Document Library

This paper introduces an NGFW reference implementation optimized with Intel technologies, including Hyperscan. It offers a reliable proof point for NGFW performance characterization on Intel platforms.

‘Uncore’ roughly equates to logic outside the CPU cores but residing on the same die. Traffic (for example, Data Reads) generated by threads executing on CPU cores or IO devices may be operated on by logic in the Uncore. Logic responsible for managing coherency, managing access to the DIMMs, managing power distribution and sleep states, and so forth.

The massive growth in 5G data traffic continues, with a projected increase in global monthly average usage per smartphone from 19 GB in 2023 to 46 GB by the end of 2028.2 At the same time, communication service providers (CoSPs) face pressure to reduce expenses and fulfill commitments to achieve Net Zero targets. These circumstances make increased energy efficiency a strategic goal for CoSPs.

vxSafenet uses Intel® technology for data plane and deep packet inspection for communications service providers services that let parents keep their child safe on the internet and manage screen time.

This document presents two methods for optimizing the YOLOv4 and YOLOv4-tiny models with customized classes and anchors using Intel® Distribution of OpenVINO™ Toolkit. The object detection use case based on the optimized models is used to verify the corresponding inference results. Furthermore, the decreased inference time of the optimized model is demonstrated with the real-time use case of an ISV.

This guide is to help users install and run Ollama with Open WebUI on Intel Hardware Platform on Windows* 11 and Ubuntu* 22.04 LTS.

The Rock Island Reference Design is a platform developed by Intel, featuring the 13th Gen Intel® Core™ Mobile Processor, specifically tailored for network and edge applications.

The OpenVINO™-based C++ demos in Open Model Zoo are built using CMake that allows developers to build simple to complex software across multiple platforms with a single set of input files. In real business use cases, the OpenVINO™ applications are integrated into the end user’s target application and the build steps may vary depending on the build tool in the production setup. However, if the end users are using g++ compiler to build their applications, they do not want to change their build tool. To facilitate this, this paper presents the steps to build the C++ object detection demo using g++ compiler on Ubuntu 20.04.

Intel® AI Edge Systems Verified Reference Blueprint –Scalable Performance Edge AI on Intel® Xeon Scalable 2S for Computer Vision, and GEN AI is based on dual socket single-node architecture, that provides an environment to execute multiple AI workloads that are common to be deployed at the edge, such as the “Intel® Automated Self-Checkout Reference Package”,and “Generative AI”

Tietoevry R&D team improves Intel FlexRAN software 5G/LTE PHY performance using Advantech SKY-8134S-11 servers featuring 4th Gen Intel® Xeon® Scalable processors with Intel® vRAN Boost.

NexCOBOT’s SCB 100 (Safety Control Board) is a Mini-ITX board with functional safety compatibility. It supports the I/Os and interfaces needed for a controller platform to build robotic control and motion control systems.Certified by TÜV Rheinland, the SCB 100 stands out as the indus try’s pioneering safety controller platform.
For more information and support, please contact our team of experts at fusa@intel.com

The BOXER-6648-ARS is a high-performance Edge AI embedded system powered by Intel® Core™ Ultra Processors, delivering exceptional computing power for AI-driven and industrial applications. Designed for rugged, fanless operation, it ensures reliability in harsh environments while maintaining peak efficiency. Its rich I/O connectivity includes three independent display interfaces, supporting multi-display applications in automation, smart surveillance, and digital signage.