Implement UseNativeLowPrecision shader flag analysis

Author: Icohedron

clang/lib/CodeGen/CGHLSLRuntime.cpp

@@ -282,10 +282,13 @@ void CGHLSLRuntime::addHLSLBufferLayoutType(const RecordType *StructType,
 
 void CGHLSLRuntime::finishCodeGen() {
   auto &TargetOpts = CGM.getTarget().getTargetOpts();
+  auto &LangOpts = CGM.getLangOpts();
   llvm::Module &M = CGM.getModule();
   Triple T(M.getTargetTriple());
   if (T.getArch() == Triple::ArchType::dxil)
     addDxilValVersion(TargetOpts.DxilValidatorVersion, M);
+  if (LangOpts.NativeHalfType)
+    M.setModuleFlag(llvm::Module::ModFlagBehavior::Error, "dx.nativelowprec", 1);
 
   generateGlobalCtorDtorCalls();
 }

clang/test/CodeGenHLSL/enable-16bit-types.hlsl

@@ -0,0 +1,9 @@
+// RUN: %clang_cc1 -fnative-half-type -finclude-default-header -triple dxil-pc-shadermodel6.3-library -emit-llvm -disable-llvm-passes -o - %s | FileCheck %s --check-prefix=FLAG
+// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.3-library -emit-llvm -disable-llvm-passes -o - %s | FileCheck %s --check-prefix=NOFLAG
+
+// NOTE: -enable-16bit-types is a DXCFlag that aliases -fnative-half-type
+
+// FLAG-DAG: ![[NLP:.*]] = !{i32 1, !"dx.nativelowprec", i32 1}
+// FLAG-DAG: !llvm.module.flags = !{{{.*}}![[NLP]]{{.*}}}
+
+// NOFLAG-NOT: dx.nativelowprec

llvm/lib/Target/DirectX/DXILShaderFlags.cpp

@@ -188,6 +188,12 @@ void ModuleShaderFlags::initialize(Module &M, DXILResourceTypeMap &DRTM,
         continue;
       }
 
+      // Set UseNativeLowPrecision using dx.nativelowprec module metadata
+      if (auto *NativeLowPrec = mdconst::extract_or_null<ConstantInt>(
+              M.getModuleFlag("dx.nativelowprec")))
+        if (NativeLowPrec->getValue() != 0)
+          SCCSF.UseNativeLowPrecision = true;
+
       ComputedShaderFlags CSF;
       for (const auto &BB : *F)
         for (const auto &I : BB)