diff --git a/clang/docs/HLSL/EntryFunctions.rst b/clang/docs/HLSL/EntryFunctions.rst
--- a/clang/docs/HLSL/EntryFunctions.rst
+++ b/clang/docs/HLSL/EntryFunctions.rst
@@ -37,10 +37,16 @@
 
 The actual exported entry function which can be called by the GPU driver is a
 ``void(void)`` function that isn't name mangled. In code generation we generate
-the unmangled entry function, instantiations of the parameters with their
-semantic values populated, and a call to the user-defined function. After the
-call instruction the return value (if any) is saved using a target-appropriate
-intrinsic for storing outputs (for DirectX, the ``llvm.dx.store.output``).
+the unmangled entry function to serve as the actual shader entry. The shader
+entry function is annotated with the ``hlsl.shader`` function attribute
+identifying the entry's pipeline stage.
+
+The body of the unmangled entry function contains first a call to execute global
+constructors, then instantiations of the user-defined entry parameters with
+their semantic values populated, and a call to the user-defined function.
+After the call instruction the return value (if any) is saved using a
+target-appropriate intrinsic for storing outputs (for DirectX, the
+``llvm.dx.store.output``). Global destructors are not supported in HLSL.
 
 .. note::
 
diff --git a/clang/lib/CodeGen/CGHLSLRuntime.h b/clang/lib/CodeGen/CGHLSLRuntime.h
--- a/clang/lib/CodeGen/CGHLSLRuntime.h
+++ b/clang/lib/CodeGen/CGHLSLRuntime.h
@@ -46,6 +46,7 @@
   virtual ~CGHLSLRuntime() {}
 
   void annotateHLSLResource(const VarDecl *D, llvm::GlobalVariable *GV);
+  void generateGlobalCtorCalls();
 
   void finishCodeGen();
 
diff --git a/clang/lib/CodeGen/CGHLSLRuntime.cpp b/clang/lib/CodeGen/CGHLSLRuntime.cpp
--- a/clang/lib/CodeGen/CGHLSLRuntime.cpp
+++ b/clang/lib/CodeGen/CGHLSLRuntime.cpp
@@ -54,6 +54,8 @@
   Triple T(M.getTargetTriple());
   if (T.getArch() == Triple::ArchType::dxil)
     addDxilValVersion(TargetOpts.DxilValidatorVersion, M);
+
+  generateGlobalCtorCalls();
 }
 
 void CGHLSLRuntime::annotateHLSLResource(const VarDecl *D, GlobalVariable *GV) {
@@ -143,3 +145,40 @@
   // FIXME: Handle codegen for return type semantics.
   B.CreateRetVoid();
 }
+
+void CGHLSLRuntime::generateGlobalCtorCalls() {
+  llvm::Module &M = CGM.getModule();
+  const auto *GlobalCtors = M.getNamedGlobal("llvm.global_ctors");
+  if (!GlobalCtors)
+    return;
+  const auto *CA = dyn_cast<ConstantArray>(GlobalCtors->getInitializer());
+  if (!CA)
+    return;
+  // The global_ctor array elements are a struct [Priority, Fn *, COMDat].
+  // HLSL neither supports priorities or COMDat values, so we will check those
+  // in an assert but not handle them.
+
+  llvm::SmallVector<Function *> CtorFns;
+  for (const auto &Ctor : CA->operands()) {
+    if (isa<ConstantAggregateZero>(Ctor))
+      continue;
+    ConstantStruct *CS = cast<ConstantStruct>(Ctor);
+
+    assert(cast<ConstantInt>(CS->getOperand(0))->getValue() == 65535 &&
+           "HLSL doesn't support setting priority for global ctors.");
+    assert(isa<ConstantPointerNull>(CS->getOperand(2)) &&
+           "HLSL doesn't support COMDat for global ctors.");
+    CtorFns.push_back(cast<Function>(CS->getOperand(1)));
+  }
+
+  // Insert a call to the global constructor at the beginning of the entry block
+  // to externally exported functions. This is a bit of a hack, but HLSL allows
+  // global constructors, but doesn't support driver initialization of globals.
+  for (auto &F : M.functions()) {
+    if (!F.hasFnAttribute("hlsl.shader"))
+      continue;
+    IRBuilder<> B(&F.getEntryBlock(), F.getEntryBlock().begin());
+    for (auto *Fn : CtorFns)
+      B.CreateCall(FunctionCallee(Fn));
+  }
+}
diff --git a/clang/test/CodeGenHLSL/GlobalConstructors.hlsl b/clang/test/CodeGenHLSL/GlobalConstructors.hlsl
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGenHLSL/GlobalConstructors.hlsl
@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.0-compute -x hlsl -S -emit-llvm -disable-llvm-passes %s -o - | FileCheck %s
+
+RWBuffer<float> Buffer;
+
+[numthreads(1,1,1)]
+void main(unsigned GI : SV_GroupIndex) {}
+
+//CHECK:      define void @main()
+//CHECK-NEXT: entry:
+//CHECK-NEXT:   call void @_GLOBAL__sub_I_GlobalConstructors.hlsl()
+//CHECK-NEXT:   %0 = call i32 @llvm.dx.flattened.thread.id.in.group()
+//CHECK-NEXT:   call void @"?main@@YAXI@Z"(i32 %0)
+//CHECK-NEXT:   ret void