Software Development & FPGA Acceleration - Vitis HLS 2023.1 introduces a new L1 library wizard [1] - The wizard facilitates downloading, viewing, and instantiating L1 library functions within the Vitis HLS GUI [1] - The report focuses on learning about Vitis L1 libraries [1]

AI Engine Rapid Prototyping Overview - AMD introduces the Versal AI Engine Rapid Prototyping using the AMD Vitis Unified IDE for early design analysis and risk reduction [1][2][12][13] - The rapid prototyping feature is available in the Vitis Unified IDE in version 20242 [13][16] Key Steps in Rapid Prototyping - Involves resource estimation, including tile count, buffer usage, PLIO resources, and stream array traffic [2] - Assesses latency and throughput feasibility with early data flow simulations, prototype kernel coding, and initiation interval loop analysis [2] - Utilizes Vitis libraries for existing block elements and develops candidate vectorization options [3] - Includes building empty kernel wrappers, building the graph and compiling, simulating and analyzing for early estimation [12] Custom Kernel Example: Digital Up Conversion (DUC) Chain - The DUC chain translates a signal from baseband to intermediate frequency band and includes a FIR fractional resampler, half-band interpolators, DDS mixer functions, and an adder functional block [5] - The FIR fractional resampler, the half-band interpolators, and DDS mixer functions can be implemented using the Vitis DSP Library [5] - Focuses on fast prototyping of the custom adder kernel, identifying input/output data types, coefficient types, number of taps, sampling rate, and the kernel function [6] AI Engine System Mapping - Identifies hardware resources such as the number of AI Engine tiles, storage, buffers, and connectivity ports [8] - Considers compute (AIE tiles), storage (buffer size, local memory, DMA size), and input/output bandwidth (PLIO ports, clocking, buffer/stream interfaces) [8] - A custom adder kernel requires a sampling rate of 1200 MSPS with a latency less than 500 ns [9] - The adder is implemented in one tile with two inputs and one output of cint16 type, taking 3KB of data at a sampling rate of 1200 MSPS [10][11] Vitis Unified IDE Implementation - Generates data flow models with parametrized kernel ports, multi-core graph topology, full buffering, stream details, and LUT storages [14] - Allows exploration of hardware utilization through AI Engine compilation and ensures throughput and latency requirements are met through AI engine emulation [14] - Requires creating a new empty AI engine component and using the "Generate AIE Prototype Code" option [15] - Involves setting kernel properties such as name, input/output port properties (data type cint16, dimension to 384 samples), and enabling "Generate Top Level graph and Simulation code" [19][20] Simulation and Analysis - The tool generates graph CPP and H files, with the graph CPP setting the graph to run for one iteration (modifiable for better analysis) [20][21] - Requires adding input text files for simulation, containing values representing cint16 samples per clock on the 64-bit interface [22][23][24][25] - Simulation results report a throughput of 5000 megabytes/second or 1250 mega 16-bit complex samples per system, meeting the requirements [26]

Key Features of AMD Vitis Unified IDE - AMD Vitis Unified IDE utilizes Eclipse Theia framework, offering a modern and responsive GUI to enhance user experience [2] - The IDE supports a bottom-up design flow, enabling the development of system components like AI Engine graphs, C/C++ sourced HLS components, RTL kernels, and software applications [2] - It provides integrated revision control using Git and Python, along with a Tcl script-based interface for command-line component management [3] HLS Component Development - HLS component development is streamlined through a bottom-up design flow managed with a configuration file [3] - The IDE facilitates independent building, simulation, analysis, and debugging of HLS components [3] - Tools like component cloning allow for design optimization exploration, while component comparison provides insights into performance and resource utilization [4] - Code analyzer offers capabilities for architectural refinement [4] Migration Flows from Classic Vitis HLS - Migration from classic Vitis HLS designs to the Unified IDE is possible via GUI, command-line, and scripting [4] - In GUI, specify the hls app file from the classic Vitis HLS project when creating an HLS component [5] - For Tcl scripting, replace `open_project` with `open_component` and remove `open_solution`; specify `-flow_target` as either `vivado` or `vitis` [6] - Python APIs are available for creating and managing HLS components, with configuration specified in a file or directly in the script [8]

HLS Design Flow in Vitis Unified IDE - The AMD Vitis Unified IDE supports a bottom-up approach for heterogeneous system design, enabling the creation of individual system elements as components [2] - The IDE offers various development flows, including HLS, AI Engine Graph, Embedded, and System Development, along with tools for report analysis and user-managed workflows [2] - The Vitis Components view provides hierarchical project navigation, organizing source files and test benches [14] HLS Component Creation and Configuration - An HLS component can be created using the 'Create HLS Component' wizard, which guides users through the process [3] - The HLS component configuration file stores commands and settings for synthesis, simulation, and export [6] - Users can specify the top-level function to be synthesized, with underlying functions also synthesized into RTL [9] - The tool automatically applies uncertainty margin during synthesis to create RTL that is more likely to meet timing in Vivado [11] - The flow target can be set to either 'Vivado IP' or 'Vitis kernel', with the default 'Vivado IP' setting generating a .zip file [11][12] Verification and Packaging - C simulation can be run with default settings, generating a summary report and simulation log file [16][17] - RTL cosimulation verifies the generated RTL against the C test bench to ensure identical results [20] - The design can be packaged into a reusable IP component, with options for Vivado IP, Vitis kernel (.xo file), or RTL output [22][23][24][25] RTL Analysis and Implementation - HLS provides estimations for resource utilization and timing, but accurate RTL analysis requires running Vivado RTL synthesis and place-and-route [25][26] - Vivado synthesis and implementation can be configured before execution using the Implementation settings [26]

Product & Technology - AMD is developing a chip with a focus on power, performance, and area (PPA) [1] - AMD has products supporting AI, which is considered a significant technology with the potential to transform lives by enabling users to perform tasks beyond their expertise [2] - Methodology serves as a recipe for design teams to achieve good PPA, allowing for easy initial setup and further customization, benefiting the entire company [1] Strategy & Culture - Badminton is viewed as a strategic game that helps with relaxation and focus for work [1][2]

Company Overview - Boosteroid is a cloud gaming provider that streams video games from cloud-based gaming rigs to end-user devices [1] - The company has built cutting-edge hardware and software infrastructure for cloud gaming [1] Technology and Infrastructure - Boosteroid utilizes AMD EPYC CPUs and AMD Radeon RX 7900 XT GPUs to deliver high-end video streams with high resolution and performance [2] - The infrastructure is spread across 27 data centers in Europe, North and South America [2] - AMD desktop GPUs are optimized for video streaming and games [3] Customer Base and Experience - Boosteroid caters to both sophisticated and casual gamers, requiring high frame rates, high resolution, and maximum game settings [2] - The platform aims to provide a low latency experience with AAA games [3] Partnership with AMD - Collaboration with AMD allows Boosteroid to offer customers modern GPU and CPU technologies [3] - The partnership facilitates collaboration with AMD engineers [3]

Product Features - AMD EPYC Embedded 9005 processors enhance compute performance, connectivity, and security for industrial, networking, and storage [1] - The processors efficiently process data to optimize Total Cost of Ownership (TCO) [1] - Embedded features enhance longevity and resiliency [1] Legal and Trademark Information - ©2025 Advanced Micro Devices, Inc [1] - AMD, the AMD Arrow Logo, and combinations thereof are trademarks of Advanced Micro Devices, Inc in the United States and other jurisdictions [1]

AI & HPC Solutions - HPE and AMD's systems are designed to address complex problems for the federal government [1] - AMD delivers end-to-end AI solutions from edge to endpoint, data center, and cloud [2] - The HPC and AI sector is experiencing a period of significant opportunity [2] Technology & Performance - AMD offers high-performance and cost-effective solutions [3] - AMD's cores are superior in quality [2] - Gen 12 efficiency and high core counts facilitate cloud platform operations, enabling workload management from anywhere [4] Partnership & Value - AMD positions itself as a partner for long-term value transformation [5] - Public sector efforts aim to benefit customers, taxpayers, and citizens [5] - Technology modernization and innovation are rapidly advancing [3]

Product Highlights - AMD Instinct™ MI350 Series GPUs are designed for Generative AI and high-performance computing (HPC) acceleration in data centers [1] - The GPUs are built on the 4th Gen AMD CDNA™ architecture [1] - The series aims to deliver efficiency and performance for training AI models, high-speed inference, and complex HPC workloads [1] Target Applications - The GPUs are suitable for training massive AI models [1] - They are also applicable for high-speed inference [1] - Complex HPC workloads such as scientific simulations, data processing, and computational modeling can also benefit from these GPUs [1] Legal and Trademark Information - ©2025 Advanced Micro Devices, Inc [1] - AMD, the AMD Arrow Logo are trademarks of Advanced Micro Devices, Inc in the United States and other jurisdictions [1]

AMD at Mobile World Congress 2025 Discover more: https://www.amd.com/en/solutions/telco-and-networking.html *** Subscribe: https://bit.ly/Subscribe_to_AMD Join the AMD Red Team Discord Server: https://discord.gg/amd-gaming Like us on Facebook: https://bit.ly/AMD_on_Facebook Follow us on Twitter: https://bit.ly/AMD_On_Twitter Follow us on Twitch: https://Twitch.tv/AMD Follow us on LinkedIn: https://bit.ly/AMD_on_Linkedin Follow us on Instagram: https://bit.ly/AMD_on_Instagram ©2025 Advanced Micro Devices, In ...