archive/rpcs3
1
0
Fork 0
mirror of https://github.com/RPCS3/rpcs3.git synced 2025-07-12 17:58:37 +12:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

fp32 precision on GPUs is embarassing

Browse source 
- Division seems to suffer from drift easily on GPUs due to limited precision
This commit is contained in:
kd-11 2017-11-18 13:02:10 +03:00
parent ccc0383f75
commit 5cf2d774f3
1 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
rpcs3/Emu/RSX/GL/GLVertexProgram.cpp
View file

@ -306,13 +306,15 @@ void GLVertexDecompilerThread::insertMainEnd(std::stringstream & OS)
//It is therefore critical that this step is done post-transform and the result re-scaled by w //It is therefore critical that this step is done post-transform and the result re-scaled by w
//SEE Naruto: UNS //SEE Naruto: UNS
OS << " float ndc_z = gl_Position.z / gl_Position.w;\n"; //NOTE: On GPUs, poor fp32 precision means dividing z by w, then multiplying by w again gives slightly incorrect results
OS << " ndc_z = (ndc_z * 2.) - 1.;\n"; //This equation is simplified algebraically to an addition and subreaction which gives more accurate results (Fixes flickering skybox in Dark Souls 2)
OS << " gl_Position.z = ndc_z * gl_Position.w;\n"; //OS << " float ndc_z = gl_Position.z / gl_Position.w;\n";
//OS << " ndc_z = (ndc_z * 2.) - 1.;\n";
//OS << " gl_Position.z = ndc_z * gl_Position.w;\n";
OS << " gl_Position.z = (gl_Position.z + gl_Position.z) - gl_Position.w;\n";
OS << "}\n"; OS << "}\n";
} }
void GLVertexDecompilerThread::Task() void GLVertexDecompilerThread::Task()
{ {
m_shader = Decompile(); m_shader = Decompile();