Hello, and welcome. In this video, we'll guide you through an overview of the AMD Versal Network on Chip, NoC, and discuss key strategies for its performance tuning. We will first start with an introduction to the AMD Versal Network on Chip, NoC, followed by the NoC architecture and terminology. Then we will show you how to access the Versal NoC for your designs.And finally, we will go over important NoC settings needed to achieve a desired bandwidth and latency. Let's get started. The AMD Versal Network on ...

In this video, we will walk you through the AMD Enterprise AI suite. The suite is a full stack solution for developing, deploying, and managing your AI workloads on a Kubernetes platform optimized for AMD compute. We will look at two main components.AMD Resource Manager enables optimization of infrastructure through cluster and node management, ensuring high GPU efficiency, providing monitoring and dynamic resource sharing, and AMD AI Workbench that supports enterprises with accelerated end to end AI develo ...

What you're seeing today is our AMDers. The drive, the energy, the compassion, and the commitment to giving back to our communities. One million meals.Boy, we're really having an impact in the lives of folks around the world and that's something to go celebrate. It's continuously important for us to partner with corporations, not just for us to grow the movement, but for us to also send these meals to our international partners so that they're able to get into the bellies of those kids and families who need ...

AI Technology & Application - Dell 14 plus integrates on-device AI, enhancing accessibility for everyday consumers [1] - AMD Ryzen AI processors feature a three-layer architecture: CPU, GPU, and NPU [1][2] - The NPU (neural processing unit) handles AI-specific tasks, freeing up the CPU and GPU for other processes [2] - AI facilitates seamless multitasking and overall functionality [2] Product Features - Dell 14 plus 2 in 1 boasts a small footprint [1]

Overview of AMD Embedded Development Framework (EDF) - AMD EDF is a methodology for developing and distributing embedded software components for AMD adaptive SoC and FPGA products [2] - EDF is based on open-source tools, including a Yocto Project-based build environment, offering a full software stack from Linux and boot firmware to RTOS and hypervisor support [3] - AMD provides pre-configured system images for evaluation, supporting advanced and multistage boot flows [4] - EDF aims to shorten the development cycle from evaluation to deployment with prebuilt images and automated flows [5] Key Features and Capabilities - Supports platform-level development and embedded software solutions [2] - Offers decoupled software and hardware environments for product development and maintenance [4] - Supports single and multistage boot options, accommodating various boot devices and configurations [9] - Multistage boot initializes hardware in two steps: primary boot via OSPI and secondary boot via SD card [10][11] Getting Started and Evaluation - Requires an AMD Versal evaluation kit and the corresponding AMD EDF Linux BSP Disk Image [6] - The demo uses the Versal AI Edge Series Gen 2 VEK385 evaluation board, supporting multistage boot via OSPI and SD card [7] - The BEAM (Board Evaluation and Management) tool, a web-based GUI, allows monitoring and modifying board parameters [18] Practical Implementation - The process involves connecting to the system controller, programming the OSPI flash with a bootloader, and booting EDF Linux from an SD card [2] - Includes loading a prebuilt PL firmware application and testing it on the development board using a Python script [2][8] - The default boot architecture for VEK385 boards is multistage boot [9]

Overview of AMD Embedded Development Framework - AMD Embedded Development Framework (EDF) explores the Software Hardware Exchange Loop (SHEL) flow [1] - The tutorial demonstrates generating an XSA from AMD Vivado design suite, building a system device tree, and creating a custom Linux image using the Yocto Project [1] SHEL and Hardware-Software Integration - SHEL streamlines hardware–software integration across AMD Vivado, Vitis tools, and open-source tools [1] - SHEL enables efficient handoff and deployment on AMD Versal™ VEK385 platforms [1] Resources and Contact - More information is available at https://www.amd.com/en/products/software/adaptive-socs-and-fpgas/embedded-software/embedded-development-framework.html [1] - Subscribe to AMD at https://bit.ly/Subscribe_to_AMD [1] - Join the AMD Red Team Discord Server: https://discord.gg/amd-gaming [1]

Development & Deployment - AMD Embedded Development Framework (EDF) supports SDK-based development flow for AMD Versal adaptive SoCs [1] - EDF SDK can be installed from a shell script and potentially speeds up build tasks compared to on-target building [1] - The SDK allows cross-compilation of applications for Arm cores using an x86 host PC [4] - On-target development allows packages to be installed from the package feed, offering flexibility compared to the fixed content of the SDK [1] Workflow & Tools - The process involves installing the AMD EDF SDK, developing and compiling applications/kernels on an x86 host PC, and deploying them to a Versal AI Edge Series Gen 2 (VEK385) evaluation board [1] - QEMU flow is explored for application deployment, offering system emulation capabilities [1][2] - The "scp" command is used to copy executable files from the SDK to the evaluation board via the PS Ethernet [1] Kernel Module Development - Kernel modules can be developed and compiled on a host PC and deployed to a Versal evaluation board [1][4] - Preparing the kernel involves setting the kernel source directory environment variable and the local version variable [1] - The generated kernel module file can be copied into the kernel module directory of the active kernel on the evaluation board [2]

Future Workforce Development - AMD emphasizes the importance of nurturing the next generation of engineers for its future [1] - AMD actively supports students in the STEM field, particularly those interested in computers and PC technology [1] - AMD provides hands-on experience to students, opening doors to future opportunities they may not have considered [2] - AMD's community engagement includes giving back through various events and programs worldwide [1] Technological Advancement & Education - AMD highlights the importance of understanding PC components in the age of AI [3] - AMD aims to inspire students through hands-on experience with processors, graphics cards, and other PC components [3] - AMD's initiatives provide students with a tangible understanding of their potential future roles in the technology sector [2]

Overview of AMD Embedded Development Framework (EDF) - AMD Embedded Development Framework (EDF) provides a fast path to develop and distribute embedded software components for AMD adaptive SoC and FPGA products [2] - EDF is based on non-proprietary and open-source tools, including a Yocto Project-based build environment, offering a full software stack from Linux and boot firmware to RTOS, hypervisor, bare-metal support, and reference designs [3] - AMD provides pre-configured, feature-rich system images for turnkey evaluation, supporting advanced flows as well as single and multistage boot flows [4] - EDF shortens the journey from evaluation to deployment with prebuilt images, automated flows, and role-based development paths [5] Hardware and Software Setup - The demonstration uses the Versal AI Edge Series Gen 2 VEK385 evaluation board, supporting multistage boot via OSPI and an SD card [7] - The default boot architecture for AMD Versal AI Edge and Prime Series Gen 2 boards (VEK385) is multistage boot [9] - The first stage of multistage boot loads the boot firmware and PLM via OSPI, while the second stage loads the Linux operating system using the SD card [10][11] - The board provides 3 COM ports: one for the processor system (PS), one for the programmable logic (PL), and one for the system controller [15] Demonstration and Testing - The Board Evaluation and Management (BEAM) tool, a web-based GUI, allows monitoring and modifying board parameters and running board tests [18] - The demonstration includes flashing the OSPI boot image and the SD card with the EDF Linux BSP Disk Image [20][21] - The prebuilt image contains an example PL firmware application accessed via the dfx-mgr-client command [23] - A Python script is used to interact with the PL, verifying that the PS and PL were both loaded successfully by reading and writing to block RAM addresses and blinking GPIO LEDs [26]

Overview of AMD EDF Linux Integration and Development - The video demonstrates how to use a prebuilt Yocto Project framework to generate EDF Linux disk images and artifacts for AMD embedded devices [1] - It covers creating custom OS images, ranging from simple Linux builds to complex setups with hypervisors and containers [1] - The process includes setting up the Yocto Project environment, building single-stage and multi-stage EDF Linux disk images, and configuring a QEMU environment for emulation [2][3][4] Key Steps and Procedures - Configuring Git with username and email, and setting up the Yocto Project environment are essential initial steps [6][7] - The Repo tool is used to manage multiple Git repositories for EDF flows [5] - Generating a single-stage boot image for VEK280 involves running specific bitbake commands [11] - Generating a multi-stage boot image for VEK385 requires creating an OSPI binary image and a Common EDF Linux disk image [3][16][17] - QEMU can be used to simulate the generated OSPI and WIC images by merging the two images using the bundled qemuboot-tool [4][20][21] Customization and SDK - Customizing the SDK involves modifying the SDK recipe and building it using bitbake [25] - The resulting SDK install script is placed in the "tmp/deploy/sdk" directory [25] File Sizes and Verification - The bootbin file for VEK280 should be approximately 3 to 4 MB [13] - The edf-linux-disk-image .wic file should be approximately 9 to 10 GB [14] - The edf-versal-2ve-2vm-vek385-sdt-seg-.bin file for VEK385 should be approximately 270 MB [19]