GPUOpen-LibrariesAndSDKs/AGS_SDK

AMD GPU Services (AGS) library and samples

Owned by AMD

View on GitHub ↗Jump to charts ↓

GPUOpen-LibrariesAndSDKs/AGS_SDK has 300+ stars and 40+ forks on GitHub, is written in C++, and was last pushed on May 27, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 51 minutes ago
Added to GitGenius on October 12th, 2026
Created on January 15th, 2016
Open Issues & Pull Requests: 24 (+0)
GitHub issues: Enabled
Number of forks: 48
Total Stargazers: 307 (+0)
Total Subscribers: 34 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 2.8 days
Mean response time: 80.5 days
90th percentile: 253.0 days
Tracked items: 4

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 9
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 733 days
Stale 30+ days: 9
Stale 90+ days: 9

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

AMD GPU Services (AGS) SDK is a C++ library that enables developers to access AMD GPU software and hardware state information beyond what standard operating systems and graphics APIs expose.

The library solves the problem of limited visibility into AMD GPU capabilities by providing direct access to driver version information, detailed GPU hardware specifications, performance metrics, and AMD-specific shader extensions for DirectX 11 and DirectX 12. It also supplies configuration data for Crossfire multi-GPU rendering and Eyefinity multi-display setups. The approach works by querying the AMD driver directly to surface this information through a programmatic interface.

Developers targeting AMD GPUs who need fine-grained control over hardware utilization should consider AGS. It suits projects where performance optimization for specific AMD architectures matters, or where applications need to adapt behavior based on GPU capabilities and driver state. The SDK includes sample code demonstrating library usage patterns.

The project maintains active support across multiple compiler toolchains and GPU architectures. Development includes regular updates to detect newly released GPU families and to add shader intrinsics that expose hardware-specific capabilities for ray tracing optimization, wave operations, and atomic operations. The library is distributed in both static and dynamic linking variants to accommodate different integration scenarios.