[dxbc] Implement option to split up fma

dxvk.conf

@@ -499,6 +499,7 @@
 # Supported values:
 # - True/False
 
+# d3d11.longMad = False
 # d3d9.longMad = False
 
 # Device Local Constant Buffers

src/d3d11/d3d11_options.cpp

@@ -32,6 +32,7 @@ namespace dxvk {
     this->maxFrameLatency       = config.getOption<int32_t>("dxgi.maxFrameLatency", 0);
     this->maxFrameRate          = config.getOption<int32_t>("dxgi.maxFrameRate", 0);
     this->exposeDriverCommandLists = config.getOption<bool>("d3d11.exposeDriverCommandLists", true);
+    this->longMad               = config.getOption<bool>("d3d11.longMad", false);
 
     // Clamp LOD bias so that people don't abuse this in unintended ways
     this->samplerLodBias = dxvk::fclamp(this->samplerLodBias, -2.0f, 1.0f);

src/d3d11/d3d11_options.h

@@ -120,6 +120,9 @@ namespace dxvk {
 
     /// Shader dump path
     std::string shaderDumpPath;
+
+    /// Should we make our Mads a FFma or do it the long way with an FMul and an FAdd?
+    bool longMad;
   };
   
 }

src/dxbc/dxbc_compiler.cpp

@@ -1623,8 +1623,13 @@ namespace dxvk {
       
       case DxbcOpcode::Mad:
       case DxbcOpcode::DFma:
-        dst.id = m_module.opFFma(typeId,
+        if (likely(!m_moduleInfo.options.longMad)) {
-          src.at(0).id, src.at(1).id, src.at(2).id);
+          dst.id = m_module.opFFma(typeId,
+            src.at(0).id, src.at(1).id, src.at(2).id);
+        } else {
+          dst.id = m_module.opFMul(typeId, src.at(0).id, src.at(1).id);
+          dst.id = m_module.opFAdd(typeId, dst.id, src.at(2).id);
+        }
         break;
       
       case DxbcOpcode::Max:

src/dxbc/dxbc_options.cpp

@@ -38,6 +38,7 @@ namespace dxvk {
     disableMsaa              = options.disableMsaa;
     forceSampleRateShading   = options.forceSampleRateShading;
     enableSampleShadingInterlock = device->features().extFragmentShaderInterlock.fragmentShaderSampleInterlock;
+    longMad                  = options.longMad;
 
     // Figure out float control flags to match D3D11 rules
     if (options.floatControls) {

src/dxbc/dxbc_options.h

@@ -54,6 +54,9 @@ namespace dxvk {
 
     /// Minimum storage buffer alignment
     VkDeviceSize minSsboAlignment = 0;
+
+    /// Should we make our Mads a FFma or do it the long way with an FMul and an FAdd?
+    bool longMad;
   };
   
 }