Radeon Raytracing Analyzer
RRA helps you to investigate the performance of your raytracing applications and highlight potential bottlenecks. We’re excited to announce that we have made the source code for RRA available, which can now be downloaded from the RRA GitHub page.
The repo can be cloned using git or the source code can be downloaded as a .zip file. Full instructions on how to build RRA are included in the BUILD.md file or via the link in the README.md file.
As well as viewing the source for RRA on GitHub, feel free to download the packaged binary (which comes with the rest of our Radeon Developer Tool Suite) or read our documentation.
RRA is available as part of the Radeon Developer Tool Suite.
AMD Radeon Data File
We’ve recently made a small library available on GitHub: amdrdf. This is a library which allows you to open, inspect, and create RDF files (short for Radeon Data File). You may have seen RDF in the wild already when you used tools like RRA which use it as the underlying storage mechanism. RDF is a container file that abstracts away the underlying details of how things are actually stored on disk. It provides a few common functions like support for compression without imposing a lot of structure on the client application.
The key concept of RDF is to have named chunks stored in the file. Each application has a set of chunk types it understands and will ignore all other chunks, making it easy to include data from multiple applications into one file. Chunks are referenced from a chunk index which makes it efficient to find the data you actually care about in the file.
amdrdf has two APIs for your convenience: A versioned and ABI-stable C API, and a C++ convenience API built on top that is compiled into the client application. amdrdf also comes with long-term support guarantees regarding API, ABI, and file format stability as outlined in the readme. If you’re planning to work on tools that interop with ours, we highly recommend using the amdrdf library which works on any reasonably modern C++ compiler over rolling your own solution.
You may also be interested in...
Raytracing Performance Revealed – How to Optimize your Game with the Radeon™ Developer Tool Suite – YouTube link
In this presentation, we demonstrate how to use Radeon™ GPU Profiler and Radeon™ Raytracing Analyzer, to illuminate performance issues.
Optimizing the raytracing pipeline can be difficult. Discover how to spot and diagnose common RT pitfalls with RRA, and how to fix them!
Radeon GPU Analyzer is an offline compiler and performance analysis tool for DirectX®, Vulkan®, SPIR-V™, OpenGL® and OpenCL™.
RGP gives you unprecedented, in-depth access to a GPU. Easily analyze graphics, async compute usage, event timing, pipeline stalls, barriers, bottlenecks, and other performance inefficiencies.
Radeon™ Memory Visualizer (RMV) is a tool to allow you to gain a deep understanding of how your application uses memory for graphics resources.
The RDP provides a communication channel with the Radeon™ Adrenalin driver. It generates event timing data used by the Radeon™ GPU Profiler (RGP), and the memory usage data used by the Radeon™ Memory Visualizer (RMV).