New ProductsMarch 9, 2021
Starter set for Developing Ethernet Connectivity
New starter set for COM-HPC from congatec offers 11th Gen Intel Core processors and options for Ethernet connectivity.
A new COM-HPC starter set presented at embedded world 2021 DIGITAL is optimized for modular system designs utilizing the latest high-speed interface technologies such as PCIe Gen4, USB 4.0 and up to ultra fast 2×25 GbE connectivity as well as integrated MIPI-CSI vision capabilities. The starter set is based on congatec’s PICMG COM-HPC Computer-on-Module conga-HPC/cTLU, which leverages 11th Gen Intel Core processor technology (code name Tiger Lake).
This new high-end embedded module generation targets system engineers working on the broadband connected edge devices that are emerging in industrial IoT. Target markets include medical, automation, transportation and autonomous mobility, as well as vision based inspection and video surveillance systems, to name just a few.
“Our new COM-HPC starter set – which can be ordered with a choice of individually compiled components from our COM-HPC ecosystem – puts engineers in the fast lane to Gen4 interface technology and further ultra fast connectivity,” said Martin Danzer, Director Product Management at congatec. “PCIe Gen4 doubles the throughput per lane compared to Gen3, which has massive effects on system designs as it enables engineers to double the number of connected extension devices. Handling all this under more complex design rules to achieve the required signal compliance makes it even more important to have a mature evaluation and benchmark platform for own system designs.”
The starter set’s various Ethernet configuration options range from 8x 1GbE switching options and 2x 2.5 GbE including TSN support up to dual 10 GbE connectivity. congatec’s comprehensive AI support for MIPI-CSI connected cameras from Basler adds further application readiness to IIoT and Industry 4.0 connected embedded systems. AI and inferencing acceleration can be achieved with Intel DL Boost running on the CPU vector neural network instructions (VNNI), or with 8-bit integer instructions on the GPU (Int8).
Attractive in this context is the support of the Intel Open Vino ecosystem for AI, which comes with a library of functions and optimized calls for OpenCV and OpenCL kernels to accelerate deep neural network workloads across multiple platforms to achieve faster, more accurate results for AI inference.