News from AMD GPUOpen

With version 1.5 of AMD Radeon™ GPU Detective (RGD) you can now use the debug information that is produced by the Microsoft DirectX® Shader Compiler.

We've released an updated AMD Radeon™ Developer Tool Suite, including enhanced versions of tools such as the Radeon GPU Detective, Profiler, Raytracing Analyzer, Memory Visualizer, GPU Analyzer, and Developer Panel, now with expanded GPU support.

Explore how Neural Intersection Functions (NIF) and the enhanced LSNIF are poised to reshape ray tracing by replacing traditional BVH traversal with efficient, GPU-friendly neural networks for accelerated performance and high-fidelity imagery.

Discover a high-performance, memory-efficient extension to Onesweep radix sort on GPUs, featuring circular buffers and advanced optimization techniques that reduce global memory access and improve sorting throughput.

A new algebraic method for hardware-accelerated bilinear interpolation on convex quadrilaterals is presented, using the Barycentric coordinate feature of modern GPUs.

Optimize CPU performance by manually writing x64 assembly code, offering a detailed comparison with compiler-generated instructions and achieving improved performance through streamlined instruction sets.

We look at optimizing CPU performance by reducing the number of instructions, and highlights methods to enhance instruction efficiency and algorithm throughput.

Read the highlights of our updates to the AMD Radeon Developer Tool Suite to support the launch of AMD RDNA 4 architecture!

Explore Radeon GPU Analyzer v2.12's enhanced ISA disassembly view, making shader and kernel analysis easier with new tooltips and automatic highlighting. Optimize your GPU workflows effortlessly!

Discover the latest Radeon GPU Profiler v2.4, now supporting Radeon RX 9000 Series GPUs and profiling for pure compute and DirectML applications. Enhance your optimization with improved ISA views and Work Graphs support.

Unlock deeper insights into GPU crashes with Radeon GPU Detective v1.4's new Hardware Crash Analysis feature. Identify in-flight shaders and pinpoint crash culprits faster, streamlining your debugging process.

Explore Radeon Raytracing Analyzer v1.8, now supporting Radeon RX 9000 Series GPUs with enhanced BVH formats, including oriented bounding boxes and expanded node capacity.

Discover AMD-optimized ONNX models on Hugging Face for AMD Ryzen™ AI APUs and Radeon™ GPUs and incredible performance with the AMD Radeon RX 9000 Series' advanced AI accelerators.

Learn about our updates on GPUOpen to support the release of AMD RDNA 4, plus other new content!

Read about the new AMD Advanced Interactive Streaming (AIS) SDK, built using our AMF SDK and designed from the ground up to transform streaming from passive viewing into an immersive experience.

Discover how AMD's Dense Geometry Compression Format (DGF) revolutionizes graphics by compressing complex models for efficient real-time rendering, bridging the gap between rasterization and ray tracing.

By connecting popular open-source RL libraries (written in Python) with the visual and physics capabilities of Unreal Engine, Schola empowers AI researchers and game developers alike to push the boundaries of intelligent gameplay.

Our latest AMD FidelityFX SDK release includes AMD FSR 3.1.3. There are multiple bug fixes, plus new frame pacing tuning options.

Part 2 of the CPU performance optimization guide explores cache invalidation issues, benchmarking, and prefetch optimization strategies for improved memory performance.

GPU Reshape is, a just-in-time instrumentation framework with instruction level validation of shaders. A deep dive into current validation methodologies, and what the future of instrumentation may hold.

Learn about the new Mesh Shader pipeline which can help to create even more better-looking games.

Read about our latest sample for D3D12 GPU Work Graphs. We're making Work Graphs more accessible with a tutorial framework.

We show how to diminish the memory footprint of meshlet geometry, thus both the index buffer and the vertex attributes. Decompression then happens on the fly on every frame in the mesh shader.

The AMD FidelityFX SDK 1.1.2 release includes fixes for issues with FSR 3.1.1, and code changes needed for the October release of the Microsoft GDK.

Read our research for a neural denoising and supersampling technique, with the aim of achieving real-time path tracing.

This integration enhances upscaling capabilities, offering improved temporal stability and detail preservation.

We’ve added mesh nodes to our Vulkan® experimental extension, VK_AMDX_shader_enqueue.

The latest beta of GPU Reshape introduces a waterfall feature, NonUniformResourceIndex validation, and much more! Read on...

Sampling the normal distribution is not as straightforward as it seems! Explore two GPU-friendly methods including implementation and performance evaluation.

Find out more about our latest tools release, including driver experiments, updates to RRA, RGP, and more!

Ever wondered why your app is not working properly on a particular GPU? Driver Experiments lets graphics programmers disable some graphics driver optimizations or enable extra safety features.

RRA 1.7 lets you associate ray dispatch data from DirectX®12 and Vulkan® applications with a user-defined string called a user marker.

Our patch release includes some FSR 3.1 fixes, support for AL2, and code changes needed for the upcoming release of the Microsoft Game Development Kit (GDK).

We're very excited to be presenting at GPC 2024! Read on to see our highlights for this brand-new European graphics conference.

The AMD RDNA™ 3.5 ISA reference guide is now available! The ISA guide is useful for anyone interested in the lowest level operation of the RDNA 3.5 GPU architecture.

Learn how to integrate the AMD Radeon Anti-Lag 2 SDK into your game. Unlike the driver-based AL 1, AL 2's point of insertion is at the optimal point inside the game's logic, just before the user controls are sampled.

A simple C++ program demonstrating how easy it is to decode instructions using the IsaDecoder API.

Learn more about our award-winning new papers covering HIP RT, ray tracing, geometry compression, and procedural generation with work graphs.

If you're a graphics dev looking to understand more about deep learning, this blog introduces the basic principles in a graphics dev context.

Frame Latency Meter (FLM) is the must-have tool for anyone who wants to measure the response time of their games with mouse events.

Mesh nodes are a new type of leaf node in work graphs that, unlike all other nodes, does not invoke a compute shader, but dispatches a mesh-shader graphics pipeline instead. This blog series covers how to get started with mesh nodes as well as best practices.

The second part of this mesh nodes blog series focusses on initial setup of a new mesh nodes project and includes an example of a HelloMeshNodes solution.

The final part of this mesh nodes blog series outlines some of the best practices for getting the best performance out of a mesh nodes project.

Mesh nodes makes it much simpler to implement a fully procedurally generated world. This blog post examines an example of procedural mesh node sample.

In this two-part blog series, we will investigate Brixelizer GI to pinpoint the problems faced with foliage-heavy scenes and then look solutions to adding support.

This article describes Brixelizer GI's functionality to better highlight the problem with foliage.

To improve the quality of foliage in Brixelizer GI, we must modify the algorithm to support alpha-clipped geometry.

AMD FidelityFX Super Resolution (FSR) 3.1 is now available. This post details some of the major updates to this latest change to FSR.

As of FidelityFX SDK version 1.1, Brixelizer and Brixelizer GI are now unleashed to world so in this article we aim to discuss a few practical use cases and provide you with some tips you can apply for getting the most performance out of Brixelizer in your application.

The AMD FidelityFX SDK v1.1 is now available. This update introduces three new FidelityFX™ technologies: FSR 3.1, Breadcrumbs, and BrixelizerGI.

We're proud to introduce a brand-new FidelityFX technology: AMD FidelityFX Breadcrumbs. Breadcrumbs is a cross-platform library for post-morten analysis of GPU crashes.

The latest version of the Radeon Developer Tool Suite is now available! This release features a number of updates including all GUI-based tools upgrading to Qt® v6.7.0.

This talk by Matthäus Chajdas gives a first look at this brand new API and shows how it's going to transform the GPU programming landscape going forward.

This series of blogs will walk readers through the analysis of the problems encountered in actual projects, thus helping them to better understand the CPU performance optimization of programs.

This article starts a series of posts about CPU performance analysis and optimization methods.

With the introduction of Microsoft’s DirectSR, the need to integrate many super resolution APIs has been reduced. Instead, developers may integrate just one API – Microsoft DirectSR.

Brotli-G (v1.1 onwards) now supports pre-conditioning of block compressed textures. Take a look for a quick summary!

This blog discusses various ROCm tools developers can leverage to port existing applications from CUDA to HIP.

This post discusses how to leverage C++17 parallel algorithms on AMD GPUs with HIPSTDPAR

Radeon™ GPU Analyzer v2.9.1 now supports D3D12 shader compilation without requiring a completely defined pipeline state. RGA v2.9.1 is available now.

RGP 2.1 adds RGA interoperability, 'Color by' modes, and additional customization options. Dive in for all the details!

This first part introduces the concept of affinity and why its important for achieving better performance on AMD GPU nodes

This second part introduces common tools to understand the topology of your system and to control affinity for different applications

This talk describes the mesh shader pipeline and how it maps to the AMD RDNA™ 3 architecture.

Learn about how AMD FSR 3 was integrated into the Snowdrop engine, which issues were faced and how the integration helped to improve FSR 3.

This session presents the latest enhancements in the RDTS, a rich set of GPU profilers and analyzers and a new GPU crash analysis tool.

This session covers different types of failures - when they occur, why they are difficult to debug, and how RGD can help to identify a crash's root cause.

This talk focusses on the micro-architecture of modern AMD CPUs, followed by optimizations, frequent issues, and benchmarking best practices.

This talk presents GPU Reshape, a just-in-time instrumentation framework with instruction level validation of shader operations.

Learn about our GDC 2024 activities, including AMD FSR 3.1, AMD FidelityFX Brixelizer, work graphs, mesh shaders, tools, CPU, and more.

This talk briefly discusses how the AMD FidelityFX™ Brixelizer works, then explores how diffuse and specular global illumination is implemented with sparse distance fields in Brix GI.

The fourth post in our mesh shaders series takes a look at the specific example of rendering detailed vegetation.

GI-1.1 is available now as part of the AMD Capsaicin Framework. GI-1.1 includes new support for glossy reflections rendering.

Introducing "mesh nodes", which make draw calls an integral part of the work graph, providing a higher perf alternative to ExecuteIndirect dispatches.

The third post in our mesh shaders series covers how to use mesh shaders to simplify font rendering.

Our GDC 2024 presentations this year include work graphs, mesh shaders, AMD FSR 3, GI with AMD FidelityFX Brixelizer, AMD Ryzen optimization, RGD, RDTS, and GPU Reshape!

Microsoft® Agility SDK 1.613.0 is out now including general availability of Work Graphs 1.0 and the GPU Upload Heaps feature.

Compressonator v4.5 introduces improved BC1-BC5 compression that reduces file sizes on average by 10%-15% using a new Brotli-G zip packaging feature, mipmap changes, ETC codec fixes, and more.

With the release of v2.2, HIP RT now support multi-level instancing. Multi-level instancing can help to reduce memory requirements, allowing you to render large scenes with limited memory.

GPU Reshape brings powerful features typical of CPU tooling to the GPU, providing validation of dynamic behaviour. Read on for all of the details.

The second post in this series on mesh shaders covers best practices for writing mesh and amplification shaders, as well as how to use the AMD Radeon™ Developer Tool Suite to profile and optimize mesh shaders.

This is a general guide focusing on CPU profiling for Unity, including which tools are useful for profiling and how to use these tools to find hotspots in your code.

In this blog post we will try to demystify what exactly occupancy is, which factors limit occupancy, and how to use tools to identify occupancy-limited workloads.

This post is the start of a new series which aims to demystify mesh shaders through examples and tutorials.

This blog series provides detailed explanations, analysis, use-case examples, tutorials, and advice about mesh shading.

We are very excited to announce the release of AMD FidelityFX Super Resolution 3 (FSR 3) technology on GPUOpen, complete with full source code for DirectX 12 and Unreal Engine 5.

Download the AMD FSR 3.1.1 plugin for Unreal Engine, and learn how to install and use it.

Radeon™ GPU Profiler 2.0 is packed with brand-new features and updates. This release includes a new customizable layout to the Wavefront Occupancy View, support for dark mode in UI, thread divergence monitoring in raytracing pipelines, and much more.

Radeon™ Memory Visualizer 1.8 is available now. v1.8 enhances the Resource usage size timeline to better visualize overlapped aliased resources.

The latest version of Radeon™ GPU Detective is out now! RGD v1.1 introduces support for post-mortem analysis of Vulkan applications on Windows.

Our DirectStorage sample renders a scene while asynchronously loading assets using the DirectStorage API.

Introducing AMD RenderStudio - a set of tools for cross-user collaboration using the OpenUSD and MaterialX ecosystem.

It is often difficult to know where to start when taking your first in the world of graphics. This guide is here to help with a discussion of first steps and a list of useful websites.

This blog post shows how it is possible to use HIP RT to accelerate neighbor search in Smoothed Particle Hydrodynamics (SPH) simulations.

Sparse matrix vector multiplication (SpMV) is a core computational kernel of nearly every implicit sparse linear algebra solver. This is the first post in the series covering SpMV.

HIP Ray Tracing v2.1 adds support for batch construction, global/dynamic stacks, transformation query functions, plus other new features.

Learn more about the power of work graphs API in our detailed blog, taking you step-by-step through an example which implements a scanline rasterizer.

With the integration of AMD FidelityFX™ Super Resolution 3 into games, we're sharing even more technical details for developers.

In this blog, we explore GPU offloading using HIP and OpenMP target directives and discuss their relative merits in terms of implementation efforts and performance.

Radeon Raytracing Analyzer v1.3 adds the ability to inspect casted rays in 3D and examine ray traversal statistics. Check it out now!

Radeon™ Memory Visualizer v1.7 introduces one of the most anticipated new features: improved support for aliased resources in the Resource overview pane. Read on for details of this features and more.

Radeon GPU Profiler v1.16 updates the GPU ISA disassembly view, adds improved dark mode support, and more.

The machine learning ecosystem is quickly exploding and this article is designed to assist data scientists/ML practitioners get their machine learning environments up and running on AMD GPUs.

"D3D12SimpleClassify" shows the use of a GPU Work Graph in a simple frame-based graphics application, plus learn about new RGP support.

Read the latest AMD FidelityFX™ Super Resolution 3 developer updates from the GPUOpen team.

Radeon GPU Detective (RGD) is a brand-new tool which is designed to help you capture and investigate GPU crashes. This tutorial covers how to use RGD to capture a crash and how to interpret the results it produces.

Radeon™ GPU Detective (RGD) is our brand-new tool for investigating GPU crashes. RGD is included in the Radeon Developer Tool Suite and is available now!

We're pleased to announce the Radeon™ ProRender SDK now supports Python. Links to everything you need to find out more are in this post.

We're pleased to announce the Radeon™ ProRender SDK now supports Python. Links to everything you need to find out more are in this post.

AMD is providing an experimental AMD extension to access GPU Work Graphs in Vulkan. Check out this post for usage examples and resources.

The AMD Tech-sharing Salon is an event dedicated to Chinese game developers, hosted by AMD GPUOpen. Our latest salon in Chengdu brought together 40 game developers to discuss the latest AMD technology.

In the fourth and final part of Finite Difference Laplacian blog series we cover scaling studies and cache size limitations

The D3D12_HEAP_TYPE_GPU_UPLOAD flag in Direct3D 12 provides a good alternative to other ways of uploading data from the CPU to the GPU. Check out our quick guide to effective use of this flag.

The AMD FidelityFX SDK is now available! The SDK is AMD FidelityFX graphics middleware helping you to integrate AMD FidelityFX features into your games without any hassle.

Want to add FSR 2 to your Unity URP project? Take a look at our quick-start guide to get you up and running. (DirectX®11 only)

Compressonator v4.4 adds AVX-512, AVX2, and SSE4 variations of BC1 encoding in the Compressonator Core library, new CLI options, and more.

Read about how the new WMMA instructions added in HLSL SM 6.8 allow shader developers to accelerate GEMM matrix operations.

Our primer on GPU Work Graphs introduces this exciting new paradigm for graphics developers, which enable a live shader kernel to dispatch new workloads on-demand without needing to circle back around to the CPU first.

Find out what you need to get started with Work Graphs for DirectX 12, including the software required, configuration, compiling, and more.

Build upon what you learned in Part 1 of Work Graphs with topics such as input and output records, SV_DispatchGrid, NodeLaunch modes, and recursion.

Our final part in our GPU Work Graphs primer shares tips and tricks, and links to where you can find out more.

Read about our improvements to AMD FidelityFX Super Resolution 2 with the FSR 2.2.1 hotfix.

MPI is the de facto standard for inter-process communication in High-Performance Computing. This post will guide you through the process of setting up an MPI application that supports execution on GPU clusters.

Read about how the latest updates for our Radeon ProRender plug-ins introduce HIP, and how this can benefit artists.

AMD now has driver support for a metacommand implementation intended to improve performance and reduce the time it takes to generate output from the model.

Register pressure of GPU kernels has a tremendous impact on performance. This post provides a practical demo on applying recommendations.

In this third part, we cover additional optimizations to fine tune the performance of the kernel, and introduce temporary files, register pressure, and occupancy.

AMD Capsaicin Framework is a research framework for real-time graphics which we have been using to develop and test new and upcoming rendering algorithms. We are now releasing it to the public.

This presentation is a practical implementation of a solution aimed at making the most of every sample by caching the estimated radiance into a cache hierarchy used for both sampling and filtering.

The latest release of the Render Pipeline Shaders (RPS) SDK adds Linux support, the ability to dynamically load Vulkan functions, and more. Check out this post for the full release notes.

Radeon Memory Visualizer v1.6 adds improved device configuration information, and more parameters on the resource details pane.

Radeon Raytracing Analyzer v1.2 introduces ray face culling flags, a ray traversal histogram, a geometry list pane, and an instance mask.

Radeon GPU Profiler v1.15 adds an enhanced user experience for GPU ISA disassembly, mesh shader event names, WMMA support, and more.

This post gives an overview of AMD's open source profiling tools, helping you diagnose bottlenecks and understand how your application is using the hardware.

The GPUOpen Matrix Compendium covers how matrices are used in 3D graphics and implementations in host code and shading languages. It's a growing guide, so keep checking back!

GPUOpen Matrix Compendium: This page shows a selection of matrices in a post-multiplication, left-handed coordinate system.

GPUOpen Matrix Compendium: This page shows a selection of matrices in the coordinate system expected by OpenGL®.

GPUOpen Matrix Compendium: This page shows a selection of matrices in the coordinate system expected by DirectX® 9.

GPUOpen Matrix Compendium: This page shows a selection of matrices in a pre-multiplication, right-handed coordinate system.

This talk focuses on temporal upscaling, describing how the algorithm generates a final image and how FSR mitigates against common artifacts.

HIPRT-v2 is now available for download! This post covers some of the most exciting features and optimizations.

Get the highlights from our GDC 2023 sessions and FidelityFX-related reveals, and find links to videos and slide decks.

Join us for a presentation about DirectStorage and how to integrate it to extract optimal load time and streaming performance.

This talk gives an overview of RGP, RMV, RRA, and RGA, introducing new features and improvements, and reveal the current work in progress.

In this talk from learn about AMD Ryzen™ products featuring advanced technologies, including laptop, desktop, and workstation processors.

This presentation introduces a novel algorithm for PC and console developers to efficiently generate sparse distance fields in real-time.

Join AMD as we unveil the FidelityFX SDK, a consolidation of all the great FidelityFX technologies into a sleek, easy-to-use SDK.

Our one-stop resource for getting great AMD RDNA™ performance on Vulkan® and DirectX®12 APIs!

Learn about our GDC 2023 activities, including the latest developments with our FidelityFX technologies, new GI techniques, and more.

We are happy to announce Radeon™ ProRender SDK 3.1.0 is finally available, so let's take a look at the latest updates and improvements.

This post introduces commonly-used memory spaces, identifies what makes each memory space unique, and discusses some common use-cases for each space.

Updates to our Unreal Engine plugin for AMD FidelityFX Super Resolution 2.2, including ghosting improvements and support for UE 5.1.

In this guest post by EBB Software, learn how they integrated our FSR 2.1 plugin for Unreal Engine into their first title: Scorn

This talk at Vulkanised 2023 covers how to use the Radeon Developer Tool Suite (RDTS) to optimize games using RADV and Steam Deck.

Today, the FSR 2.2 source code and accompanying sample is available to all through our GitHub repository.

Our GDC23 presentations this year include temporal upscaling, our NEW FidelityFX SDK, GI, DirectStorage, CPU optimizations, tools, and more!

AMD GPU Services (AGS) 6.1 is now available, adding RDNA 3 GPU support, VS2022 versions of the static libs, and a new sample showing you how to use AGS extensions from DX12.

Compressonator v4.3 is out now! v4.3 features Brotli-G lossless compression, multi-texture mipmap generation, and much more.

Installation of the AMD ROCm™ software package can be challenging. This introductory material shows how to install ROCm on a workstation with an AMD GPU card that supports the AMD GFX9 architecture.

AMD and LunarG are pleased to announce DirectX®12 (D3D12) and DirectX® Raytracing (DXR) support for the GFXReconstruct capture/replay tool.

This blog is a quick how-to guide for using the WMMA feature with our RDNA 3 GPU architecture using a Hello World example.

The AMD RDNA™ 3 ISA reference guide is now available! The ISA guide is useful for anyone interested in the lowest level operation of the RDNA 3 shader core.

In this post we introduce two common optimizations that can be applied to the kernel to reduce data movement and bring us closer to the new peak: loop tiling to explicitly reduce memory loads and re-order the memory access pattern to improve caching.

In this video Zhuo Chen takes a look at the overview of the design and implementation of the AMD Render Pipeline Shaders SDK!

Render Pipeline Shaders (RPS) SDK is now available for open beta access!

Following two years of work based on AMD’s TressFX open source high quality real-time hair simulation and rendering framework, Unity China HairFX is now available!

Read this high level summary of our updates to RDTS for RDNA™ 3, including other new features and improvements, plus updates to GPUPerfAPI.

Radeon GPU Profiler 1.14 is here, with support for Radeon™ RX 7000 series GPUs, profiling HIP applications, and much more. Take a look!

The latest update for RRA includes changes to the camera system and support for split triangles and rebraided instances. Check it all out here!

ADLX is a modern library and SDK designed to access features and functionality of AMD systems in the categories of Display, 3D graphics, and more.

Get the details on Brotli-G, including the modifications we made to Brotli, and how you can use it via our new SDK and Compressonator.

The finite difference method is a powerful tool for computational physics. This post covers how to implement a GPU-accelerated finite difference code using AMD's HIP API.

In this blog series, we share the lessons learned from tuning a wide range of scientific applications, libraries, and frameworks for AMD GPUs.

This first post in the 'AMD lab notes' series takes a look at AMD’s Matrix Core technology and how best to use it to speed up your matrix operations.

Analyze the source code to RRA, and learn about amdrdf, a library for handling Radeon Data File (RDF) format, used by RRA and others.

AMD is pleased to support Microsoft’s recently released DirectStorage 1.1 with GPU Decompression. DirectStorage must be enabled by developers to realize the benefits.

Read about our improvements to RPR Interactive mode, a faster Vulkan ray-tracing renderer with better support for lights and materials, new nodes, and more.

Discover one of several ways to improve upscaled foliage appearance in the first of this five part blog series on getting the most out of our FSR 2.1 Unreal Engine plugin.

Learn which content changes you can make in the Unreal Engine editor to improve the appearance of upscaled foliage.

Find out how to apply one of our supplied Unreal Engine patches to improve upscaled foliage appearance with our FSR 2.1 plugin.

See ways you can improve suboptimal FSR 2 results caused by animated materials obscured by a fine mesh or grill with no motion vectors.

This final part demonstrates how to apply the LitReativeShadingModel patch which adds a new Lit Reactive shading model.

In this video, Can Alper introduces RRA V1.0. He explains how to capture games using RDP and evaluate when to use RRA.

A member of our GPUOpen team in China shares her report on the details of AMD Tech-Sharing Salon 2022, which took place in Shanghai.

Optimizing the raytracing pipeline can be difficult. Discover how to spot and diagnose common RT pitfalls with RRA, and how to fix them!

One of our engineers shares the improvements we've made with AMD FidelityFX Super Resolution 2 to ghosting, temporal stability, and more.

New or fairly new to AMD's tools, libraries, and effects? This is the best place to get started on GPUOpen!

Looking for tips on getting started with developing and/or optimizing your game, whether on AMD hardware or generally? We've got you covered!

This talk is a joint-presentation with Avalanche Studios Group explaining how their in-house APEX Engine manages memory with the help of VMA/D3D12MA.

This talk introduces compute shaders, explaining ideas from a software and hardware perspective, as well as considerations when writing compute shaders.

We're proud to announce Radeon Raytracing Analyzer. RRA provides the tools you need to investigate raytracing performance in your apps.

New PreAnalysis modes include perceptual adaptive quantization, temporal adaptive quantization, and high motion quality boost. And there's more!

The upcoming AMD Radeon Software Adrenalin Edition release offers full Shader Model 6.7 support to align with the new update to Agility SDK from Microsoft.

Find out how to install and configure the AMD FidelityFX Super Resolution (FSR) 2 plugin for Unreal Engine 4.26/4.27 and UE5.

AMD FSR 2 source code is now available! Take a look at our powerful FSR 2 API, as well as full source, samples, and documentation.

VMA appears as an optional component that can be selected in the Vulkan SDK 1.3.216.0 installer.

RMV is now available on Linux. RMV and RDP officially support Ubuntu 20.04 with Linux distros requiring additional dependencies. Check it out!

Find out more about all our updates to the Radeon ProRender plug-ins, including new fog and shadow settings for ProRender in Blender and Maya.

Watch this video digest of our recent ray tracing research, including efficient global illumination sampling, light sampling, and multi-resolution geometric representation.

EXOR Studios and AMD have collaborated to add Variable Rate Shading in The Riftbreaker. Read this guest blog to find out more!

The benefits of the level of details technique for ray tracing are not trivial. This blog explores the issues, giving the rationale for our new technique.

ANARI is a (provisional) open standard API for scalable 3D data visualization, and is a big step in standardizing the scientific rendering pipeline.

UE4 TressFX 5.0 has been designed to build upon the many features of UE4 TressFX 4.1, while being much easier to use. Find out what's new!

Watch our video explaining what UE4 TressFX 5.0 is, and how to use it. TressFX is designed to simulate and render realistic hair and fur.

RGP 1.13 adds enhanced ray tracing features, such as new performance counters and inline RT. RDP 2.6 includes improved data capture.

Find out in this blog post how you can make all memory visible to the CPU in Radeon Memory Visualizer (RMV) v1.4 with Smart Access Memory.

HIP RT is a new ray tracing library for HIP. It makes it easy to write a ray tracing app using HIP. Check out this page for more information.

Orochi is a library that loads HIP and CUDA driver APIs dynamically at runtime, eliminating the overhead of maintaining separate backends.

Discover our videos and slides from the GDC 2022, including FSR 2.0, ray tracing, Ryzen optimizations, and presentations with game devs.

Join AMD for an introduction to the AMD Ryzen™ family of processors which power today’s game consoles and PCs.

This talk will deep-dive into the rendering technology of Deathloop. We will explore the challenges and lessons learned.

In this presentation, we demonstrate how to use Radeon™ GPU Profiler and Radeon™ Raytracing Analyzer, to illuminate performance issues.

This session covers the collaboration between AMD and Luminous Productions on their upcoming title: Forspoken.

This session covers the collaboration between AMD and Ubisoft on Far Cry 6, implementing Hybrid RayTraced Reflections.

FidelityFX Super Resolution 2.0 is AMD's next generation upscaling technology. Check out our GDC talk to understand exactly how it works.

Time. Get it? Never mind.

AMD is proud to announce our support of Microsoft® and its release of DirectStorage. The DirectStorage SDK is now available for download.

GDC 2022 is just around the corner, so why not take some time to get ahead of the game and check out all of our upcoming GDC talks?

The latest release of the ProRender SDK introduces support for primitive variables, enhanced Cryptomatte AOVs, AMD's HIP API, and much more.

AMD was recently involved in an exciting rendering challenge for teams taking part in AWS GameDay as part of AWS re:Invent 2021.

RGP 1.12 provides some significant enhancements to the Instruction Timing feature, including wavefront filtering and single-wavefront mode.

Radeon Memory Visualizer (RMV) now supports Named Resources in DirectX® 12 applications. This blog explains how you can view them in RMV.

Radeon GPU Analyzer 2.6 introduces VGPR Pressure Visualization. This post explains exactly how to get the most out of this brand-new feature.

This Digital Dragons 2021 talk presents the current state of access to memory resources through the DirectX® 12 and Vulkan® APIs.

A new focus on USD and MaterialX workflows, including our brand new MaterialX library, and updates to our Radeon ProRender plug-ins.

Introducing a new renderer backend and support for simpler volumes, cutting planes, and artistic control of shadow color. Also, new SDK tutorials are now available.

Read our latest ray tracing papers presented at SIGGRAPH ASIA 2021, along with dozens of our other publications.

Discover our published publications.

Find out how to read and understand graphs in Radeon GPU Profiler and GPUView in order to optimize your game more effectively.

AMF v1.4.23 brings you a new Auto LTR encoder mode, plus additional encoder usage presets and encoder statistics/feedback.

Our handy software release blogs will help you make good use of our tools, SDKs, and effects, as well as sharing the latest features with new releases.

Find out how to install and configure the AMD FidelityFX Super Resolution (FSR) 1.0 plugin for Unreal Engine 4.

AMD has been working with Blender to improve support for GPU rendering in Cycles using the open source HIP API.

Introducing AMD checks for the Vulkan® Best Practice validation layer! Find out more about how it now incorporates many of our performance suggestions.

Introducing support for Apple M1, heterogeneous volume, and deepEXR. Plus improved CPU rendering, and toon contour rendering.

This tutorial video demonstrates how to use our USD Hydra plug-in for Blender®, which uses the power of Open Standards to enable you to reference and assemble USD™, and use MaterialX.

Find out about our exciting new plug-in for Blender®, which uses the power of Open Standards to enable you to reference and assemble USD™, and use MaterialX.

Find out how to take a closer look at how FSR works, and get inspiration for how to integrate it into your own engine.

A wonderful Saturday in Shanghai! Check out the first stop of AMD's GPUOpen Tech-Sharing Salon at ChinaJoy 2021.

Compressonator v4.2 brings improvements for BC1 and BC7 codecs, plus API, SDK, and CMake updates.

FidelityFX-CLI is a command-line Windows® program to test FidelityFX Super Resolution (FSR) 1.0 and Contrast Adaptive Sharpening (CAS) on image files.

RGP 1.11 introduces ray tracing call targets, enhancements to cache counters, and more.

RMV v1.2 introduces range-based address searching, resource tooltip, and has been updated to work with Qt 5.15.2.

The source code for AMD FidelityFX Super Resolution is now available here on GPUOpen. But that's not all...

Our Blender® add-on, Autodesk® Maya® plug-in, and the SideFX® Houdini™ (USD) plug-in now incorporate the latest Radeon™ ProRender SDK.

Smart Access Memory (SAM) provides the CPU with direct access to all video memory. These guidelines help you to improve CPU and GPU performance using SAM.

We're very excited to share some early details for developers about our upcoming AMD FidelityFX Super Resolution.

We are very excited to announce our support for Unreal Engine 5 early access, including the release of our UE5-optimized developer driver.

Our accelerated ray intersection library for DirectX®12 and Vulkan®. The source code for v4.1 is now available on GitHub under the MIT license.

Join AMD on an adventure thru Zen 2 and Zen 3 processors which power today’s game consoles and PCs. Dive into instruction sets, cache hierarchies, resource sharing, and simultaneous multi-threading. Journey across the sands of silicon to master microarchitecture and uncover best practices!

We explain how FidelityFX Denoiser allows for high-quality raytracing results without increasing rays per pixel, and deep dive into specific AMD RDNA™ 2-based optimizations that benefit both Xbox Series X|S and PC.

RGP 1.9 and 1.10 introduce support for AMD Radeon™ RX6000 series GPUs, a new memory cache counter feature, and support for DirectX® and Vulkan® ray tracing.

Find out about our new Hybrid Shadows sample, watch our new RGP video, and see our latest FidelityFX updates!

Read about Cryptomatte support, light group AOVs, deformation motion blur, homogeneous volume support, and our toon material in Radeon™ ProRender.

Design faster. Render faster. Iterate faster. Our one-stop resource for getting great AMD Ryzen performance.

New GPUOpen content to support our Microsoft® Game Stack Live presentations. Meet FidelityFX Shadow Denoiser, Ryzen Perf guide, and more!

Game developers can now access select AMD FidelityFX effects with specific optimizations for Windows® and Xbox.

This latest release adds support for GPU cache counters, Vulkan® ray tracing, the latest RDNA™ 2 GPUs, and more.

One of our Developer Technology Engineers, Lou Kramer, talks about the journey to start her career with AMD, what she actually does, and how she finds being a woman in engineering.

More feature patch updates available for UE4.26: Advanced Media Framework (AMF), chroma keying, and 360 video stitching.

Our latest developer driver has just been released, providing initial support for the Vulkan VK_KHR_synchronization2 extension.

Radeon™ GPU Analyzer v2.4.1 introduces support for DXR shaders in a new mode of the command line tool.

Feature patch updates for UE4.26, including new FidelityFX Variable Shading, and updates to FidelityFX LPM, SPD, and CAS, plus TressFX 4.1.

Our five year anniversary is January 26th 2021. Here's a look back at some of our successes!

This presentation by one of our engineers at GIC 2020 provides an introduction to the graphics pipeline.

ADL is designed to access low-level display driver functionality. v15.0 provides new APIs, new samples, improvements to layout and documentation, and more.

The latest version of our Open Capture and Analysis Tool (OCAT) brings support for all RDNA™ architectures, and now retrieves resolution information in window mode.

We're delighted to announce that our Radeon™ Memory Visualizer (RMV) tool is now available as open source under the MIT license.

The AMD RDNA™ 2 Instruction Set Architecture (ISA) PDF has been released. Get it here!

Read about the Vulkan® ray tracing extensions now supported by our latest driver.

To accompany the launch of the AMD Radeon™ RX 6000 series graphics cards, we are excited to share new content and updates to GPUOpen with you.

The Radeon™ Developer Tool Suite combines our Radeon™ GPU Profiler, Radeon™ Memory Visualizer, Radeon™ GPU Analyzer, and Radeon™ Developer Panel in one handy package.

Read about our three new AMD FidelityFX effects, launched as part of the Radeon™ RX 6000 series graphics card release.

With specific hardware acceleration features implemented, content creators can accelerate their rendering using AMD Radeon™ RX 6000 Series graphics cards with Radeon™ ProRender 2.0.

The latest release of RGP introduces support for Radeon™ RX 6000 Series (RDNA™ 2) and DirectX® Raytracing, along with several additional new features.

Radeon Memory Visualizer V1.1 introduces support for aliased resources, and allows selection of a resource in the memory leak finder pane.

Compressonator v4.1 adds SNORM support for BC4 and BC5, MIP map filter support using either GPU or CPU, GPU-based compression and MIP map generation, and much more.

GPUPerfAPI v3.7 brings support for Radeon™ RX 6000 series GPUs, new raytracing counters for DirectX® Raytracing, a new scalar and instruction cache counter, and new raytracing High-Frequency counters in Microsoft® PIX2.

Graphics feature architect Rys Sommefeldt provides a short presentation on the major advantages of the new API, and how to best utilize it on AMD RDNA™ 2-based hardware.

Engineer Stephan Hodes provides a short description how VRS works, and how AMD’s FidelityFX Variable Shading technique can assist with integrating VRS into your engine.

Engineer Colin Riley provides a short description of Sampler Feedback and Mesh Shaders, as well as important performance guidelines that graphics developers should consider when using AMD RDNA™ 2-based GPUs.

This video describes the benefits of bundling the Radeon™ GPU Profiler, Radeon™ Memory Visualizer, Radeon™ GPU Analyzer, and the Radeon™ Developer Panel into a single downloadable suite.

This video describes the changes and improvements made to the Radeon™ Memory Visualizer update 1.1.

Introducing the new version of AMD Radeon™ ProRender 2.0 with AMD Radeon™ RX 6000 Series graphics cards support. Find out about the performance optimizations we achieved from the hardware ray tracing support.

Oxide talk about working out how to make the very best use of multi-core CPUs and the GPU to reduce motion-to-photon latency, using Not Enough Bullets to drive things forwards.

This talk discusses how subsurface scattering is implemented in Unreal Engine’s forward renderer. Because UE4 implements subsurface scattering as a screen space effect, it wasn’t available on the forward path by default, so a new technique had to be implemented, and one that had to still work with the UE4 material system and editor.

How Creative Assembly have evolved their engine, which originally targeted DirectX® 9, to abstract over the disparate graphics APIs they need to support for Warhammer now, including DirectX®12.

Binomial are the creators of Basis, a very exciting new take on multi-platform texture compression that has wide applicability, and not just to games. This talk by Stephanie Hurlburt is a great primer on Basis and the problems it’s designed and engineered to solve.

Aras Pranckevicius (Unity) presents a new rendering system being developed out in the open for Unity 5. With a tightly controlled and highly-efficient C core unpinning a scriptable surface area in C#, it’s one of biggest graphics focused changes to Unity in its history.

Arne Schober at Epic gives a rundown of a number of recent (2017) interesting improvements to UE4’s renderers, from MSAA support in the forward renderer for VR, to compositing a usable UI on top of a HDR image.

This talk by AMD's Ste Tovey discusses memory management with Vulkan® at Vulkanised 2018.

This talk by AMD's Lou Kramer at 4C in 2018 discusses optimising your engine using compute.

This talk by AMD's Lou Kramer discusses optimising AAA Vulkan® titles on desktop.

A talk by AMD's Jordan Logan and Saber Interactive's Nikolai Petrov at Reboot DEVELOPRED in 2019.

This talk by AMD's Adam Sawicki at Digital Dragons in 2018 discusses how to port your engine to Vulkan® or DirectX®12.

This talk will discuss Direct3D® 12 in general, as well as some of the features that were leveraged to accomplish this goal, such as Async Compute, Tiled Resources, Debugging, Copy Queues, and HDR.

Introducing the new version of Radeon™ ProRender 2.0, the Universal Rendering API.

This video introduces the new Radeon™ Memory Visualizer to help answer questions about memory allocations, resource bindings, page mappings, and more. Includes updates on RGP and RGA.

This presentation will provide a technical overview of existing and new graphics effects available in GPUOpen and detail integration procedures for them.

Join AMD Game Engineering team members for an introduction to the AMD Ryzen family of processors followed by advanced optimization topics. Learn about the high-performance AMD Zen 2 microarchitecture and profiling tools. Gain insight into code optimization opportunities and lessons learned.

This video will take you from the original source code down to the RDNA ISA. It covers control-flow, bindless resource access and scalarization, along with DXC, instruction selection, scheduling, and register allocation for the RDNA instruction set.

Learn about the details of RDNA and how it differs from the previous GCN architecture. Includes examples of optimizations based on the case study of implementing an efficient downsampler. Covers topics such as characteristics of workload distribution, shader optimizations, and efficient texture access.

This tutorial explains how to take advantage of the functionality in RDP v2.1 onwards, which unifies the RMV and RGP functionality from earlier versions to provide a unified workflow.

Read about the three new Vulkan® extensions in the latest release of our Radeon™ Software Adrenalin Edition driver 20.9.2: VK_KHR_buffer_device_address, VK_EXT_robustness2, and VK_EXT_shader_image_atomic_int64.

The final part of this joint series with Quantic Dream discusses shader scalarization, async compute, multithreaded render lists, memory management using our Vulkan Memory Allocator (VMA), and much more.

Part 2 of this joint post between Quantic Dream and AMD looks at non-uniform resource indexing on PC and for AMD cards specifically.

Porting the PS4® game Detroit: Become Human to PC presented some interesting challenges. This first part of a joint collaboration from engineers at Quantic Dream and AMD discusses the decision to use Vulkan® and talks shader pipelines and descriptors.

The latest release of Radeon™ GPU Profiler introduces an updated Radeon Developer Panel, Instruction Timing, and more.

Our latest Radeon Software Adrenalin Edition driver – 20.8.3 – includes a few recent extensions that aim to improve developer and user experience.

Announcing the Vulkan® versions of three of our newer FidelityFX effects - SSSR, LPM, and CACAO.

FidelityFX SPD (Single Pass Downsampler) 2.0 is now available. Find out about the new features!

This sample demonstrates how to use most of Cauldron's features. It is also a useful reference for getting started with developing your own samples and prototypes.

Announcing a big update to the Radeon™ ProRender SDK 2.0 beta, along with new beta versions of our open-source plug-ins for Autodesk® Maya, Blender®, and SideFX® Houdini.

New Unreal Engine Feature Patches now available for 4.25, including new support for FidelityFX LPM, and updates for FidelityFX CAS, and more.

One of our engineers explains a few small code changes that can help you integrate RenderDoc for more unconventional applications.

When associated with DDS files, RenderDoc generates thumbnails for DDS formats and displays them in Windows Explorer. Compressonator Core provides functions for compressing and decompressing DDS files.

GPUOpen now has its own dedicated video page, including links to slides from the Let's Build... 2020 virtual event.

AGS v5.4.1 now out, which includes GetWaveSize intrinsics as well as BaseInstance and BaseVertex for indirect drawing.

Bringing the Gears franchise to the PC is not something the Coalition takes lightly. This talk will discuss Direct3D® 12 in general, as well as features such as Async Compute, Tiled Resources, Debugging, Copy Queues, and HDR.

Watch our Let's build... 2020 presentations your way.

Appreciate your allocations. Obliterate your oversubscription. And make good those memory leaks. Show your video memory some love, with Radeon™ Memory Visualizer.

It's dangerous to go alone! Read our RDNA Performance Guide to equip you with optimization tips and tricks.

Radeon™ Memory Visualizer (RMV) is a tool provided by AMD for use by game engine developers. It allows engineers to examine, diagnose, and understand the GPU memory management within their projects.

Welcome Radeon™ ProRender developers to your new home! It's never been easier to get started with Radeon™ ProRender, its now available under Apache 2.0 license.

Our new performance patches, feature patches and documentation making working with Unreal Engine easier than ever.

Mass effects.

Director of Game Engineering, Nick Thibieroz, introduces the relaunch of the GPUOpen website.

The Windows version of Compressonator 4.0 supports GPU encoding with DirectX® Compute (DXC) or OpenCL™ (OCL) shaders.

Discover our Vulkan blog posts, presentations, samples, and more. Find out how we can help you create and optimize your Vulkan applications!

Developing with DirectX? This page shares our DirectX blog posts, presentations, samples, and more. Let us help you create and optimize your DirectX applications!

Browse all our useful samples. Perfect for when you're needing to get started, want to integrate one of our libraries, and much more.

Browse our technical blogs, and find valuable advice on developing with AMD hardware, ray tracing, Vulkan®, DirectX®, Unreal Engine, and lots more.

Since we launched GPUOpen back in 2016, we’ve had a steady flow of guest posts from, or in collaboration with, a variety of games developers.

Don't miss our manual documentation! And if slide decks are what you're after, you'll find 100+ of our finest presentations here.

Highlights include further optimization of the physics simulation shaders, new rendering features, documentation and tutorials, and an updated TressFX Exporter for Autodesk® Maya®.

Part 4 of a series of posts on AMD FreeSync™ Premium Pro Technology. Here, we look at how to enable FreeSync Premium Pro with all next gen graphics APIs.

This sample demonstrates how to enable Freesync Premium Pro (HDR) with the DirectX® 12 and Vulkan® APIs.

We have just released our Vulkan® 1.2 driver as part of the official AMD Radeon™ Software Adrenalin 2020 Edition 20.1.2. Vulkan 1.2 is a large update which promotes many extensions into core.

The latest version of Compressonator is now available, featuring new BCn codec kernels, framework interfaces, cube maps, and more.

This is a Visual Studio® Code extension for the Radeon GPU Analyzer (RGA). This extension makes it possible to use RGA directly from within VS Code.

The latest Radeon™ GPU Profiler (RGP) v1.7 release adds support for the latest Radeon™ graphics cards: the RX 5500/RX 5300 series, and adds new UI features to help you better understand your GPU workloads.

Tom Hammersley from Codemasters talks about integrating FidelityFX into the Ego Engine and implementing Contrast Adaptive Sharpening (CAS).

The AMD "Vega" 7nm ISA is now available for download.

The latest Open source Capture and Analytics Tool (OCAT) 1.6 allows you to disable the overlay during capture.

The latest Vulkan Memory Allocator v2.3.0 adds support for Vulkan 1.1, support for query for memory budget, and support for VK_KHR_bind_memory2 extension.

When determining total available graphics memory, things can often be complicated by whether you're on an APU or a discrete GPU, and whether the information you require is available in the graphics API you're using.

Our latest Radeon Software Adrenalin Edition driver - 19.11.1 - was released on 4th November 2019. It comes packed with several useful Vulkan® extensions you may be interested in.

When creating state-of-the-art sound for a game or experience, many sound designers focus on accurate spatial 3D rendering of direct sound sources. Spatialized direct sound is important for realizing believable soundscapes that pull the player into the game world.

Higher levels of realism and believability can be achieved when accurate sound reflections are deployed in a game or experience. Spatialized, physically generated reflections can achieve this goal.

Earlier this year, RGA 2.2 shipped with a new mode of the command line tool that added support for Direct3D® 12 compute pipelines. RGA 2.3 extends that functionality to support graphics pipelines as well.

With DirectX 12 comes the power of generating disassembly and hardware resource usage statistics that are closest to the real-world case, and therefore making better performance optimization decisions.

Announcing the D3D12 version of our Memory Allocator tool.

The Game Engineering team - in collaboration with others - has put together an RDNA architecture presentation containing doodles, notes and explanation about the structure of RDNA, how it works, and the differences from our previous architectures.

The RDNA Shader Instruction Set Architecture reference guide is now available.

We have added support for AMD’s new Radeon RX 5700 and RX 5700 XT ‘Navi’ graphics cards.

Cauldron is a framework for rapid prototyping that will be used in AMD SDK samples and effects. It supports Direct3D 12 and Vulkan®.

Radeon GPU Analyzer (RGA) 2.2 introduces support for Direct3D 12 compute shaders in a new mode (-s dx12) of the command line tool.

Radeon GPU Analyzer (RGA) has support for DirectX12 compute shaders with the command line tool. This mode can generate GCN/RDNA ISA disassembly for your compute shaders, regardless of the physically installed GPU.

OCAT is our open source capture and analytics tool. This latest version 1.5 adds a lag indicator.

On Monday 17th of June we released new version of our graphics driver - 19.6.2. With it we added support for 5 new Vulkan® extensions.

In this tutorial, we will be going over what gamut mapping is, how we implemented a gamut mapper to show how FreeSync HDR works, and some pitfalls with different gamut mapping algorithms.

Microsoft® PIX is the premiere integrated performance tuning and debugging tool for Windows game developers using DirectX® 12.

The v1.5 RGP release has one of the biggest upgrades of its feature set since its first release.

In part two of this tutorial, we cover the terminology of tone mapping, what tone mapping is, as well as different monitor features that influence how well a tone mapper will work.

The first in a series of four tutorials related to AMD Freesync™ Premium Pro HDR. This tutorial covers terminology related to color.

OCAT is our open source capture and analytics tool, designed to help game developers and performance analysts dig into the details of how the GPU presents finished frames to the display.

RGA lets you write and edit shader or kernel programs, and then analyse the generated machine ISA for a wide range of supported AMD GPUs, showing you the isolated cost of a particular program as you develop it.

Links to AMD Presentations shown at GDC 2019

Guest post by Sebastian Aaltonen, co-founder of Second Order. It covers optimising building the engine and asset production when using AMD Ryzen Threadripper processors.

This version contains several new features and optimizations, including new installers for the SDK, CLI and GUI tool, new batch compress support, improvements to Compressonator's BC6H and ETC2 support, a new glTF model previewer, and more.

A guide to using our machine-readable mapping that you can integrate into your software for decoding Radeon™ Vulkan® versions.

Adam Sawicki, a member of AMD RTG's Game Engineering team, has spent the best part of a year assisting one of the world's biggest game studios in porting one of their AAA games to Vulkan.

Learn what a context roll on our GPUs is, how they apply to the pipeline and how they're managed, and what you can do to analyse them and find out if they're a limiting factor in the performance of your game or application.

Microsoft PIX is the premiere integrated performance tuning and debugging tool for Windows game developers using DirectX 12.

Compressonator is a set of tools that allows artists and developers to work easily with compressed assets and easily visualize the quality impact of various compression technologies.

This update has a number of notable performance and feature improvements, and it reflects the enhancements built into the version of TAN supported in Steam Audio.

This guest post, by Arseny Kapoulkine from Roblox, looks at the costs associated with calling various Vulkan functions tens or hundreds of thousands of times per frame, and ways to bring them down.

Half-precision (FP16) computation is a performance-enhancing GPU technology long exploited in console and mobile devices not previously used or widely available in mainstream PC development.

AMD announces the release of V-EZ, a middleware layer that significantly reduces the house-keeping overhead of Vulkan making it easier to use and more accessible to a broader base of developers.

AMD announces Radeon™ ProRender support for real-time GPU acceleration of ray tracing techniques mixed with traditional rasterization based rendering.

Links to AMD Presentations shown at GDC 2018

The GPU processing power of TrueAudio Next (TAN) has now been integrated into Steam Audio from Valve (Beta 13 release).

Insights from Enscape as to how they designed a renderer that produces path traced real time global illumination and can also converge to offline rendered image quality.

Information about the new features and optimizations in Compressonator v2.7.

Due to architectural differences between Zen and our previous processor architecture, Bulldozer, developers need to take care when using the Windows® APIs for processor and core enumeration.

The AMD GCN Vulkan extensions allow developers to get access to the barycentric coordinates at the fragment-shader level.

An important part of learning the Vulkan® API is to understand what types of objects are defined by it, what they represent and how they relate to each other.

Information about the open-source availability of the Radeon™ ProRender renderer. We will give a brief summary of its features and provide some technical insights into the internals of the renderer.

A focus on three of the improvements in TressFX 4 - bone-based skinning, signed distance field collisions, and sudden shock handling.

Information on the new features of Compressonator v2.6.

Sebastian Aaltonen, co-founder of Second Order Ltd, talks about how to optimize GPU occupancy and resource usage of compute shaders that use large thread groups.

PIX is a performance tuning and debugging tool for Windows developers using DirectX 12.

mGPU isn't just for gamers - if you’re a developer working on a game, you should think of using mGPU to make your life easier.

This sample code correctly detects the physical and logical cores of today's modern processors, along with the processor vendor and family.

Links to AMD Presentations shown at the Capsaicin and Cream event at GDC 2017.

The BC6H codec has been improved and now offers better quality than previous releases, along with support for both 16 bit Half Float and 32 bit Float formats per channel.

This tutorial explains how to use Radeon GPU Analyzer (RGA) to produce a live VGPR analysis report for your shaders and kernels. Basic RGA usage knowledge is assumed.

Croteam's Karlo Jez writes about AMD LiquidVR MultiView Rendering in Serious Sam VR with the GPU Services (AGS) Library.

Sub DWord Addressing is a feature of the AMD GCN architecture which allows the efficient extraction of 8-bit and 16-bit values from a 32-bit register.

A guide to using the Windows Performance Analyzer tool, with a focus on video resources.

Links to AMD Presentations shown at GDC 2017

Guide to using the shader compiler control API in AGS 5.0

One thing which is often forgotten is shadow map rendering. As the tessellation level of the terrain is not optimized for the shadow camera, but for the primary camera, this often results in a very strong mismatch and shadow maps end up getting extremely over-tessellated.

Understanding concurrency (and what breaks it) is extremely important when optimizing for modern GPUs.

3D intensive application performance may suffer greatly if the best graphics device is not selected. As a developer you can easily fix this problem by adding only one line to your executable's source code.

This post takes a look at the interesting bits of helping id Software with their DOOM Vulkan effort, from the perspective of AMD's Game Engineering Team.

This guest post by Croteam's Karlo Jez gives a detailed look at how Affinity Multi-GPU support was added to their game engine.

How to set up the AMD Driver Symbol Server in Visual Studio.

Barriers control resource and command synchronisation in Vulkan applications and are critical to performance and correctness. Learn more here.

Follow up on VDR and practical advice on adapting a game's tonemapping pipeline to both traditional display signals and new HDR output signals.

RapidFire SDK captures and encodes the input images entirely on the GPU and then copies the encoded result into the system memory for processing on the CPU.

Where does TrueAudio Next really fit into this emerging new ecosystem of audio processing for VR?

The final instalment in Tamas Rabel's insight into developing the Total War engine looks at Multi-GPU.

The AMD TrueAudio Next open-source library and driver-controlled CU Reservation enables dramatically higher levels of audio rendering realism in VR.

Tamas Rabel talks about how Total War: Warhammer utilized asynchronous compute to extract some extra GPU performance in DirectX® 12 and delves into the process of moving some of the passes in the engine to asynchronous compute pipelines.

Cross-lane operations are an efficient way to share data between wavefront lanes. This article covers in detail the cross-lane features that GCN3 offers.

Here’s Tamas Rabel again with some juicy details about how Creative Assembly brought Total War to DirectX® 12.

Tamas Rabel from Creative Assembly discusses how performance was measured with the Total War Engine.

Tamas Rabel, Lead Graphics Programmer on the Total War series provides a detailed look at the Total War renderer as well as digging deep into some of the optimizations that the team at Creative Assembly did for the brilliant, Total War: Warhammer.

Game engines do most of their shading work per-pixel or per-fragment. But there is another alternative that has been popular in film for decades...

This post serves as a guide on how to best use the various Memory Heaps & Memory Types exposed in Vulkan on AMD drivers, starting with some high-level tips.

This article explains how to produce Hsaco from assembly code and also takes a closer look at some new features of the GCN architecture.

Compressonator is a set of tools to allow artists and developers to more easily create compressed texture image assets and easily visualize the quality impact of various compression technologies.

Today, we are excited to announce that we are releasing an update for ShadowFX that adds support for DirectX® 12.

One of the mandates of GPUOpen is to give developers better access to the hardware, and this post details extensions for Vulkan and Direct3D12 that expose additional GCN features to developers.

The Barycentrics samples show how to enable intrinsic instructions in your DirectX®11 or DirectX®12 HLSL code.

DOPPEngine changes the output of your desktop in ways that can be very useful with various effects.

With shader extensions, we provide access to a much better tool to get compaction done: GCN provides a special op-code for compaction within a wavefront.

This sample shows how to use the AMD_shader_ballot extension and mbcnt to perform a fast reduction within a wavefront.

Our biggest update in this release is a new order-independent transparency (OIT) option we call "ShortCut".

With cluster culling, GeometryFX is able to reject large chunks of the geometry - with corresponding performance increases.

GCN hardware supports a special out-of-order rasterization mode which relaxes the ordering guarantee, and allows fragments to be produced out-of-order.

The Vulkan™ out-of-order rasterization sample shows how to use the out-of-order rasterization extension.

HelloVulkan is a small, introductory Vulkan® "Hello Triangle" sample which shows how to set up a window, set up a Vulkan context, and render a triangle.

Alternate Frame Rendering (AFR) is the method used to take advantage of Multiple GPUs in DirectX® 11 and OpenGL® applications.

Useful information about features within our AMD GPU Services (AGS) library.

This post is going to look at very subtle changes to improve grain and fine details using the same 3-bit/channel quantization case from the prior post.

Expanding on Advanced Techniques and Optimization of VDR Color Pipelines: Details on the generation of film grain ideal for transfer functions like sRGB.

An explanation of how GCN hardware coalesces memory operations to minimize traffic throughout the memory hierarchy.

DCC is a domain-specific compression that tries to take advantage of data coherence. It’s lossless, and adapted for 3D rendering. The key idea is to process whole blocks instead of individual pixels.

Vulkan validation layers make it easier to catch any mistakes, provide useful information beyond basic errors and minimize portability issues.

This sample demonstrates how to use the explicit Crossfire™ application programming interface (API).

Links to AMD Presentations shown at GDC 2016

Renderpasses are objects designed to allow an application to communicate the high-level structure of a frame to the driver.

For GPU-side dynamically generated data structures which need 3D spherical mappings, two of the most useful mappings are cubemaps and octahedral maps. This post explores the overhead of both mappings.

GPUOpen - Our initial announcement from 2016

Asynchronous compute can help you to get the maximum GPU usage. I’ll be explaining the details based on the nBodyGravity sample from Microsoft.

Optimized tonemapper form of the technique Brian Karis talks about on Graphics Rants: Tone mapping. Replace the luma computation with max3(red,green,blue).

This sample presents the GL_AMD_sparse_texture extension introduced by AMD FirePro W and AMD Radeon HD 7000 series.

This sample shows how to enable Framelock in an application using the WGL_NV_swap_group extension.

This is a slightly modified version of the Microsoft D3D12nBodyGravity sample, This sample demonstrates the use of asynchronous compute shaders (multi-engine) to simulate an n-body gravity system.

HelloD3D12 is a small, introductory Direct3D 12 sample, which shows how to set up a window and render a textured quad complete with proper uploading handling, multiple frames queued and constant buffers.

This sample demonstrates some of the ways in which to reduce scene aliasing without using a post process technique.

This SDK sample implements PN Triangles and Phong tessellation. It also shows how to optimize performance by using adaptive tessellation techniques.

This sample presents a technique for achieving highly optimized, user-defined separable filters.

This sample demonstrates a post-process pixel shader technique that applies fullscreen anti-aliasing to an image.

This sample demonstrates how to implement a simple GPU-based particle system.

This sample provides an example implementation of the Forward+ algorithm, which extends traditional forward rendering to support high numbers of dynamic lights while maintaining performance.

The DepthBoundsTest11 sample shows how to use the Depth Bounds driver extension.

This sample provides an example implementation of two tile-based light culling methods: Forward+ and Tiled Deferred.

Links to AMD Presentations shown at GDC 2015

Our one-stop guide to performance with Unreal Engine.