Jump to content
  • Advertisement
Sign in to follow this  
Narf the Mouse

Does Shader Model 4 support matrices composed of 64-bit floating-point values

This topic is 2158 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Recommended Posts

Advertisement
SM4.0 has no double support. It's an (optional) feature that was added for SM5.0. You can check for it with ID3D11Device::CheckFeatureSupport. Wikipedia also has comparison tables for AMD and Nvidia GPU's that tell you which ones support double precision.

As for "double4x4" in particular, the HLSL docs say that "double" is a valid type for matrices. Edited by MJP

Share this post


Link to post
Share on other sites

SM4.0 has no double support. It's an (optional) feature that was added for SM5.0. You can check for it with ID3D11Device::CheckFeatureSupport. Wikipedia also has comparison tables for AMD and Nvidia GPU's that tell you which ones support double precision.

As for "double4x4" in particular, the HLSL docs say that "double" is a valid type for matrices.

Thanks.

Share this post


Link to post
Share on other sites
It's important to note that current generation GPUs are MUCH slower when in double processing mode.

For example AMD's latest runs double precision at 1/4 the rate of floating point on it's top end chip (Tahiti) while NV's Kepler series (6x0) runs double precision at 1/12th floating point speed (slower than the previous gen which run at 1/4 rate).

In short; unless you really need doubles and can afford the ALU speed hit it's really not a good idea on consumer cards.

Share this post


Link to post
Share on other sites
Sign in to follow this  

  • Advertisement
×

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

Participate in the game development conversation and more when you create an account on GameDev.net!

Sign me up!