AMD Radeon™ GPU Profiler logo

Analyze. Adjust. Accelerate. Now available as part of the AMD Radeon™ Developer Tool Suite.

AMD RGP UI image

Meet the AMD Radeon™ GPU Profiler, a ground-breaking low-level optimization tool that provides detailed information on AMD Radeon™ GPUs.

Download the latest version - v2.5

This release adds the following features:

  • Support for additional AMD RDNA™ 4 architecture hardware (AMD Radeon™ RX 9060 XT, AMD Radeon™ RX 9070 GRE, and AMD Radeon™ AI PRO R9700 GPUs).
  • Counter collection is now supported on AMD RDNA™ 3 architecture-based APUs (requires a 25.10-based driver or newer).
  • Support for showing pipeline data in the Pipelines Overview pane for Work Graph pipelines (requires a 25.10-based driver or newer).
  • Improved interoperability between AMD Radeon™ GPU Profiler and AMD Radeon™ GPU Analyzer for pipelines that contain multiple shaders (like some ray tracing and compute pipelines).
  • Improved instruction latency tooltip in the Instruction timing pane.
  • Improved annotations on event names for DirectX® 12 events launched from ExecuteIndirect.
  • Improved loading performance for profiles with large number of events.
  • Many bug/stability/usability fixes.

Features

Unlike the black box approach of the past, PC game developers now have unprecedented, in-depth access to a GPU and can easily analyze graphics, async compute usage, event timing, pipeline stalls, barriers, bottlenecks, and other performance inefficiencies.

This unique tool generates easy to understand visualizations of how your DirectX® 12, Vulkan®, OpenCL™, and HIP applications interact with the GPU at the hardware level. Profiling a game is both a quick and simple process using the AMD Radeon™ Developer Panel and our AMD Software: Adrenalin Edition™ driver.

Figure out your frame

Get a bird’s eye view of how your command buffers got submitted to each GPU queue.

Understand how your graphics, async compute, and copy workloads interact and synchronize.

AMD RGP frame summary

Wade through your wavefronts

Understand how your wavefronts were pushed through the GPU. We can also correlate between wavefronts and the GPU events which launched them and provide insight into how your frame utilizes the various GPU memory caches.

The data displayed in this view is highly filterable, groupable, and includes a side panel with added detail about user selections.

AMD RGP wavefront occupancy

Speed up your shaders

Quickly and easily find hotspots in your shaders using the instruction timing view.

Each instruction in your AMD RDNA™ arcitecture ISA has a bar showing its average latency, allowing you find the right things to optimize.

AMD RGP instruction timing

Banish those barriers!

Find out which barriers flushed caches, caused a synchronization point or even ran their own, internal shaders.

Burst those pipeline bubbles and claim back your performance.

AMD RGP barriers

Requirements

Supported GPUs

  • AMD Radeon™ RX 9000 Series Graphics
  • AMD Radeon™ RX 7000 Series Graphics
  • AMD Radeon™ RX 6000 Series Graphics
  • AMD Radeon™ RX 5000 Series Graphics
  • AMD Ryzen™ Processors with AMD Radeon™ Graphics based on AMD RDNA™ architecture or better
  • AMD Radeon™ AI PRO R9700 Graphics

Supported graphics APIs

  • DirectX® 12
  • Vulkan®

Supported compute APIs

  • OpenCL™
  • HIP

Supported OSs

  • Windows® 10
  • Windows® 11
  • Linux® – Ubuntu 22.04.1 LTS (Vulkan® only)
  • Linux® – Ubuntu 24.04.1 LTS (Vulkan® only)

Version history

  • Support for additional AMD RDNA™ 4 architecture hardware (AMD Radeon™ RX 9060 XT, AMD Radeon™ RX 9070 GRE, and AMD Radeon™ AI PRO R9700 GPUs).

  • Counter collection is now supported on AMD RDNA™ 3 architecture-based APUs (requires a 25.10-based driver or newer).

  • Support for showing pipeline data in the Pipelines Overview pane for Work Graph pipelines (requires a 25.10-based driver or newer).

  • Improved interoperability between AMD Radeon™ GPU Profiler and AMD Radeon™ GPU Analyzer for pipelines that contain multiple shaders (like some ray tracing and compute pipelines).

  • Improved instruction latency tooltip in the Instruction timing pane.

  • Improved annotations on event names for DirectX® 12 events launched from ExecuteIndirect.

  • Improved loading performance for profiles with large number of events.

  • Many bug/stability/usability fixes.

Related news and technical articles

Related videos