SCA825-W is an exceptional part of the Fibocom smart module family, which will take a big step forward in the AIoT field with technological advancements.”