Google Partners with AMD for Custom Stadia GPU
How do we enable thousands, even millions, of simultaneous cloud gamers to push their gaming skills to the limit? AMD datacenter GPUs address critical, behind-the-scene datacenter requirements with purpose-built, proven technologies for security, manageability, and scalability. The industry’s first hardware-based GPU virtualization solution built on industry-standard SR-IOV (Single Root I/O Virtualization) technology delivers fast, predictable performance with enhanced security features. HBM2 memory provides power savings in a space-saving footprint, as well as important features such as Error Correcting Code (EEC) protection to help ensure data integrity.
Our commitment to open source platforms, including support for Linux-based Vulkan drivers, offers developers confidence to deliver their games to multiple platforms. Many of today’s biggest games are already optimized for AMD GPUs and developers expect many of those decisions will carry over when running on the AMD datacenter GPUs that power cloud-gaming. AMD also provides developers with tools and enhancements needed to fine tune game experiences. These include:
- The AMD Linux driver includes an application tracing component that, together with the AMD Radeon™ GPU Profiler (RGP), provides access to detailed, low-level information about how workloads run on AMD GPUs. Identifying timing issues that might suggest potential optimizations, this capability can dramatically improve developers’ ability to create applications that deliver the best possible performance on AMD GPUs.
- RGP also allows game developers to visualize precisely how their application is utilizing the AMD GPU, including how graphics and compute thread groups occupy the GPU, enabling them to track event timing and optimize their games for the Stadia platform.
- RGP interoperates with the popular open-source RenderDoc graphics debugging tool to give developers deeper real-time insights into the rendering of each frame, which can significantly reduce the time required to debug and profile frames during the development process.
- RGP operates the same way in a virtualized environment as it does when running on a dedicated PC client, making it as easy for developers to optimize their applications for virtualized GPUs in large scale environments as they would for any other gaming platform
If you’ve got your eye on the fast-approaching cloud-gaming future, you’ll want to check out the GDC keynote. And be sure to check back for more exciting cloud gaming news from AMD in the coming weeks and months.
- Learn more about AMD and cloud gaming solutions here
- Learn more about Radeon GPU Profiler here
- Learn more about RenderDoc here
- Discover AMD Open Software support on GPUOpen.com
--Scott Jackson, Director Product Management, Datacenter GPU Business Unit