Google has announced WebGPU, an API that gives web browsers more access to your device's GPU for better 3D graphics performance and data-parallel computation on the web. Google has implemented WebGPU in Chrome 113, which is currently in the beta testing stage. Chrome 113 will make use of WebGPU on ChromeOS devices with Vulkan, Windows machines with Direct3D 12, and macOS devices.
WebGPU allows rendering and computation operations on a GPU, similar to other graphics APIs, such as Direct3D 12, Metal, and Vulkan, but it is designed for the web. According to Google, it offers “greatly reduced JavaScript workload for the same graphics and more than three times improvements in machine learning model inference” and is designed with “the web platform in mind, featuring an idiomatic JavaScript API, integration with promises, support for importing videos, and a polished developer experience with great error messages.“
In a blog post announcing the launch of WebGPU, Google shared the development journey of the new graphics API. According to the company, the development of WebGPU kicked off in 2017 as a result of a collaborative effort by the W3C's “GPU for the Web” Community Group and contributions from major companies such as Apple, Intel, Microsoft, and Mozilla.
With Chrome 113 on your Samsung Chromebook and Galaxy Books powered by Windows 10/11 operating system, you can experience better graphics performance on webpages in the future. Implementation of WebGPU in Firefox and Safari is currently in progress and should be available to the public soon.
