Difference between revisions of "VRWorks"

From Virtual Reality, Augmented Reality Wiki
Jump to: navigation, search
m (Text replacement - "pixel density" to "pixel density")
Line 2: Line 2:
  
 
==Features==
 
==Features==
 +
{{#ev:youtube|09dT3vkwXBA|300}}
 
===VR SLI===
 
===VR SLI===
 
[[VR SLI]] increases the performance of [[VR Apps]] by assigning 1 or more [[GPU]]s to each eye when [[stereo rendering]] (creating a different image for each eye). Because VR utilizes 2 independent views, developers can parallax the rendering across 2 different GPUs then combine the images into a single frame in the [[HMD]]. It allows the app to have higher [[fps]] or graphical settings. Additionally, VR SLI API allows developers to scale the entire system to more than 2 GPUs. Developers can split up the rendering anyway they want across any number of GPUs they desire.<ref name="GameWorks_VR_Site">https://developer.nvidia.com/virtual-reality-development</ref>
 
[[VR SLI]] increases the performance of [[VR Apps]] by assigning 1 or more [[GPU]]s to each eye when [[stereo rendering]] (creating a different image for each eye). Because VR utilizes 2 independent views, developers can parallax the rendering across 2 different GPUs then combine the images into a single frame in the [[HMD]]. It allows the app to have higher [[fps]] or graphical settings. Additionally, VR SLI API allows developers to scale the entire system to more than 2 GPUs. Developers can split up the rendering anyway they want across any number of GPUs they desire.<ref name="GameWorks_VR_Site">https://developer.nvidia.com/virtual-reality-development</ref>

Revision as of 22:56, 3 December 2015

GameWorks VR is a suite of virtual reality technologies developed by Nvidia to tackle high-performance VR rendering. It contains a set of APIs, libraries and features that enable both engine and HMD developers to create the ideal VR experiences.

Features

VR SLI

VR SLI increases the performance of VR Apps by assigning 1 or more GPUs to each eye when stereo rendering (creating a different image for each eye). Because VR utilizes 2 independent views, developers can parallax the rendering across 2 different GPUs then combine the images into a single frame in the HMD. It allows the app to have higher fps or graphical settings. Additionally, VR SLI API allows developers to scale the entire system to more than 2 GPUs. Developers can split up the rendering anyway they want across any number of GPUs they desire.[1]

Multi-resolution shading

Multi-resolution shading renders different parts of the image with different resolutions to better match the pixel density of a warped image. When a flat image is viewed from the lenses of an HMD, the image is distorted. The processor has to perform an additional task that "de-distort" or warps the image. The warp pass compresses the edges of the image, reducing pixels there. Multi-res shading renders a warped image directly, keeping full resolution in the center of image while reducing the resolution of the edges of the image.[1]

Context Priority

Context Priority gives HMD developers the control over GPU scheduling to support important VR features such as asynchronous timewarp.[1]

Direct Mode

In Direct Mode, the display driver treats the HMD as an entity separate from the operating system and accessible only to VR apps. It improves plug-and-play capabilities and prevents numerous UX issues that occur when the OS treats the HMD as just another monitor. It also allows HMD developers to reduce latency by giving them the control over frame queuing and vsync behavior.[1]

Front Render Buffering

Front Render Buffering allows the GPU to render directly to the front buffer to reduce latency.[1]

References

  1. 1.0 1.1 1.2 1.3 1.4 https://developer.nvidia.com/virtual-reality-development