Get Started with Intel® Graphics Performance Analyzers (Intel GPA)
Use this document to get started with Intel® Graphics Performance Analyzers (Intel® GPA), which is a toolset for graphics performance analysis and optimization of games and other graphics-intensive Microsoft* DirectX*, Apple* Metal*, Vulkan*, and OpenGL* applications. Intel GPA is available on Windows*, macOS*, and Ubuntu* hosts.
Supported Graphics APIs
API
| Windows Host
| Ubuntu Host
| macOS Host
|
---|---|---|---|
DirectX
| yes
| no
| no
|
Vulkan
| yes
| yes
| no
|
Metal
| no
| no
| yes
|
OpenGL
| no
| yes
| yes
|
For details on software and hardware requirements for Intel GPA, see the product
Release Notes.
System Analysis: Understand High-Level Performance Profile of Your Game
- View CPU, GPU, and Graphics API metrics in real time to determine whether your application is CPU or GPU bound
- Experiment with graphics pipeline state overrides to perform a high-level iterative analysis of your game without changing a single line of code
- Capture frames and traces for detailed analysis with Graphics Frame Analyzer and Graphics Trace Analyzer, respectively

Stream Analysis: Spot Frames with Potential Performance Bottlenecks
- Quickly pinpoint problem areas with fast, efficient iterations over stream data
- Spot intermittent anomalies and multiframe algorithms
- No need to recapture data to look at different frames

Frame Analysis: Pinpoint Performance Bottlenecks within a Frame
- Explore a variety of metrics at the API call level to find performance bottlenecks
- Analyze all graphics resources and textures used in the frame
- Experiment with rendering states, graphics primitive parameters, as well as shaders without recompiling your game code
- Analyze pixel history for your application
- Correlate rendering issues with the exact stage of the graphics pipeline

Platform Analysis: Visualize the Interaction of Your App and Its Threads Across All CPUs and the GPU
- Correlate CPU and GPU activity to understand whether your app is effectively using all compute resources, or it is CPU/GPU bound
- Explore GPU usage and analyze a software queue for GPU engines at each moment of time
- Identify GPU and CPU application frame rate and how it depends on vertical synchronization
- Explore the performance of your application per selected GPU metrics over time
