FAQ on the Purpose and Uses of Edge Microvisor Toolkit #545
stevenhoenisch
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
What is Edge Microvisor Toolkit? It is an open source reference Linux operating system that acts as a demonstration vehicle to showcase the full capabilities of Intel processors for Edge AI workloads through Linux patches from Intel that are yet to be upstreamed.
What do the Linux patches from Intel do? The Linux patches optimize performance, security, and other capabilities for Intel silicon -- a result that streamlines integration for operating system vendors and other technology partners.
What Intel processors are typically supported by Edge Microvisor Toolkit?
Edge Microvisor Toolkit has undergone extensive validation across the following Intel processors. The toolkit also provides robust support for integrated and Intel discrete GPU cards as well as an integrated NPU. There are pre-tuned drivers and acceleration libraries for Intel® CPUs and GPUs. Intel® Arc™ B-Series Graphics are discoverable for containerized applications and VMs with pass-through mode to deliver processing power to distributed edge applications. See system requirements.
What forms of the toolkit are available?
The toolkit comes in three principal forms; to obtain and deploy one of the following versions, see our getting started guide:
Edge Microvisor Toolkit Standalone Node, an immutable version integrated with Kubernetes and foundational extensions to deploy and rapidly evaluate edge AI applications on virtual machines and containers powered by Intel platforms.
Edge Microvisor Toolkit Developer Node, a mutable, ready-made version for development, customization, testing, benchmarking, and VM exploration.
Edge Microvisor Toolkit with Preempt_RT, a version you build by using a predefined JSON file with a custom configuration for real-time computing. The Preempt_RT patch for Linux Kernel 6.12 improves real-time performance.
Here's a diagram that illustrates the main differences between the standalone node and the developer node:
I have custom requirements for evaluating Intel processors for my edge and AI workloads. Can I create a custom version for benchmarking my workloads?
Yes, you can build your own mutable or immutable version by selecting a predefined JSON image configuration file and a package list file that determine the image's properties and capabilities. In addition, you can create your own image configuration file and package list to build exactly the version that you want -- a powerful approach to customizing a Linux operating system to validate your edge AI workload on Intel processors.
My organization deployed Edge Manageability Framework. Is there a version of the toolkit for that framework?
Yes, versions of the toolkit are coupled with Edge Manageability Framework to help deliver early access to next-generation Intel platform features. Edge Manageability Framework automates the rollout of new OS profiles to compatible hardware platforms so that you can quickly deploy the latest Intel optimizations. For more information, see Deployment with Edge Manageability Framework and the project's GitHub repository.
What images of the toolkit are available?
The toolkit comes in a variety of images and form factors so you can quickly deploy and validate workloads for various scenarios on Intel® platforms.
What scenarios does Edge Microvisor Toolkit support? The toolkit supports multiple industry scenarios for evaluating various edge and AI workloads on Intel platforms. You can, for instance, use industry-specific sample applications with benchmarks, as well as edge AI libraries with OpenVINO™ inferencing runtime software development kits, to rapidly build, validate, and optimize edge AI solutions on Intel silicon across scenarios and industries.
Does the toolkit include security features and capabilities? Yes, with the toolkit's opt-in security model, you can typically select which security features to enable for your validation or benchmarking effort so you can tune your deployment to balance the trade-offs between mitigating risks and minimizing overhead. These security options protect computers, hypervisors, apps, and data with such capabilities as the following:
What is the Unified Kernel Image? With Edge Microvisor Toolkit, it is a single EFI binary that packages together the Intel® kernel,
initramfs, and associated kernel command-line parameters, a design that simplifies the boot process on UEFI systems and improves security, especially when combined with Secure Boot.How can I contribute to or participate in Edge Microvisor Toolkit? Vendors, developers, and technology partners can take part in our GitHub community in various ways: contributing code, proposing a design, downloading and trying out releases, opening an issue, benchmarking application performance, and -- perhaps most important of all for building community -- participating in discussions:
Beta Was this translation helpful? Give feedback.
All reactions