diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.h
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.h
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.h
@@ -25,6 +25,10 @@
 
 Align getAlign(DataLayout const &DL, const GlobalVariable *GV);
 
+/// \returns true if a given global variable \p GV (or its global users) appear
+/// as an use within some instruction (either from kernel or from non-kernel).
+bool hasUserInstruction(const GlobalVariable *GV);
+
 /// \returns true if an LDS global requres lowering to a module LDS structure
 /// if \p F is not given. If \p F is given it must be a kernel and function
 /// \returns true if an LDS global is directly used from that kernel and it
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.cpp
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.cpp
@@ -60,15 +60,37 @@
   }
 }
 
+bool hasUserInstruction(const GlobalVariable *GV) {
+  SmallPtrSet<const User *, 8> Visited;
+  SmallVector<const User *, 16> Stack(GV->users());
+  while (!Stack.empty()) {
+    const User *U = Stack.pop_back_val();
+
+    if (!Visited.insert(U).second)
+      continue;
+
+    if (isa<Constant>(U)) {
+      append_range(Stack, U->users());
+      continue;
+    }
+
+    if (isa<Instruction>(U))
+      return true;
+  }
+
+  return false;
+}
+
 bool shouldLowerLDSToStruct(const SmallPtrSetImpl<GlobalValue *> &UsedList,
                             const GlobalVariable &GV, const Function *F) {
-  // Any LDS variable can be lowered by moving into the created struct
-  // Each variable so lowered is allocated in every kernel, so variables
-  // whose users are all known to be safe to lower without the transform
-  // are left unchanged.
+  // We are not interested in kernel LDS lowering for module LDS itself.
+  if (F && GV.getName() == "llvm.amdgcn.module.lds")
+    return false;
+
   bool Ret = false;
   SmallPtrSet<const User *, 8> Visited;
   SmallVector<const User *, 16> Stack(GV.users());
+  SmallPtrSet<const GlobalVariable *, 8> GlobalUsers;
 
   assert(!F || isKernelCC(F));
 
@@ -76,10 +98,16 @@
     const User *V = Stack.pop_back_val();
     Visited.insert(V);
 
-    if (auto *G = dyn_cast<GlobalValue>(V->stripPointerCasts())) {
-      if (UsedList.contains(G)) {
-        continue;
+    if (auto *G = dyn_cast<GlobalVariable>(V)) {
+      StringRef GName = G->getName();
+      if (F && GName != "llvm.used" && GName != "llvm.compiler.used") {
+        // For kernel LDS lowering, if G is not a compiler.used list, then we
+        // cannot lower the lds GV since we cannot replace the use of GV within
+        // G.
+        return false;
       }
+      GlobalUsers.insert(G);
+      continue;
     }
 
     if (auto *I = dyn_cast<Instruction>(V)) {
@@ -101,11 +129,15 @@
       }
       continue;
     }
+  }
 
-    // Unknown user, conservatively lower the variable.
-    // For module LDS conservatively means place it into the module LDS struct.
-    // For kernel LDS it means lower as a standalone variable.
-    return !F;
+  if (!F && !Ret) {
+    // For module LDS lowering, we have not yet decided if we should lower GV or
+    // not. Explore all global users of GV, and check if atleast one of these
+    // global users appear as an use within an instruction (possibly nested use
+    // via constant expression), if so, then conservately lower LDS.
+    for (auto *G : GlobalUsers)
+      Ret |= hasUserInstruction(G);
   }
 
   return Ret;
diff --git a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-global-uses.ll b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-global-uses.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-global-uses.ll
@@ -0,0 +1,55 @@
+; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-module-lds < %s | FileCheck %s
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s | FileCheck %s
+
+;.
+; Kernel LDS lowering.
+;.
+; @lds.1:  is part of @llvm.used list, and also it is used within kernel, hence it is lowered.
+; @lds.2:  is part of @llvm.compiler.used list, and also it is used within kernel, hence it is lowered.
+; @lds.3:  is used as initializer to @gptr.3, hence @lds.3 is not lowered, though it is used within kernel.
+; @lds.4:  is used as initializer to @gptr.4, hence @lds.4 is not lowered, though it is used within kernel,
+;          irrespective of the uses of @gptr.4 itself ( @gptr.4 is part of llvm.compiler.used list ).
+; @lds.5:  is part of @llvm.used list, but is not used within kernel, hence it is not lowered.
+; @lds.6:  is part of @llvm.compiler.used list, but is not used within kernel, hence it is not lowered.
+;.
+
+; CHECK: %llvm.amdgcn.kernel.k0.lds.t = type { i32, i16 }
+
+; CHECK-NOT: @lds.1
+; CHECK-NOT: @lds.2
+; CHECK: @lds.3 = addrspace(3) global i64 undef, align 8
+; CHECK: @lds.4 = addrspace(3) global float undef, align 4
+; CHECK: @lds.5 = addrspace(3) global i16 undef, align 2
+; CHECK: @lds.6 = addrspace(3) global i32 undef, align 4
+@lds.1 = addrspace(3) global i16 undef, align 2
+@lds.2 = addrspace(3) global i32 undef, align 4
+@lds.3 = addrspace(3) global i64 undef, align 8
+@lds.4 = addrspace(3) global float undef, align 4
+@lds.5 = addrspace(3) global i16 undef, align 2
+@lds.6 = addrspace(3) global i32 undef, align 4
+
+; CHECK: @gptr.3 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* @lds.3 to i64*), align 8
+; CHECK: @gptr.4 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* bitcast (float addrspace(3)* @lds.4 to i64 addrspace(3)*) to i64*), align 8
+@gptr.3 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* @lds.3 to i64*), align 8
+@gptr.4 = addrspace(1) global i64* addrspacecast (float addrspace(3)* @lds.4 to i64*), align 8
+
+; CHECK: @llvm.amdgcn.kernel.k0.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k0.lds.t undef, align 4
+
+; CHECK: @llvm.used = appending global [1 x i8*] [i8* addrspacecast (i8 addrspace(3)* bitcast (i16 addrspace(3)* @lds.5 to i8 addrspace(3)*) to i8*)], section "llvm.metadata"
+; CHECK: @llvm.compiler.used = appending global [2 x i8*] [i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.4 to i8 addrspace(1)*) to i8*), i8* addrspacecast (i8 addrspace(3)* bitcast (i32 addrspace(3)* @lds.6 to i8 addrspace(3)*) to i8*)], section "llvm.metadata"
+@llvm.used = appending global [2 x i8*] [i8* addrspacecast (i8 addrspace(3)* bitcast (i16 addrspace(3)* @lds.1 to i8 addrspace(3)*) to i8*), i8* addrspacecast (i8 addrspace(3)* bitcast (i16 addrspace(3)* @lds.5 to i8 addrspace(3)*) to i8*)], section "llvm.metadata"
+@llvm.compiler.used = appending global [3 x i8*] [i8* addrspacecast (i8 addrspace(3)* bitcast (i32 addrspace(3)* @lds.2 to i8 addrspace(3)*) to i8*), i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.4 to i8 addrspace(1)*) to i8*), i8* addrspacecast (i8 addrspace(3)* bitcast (i32 addrspace(3)* @lds.6 to i8 addrspace(3)*) to i8*)], section "llvm.metadata"
+
+; CHECK-LABEL: @k0()
+; CHECK:   %ld.lds.1 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, %llvm.amdgcn.kernel.k0.lds.t addrspace(3)* @llvm.amdgcn.kernel.k0.lds, i32 0, i32 1), align 2
+; CHECK:   %ld.lds.2 = load i32, i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, %llvm.amdgcn.kernel.k0.lds.t addrspace(3)* @llvm.amdgcn.kernel.k0.lds, i32 0, i32 0), align 4
+; CHECK:   %ld.lds.3 = load i64, i64 addrspace(3)* @lds.3, align 4
+; CHECK:   %ld.lds.4 = load float, float addrspace(3)* @lds.4, align 4
+; CHECK:   ret void
+define amdgpu_kernel void @k0() {
+  %ld.lds.1 = load i16, i16 addrspace(3)* @lds.1
+  %ld.lds.2 = load i32, i32 addrspace(3)* @lds.2
+  %ld.lds.3 = load i64, i64 addrspace(3)* @lds.3
+  %ld.lds.4 = load float, float addrspace(3)* @lds.4
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-global-uses.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-global-uses.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-global-uses.ll
@@ -0,0 +1,88 @@
+; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-module-lds < %s | FileCheck %s
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s | FileCheck %s
+
+;.
+; @lds.1:  is part of @llvm.used list, and is no-where used. Hence it is not lowered.
+; @lds.2:  is part of @llvm.compiler.used list, and is no-where used. Hence it is not lowered.
+; @lds.3:  is used as initializer to @gptr.3, and is no-where used. @gptr.3 itself is also not
+;          used anywhere else, hence @lds.3 is not lowered.
+; @lds.4:  is used as initializer to @gptr.4, and is no-where used. @gptr.4 is part of
+;          @llvm.compiler.used list, but is no-where else used. hence @lds.4 is not lowered.
+;
+; @lds.5:  is used as initializer to @gptr.5, and is no-where used. @gptr.5 is part of
+;          @llvm.compiler.used list, but is also used within kernel @k0. Hence @lds.5 is lowered.
+; @lds.6:  is used as initializer to @gptr.6, and is no-where used. @gptr.6 is part of
+;          @llvm.compiler.used list, but is also used within non-kernel function @f0. Hence @lds.6 is lowered.
+; @lds.7:  is used as initializer to @gptr.7, and is no-where used. @gptr.7 is used as initializer to @gptr.8,
+;          and @gptr.8 is used within non-kernel function @f1. Hence @lds.7 is lowered.
+;.
+
+; CHECK: %llvm.amdgcn.module.lds.t = type { [3 x float], [4 x i8], [2 x float], [1 x float] }
+
+; CHECK: @lds.1 = addrspace(3) global i16 undef, align 2
+; CHECK: @lds.2 = addrspace(3) global i32 undef, align 4
+; CHECK: @lds.3 = addrspace(3) global i64 undef, align 8
+; CHECK: @lds.4 = addrspace(3) global float undef, align 4
+; CHECK-NOT: @lds.5
+; CHECK-NOT: @lds.6
+; CHECK-NOT: @lds.7
+@lds.1 = addrspace(3) global i16 undef, align 2
+@lds.2 = addrspace(3) global i32 undef, align 4
+@lds.3 = addrspace(3) global i64 undef, align 8
+@lds.4 = addrspace(3) global float undef, align 4
+@lds.5 = addrspace(3) global [1 x float] undef, align 4
+@lds.6 = addrspace(3) global [2 x float] undef, align 8
+@lds.7 = addrspace(3) global [3 x float] undef, align 16
+
+; CHECK: @gptr.3 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* @lds.3 to i64*), align 8
+; CHECK: @gptr.4 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* bitcast (float addrspace(3)* @lds.4 to i64 addrspace(3)*) to i64*), align 8
+; CHECK: @gptr.5 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* bitcast ([1 x float] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 3) to i64 addrspace(3)*) to i64*), align 8
+; CHECK: @gptr.6 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* bitcast ([2 x float] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2) to i64 addrspace(3)*) to i64*), align 8
+; CHECK: @gptr.7 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* bitcast (%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds to i64 addrspace(3)*) to i64*), align 8
+; CHECK: @gptr.8 = addrspace(1) global i64** addrspacecast (i64* addrspace(1)* @gptr.7 to i64**), align 8
+@gptr.3 = addrspace(1) global i64* addrspacecast (i64 addrspace(3)* @lds.3 to i64*), align 8
+@gptr.4 = addrspace(1) global i64* addrspacecast (float addrspace(3)* @lds.4 to i64*), align 8
+@gptr.5 = addrspace(1) global i64* addrspacecast ([1 x float] addrspace(3)* @lds.5 to i64*), align 8
+@gptr.6 = addrspace(1) global i64* addrspacecast ([2 x float] addrspace(3)* @lds.6 to i64*), align 8
+@gptr.7 = addrspace(1) global i64* addrspacecast ([3 x float] addrspace(3)* @lds.7 to i64*), align 8
+@gptr.8 = addrspace(1) global i64** addrspacecast (i64* addrspace(1)* @gptr.7 to i64**), align 8
+
+; CHECK: @llvm.used = appending global [1 x i8*] [i8* addrspacecast (i8 addrspace(3)* bitcast (i16 addrspace(3)* @lds.1 to i8 addrspace(3)*) to i8*)], section "llvm.metadata"
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 16
+; CHECK: @llvm.compiler.used = appending global [5 x i8*] [i8* addrspacecast (i8 addrspace(3)* bitcast (i32 addrspace(3)* @lds.2 to i8 addrspace(3)*) to i8*), i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.4 to i8 addrspace(1)*) to i8*), i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.5 to i8 addrspace(1)*) to i8*), i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.6 to i8 addrspace(1)*) to i8*), i8* addrspacecast (i8 addrspace(3)* bitcast (%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds to i8 addrspace(3)*) to i8*)], section "llvm.metadata"
+@llvm.used = appending global [1 x i8*] [i8* addrspacecast (i8 addrspace(3)* bitcast (i16 addrspace(3)* @lds.1 to i8 addrspace(3)*) to i8*)], section "llvm.metadata"
+@llvm.compiler.used = appending global [4 x i8*] [i8* addrspacecast (i8 addrspace(3)* bitcast (i32 addrspace(3)* @lds.2 to i8 addrspace(3)*) to i8*), i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.4 to i8 addrspace(1)*) to i8*), i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.5 to i8 addrspace(1)*) to i8*), i8* addrspacecast (i8 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.6 to i8 addrspace(1)*) to i8*)], section "llvm.metadata"
+
+; CHECK-LABEL: @f1()
+; CHECK:   %ld = load i64**, i64** addrspace(1)* @gptr.8, align 8
+; CHECK:   ret void
+define void @f1() {
+  %ld = load i64**, i64** addrspace(1)* @gptr.8
+  ret void
+}
+
+; CHECK-LABEL: @f0()
+; CHECK:   %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.6 to i32 addrspace(1)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32
+; CHECK: addrspace(1)* bitcast (i64* addrspace(1)* @gptr.6 to i32 addrspace(1)*) to i32*) to i64)) to i32*), align 4
+; CHECK:   ret void
+define void @f0() {
+  %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.6 to i32 addrspace(1)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.6 to i32 addrspace(1)*) to i32*) to i64)) to i32*), align 4
+  ret void
+}
+
+; CHECK-LABEL: @k0()
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.5 to i32 addrspace(1)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32
+; CHECK: addrspace(1)* bitcast (i64* addrspace(1)* @gptr.5 to i32 addrspace(1)*) to i32*) to i64)) to i32*), align 4
+; CHECK:   ret void
+define amdgpu_kernel void @k0() {
+  %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.5 to i32 addrspace(1)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(1)* bitcast (i64* addrspace(1)* @gptr.5 to i32 addrspace(1)*) to i32*) to i64)) to i32*), align 4
+  ret void
+}
+
+; CHECK-LABEL: @k1()
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   ret void
+define amdgpu_kernel void @k1() {
+  ret void
+}