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
@@ -202,4 +202,14 @@
     for (auto *Fn : DtorFns)
       B.CreateCall(FunctionCallee(Fn));
   }
+
+  // No need to keep global ctors/dtors for non-lib profile after call to
+  // ctors/dtors added for entry.
+  Triple T(M.getTargetTriple());
+  if (T.getEnvironment() != Triple::EnvironmentType::Library) {
+    if (auto *GV = M.getNamedGlobal("llvm.global_ctors"))
+      GV->eraseFromParent();
+    if (auto *GV = M.getNamedGlobal("llvm.global_dtors"))
+      GV->eraseFromParent();
+  }
 }
diff --git a/clang/lib/Sema/SemaDeclAttr.cpp b/clang/lib/Sema/SemaDeclAttr.cpp
--- a/clang/lib/Sema/SemaDeclAttr.cpp
+++ b/clang/lib/Sema/SemaDeclAttr.cpp
@@ -6895,7 +6895,10 @@
 static void handleHLSLSVGroupIndexAttr(Sema &S, Decl *D, const ParsedAttr &AL) {
   using llvm::Triple;
   Triple Target = S.Context.getTargetInfo().getTriple();
-  if (Target.getEnvironment() != Triple::Compute) {
+  if (Target.getEnvironment() != Triple::Compute &&
+      Target.getEnvironment() != Triple::Library) {
+    // FIXME: it is OK for a compute shader entry and pixel shader entry live in
+    // same HLSL file.
     uint32_t Pipeline =
         (uint32_t)S.Context.getTargetInfo().getTriple().getEnvironment() -
         (uint32_t)llvm::Triple::Pixel;
diff --git a/clang/test/CodeGenHLSL/GlobalConstructorFunction.hlsl b/clang/test/CodeGenHLSL/GlobalConstructorFunction.hlsl
--- a/clang/test/CodeGenHLSL/GlobalConstructorFunction.hlsl
+++ b/clang/test/CodeGenHLSL/GlobalConstructorFunction.hlsl
@@ -17,6 +17,10 @@
 [numthreads(1,1,1)]
 void main(unsigned GI : SV_GroupIndex) {}
 
+// Make sure global variable for ctors/dtors removed.
+// CHECK-NOT:@llvm.global_ctors
+// CHECK-NOT:@llvm.global_dtors
+
 //CHECK: define void @main()
 //CHECK-NEXT: entry:
 //CHECK-NEXT:   call void @"?call_me_first@@YAXXZ"()
diff --git a/clang/test/CodeGenHLSL/GlobalConstructorLib.hlsl b/clang/test/CodeGenHLSL/GlobalConstructorLib.hlsl
--- a/clang/test/CodeGenHLSL/GlobalConstructorLib.hlsl
+++ b/clang/test/CodeGenHLSL/GlobalConstructorLib.hlsl
@@ -1,5 +1,8 @@
 // RUN: %clang_cc1 -triple dxil-pc-shadermodel6.3-library -S -emit-llvm -disable-llvm-passes %s -o - | FileCheck %s
 
+// Make sure global variable for ctors exist for lib profile.
+// CHECK:@llvm.global_ctors
+
 RWBuffer<float> Buffer;
 
 [shader("compute")]
diff --git a/clang/test/CodeGenHLSL/GlobalConstructors.hlsl b/clang/test/CodeGenHLSL/GlobalConstructors.hlsl
--- a/clang/test/CodeGenHLSL/GlobalConstructors.hlsl
+++ b/clang/test/CodeGenHLSL/GlobalConstructors.hlsl
@@ -5,6 +5,9 @@
 [numthreads(1,1,1)]
 void main(unsigned GI : SV_GroupIndex) {}
 
+// Make sure global variable for ctors/dtors removed.
+// CHECK-NOT:@llvm.global_ctors
+// CHECK-NOT:@llvm.global_dtors
 //CHECK:      define void @main()
 //CHECK-NEXT: entry:
 //CHECK-NEXT:   call void @_GLOBAL__sub_I_GlobalConstructors.hlsl()
diff --git a/clang/test/CodeGenHLSL/GlobalDestructors.hlsl b/clang/test/CodeGenHLSL/GlobalDestructors.hlsl
--- a/clang/test/CodeGenHLSL/GlobalDestructors.hlsl
+++ b/clang/test/CodeGenHLSL/GlobalDestructors.hlsl
@@ -39,6 +39,9 @@
   Wag();
 }
 
+// Make sure global variable for ctors/dtors removed.
+// CHECK-NOT:@llvm.global_ctors
+// CHECK-NOT:@llvm.global_dtors
 //CHECK:      define void @main()
 //CHECK-NEXT: entry:
 //CHECK-NEXT:   call void @_GLOBAL__sub_I_GlobalDestructors.hlsl()
diff --git a/clang/test/CodeGenHLSL/GlobalDestructors.hlsl b/clang/test/CodeGenHLSL/GlobalDestructorsLib.hlsl
copy from clang/test/CodeGenHLSL/GlobalDestructors.hlsl
copy to clang/test/CodeGenHLSL/GlobalDestructorsLib.hlsl
--- a/clang/test/CodeGenHLSL/GlobalDestructors.hlsl
+++ b/clang/test/CodeGenHLSL/GlobalDestructorsLib.hlsl
@@ -1,4 +1,7 @@
-// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.0-compute -std=hlsl202x -S -emit-llvm -disable-llvm-passes %s -o - | FileCheck %s
+// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.3-library -std=hlsl202x -S -emit-llvm -disable-llvm-passes %s -o - | FileCheck %s
+
+// Make sure global variable for dtors exist for lib profile.
+// CHECK:@llvm.global_dtors
 
 struct Tail {
   Tail() {
@@ -39,9 +42,10 @@
   Wag();
 }
 
+
 //CHECK:      define void @main()
 //CHECK-NEXT: entry:
-//CHECK-NEXT:   call void @_GLOBAL__sub_I_GlobalDestructors.hlsl()
+//CHECK-NEXT:   call void @_GLOBAL__sub_I_GlobalDestructorsLib.hlsl()
 //CHECK-NEXT:   %0 = call i32 @llvm.dx.flattened.thread.id.in.group()
 //CHECK-NEXT:   call void @"?main@@YAXI@Z"(i32 %0)
 //CHECK-NEXT:   call void @_GLOBAL__D_a()