Developer Kits with Intel® Xeon® D-2100 Processor Product Family
Overview
Develop and deploy solutions on Intel's transformative and groundbreaking data center processor architecture for edge computing demands.
- Accelerate network security, routing, and real-time data compression using an Intel® Xeon® D processor in a low-power SoC.
- Use preinstalled, configured, and validated software.
- Get set up quickly using preloaded samples.
- Accelerate workloads on CPUs using the Intel® Distribution of OpenVINO™ toolkit.
- Manage networking applications and services with the optimized and cohesive Open Network Edge Services Software (OpenNESS) framework.
- Converge IoT edge and network service capabilities to merge network workloads with inference, analytics, media, and IoT applications on a common infrastructure, thereby delivering ultimate time-to-business outcomes while reducing the total cost of ownership.
Preinstalled Software
Get the most out of your hardware performance with OpenNESS, Intel Distribution of OpenVINO toolkit, CentOS*, and libraries.
Pretrained Models for Acceleration
Choose from a variety of optimized detection and recognition models to develop deep learning applications.
Training Extensions for Deep Learning
Modify, customize, train, and extend computer vision models for deep learning and inference optimization.
Who Needs This Product
System integrators, independent software vendors (ISVs), and IoT developers who build vision-based inferencing applications for edge computing that support:
- Wireless communications networks
- Enterprise IT
- Cloud service providers
Reference Implementations
These solutions have been prebuilt and validated for developers to test and deploy industrial, retail, and smart city applications enabled for computer vision.
Hardware
Prevalidated developer kits with an Intel® Vision Accelerator Design product.
Intel Xeon D-2100 Processor Product Family
Intel® Movidius™ Myriad™ X VPU
Deep-Learning Performance Benchmark Data on Intel® Platforms
IEI* PUZZLE Developer Kit
Included:
Software
The following software is preinstalled on the development kits:
CentOS*
Open Network Edge Services Software (OpenNESS)
This open-source, multi-access edge computing (MEC) software toolkit enables highly optimized and performance edge platforms to onboard and manage applications and network functions with cloud-like agility across any type of network.
Intel® Distribution of OpenVINO™ Toolkit Runtimes
- Enable convolutional neural network-based deep learning inference on the edge.
- Support heterogeneous execution across various accelerators—CPU, GPU, Intel® Movidius™ Neural Compute Stick (NCS), and Intel Vision Accelerator Design products—using a common API.
- Speed up time to market via a library of functions and preoptimized kernels.
Intel® Edge Software Hub
- Develop, test, deploy, and maintain solutions at the edge with software packages and tools.
- Optimize your computer vision and deep learning applications for Intel® architecture with the Intel Distribution of OpenVINO toolkit.
- Maintain and manage your applications with containerized architecture and regular updates.
- Get started quickly with reference implementations, tutorials, and samples.
Additional Software Available for Download
Intel® oneAPI Base & IoT Toolkit
The combination of Intel® oneAPI Base Toolkit and Intel® oneAPI IoT Toolkit provides a core set of high-performance build tools, libraries, and analysis tools to simplify IoT system design, development, and deployment across CPU, GPU, FPGA, and other accelerator architectures that run at the network’s edge.
Get Help
Your success is our success. Access these support resources when you need assistance.
Support for IEI* Puzzle AIoT Developer Kits
Supermicro Services and Support
Product and Performance Information
As measured by a ResNet-50 network with a batch size of 1 and int8 precision on Intel® Core™ i7-9700E vs. Intel® Core™ i7-7700 processor Intel® Core™ i7-9700E processor, PL1= 65 W TDP, 8C8T, Turbo up to 4.4 GHz, Intel® UHD Graphics 630, Motherboard: Asus* Prime Q370M-C, Memory: 2 times 8 GB DDR4-2666, Storage: 512 GB Intel® SSD 545s Series, OS: Ubuntu* 18.04 LTS (Bionic Beaver). Intel® Core™ i7-7700 processor, PL1=65W TDP, 4C8T, Turbo up to 4.2 GHz, Intel® HD Graphics 630, Motherboard: Asus* Prime Q270M-C, Memory: 2 times 8 GB DDR4-2400, Storage: 512 GB Intel® SSD 545s Series, OS: Ubuntu 18.04 LTS (Bionic Beaver). ResNet-50 is a popular CNN (Convoluted Neural Network) architecture that uses inception modules for computer vision recognition tasks (such as image classification). Image classification is the task of classifying a given image into one of the predefined categories. Reported metrics: Performance = Images/Second Performance results are based on testing as of May 24, 2019 and may not reflect all publicly available security updates. No product can be absolutely secure.