2026-09-09 13:00
Exciting advancements in real-time global illumination were showcased at ECCV 2026. A new generative method employs a single-step latent diffusion model for stable, high-quality lighting. ✨ This model eliminates the need for costly iterative processing and enhances temporal coherence for frame-by-frame generation. It effectively uses scene signals and lighting hints to improve rendering quality. 🖼️ Results show significant improvements in visual fidelity and stability compared to previous...
Source: AMD Developer Blog
2026-08-27 12:00
🚀 Exciting news for developers! The AMD FSR plugin has been updated for Unreal Engine 5.8. This update includes support for AMD Radeon RX 7000 Series GPUs and introduces FSR Upscaling version 4.1.1, enhancing image quality significantly. The update features machine learning-powered frame generation, delivering smoother gameplay and improved visuals. Plus, integration for developers is simplified with automatic updates for FSR versions. Learn more about the advancements in Unreal Engine 5.8!...
Source: AMD Developer Blog
2026-08-20 18:00
🚀 Introducing a lightweight, attention-based neural model for global illumination (GI) that enhances off-screen indirect lighting using reflective shadow maps. This approach balances real-time performance with quality, predicting only the indirect illumination component to improve shadow effects. It trains on synthetic data from 11 scenes and shows promising results in unseen scenarios. The model operates efficiently, achieving quick processing times while maintaining high fidelity in...
Source: AMD Developer Blog
2026-08-13 14:30
🚀 MiniDXNN v0.4.0 has been released! This update enhances GPU-accelerated MLP training and inference on DirectX® 12. Key features include support for D3D12 Linear Algebra (SM 6.10) and input encoding for neural texture compression. A new interactive GUI app allows for real-time training and visualization. For developers, the update requires the Microsoft AgilitySDK 1.721-preview. #MiniDXNN #DirectX12 #NeuralNetworks #MachineLearning #TechUpdates
Source: AMD Developer Blog
2026-07-22 13:00
🚀 Exciting advancements in ray tracing! A recent study by Gruen et al. addresses the challenges of animating complex geometry in real-time graphics. By using tetrahedral cages, it effectively decouples animation costs from triangle counts. This method allows for massive scenes with hundreds of millions of animated triangles to be rendered efficiently, significantly cutting down memory usage and update costs. 🌳✨ The paper showcases performance with 585 million animated triangles at 60 FPS on...
Source: AMD Developer Blog
2026-07-14 12:00
🚀 Exciting advancements in GPU crash debugging! AMD has introduced the Radeon GPU Detective (RGD) MCP Server, which connects LLM agents to its crash analysis pipeline. This tool simplifies post-mortem debugging, allowing developers to analyze GPU crash dumps with a single prompt. By using structured access to crash data, LLMs can quickly identify root causes and suggest fixes, enhancing efficiency for developers. Discover how this innovation transforms the debugging process! #GPUDebugging...
Source: AMD Developer Blog
2026-06-24 19:07
🚀 Exciting news for gamers and developers! The AMD FSR "Redstone" SDK 2.3 update introduces ML-powered FSR Upscaling 4.1.1, enhancing performance on AMD Radeon RX 7000 Series GPUs. This update also includes Frame Generation 4.0.1 and Ray Regeneration 1.2 improvements for RDNA 4 GPUs. Neural rendering is set to transform real-time graphics, making it easier to deliver high-quality visuals across various platforms. 🎮💻 #AMD #FSR #GamingTech #Graphics #GameDevelopment
Source: AMD Developer Blog
2026-06-11 16:26
🚀 Exciting updates are here! The AMD Radeon Developer Tool Suite (RDTS) has released RGP 2.7, enhancing optimization for DirectX® 12 and ray tracing workloads. Key features include: - Viewing DirectX 12 shader source code directly in the profiler - New metrics for tracking instruction-level thread divergence This update supports the latest AMD hardware including Radeon AI PRO R9600 Series and Ryzen AI 400 Series processors. Ensure you’re using AMD Software: Adrenalin Edition™ 26.5.2 or higher...
Source: AMD Developer Blog
2026-06-02 19:02
Unlock the potential of AMD RDNA™ 4 architecture GPUs with in-register matrix transpose techniques! 🔄 This article delves into optimizing matrix transposition for FFT and Neural Texture Compression using WMMA. It highlights the challenges faced due to the absence of shared-memory transpose loading and in-register capabilities. A practical solution involves using warp shuffle instructions, though it has its limitations due to the RDNA 4 WMMA layout. Explore innovative coding methods to enhance...
Source: AMD Developer Blog
2026-06-02 19:01
Unlock the potential of AMD RDNA™ 4 architecture GPUs with the latest insights on Wide WMMA. 📈 This article explores methods to maximize memory bandwidth for low-precision GEMM operations, crucial for deep learning models like MLPs and CNNs. By extending the K dimension, users can achieve double the memory throughput for FP8 and INT8 data types, maintaining numerical accuracy. Learn more about optimizing performance and check out the sample code provided! 💻 #AMD #RDNA4 #DeepLearning #GEMM...
Source: AMD Developer Blog
2026-06-02 19:00
🚀 Discover the latest insights on optimizing deep learning with AMD RDNA™ 4 architecture GPUs! This article dives into fused GEMMs, a key technique for enhancing performance. 📊 It explains the WMMA layout crucial for effective execution, emphasizing the need to transpose matrix D from M-major to N-major format. 💻 The guide also includes sample code and verification against hipBLAS, ensuring accuracy in implementation. #AMD #RDNA4 #DeepLearning #GEMM #TechGuide
Source: AMD Developer Blog
2026-05-19 06:04
🚀 Exciting updates in AMD Schola v2.1! This release enhances Unreal Engine integration, introducing StateTree support for smoother training and inference. It also brings Kubernetes support for distributed training, allowing scaling in cluster environments. Imitation learning workflows are strengthened with expanded Minari tools, making data collection easier. Command-line enhancements simplify the evaluation and configuration processes. Explore the new features to streamline your AI training...
Source: AMD Developer Blog
2026-05-07 20:51
🚀 AMD has partnered with Samsung to introduce the Dense Geometry Format (DGF), a new open standard for geometry compression. This innovation aims to enhance ray-traced real-time 3D applications by reducing memory usage and latency. 🔍 The updated AMD DGF SDK now includes DGF SuperCompression technology, making geometry even smaller and easier to render on non-DGF devices. 📅 Since its introduction in July 2024, AMD has released an open-source toolchain and a provisional Vulkan extension to...
Source: AMD Developer Blog
2026-05-07 14:37
🚀 AMD has introduced DGF SuperCompression (DGFS), a new software system that reduces Dense Geometry Format file sizes while maintaining block reconstruction accuracy. This update allows for efficient decoding to both DGF blocks and traditional meshlets, enhancing cross-device compatibility. Key benefits include up to 22% smaller file sizes and the ability to target both DGF and non-DGF devices with a unified asset format. Learn more about this innovative technology! #AMD #DGF...
Source: AMD Developer Blog
2026-04-09 01:21
🚀 Exciting news for developers! Introducing MiniDXNN, a native HLSL and DirectX 12 library designed for fast MLP inference. This library leverages AMD Radeon™ RX 9000 series matrix cores, streamlining the integration of MLPs into real-time rendering. MiniDXNN offers optimized kernels, unit tests, and full documentation. It aims to enhance performance by reducing the need for interop with compute APIs. Training support is also on the way! 🔗 Explore MiniDXNN on GitHub and see what you can...
Source: AMD Developer Blog
2026-04-09 00:21
🚀 Exciting news for game developers! Introducing MinDXNN, a native HLSL and DirectX 12 library designed for fast multi-layer perceptron (MLP) inference. This library leverages AMD Radeon™ RX 9000 series matrix cores for optimized performance, streamlining the integration of MLPs into real-time rendering pipelines. Key features include optimized inference kernels, unit tests, sample applications, and complete documentation. Training support will be available in future updates. Explore MinDXNN...
Source: AMD Developer Blog
2026-04-02 09:00
Discover how GOALS is transforming esports performance on handheld PCs! 🎮 In part 1, the article highlights the use of AMD Ryzen processors and the ADLX SDK to enhance power management and thermal regulation. This approach benefits players using both outdated and modern hardware. By addressing power management, GOALS aims to minimize fan noise and carbon footprint while maintaining competitive gameplay. This is crucial for players in hot climates who may experience discomfort during gaming...
Source: AMD Developer Blog
2026-04-02 09:00
Discover how GOALS enhances esports performance on AMD Ryzen handheld PCs! 🎮 This article explores tailored device profiles that ensure optimal gaming experiences without player setup. It highlights the integration of AMD FSR for upscaling and frame generation, adjusting to power states for extended play. Learn about unique configurations that cater specifically to each handheld device. #Esports #Gaming #AMD #HandheldPC #GameDevelopment
Source: AMD Developer Blog
2026-03-23 09:00
🚀 Exciting news for game developers! The AMD FSR SDK 2.2 is now available on GPUOpen. This update introduces ML-powered FSR Upscaling 4.1 and FSR Ray Regeneration 1.1, optimized for AMD RDNA 4 graphics. These features enhance visual fidelity and performance across handhelds, consoles, and PCs. Key updates include improved image quality in FSR Upscaling 4.1, especially during motion, ensuring sharper visuals. Plus, the SDK supports earlier architectures with analytical fallbacks. #AMD #FSRSDK...
Source: AMD Developer Blog
2026-03-17 16:00
🚀 Exciting news for developers! AMD has introduced Smoldr, an open-source command-line tool designed to simplify the process of running DirectX 12 HLSL shaders. With Smoldr, you can compile shaders and manage resources using just a text script—no need for C++ coding! This tool focuses on compute shaders but also supports raytracing. Smoldr is currently a work-in-progress, and contributions are encouraged. Explore more on GitHub! 🖥️✨ #AMD #DirectX12 #OpenSource #GameDev #ShaderDevelopment
Source: AMD Developer Blog
2026-03-13 13:00
🚀 Exciting developments from GDC 2026! Microsoft and AMD have announced new technologies for Windows developers, including DirectStorage 1.4 and updates to PIX tools. These innovations focus on real-time graphics and improved performance, with support for the latest Agility SDK. DirectStorage 1.4 introduces Zstandard compression for faster load times and better asset streaming. Collaboration continues to enhance the Windows graphics ecosystem, ensuring developers have the tools they need....
Source: AMD Developer Blog
2026-02-24 13:30
🚗 At CES 2026, Epic Games and AMD introduced the Unreal Engine 5 Next-Gen HMI Experience. This innovation integrates instrument clusters, maps, and applications into one seamless interface. The AMD Ryzen AI Embedded P100 Series powers this system, offering customizable, high-performance in-cockpit experiences at 60 FPS. This new approach simplifies the user experience, moving away from the traditional, fragmented automotive HMI systems. #CES2026 #AutomotiveInnovation #EpicGames #AMD #HMI
Source: AMD Developer Blog
2026-02-19 10:10
🚀 Struggling with CPU hotspots while your GPU sits idle? HIP Threads is here to help! This C++ concurrency library allows teams to run familiar multithreaded code on AMD GPUs without the need for kernel rewrites or GPU expertise. Early users have reported significant speedups in just days, making GPU acceleration accessible to all development teams. 💻 Perfect for C++ teams facing performance issues and those who want simple GPU integration. Don’t miss out on optimizing your performance!...
Source: AMD Developer Blog
2026-02-12 16:00
🚀 Exciting updates from Youthcat Games on the Dyson Sphere Program! The team has revamped the multithreading system, enhancing performance by up to 88%. This overhaul includes custom core binding and dynamic task allocation, aiming to support complex gameplay as players build their interstellar empires. With the game's increasing demands, these improvements are crucial for maintaining smooth performance. #DysonSphereProgram #GameDevelopment #Multithreading #PerformanceBoost #YouthcatGames
Source: AMD Developer Blog
2025-12-04 16:00
🚀 Explore how to train the X-ARM 5 robotic arm using reinforcement learning with AMD Schola and Unreal Engine! In this process, tasks increase in complexity, starting with reaching a fixed target block and progressing to randomizing block locations. The training employs the SAC algorithm, enabling efficient learning and exploration. As the agent adapts, it aims to optimize its actions based on rewards and penalties. #Robotics #ReinforcementLearning #AI #TechInnovation #UnrealEngine
Source: AMD Developer Blog
2025-12-02 16:00
🚀 Exciting news for developers! AMD has released Schola v2, an update to its open-source reinforcement learning plugin for Unreal® Engine 5. This version enhances capabilities and performance for AI agents. Key updates include a flexible inference architecture and native support for the Minari dataset format. The new design allows for easy customization of agent behaviors and improved management of agents during episodes. Explore the future of AI in Unreal Engine! 🎮🤖 #AMD #UnrealEngine...
Source: AMD Developer Blog
2025-11-20 16:00
🚀 Exciting news from AMD! The AMD GI-1.2, a real-time Global Illumination solution, is now available through the AMD Capsaicin Framework v1.3. This update enhances the previous GI-1.1 version with a new feature called multibounce, improving bounce lighting approximation. Discover the advancements in rendering technology! 🌟 #AMD #GlobalIllumination #Rendering #TechUpdate #GameDev
Source: AMD Developer Blog
2025-11-17 18:00
🚀 Exciting news for game developers! The AMD FidelityFX Super Resolution 4 (FSR 4) plugin has been updated for Unreal Engine 5.7. This enhancement supports AMD RDNA 4 graphics, improving detail and reducing ghosting for a more immersive gaming experience. Developers can now easily integrate updates, ensuring players enjoy high-quality upscaling with minimal hassle. The plugin also supports older AMD architectures, boosting framerates in supported games. Stay tuned for the update of the AMD...
Source: AMD Developer Blog
2025-11-03 17:00
🔧 Exciting news for developers! The AMD Radeon™ Developer Tool Suite (RDTS) has been updated to enhance GPU application profiling and optimization. 🖥️ This release supports the latest AMD hardware, including the Radeon™ RX 9060 and Ryzen™ AI 5 330. Developers are encouraged to use AMD Software: Adrenalin Edition™ 25.10.2 or higher for optimal performance. 📊 Key updates include AMD Radeon GPU Profiler (RGP) 2.6, which now offers more memory-related performance counters for deeper insights into...
Source: AMD Developer Blog
2025-10-29 17:00
Unlock the power of AMD hardware for neural network inference with the ONNX Runtime and DirectML execution provider. 🚀 This guide discusses optimizing performance by minimizing data transfer between CPU and GPU. It highlights the importance of establishing a native inference pipeline using DirectX 12 to enhance efficiency. Setting up the ONNX Runtime with DirectX 12 involves creating a shared context for pre- and post-processing, allowing smoother operations. #MachineLearning #ONNX #DirectML...
Source: AMD Developer Blog
2025-10-29 17:00
🚀 Dive into the latest guide on optimizing neural network inference on AMD hardware using ONNX Runtime with DirectML! This second part focuses on integrating DirectML into DirectX 11 applications. It addresses resource sharing challenges between DirectX 11 and 12, emphasizing the need for efficient data pipelines. Key points include: - Importance of sharing textures without mipmaps. - Conditions for successful resource sharing with DirectX APIs. Explore the potential of your applications! 💻🔧...
Source: AMD Developer Blog
2025-10-23 17:00
Topaz Labs and AMD have teamed up to enhance video processing using generative AI on AMD Radeon GPUs. This collaboration enables real-time performance and improved workflows for users. The new diffusion-based video enhancement feature runs on AMD Ryzen processors and RDNA architecture, maximizing processing efficiency. The innovative Project Starlight transforms low-res video to HD, achieving seamless motion across frames. This technology is optimized for AMD devices, offering up to 3.3x...
Source: AMD Developer Blog
2025-10-02 17:00
Discover the process of sim-to-real in the latest guide using AMD Schola! This article explains how to replicate the SunFounder PiCar-X device in Unreal® Engine and train it with reinforcement learning. The goal is to teach the agent to follow a line on the floor using simulated color sensors. The training leverages the Stable Baselines3 library with the PPO algorithm, achieving strong results after 2 million steps. #ReinforcementLearning #SimToReal #UnrealEngine #Robotics #AMDSchola 🚗💻🎮
Source: AMD Developer Blog
2025-09-30 17:00
Discover the process of sim-to-real in the latest guide using AMD Schola! This article explains how to replicate the SunFounder PiCar-X device in Unreal® Engine and train it with reinforcement learning. The goal is to teach the agent to follow a line on the floor using simulated color sensors. The training leverages the Stable Baselines3 library with the PPO algorithm, achieving strong results after 2 million steps. #ReinforcementLearning #SimToReal #UnrealEngine #Robotics #AMDSchola 🚗💻🎮
Source: AMD Developer Blog
2025-09-24 19:00
🚀 Interested in deploying AI models on your Windows PC? Check out this beginner's guide on using PyTorch with AMD graphics hardware. No need for dedicated AI infrastructure; just a modern AMD GPU or APU will do! The public preview of PyTorch for Windows supports several AMD models, enabling efficient AI workload execution. Perfect for developers, this guide walks you through setup, configuration, and execution of Large Language Models (LLMs). 🖥️✨ #AI #PyTorch #AMD #MachineLearning #TechGuide
Source: AMD Developer Blog
2025-09-23 19:00
🚀 The AMD DGF SDK has been updated, introducing new features, including an animation-aware encoding pipeline. The Dense Geometry Format (DGF) allows for a cache-friendly representation of compressed triangles. This update offers improvements and bug fixes, making it easier to create animations in ray tracing applications. For a complete list of changes, refer to the release notes. #AMD #DGF #Animation #GraphicsProgramming #RayTracing
Source: AMD Developer Blog
2025-09-08 19:00
🎮 Exciting news for gamers! AMD has launched FidelityFX™ Super Resolution 4 (FSR 4), now available in over 85 games. This advanced neural rendering technology enhances graphics quality using machine learning, resulting in clearer visuals without compromising performance. To experience FSR 4, simply update your AMD Software: Adrenalin Edition driver and enable it in supported games. Explore enhanced gaming today! 🌟 #AMD #FSR4 #GamingTech #Graphics #GameOn
Source: AMD Developer Blog
2025-08-20 16:00
🚀 AMD has launched the FidelityFX SDK 2.0, introducing new machine learning-based rendering technologies for developers. This update simplifies integration of FidelityFX features, starting with AMD FSR 4 upscaling. It allows for automatic upgrades in supported games without needing separate updates. Developers will need to use specific DLLs for the new technologies, ensuring compatibility with the latest AMD hardware. #AMDFidelityFX #GamingTech #GameDevelopment #FSR4 #MachineLearning
Source: AMD Developer Blog
2025-08-20 16:00
🚀 Exciting news for gamers! AMD has launched FidelityFX Super Resolution 4 (FSR 4), now available on GPUOpen. This new machine learning-based upscaler significantly enhances image quality compared to FSR 3.1. FSR 4 utilizes AMD Instinct GPUs and RDNA 4 architecture for optimal performance. It improves temporal stability, detail preservation, and reduces ghosting on moving objects. Upgrade your gaming experience today! 🎮✨ #AMD #FSR4 #GamingTechnology #GameDev #Graphics
Source: AMD Developer Blog
2025-08-20 16:00
🚀 Exciting news for game developers! The AMD FidelityFX Super Resolution 4 (FSR 4) plugin is now available for Unreal Engine 5.1 to 5.6. This plugin enhances framerates with a machine learning upscaler and frame generation. 🎮 FSR 4 combines advanced upscaling algorithms with AMD RDNA 4 architecture for improved performance. It also includes the FSR4MovieRenderPipeline for efficient rendering. For optimal results, developers should review recommendations and known issues specific to their...
Source: AMD Developer Blog