diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -29,7 +29,9 @@
 #include "AMDGPU.h"
 #include "Utils/AMDGPUBaseInfo.h"
 #include "Utils/AMDGPULDSUtils.h"
+#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/SetOperations.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/IRBuilder.h"
@@ -48,6 +50,355 @@
 
 namespace {
 
+// ReplaceLDSUseWithPointer replaces all the uses of LDS within non-kernel
+// functions by corresponding pointer counter-parts.
+//
+// The main motivation behind this pointer replacement phase is - to *avoid*
+// subsequent LDS lowering phase from directly packing LDS (assume large LDS)
+// into a struct type which would otherwise cause allocating huge memory for
+// struct instance within every kernel.
+//
+// Brief sketch of the algorithm is as below:
+//
+//   1. Collect all the LDS defined in the module which qualify for pointer
+//      replacement, say it is, LDSGlobals set.
+//
+//   2. Collect all the reachable callees for each kernel defined in the module,
+//      say it is, KernelToCallees map.
+//
+//   3. FOR (each global GV from LDSGlobals set) DO
+//        LDSUsedNonKernels = Collect all non-kernel functions which use GV.
+//        FOR (each kernel K in KernelToCallees map) DO
+//           ReachableCallees = KernelToCallees[K]
+//           ReachableAndLDSUsedCallees =
+//              SetIntersect(LDSUsedNonKernels, ReachableCallees)
+//           IF (ReachableAndLDSUsedCallees is not empty) THEN
+//             Pointer = Create a pointer to point-to GV if not created.
+//             Initialize Pointer to point-to GV within kernel K.
+//           ENDIF
+//        ENDFOR
+//        Replace all uses of GV within non kernel functions by Pointer.
+//      ENFOR
+//
+// LLVM IR example:
+//
+//    Input IR:
+//
+//    @lds = internal addrspace(3) global [4 x i32] undef, align 16
+//
+//    define internal void @f0() {
+//    entry:
+//      %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds,
+//             i32 0, i32 0
+//      ret void
+//    }
+//
+//    define protected amdgpu_kernel void @k0() {
+//    entry:
+//      call void @f0()
+//      ret void
+//    }
+//
+//    Output IR:
+//
+//    @lds = internal addrspace(3) global [4 x i32] undef, align 16
+//    @lds.ptr = internal unnamed_addr addrspace(3) global i16 undef, align 2
+//
+//    define internal void @f0() {
+//    entry:
+//      %0 = load i16, i16 addrspace(3)* @lds.ptr, align 2
+//      %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+//      %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+//      %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2,
+//             i32 0, i32 0
+//      ret void
+//    }
+//
+//    define protected amdgpu_kernel void @k0() {
+//    entry:
+//      store i16 ptrtoint ([4 x i32] addrspace(3)* @lds to i16),
+//            i16 addrspace(3)* @lds.ptr, align 2
+//      call void @f0()
+//      ret void
+//    }
+//
+class ReplaceLDSUseWithPointer {
+  Module &M;
+  LLVMContext &Ctx;
+  const DataLayout &DL;
+  Constant *LDSMemBaseAddr;
+
+  SmallPtrSet<GlobalValue *, 32> UsedList;
+  std::vector<GlobalVariable *> LDSGlobals;
+  DenseMap<GlobalVariable *, GlobalVariable *> LDSToPointer;
+  DenseMap<GlobalVariable *, SmallPtrSet<Function *, 8>> LDSToNonKernels;
+  DenseMap<Function *, SmallPtrSet<Function *, 8>> KernelToCallees;
+  DenseMap<Function *, SmallPtrSet<GlobalVariable *, 8>> KernelToLDSPointers;
+  DenseMap<Function *, DenseMap<GlobalVariable *, Value *>>
+      FunctionToLDSToReplaceInst;
+
+  // Collect LDS which requires their uses to be replaced by pointer.
+  bool collectLDSRequiringPointerReplace() {
+    // Collect LDS which requires module lowering.
+    LDSGlobals = AMDGPU::findVariablesToLower(M, UsedList);
+
+    // Remove LDS which don't qualify for replacement.
+    LDSGlobals.erase(std::remove_if(LDSGlobals.begin(), LDSGlobals.end(),
+                                    [&](GlobalVariable *GV) {
+                                      return shouldIgnorePointerReplacement(GV);
+                                    }),
+                     LDSGlobals.end());
+
+    return !LDSGlobals.empty();
+  }
+
+  // Returns true if an LDS global does not require its non-kernel function uses
+  // to be replaced by pointer.
+  bool shouldIgnorePointerReplacement(GlobalVariable *GV) {
+    // LDS whose size is very small and doesn`t exceed pointer size is not worth
+    // replacing.
+    if (DL.getTypeAllocSize(GV->getValueType()) <= 2)
+      return true;
+
+    // LDS which is not used from non-kernel function scope or it is used from
+    // global scope does not qualify for replacement.
+    LDSToNonKernels[GV] = AMDGPU::collectNonKernelAccessorsOfLDS(GV);
+    if (LDSToNonKernels[GV].empty())
+      return true;
+
+    // FIXME: Any other scenarios which disqualify LDS from replacement?
+
+    return false;
+  }
+
+  // Insert new global LDS pointer which points to LDS.
+  GlobalVariable *createLDSPointer(GlobalVariable *GV) {
+    // LDS pointer which points to LDS is already created? return it.
+    auto Entry = LDSToPointer.insert(std::make_pair(GV, nullptr));
+    if (!Entry.second)
+      return Entry.first->second;
+
+    // We need to create new LDS pointer which points to LDS.
+    //
+    // Each CU owns 64K of LDS memory, so address ranges from 0 to 2^16 - 1.
+    // Hence 16 bit pointer is enough to hold the LDS address.
+    auto *I16Ty = Type::getInt16Ty(Ctx);
+    GlobalVariable *LDSPointer = new GlobalVariable(
+        M, I16Ty, false, GlobalValue::InternalLinkage, UndefValue::get(I16Ty),
+        GV->getName() + Twine(".pointer"), nullptr,
+        GlobalVariable::NotThreadLocal, AMDGPUAS::LOCAL_ADDRESS);
+
+    LDSPointer->setUnnamedAddr(GlobalValue::UnnamedAddr::Global);
+    LDSPointer->setAlignment(AMDGPU::getAlign(DL, LDSPointer));
+
+    // Mark that an associated LDS pointer is created for LDS.
+    LDSToPointer[GV] = LDSPointer;
+
+    return LDSPointer;
+  }
+
+  // Within given kernel, initialize given LDS pointer to point to given LDS.
+  void initializeLDSPointer(Function *K, GlobalVariable *GV,
+                            GlobalVariable *LDSPointer) {
+    // If LDS pointer is already initialized within K, then nothing to do.
+    auto Entry = KernelToLDSPointers.insert(
+        std::make_pair(K, SmallPtrSet<GlobalVariable *, 8>()));
+    if (!Entry.second)
+      if (Entry.first->second.contains(LDSPointer))
+        return;
+
+    // Insert instructions at EI which initialize LDS pointer to point-to LDS
+    // within kernel K.
+    //
+    // That is, convert pointer type of GV to i16, and then store this converted
+    // i16 value within LDSPointer which is of type i16*.
+    auto *EI = &(*(K->getEntryBlock().getFirstInsertionPt()));
+    IRBuilder<> Builder(EI);
+    Builder.CreateStore(Builder.CreatePtrToInt(GV, Type::getInt16Ty(Ctx)),
+                        LDSPointer);
+
+    // Mark that LDS pointer is initialized within kernel K.
+    KernelToLDSPointers[K].insert(LDSPointer);
+  }
+
+  // We have created an LDS pointer for LDS, and initialized it to point-to LDS
+  // within all relevent kernels. Now replace all the uses of LDS within
+  // non-kernel functions by LDS pointer.
+  void replaceLDSUseByPointer(GlobalVariable *GV, GlobalVariable *LDSPointer) {
+    SmallVector<User *, 8> LDSUsers(GV->users());
+    for (auto *U : LDSUsers) {
+      // When `U` is a constant expression, it is possible that same constant
+      // expression exists within multiple instructions, and within multiple
+      // non-kernel functions. Collect all those non-kernel functions and all
+      // those instructions within which `U` exist.
+      auto FunctionToInsts = AMDGPU::getNonKernelFunctionToInstsMap(U);
+
+      for (auto FI = FunctionToInsts.begin(), FE = FunctionToInsts.end();
+           FI != FE; ++FI) {
+        Function *F = FI->first;
+        auto InstSet = FI->second;
+        for (auto *I : InstSet) {
+          // If `U` is a constant expression, then we need to break the
+          // associated instruction into a set of separate instructions by
+          // converting constant expressions into instructions.
+          SmallPtrSet<Instruction *, 8> UserInsts;
+
+          if (U == I) {
+            // `U` is an instruction, conversion from constant expression to
+            // set of instructions is *not* required.
+            UserInsts.insert(I);
+          } else {
+            // `U` is a constant expression, convert it into corresponding set
+            // of instructions.
+            auto *CE = cast<ConstantExpr>(U);
+            AMDGPU::convertConstExprsToInstructions(I, CE, UserInsts);
+          }
+
+          // Go through all the user instrutions, if LDS exist within them as an
+          // operand, then replace it by replace instruction.
+          for (auto *II : UserInsts) {
+            auto *ReplaceInst = getReplacementInst(F, GV, LDSPointer);
+            AMDGPU::updateUserOperand(II, GV, ReplaceInst);
+          }
+        }
+      }
+    }
+  }
+
+  // Create a set of replacement instructions which together replace LDS within
+  // non-kernel function F by accessing LDS indirectly using LDS pointer.
+  Value *getReplacementInst(Function *F, GlobalVariable *GV,
+                            GlobalVariable *LDSPointer) {
+    // If the instruction which replaces LDS within F is already created, then
+    // return it.
+    auto Entry = FunctionToLDSToReplaceInst.insert(
+        std::make_pair(F, DenseMap<GlobalVariable *, Value *>()));
+    if (!Entry.second) {
+      auto Entry2 = Entry.first->second.insert(std::make_pair(GV, nullptr));
+      if (!Entry2.second)
+        return Entry2.first->second;
+    }
+
+    // Get the instruction insertion point within the beginning of the entry
+    // block of current non-kernel function.
+    auto *EI = &(*(F->getEntryBlock().getFirstInsertionPt()));
+    IRBuilder<> Builder(EI);
+
+    // Insert required set of instructions which replace LDS within F.
+    auto *V = Builder.CreateBitCast(
+        Builder.CreateGEP(
+            LDSMemBaseAddr,
+            Builder.CreateLoad(LDSPointer->getValueType(), LDSPointer)),
+        GV->getType());
+
+    // Mark that the replacement instruction which replace LDS within F is
+    // created.
+    FunctionToLDSToReplaceInst[F][GV] = V;
+
+    return V;
+  }
+
+public:
+  ReplaceLDSUseWithPointer(Module &M, SmallPtrSet<GlobalValue *, 32> &UList)
+      : M(M), Ctx(M.getContext()), DL(M.getDataLayout()), UsedList(UList) {
+    LDSMemBaseAddr = Constant::getIntegerValue(
+        PointerType::get(Type::getInt8Ty(M.getContext()),
+                         AMDGPUAS::LOCAL_ADDRESS),
+        APInt(32, 0));
+  }
+
+  // Entry-point function which interface ReplaceLDSUseWithPointer with outside
+  // of the class.
+  bool replaceLDSUse();
+
+private:
+  // For a given LDS from collected LDS globals set, replace its non-kernel
+  // function scope use by pointer.
+  bool replaceLDSUse(GlobalVariable *GV);
+};
+
+// For given LDS from collected LDS globals set, replace its non-kernel function
+// scope use by pointer.
+bool ReplaceLDSUseWithPointer::replaceLDSUse(GlobalVariable *GV) {
+  // Holds all those non-kernel functions within which LDS is being accessed.
+  SmallPtrSet<Function *, 8> LDSAccessors = LDSToNonKernels[GV];
+
+  // The LDS pointer which points to LDS and replaces all the uses of LDS.
+  GlobalVariable *LDSPointer = nullptr;
+
+  // Traverse through each kernel K, check and if required, initialize the
+  // LDS pointer to point to LDS within K.
+  for (auto KI = KernelToCallees.begin(), KE = KernelToCallees.end(); KI != KE;
+       ++KI) {
+    Function *K = KI->first;
+    SmallPtrSet<Function *, 8> Callees = KI->second;
+
+    // Compute reachable and LDS used callees for kernel K.
+    set_intersect(Callees, LDSAccessors);
+
+    // None of the LDS accessing non-kernel functions are reachable from
+    // kernel K. Hence, no need to initialize LDS pointer within kernel K.
+    if (Callees.empty())
+      continue;
+
+    // We have found reachable and LDS used callees for kernel K, and we need to
+    // initialize LDS pointer within kernel K, and we need to replace LDS use
+    // within those callees by LDS pointer.
+    //
+    // But, first check if LDS pointer is already created, if not create one.
+    LDSPointer = createLDSPointer(GV);
+
+    // Initialize LDS pointer to point to LDS within kernel K.
+    initializeLDSPointer(K, GV, LDSPointer);
+  }
+
+  // We have not found reachable and LDS used callees for any of the kernels,
+  // and hence we have not created LDS pointer.
+  if (!LDSPointer)
+    return false;
+
+  // We have created an LDS pointer for LDS, and initialized it to point-to LDS
+  // within all relevent kernels. Now replace all the uses of LDS within
+  // non-kernel functions by LDS pointer.
+  replaceLDSUseByPointer(GV, LDSPointer);
+
+  return true;
+}
+
+// Entry-point function which interface ReplaceLDSUseWithPointer with outside of
+// the class.
+bool ReplaceLDSUseWithPointer::replaceLDSUse() {
+  // Collect LDS which requires their uses to be replaced by pointer.
+  if (!collectLDSRequiringPointerReplace())
+    return false;
+
+  // Collect reachable callee set for each kernel defined in the module.
+  AMDGPU::collectReachableCallees(M, KernelToCallees);
+
+  if (KernelToCallees.empty()) {
+    // Either module does not have any kernel definitions, or none of the kernel
+    // has a call to non-kernel functions, or we could not resolve any of the
+    // call sites to proper non-kernel functions, because of the situations like
+    // inline asm calls. Nothing to replace.
+    return false;
+  }
+
+  // For every LDS from collected LDS globals set, replace its non-kernel
+  // function scope use by pointer.
+  bool Changed = false;
+  for (auto *GV : LDSGlobals)
+    Changed |= replaceLDSUse(GV);
+
+  return Changed;
+}
+
+// Interface function between AMDGPULowerModuleLDS and ReplaceLDSUseWithPointer.
+static bool replaceLDSUseWithPointer(Module &M,
+                                     SmallPtrSet<GlobalValue *, 32> &UsedList) {
+  ReplaceLDSUseWithPointer LDSUseReplacer{M, UsedList};
+  return LDSUseReplacer.replaceLDSUse();
+}
+
 class AMDGPULowerModuleLDS : public ModulePass {
 
   static void removeFromUsedList(Module &M, StringRef Name,
@@ -144,10 +495,19 @@
   }
 
   bool runOnModule(Module &M) override {
+    bool Changed = false;
+
     UsedList = AMDGPU::getUsedList(M);
 
-    bool Changed = processUsedLDS(M);
+    // As a first step, before proceding with LDS lowering process, replace
+    // non-kernel function use of LDS by pointers. This will help reduce the
+    // memory overhead being introduced during lowering process.
+    Changed = replaceLDSUseWithPointer(M, UsedList);
 
+    // As a second step, perform module LDS lowering.
+    Changed |= processUsedLDS(M);
+
+    // As a third step, perform kernel LDS lowering.
     for (Function &F : M.functions()) {
       if (!AMDGPU::isKernelCC(&F))
         continue;
@@ -155,6 +515,7 @@
     }
 
     UsedList.clear();
+
     return Changed;
   }
 
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
@@ -14,11 +14,42 @@
 #define LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPULDSUTILS_H
 
 #include "AMDGPU.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/IR/Constants.h"
 
 namespace llvm {
 
 namespace AMDGPU {
 
+// Collect reachable callees for each kernel defined in the module.
+void collectReachableCallees(
+    Module &M,
+    DenseMap<Function *, SmallPtrSet<Function *, 8>> &KernelToCallees);
+
+// For the given LDS, visit its user list and find all those non-kernel
+// functions within which the LDS is being used.
+SmallPtrSet<Function *, 8> collectNonKernelAccessorsOfLDS(GlobalVariable *GV);
+
+// Collect all those non-kernel functions and all those instructions within
+// which the given user U exist.
+DenseMap<Function *, SmallPtrSet<Instruction *, 8>>
+getNonKernelFunctionToInstsMap(User *U);
+
+// Given an instruction I which use given constant expression CE either directly
+// or indirectly, return all such constant expression operands of I.
+SmallPtrSet<Value *, 4> getCEOperands(Instruction *I, ConstantExpr *CE);
+
+// The instruction I contains const expressions(possibly nested) as its
+// operands, convert those const expressions into corresponding instructions.
+void convertConstExprsToInstructions(Instruction *I,
+                                     SmallPtrSetImpl<Value *> &Operands,
+                                     SmallPtrSetImpl<Instruction *> &UserInsts);
+void convertConstExprsToInstructions(Instruction *I, ConstantExpr *CE,
+                                     SmallPtrSetImpl<Instruction *> &UserInsts);
+
+// Within User U replace the use(s) of old value OldV by new value NewV.
+void updateUserOperand(User *U, Value *OldV, Value *NewV);
+
 bool isKernelCC(const Function *Func);
 
 Align getAlign(DataLayout const &DL, const GlobalVariable *GV);
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
@@ -12,7 +12,8 @@
 
 #include "AMDGPULDSUtils.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/IR/Constants.h"
+#include "llvm/ADT/SCCIterator.h"
+#include "llvm/Analysis/CallGraph.h"
 
 using namespace llvm;
 
@@ -20,6 +21,266 @@
 
 namespace AMDGPU {
 
+// An helper class for collecting all reachable callees for each kernel defined
+// within the module.
+class CollectReachableCallees {
+  Module &M;
+  CallGraph CG;
+  SmallPtrSet<CallGraphNode *, 8> AddressTakenFunctions;
+
+  // Collect all address taken functions within the module.
+  void collectAddressTakenFunctions() {
+    auto *ECNode = CG.getExternalCallingNode();
+
+    for (auto GI = ECNode->begin(), GE = ECNode->end(); GI != GE; ++GI) {
+      auto *CGN = GI->second;
+      auto *F = CGN->getFunction();
+      if (!F || F->isDeclaration() || AMDGPU::isKernelCC(F))
+        continue;
+      AddressTakenFunctions.insert(CGN);
+    }
+  }
+
+  // Collect all reachable call graph nodes from given call graph node.
+  SmallPtrSet<CallGraphNode *, 8> collectCGNodes(CallGraphNode *CGN) {
+    SmallPtrSet<CallGraphNode *, 8> CGNodes;
+
+    for (scc_iterator<CallGraphNode *> I = scc_begin(CGN); !I.isAtEnd(); ++I) {
+      const std::vector<CallGraphNode *> &SCC = *I;
+      assert(!SCC.empty() && "SCC with no functions?");
+      for (auto *CGNode : SCC)
+        CGNodes.insert(CGNode);
+    }
+
+    return CGNodes;
+  }
+
+  // For given kernel, collect all its reachable non-kernel functions.
+  SmallPtrSet<Function *, 8> collectReachableCallees(Function *K) {
+    SmallPtrSet<Function *, 8> ReachableCallees;
+
+    // Call graph node which represents this kernel.
+    auto *KCGN = CG[K];
+
+    // Collect all reachable call graph nodes from the node representing this
+    // kernel.
+    SmallPtrSet<CallGraphNode *, 8> CGNodes = collectCGNodes(KCGN);
+
+    // Go through collected reachable nodes, visit all thier call sites, if the
+    // call site is direct, add corresponding callee to reachable callee set, if
+    // it is indirect, resolve the indirect call site to potential reachable
+    // callees, add them to reachable callee set, and repeat the process for the
+    // newly added potential callee nodes.
+    //
+    // FIXME: Need to handle bit-casted function pointers.
+    //
+    SmallVector<CallGraphNode *, 8> CGNStack(CGNodes.begin(), CGNodes.end());
+    SmallPtrSet<CallGraphNode *, 8> VisitedCGNodes;
+    while (!CGNStack.empty()) {
+      auto *CGN = CGNStack.pop_back_val();
+
+      if (!VisitedCGNodes.insert(CGN).second)
+        continue;
+
+      for (auto GI = CGN->begin(), GE = CGN->end(); GI != GE; ++GI) {
+        auto *RCB = cast<CallBase>(GI->first.getValue());
+        auto *RCGN = GI->second;
+
+        if (auto *DCallee = RCGN->getFunction()) {
+          ReachableCallees.insert(DCallee);
+        } else if (RCB->isIndirectCall()) {
+          auto *RCBFTy = RCB->getFunctionType();
+          for (auto *ACGN : AddressTakenFunctions) {
+            auto *ACallee = ACGN->getFunction();
+            if (ACallee->getFunctionType() == RCBFTy) {
+              ReachableCallees.insert(ACallee);
+              SmallPtrSet<CallGraphNode *, 8> IGCNNodes = collectCGNodes(ACGN);
+              for (auto *IGCN : IGCNNodes)
+                CGNStack.push_back(IGCN);
+            }
+          }
+        }
+      }
+    }
+
+    return ReachableCallees;
+  }
+
+public:
+  explicit CollectReachableCallees(Module &M) : M(M), CG(CallGraph(M)) {
+    // Collect address taken functions.
+    collectAddressTakenFunctions();
+  }
+
+  void collectReachableCallees(
+      DenseMap<Function *, SmallPtrSet<Function *, 8>> &KernelToCallees) {
+    // Collect reachable callee set for each kernel defined in the module.
+    for (Function &F : M.functions()) {
+      if (!AMDGPU::isKernelCC(&F))
+        continue;
+      Function *K = &F;
+      KernelToCallees[K] = collectReachableCallees(K);
+    }
+  }
+};
+
+// Collect reachable callees for each kernel defined in the module.
+void collectReachableCallees(
+    Module &M,
+    DenseMap<Function *, SmallPtrSet<Function *, 8>> &KernelToCallees) {
+  CollectReachableCallees CRC{M};
+  CRC.collectReachableCallees(KernelToCallees);
+}
+
+// For the given LDS, visit its user list and find all those non-kernel
+// functions within which the LDS is being used.
+SmallPtrSet<Function *, 8> collectNonKernelAccessorsOfLDS(GlobalVariable *GV) {
+  SmallPtrSet<Function *, 8> LDSAccessors;
+  SmallVector<User *, 8> UserStack(GV->users());
+  SmallPtrSet<User *, 8> VisitedUsers;
+
+  while (!UserStack.empty()) {
+    auto *U = UserStack.pop_back_val();
+
+    // `U` is already visited? continue to next one.
+    if (!VisitedUsers.insert(U).second)
+      continue;
+
+    // `U` is a global variable which is initialized with LDS. Ignore LDS.
+    if (isa<GlobalVariable>(U))
+      return SmallPtrSet<Function *, 8>();
+
+    // Recursively explore constant users.
+    if (isa<Constant>(U)) {
+      append_range(UserStack, U->users());
+      continue;
+    }
+
+    // `U` should be an instruction, if it belongs to a non-kernel function F,
+    // then collect F.
+    Function *F = cast<Instruction>(U)->getFunction();
+    if (!AMDGPU::isKernelCC(F))
+      LDSAccessors.insert(F);
+  }
+
+  return LDSAccessors;
+}
+
+// Collect all those non-kernel functions and all those instructions within
+// which the given user U exist.
+DenseMap<Function *, SmallPtrSet<Instruction *, 8>>
+getNonKernelFunctionToInstsMap(User *U) {
+  DenseMap<Function *, SmallPtrSet<Instruction *, 8>> FunctionToInsts;
+  SmallVector<User *, 8> UserStack;
+  SmallPtrSet<User *, 8> VisitedUsers;
+
+  UserStack.push_back(U);
+
+  while (!UserStack.empty()) {
+    auto *UU = UserStack.pop_back_val();
+
+    if (!VisitedUsers.insert(UU).second)
+      continue;
+
+    if (isa<GlobalVariable>(UU))
+      continue;
+
+    if (isa<Constant>(UU)) {
+      append_range(UserStack, UU->users());
+      continue;
+    }
+
+    auto *I = cast<Instruction>(UU);
+    Function *F = I->getFunction();
+    if (!AMDGPU::isKernelCC(F)) {
+      FunctionToInsts.insert(
+          std::make_pair(F, SmallPtrSet<Instruction *, 8>()));
+      FunctionToInsts[F].insert(I);
+    }
+  }
+
+  return FunctionToInsts;
+}
+
+// Given an instruction I which use given constant expression CE either directly
+// or indirectly, return all such constant expression operands of I.
+SmallPtrSet<Value *, 4> getCEOperands(Instruction *I, ConstantExpr *CE) {
+  SmallPtrSet<Value *, 4> CEOperands;
+
+  for (Use &UU : I->operands()) {
+    auto *CE2 = dyn_cast<ConstantExpr>(UU.get());
+    if (!CE2)
+      continue;
+
+    if (CE2 != CE) {
+      SmallVector<Value *, 8> Stack;
+      Stack.push_back(CE2);
+
+      while (!Stack.empty()) {
+        Value *V = Stack.pop_back_val();
+        if (auto *CE3 = dyn_cast<ConstantExpr>(V)) {
+          if (CE3 == CE) {
+            CEOperands.insert(UU.get());
+            break;
+          } else {
+            for (Use &UU : CE3->operands())
+              Stack.push_back(UU.get());
+          }
+        }
+      }
+    } else
+      CEOperands.insert(UU.get());
+  }
+
+  return CEOperands;
+}
+
+// Convert const expression operands of I which are collected in Operands to
+// corresponding instructions.
+void convertConstExprsToInstructions(
+    Instruction *I, SmallPtrSetImpl<Value *> &Operands,
+    SmallPtrSetImpl<Instruction *> &UserInsts) {
+  for (auto *V : Operands) {
+    auto *CE = dyn_cast<ConstantExpr>(V);
+    if (!CE)
+      continue;
+
+    auto *NI = CE->getAsInstruction();
+    NI->insertBefore(I);
+    updateUserOperand(I, CE, NI);
+    CE->removeDeadConstantUsers();
+    UserInsts.insert(NI);
+
+    SmallPtrSet<Value *, 4> Operands2;
+    for (Use &UU : CE->operands())
+      Operands2.insert(UU.get());
+    convertConstExprsToInstructions(NI, Operands2, UserInsts);
+  }
+}
+
+// The instruction I contains const expressions(possibly nested) as its
+// operands, collect those const expressions operands and convert them to
+// corresponding instructions.
+void convertConstExprsToInstructions(
+    Instruction *I, ConstantExpr *CE,
+    SmallPtrSetImpl<Instruction *> &UserInsts) {
+  // Get all operands of I which use CE either directly or indirectly.
+  SmallPtrSet<Value *, 4> CEOperands = AMDGPU::getCEOperands(I, CE);
+
+  // Convert const expressions operands of I to instructions.
+  convertConstExprsToInstructions(I, CEOperands, UserInsts);
+}
+
+// Within User U replace the use(s) of old value OldV by new value NewV.
+void updateUserOperand(User *U, Value *OldV, Value *NewV) {
+  unsigned Ind = 0;
+  for (Use &UU : U->operands()) {
+    if (UU.get() == OldV)
+      U->setOperand(Ind, NewV);
+    ++Ind;
+  }
+}
+
 bool isKernelCC(const Function *Func) {
   return AMDGPU::isModuleEntryFunctionCC(Func->getCallingConv());
 }
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll
@@ -3,7 +3,8 @@
 
 ; Padding to meet alignment, so references to @var1 replaced with gep ptr, 0, 2
 ; No i64 as addrspace(3) types with initializers are ignored. Likewise no addrspace(4).
-; CHECK: %llvm.amdgcn.module.lds.t = type { float, [4 x i8], i32 }
+; CHECK: %llvm.amdgcn.module.lds.t = type { i32, i16 }
+; CHECK: %llvm.amdgcn.kernel.kern_call.lds.t = type { float }
 
 ; Variables removed by pass
 ; CHECK-NOT: @var0
@@ -12,22 +13,32 @@
 @var0 = addrspace(3) global float undef, align 8
 @var1 = addrspace(3) global i32 undef, align 8
 
+; Pointer created for @var0 should have lowered.
+; CHECK-NOT: @var0.pointer
+
+; CHECK: @ptr = addrspace(1) global i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 4
 @ptr =  addrspace(1) global i32 addrspace(3)* @var1, align 4
 
 ; A variable that is unchanged by pass
 ; CHECK: @with_init = addrspace(3) global i64 0
 @with_init = addrspace(3) global i64 0
 
-; Instance of new type, aligned to max of element alignment
+; Module and kernel LDS instances.
 ; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 8
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+; CHECK: @llvm.amdgcn.kernel.kern_call.lds = internal addrspace(3) global %llvm.amdgcn.kernel.kern_call.lds.t undef, align 8
 
 ; Use in func rewritten to access struct at address zero
 ; CHECK-LABEL: @func()
-; CHECK: %dec = atomicrmw fsub float addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), float 1.0
-; CHECK: %val0 = load i32, i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 4
-; CHECK: %val1 = add i32 %val0, 4
-; CHECK: store i32 %val1, i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 4
-; CHECK: %unused0 = atomicrmw add i64 addrspace(3)* @with_init, i64 1 monotonic
+; CHECK:   %1 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   %2 = getelementptr i8, i8 addrspace(3)* null, i16 %1
+; CHECK:   %3 = bitcast i8 addrspace(3)* %2 to float addrspace(3)*
+; CHECK:   %dec = atomicrmw fsub float addrspace(3)* %3, float 1.000000e+00 monotonic, align 4
+; CHECK:   %val0 = load i32, i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 4
+; CHECK:   %val1 = add i32 %val0, 4
+; CHECK:   store i32 %val1, i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 4
+; CHECK:   %unused0 = atomicrmw add i64 addrspace(3)* @with_init, i64 1 monotonic, align 8
+; CHECK:   ret void
 define void @func() {
   %dec = atomicrmw fsub float addrspace(3)* @var0, float 1.0 monotonic
   %val0 = load i32, i32 addrspace(3)* @var1, align 4
@@ -39,9 +50,11 @@
 
 ; This kernel calls a function that uses LDS so needs the block
 ; CHECK-LABEL: @kern_call()
-; CHECK: call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
-; CHECK: call void @func()
-; CHECK: %dec = atomicrmw fsub float addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), float 2.000000e+00 monotonic, align 4
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint (%llvm.amdgcn.kernel.kern_call.lds.t addrspace(3)* @llvm.amdgcn.kernel.kern_call.lds to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   call void @func()
+; CHECK:   %dec = atomicrmw fsub float addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.kern_call.lds.t, %llvm.amdgcn.kernel.kern_call.lds.t addrspace(3)* @llvm.amdgcn.kernel.kern_call.lds, i32 0, i32 0), float 2.000000e+00 monotonic, align 4
+; CHECK:   ret void
 define amdgpu_kernel void @kern_call() {
   call void @func()
   %dec = atomicrmw fsub float addrspace(3)* @var0, float 2.0 monotonic
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-call-diamond-shape.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-call-diamond-shape.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-call-diamond-shape.ll
@@ -0,0 +1,80 @@
+; 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_used_within_func is used within @func_uses_lds which is recheable from kernel
+; @kernel_reaches_lds, hence pointer replacement takes place for @lds_used_within_func.
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.kernel.kernel_reaches_lds.lds.t = type { [4 x i32] }
+; CHECK: %llvm.amdgcn.kernel.kernel_does_not_reach_lds.lds.t = type { %llvm.amdgcn.kernel.kernel_reaches_lds.lds.t }
+
+; Original LDS should not exist
+; CHECK-NOT: @lds_used_within_func
+@lds_used_within_func = internal addrspace(3) global [4 x i32] undef, align 4
+
+; Pointer should not exist
+; CHECK-NOT: @lds_used_within_func.pointer
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 2
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+; CHECK: @llvm.amdgcn.kernel.kernel_reaches_lds.lds = internal addrspace(3) global %llvm.amdgcn.kernel.kernel_reaches_lds.lds.t undef, align 4
+; CHECK: @llvm.amdgcn.kernel.kernel_does_not_reach_lds.lds = internal addrspace(3) global %llvm.amdgcn.kernel.kernel_does_not_reach_lds.lds.t undef, align 4
+
+define internal void @func_uses_lds() {
+; CHECK-LABEL: entry:
+; CHECK:  %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:  %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:  %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:  ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_func, i32 0, i32 0
+  ret void
+}
+
+define internal void @func_does_not_use_lds_3() {
+; CHECK-LABEL: entry:
+; CHECK:  call void @func_uses_lds()
+; CHECK:  ret void
+entry:
+  call void @func_uses_lds()
+  ret void
+}
+
+define internal void @func_does_not_use_lds_2() {
+; CHECK-LABEL: entry:
+; CHECK:  call void @func_uses_lds()
+; CHECK:  ret void
+entry:
+  call void @func_uses_lds()
+  ret void
+}
+
+define internal void @func_does_not_use_lds_1() {
+; CHECK-LABEL: entry:
+; CHECK:  call void @func_does_not_use_lds_2()
+; CHECK:  call void @func_does_not_use_lds_3()
+; CHECK:  ret void
+entry:
+  call void @func_does_not_use_lds_2()
+  call void @func_does_not_use_lds_3()
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_reaches_lds() {
+; CHECK-LABEL: entry:
+; CHECK:    call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:    store i16 ptrtoint (%llvm.amdgcn.kernel.kernel_reaches_lds.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel_reaches_lds.lds to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:    call void @func_does_not_use_lds_1()
+; CHECK:    ret void
+entry:
+  call void @func_does_not_use_lds_1()
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_does_not_reach_lds() {
+; CHECK-LABEL: entry:
+; CHECK:  call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:  ret void
+entry:
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-call-selected_functions.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-call-selected_functions.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-call-selected_functions.ll
@@ -0,0 +1,96 @@
+; 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
+
+; All the three lds require pointer replacement since functions which access them are reachable.
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16, i16, i16 }
+
+; FIXME: Original LDS should have lowered by kernel lowering phase. But it is not.
+@lds_used_within_function_1 = internal addrspace(3) global [1 x i32] undef, align 4
+@lds_used_within_function_2 = internal addrspace(3) global [2 x i32] undef, align 4
+@lds_used_within_function_3 = internal addrspace(3) global [3 x i32] undef, align 4
+
+; Pointers should have lowered.
+; CHECK-NOT: @lds_used_within_function_1.pointer
+; CHECK-NOT: @lds_used_within_function_2.pointer
+; CHECK-NOT: @lds_used_within_function_3.pointer
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 2
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+
+define internal void @function_3() {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [3 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [3 x i32], [3 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [3 x i32], [3 x i32] addrspace(3)* @lds_used_within_function_3, i32 0, i32 0
+  ret void
+}
+
+define internal void @function_2() {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [2 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* @lds_used_within_function_2, i32 0, i32 0
+  ret void
+}
+
+define internal void @function_1() {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [1 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [1 x i32], [1 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [1 x i32], [1 x i32] addrspace(3)* @lds_used_within_function_1, i32 0, i32 0
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_calls_function_3_and_1() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([3 x i32] addrspace(3)* @lds_used_within_function_3 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   store i16 ptrtoint ([1 x i32] addrspace(3)* @lds_used_within_function_1 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   call void @function_3()
+; CHECK:   call void @function_1()
+; CHECK:   ret void
+entry:
+  call void @function_3()
+  call void @function_1()
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_calls_function_2_and_3() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([3 x i32] addrspace(3)* @lds_used_within_function_3 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   store i16 ptrtoint ([2 x i32] addrspace(3)* @lds_used_within_function_2 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   call void @function_2()
+; CHECK:   call void @function_3()
+; CHECK:   ret void
+entry:
+  call void @function_2()
+  call void @function_3()
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_calls_function_1_and_2() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([2 x i32] addrspace(3)* @lds_used_within_function_2 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   store i16 ptrtoint ([1 x i32] addrspace(3)* @lds_used_within_function_1 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   call void @function_1()
+; CHECK:   call void @function_2()
+; CHECK:   ret void
+entry:
+  call void @function_1()
+  call void @function_2()
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-global-scope-use.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-global-scope-use.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-global-scope-use.ll
@@ -0,0 +1,39 @@
+; 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
+
+; DESCRIPTION ;
+;
+; LDS global @globaly_used_lds is used within non-kernel function @func, and @func is reachable
+; from kernel @kern, but since @globaly_used_lds is also used in global scope as an initializer
+; @global_var replacement does not take place. Instead @globaly_used_lds is directly lowered.
+;
+
+; CHECK-NOT: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.module.lds.t = type { [4 x i32] }
+
+; CHECK-NOT: @globaly_used_lds
+; CHECK: @global_var = addrspace(1) global float* addrspacecast (float addrspace(3)* bitcast (%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds to float addrspace(3)*) to float*), align 8
+@globaly_used_lds = internal addrspace(3) global [4 x i32] undef, align 4
+@global_var = addrspace(1) global float* addrspacecast ([4 x i32] addrspace(3)* @globaly_used_lds to float*), align 8
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 4
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+
+define void @func() {
+; CHECK-LABEL: entry:
+; CHECK:  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), i32 0, i32 0
+; CHECK:  ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @globaly_used_lds, i32 0, i32 0
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel() {
+; CHECK-LABEL: entry:
+; CHECK:  call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:  call void @func()
+; CHECK:  ret void
+entry:
+  call void @func()
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-inline-asm-call.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-inline-asm-call.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-inline-asm-call.ll
@@ -0,0 +1,34 @@
+; 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
+
+; We do not know what to do with inline asm call, we ignore it, hence @used_only_within_func
+; is directly lowered.
+
+; CHECK-NOT: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.module.lds.t = type { [4 x i32] }
+
+; CHECK-NOT: @used_only_within_func
+@used_only_within_func = addrspace(3) global [4 x i32] undef, align 4
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 4
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+
+define void @f0(i32 %x) {
+; CHECK-LABEL: entry:
+; CHECK:   store i32 %x, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds,
+; CHECK: i32 0, i32 0, i32 0) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0, i32 0) to i32*) to i64)) to i32*), align 4
+; CHECK:   ret void
+entry:
+  store i32 %x, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_func to i32 addrspace(3)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_func to i32 addrspace(3)*) to i32*) to i64)) to i32*), align 4
+  ret void
+}
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   %0 = call i32 asm "s_mov_b32 $0, 0", "=s"()
+; CHECK:   ret void
+entry:
+  call i32 asm "s_mov_b32 $0, 0", "=s"()
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-kernel-only-used-lds.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-kernel-only-used-lds.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-kernel-only-used-lds.ll
@@ -0,0 +1,29 @@
+; 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
+
+; DESCRIPTION ;
+;
+; LDS global @used_only_within_kern is used only within kernel @k0, hence this variable
+; is untouched by both pointer replacement and module lowering phase, but kernel lowering
+; phase lowers it.
+;
+
+; CHECK: %llvm.amdgcn.kernel.k0.lds.t = type { [4 x i32] }
+
+; CHECK-NOT: @used_only_within_kern
+@used_only_within_kern = addrspace(3) global [4 x i32] undef, align 4
+
+; CHECK: @llvm.amdgcn.kernel.k0.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k0.lds.t undef, align 4
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: entry:
+; CHECK:   %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (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, i32 0) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (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, i32 0) to i32*) to i64)) to i32*), align 4
+; CHECK:   %mul = mul i32 %ld, 2
+; CHECK:   store i32 %mul, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (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, i32 0) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (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, i32 0) to i32*) to i64)) to i32*), align 4
+; CHECK:   ret void
+entry:
+  %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_kern to i32 addrspace(3)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_kern to i32 addrspace(3)*) to i32*) to i64)) to i32*), align 4
+  %mul = mul i32 %ld, 2
+  store i32 %mul, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_kern to i32 addrspace(3)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_kern to i32 addrspace(3)*) to i32*) to i64)) to i32*), align 4
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-not-reachable-lds.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-not-reachable-lds.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-not-reachable-lds.ll
@@ -0,0 +1,38 @@
+; 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
+
+; DESCRIPTION ;
+;
+; LDS global @not-reachable-lds is used within non-kernel function @func, but @func is *not*
+; reachable from kernel @kern, hence pointer replacement does not take place. Instead
+; @not-reachable-lds is directly lowered.
+;
+; FIXME: Strictly speaking module lds lowering phase should not lower @not-reachable-lds, but
+; at the moment, we are taking a conservative decision to lower all non-kernel used LDS. On the
+; other-hand we may not exactly know what to do for these cases.
+
+; CHECK-NOT: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.module.lds.t = type { [4 x i32] }
+
+; CHECK-NOT: @not-reachable-lds
+@not-reachable-lds = internal addrspace(3) global [4 x i32] undef, align 4
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 4
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+
+define internal void @func() {
+; CHECK-LABEL: entry:
+; CHECK:  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), i32 0, i32 0
+; CHECK:  ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @not-reachable-lds, i32 0, i32 0
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel() {
+; CHECK-LABEL: entry:
+; CHECK:  call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:  ret void
+entry:
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-small-lds.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-small-lds.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-ignore-small-lds.ll
@@ -0,0 +1,37 @@
+; 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
+
+; DESCRIPTION ;
+;
+; LDS global @small_lds is used within non-kernel function @func, and @func is reachable
+; from kernel @kern, but since @small_lds too small for pointer replacement, pointer
+; replacement does not take place. Instead @small_lds is directly lowered.
+;
+
+; CHECK-NOT: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.module.lds.t = type { i8 }
+
+; CHECK-NOT: @small_lds
+@small_lds = addrspace(3) global i8 undef, align 1
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 1
+; CHECK: @llvm.compiler.used = appending global [1 x i8*] [i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0) to i8*)], section "llvm.metadata"
+
+define void @func() {
+; CHECK-LABEL: entry:
+; CHECK:  store i8 1, i8 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 1
+; CHECK:  ret void
+entry:
+  store i8 1, i8 addrspace(3)* @small_lds, align 1
+  ret void
+}
+
+define amdgpu_kernel void @kern() {
+; CHECK-LABEL: entry:
+; CHECK:  call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:  call void @func()
+; CHECK:  ret void
+entry:
+  call void @func()
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-diamond-shape.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-diamond-shape.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-diamond-shape.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_used_within_func is used within @func_uses_lds which is *indirectly* recheable from
+; kernel @kernel_reaches_lds, hence pointer replacement takes place for @lds_used_within_func.
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.kernel.kernel_reaches_lds.lds.t = type { [4 x i32] }
+; CHECK: %llvm.amdgcn.kernel.kernel_does_not_reach_lds.lds.t = type { %llvm.amdgcn.kernel.kernel_reaches_lds.lds.t }
+
+; Original LDS should not exit.
+; CHECK-NOT: @lds_used_within_func
+@lds_used_within_func = internal addrspace(3) global [4 x i32] undef, align 4
+
+; Pointer should not exist.
+; CHECK-NOT: @lds_used_within_func.pointer
+
+; CHECK: @ptr_to_func = internal local_unnamed_addr externally_initialized global void ()* @func_uses_lds, align 8
+@ptr_to_func = internal local_unnamed_addr externally_initialized global void ()* @func_uses_lds, align 8
+
+; Module and kernel LDS
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 2
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+; CHECK: @llvm.amdgcn.kernel.kernel_reaches_lds.lds = internal addrspace(3) global %llvm.amdgcn.kernel.kernel_reaches_lds.lds.t undef, align 4
+; CHECK: @llvm.amdgcn.kernel.kernel_does_not_reach_lds.lds = internal addrspace(3) global %llvm.amdgcn.kernel.kernel_does_not_reach_lds.lds.t undef, align 4
+
+define internal void @func_uses_lds() {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_func, i32 0, i32 0
+  ret void
+}
+
+define internal void @func_does_not_use_lds_3() {
+; CHECK-LABEL: entry:
+; CHECK:   %fptr = load void ()*, void ()** @ptr_to_func, align 8
+; CHECK:   call void %fptr()
+; CHECK:   ret void
+entry:
+  %fptr = load void ()*, void ()** @ptr_to_func, align 8
+  call void %fptr()
+  ret void
+}
+
+define internal void @func_does_not_use_lds_2() {
+; CHECK-LABEL: entry:
+; CHECK:   %fptr = load void ()*, void ()** @ptr_to_func, align 8
+; CHECK:   call void %fptr()
+; CHECK:   ret void
+entry:
+  %fptr = load void ()*, void ()** @ptr_to_func, align 8
+  call void %fptr()
+  ret void
+}
+
+define internal void @func_does_not_use_lds_1() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @func_does_not_use_lds_2()
+; CHECK:   call void @func_does_not_use_lds_3()
+; CHECK:   ret void
+entry:
+  call void @func_does_not_use_lds_2()
+  call void @func_does_not_use_lds_3()
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_reaches_lds() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint (%llvm.amdgcn.kernel.kernel_reaches_lds.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel_reaches_lds.lds to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   call void @func_does_not_use_lds_1()
+; CHECK:   ret void
+entry:
+  call void @func_does_not_use_lds_1()
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_does_not_reach_lds() {
+; CHECK-LABEL: entry:
+; CHECK-LABEL: call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   ret void
+entry:
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-misc1.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-misc1.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-misc1.ll
@@ -0,0 +1,81 @@
+; 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
+
+; Since indirect call site resolves all the three functions as potential callees (because signature matches),
+; all the LDS require pointer replacement.
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16, i16, i16 }
+; CHECK: %llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds.t = type { [4 x i32], [4 x i32], [4 x i32] }
+
+; CHECK-NOT: @lds_used_within_function_1
+; CHECK-NOT: @lds_used_within_function_2
+; CHECK-NOT: @lds_used_within_function_3
+@lds_used_within_function_1 = internal addrspace(3) global [4 x i32] undef, align 4
+@lds_used_within_function_2 = internal addrspace(3) global [4 x i32] undef, align 4
+@lds_used_within_function_3 = internal addrspace(3) global [4 x i32] undef, align 4
+
+; CHECK-NOT: @lds_used_within_function_1.pointer
+; CHECK-NOT: @lds_used_within_function_2.pointer
+; CHECK-NOT: @lds_used_within_function_3.pointer
+
+; CHECK: @ptr_to_func1 = internal local_unnamed_addr externally_initialized global void (i16)* @function_1, align 8
+; CHECK: @ptr_to_func2 = internal local_unnamed_addr externally_initialized global void (i16)* @function_2, align 8
+; CHECK: @ptr_to_func3 = internal local_unnamed_addr externally_initialized global void (i16)* @function_3, align 8
+@ptr_to_func1 = internal local_unnamed_addr externally_initialized global void (i16)* @function_1, align 8
+@ptr_to_func2 = internal local_unnamed_addr externally_initialized global void (i16)* @function_2, align 8
+@ptr_to_func3 = internal local_unnamed_addr externally_initialized global void (i16)* @function_3, align 8
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 2
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+; CHECK: @llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds = internal addrspace(3) global %llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds.t undef, align 4
+
+define internal void @function_3(i16 %i) {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_function_3, i32 0, i32 0
+  ret void
+}
+
+define internal void @function_2(i16 %i) {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_function_2, i32 0, i32 0
+  ret void
+}
+
+define internal void @function_1(i16 %i) {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_function_1, i32 0, i32 0
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_calls_function_1_and_2() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds.t, %llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds, i32 0, i32 2) to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0,
+; CHECK: i32 2), align 2
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds.t, %llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds, i32 0, i32 1) to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   store i16 ptrtoint (%llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel_calls_function_1_and_2.lds to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %fptr1 = load void (i16)*, void (i16)** @ptr_to_func1, align 8
+; CHECK:   call void %fptr1(i16 6)
+; CHECK:   ret void
+entry:
+  %fptr1 = load void (i16)*, void (i16)** @ptr_to_func1, align 8
+  call void %fptr1(i16 6)
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-selected_functions.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-selected_functions.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-indirect-call-selected_functions.ll
@@ -0,0 +1,112 @@
+; 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
+
+; All the three lds require pointer replacement since functions which access them are
+; *indirectly* reachable.
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16, i16, i16 }
+
+; FIXME: Original LDS should have lowered by kernel lowering.
+@lds_used_within_function_1 = internal addrspace(3) global [4 x i32] undef, align 4
+@lds_used_within_function_2 = internal addrspace(3) global [4 x i32] undef, align 4
+@lds_used_within_function_3 = internal addrspace(3) global [4 x i32] undef, align 4
+
+; CHECK-NOT: @lds_used_within_function_1.pointer
+; CHECK-NOT: @lds_used_within_function_2.pointer
+; CHECK-NOT: @lds_used_within_function_3.pointer
+
+; CHECK: @ptr_to_func1 = internal local_unnamed_addr externally_initialized global void (float)* @function_1, align 8
+; CHECK: @ptr_to_func2 = internal local_unnamed_addr externally_initialized global void (i16)* @function_2, align 8
+; CHECK: @ptr_to_func3 = internal local_unnamed_addr externally_initialized global void (i8)* @function_3, align 8
+@ptr_to_func1 = internal local_unnamed_addr externally_initialized global void (float)* @function_1, align 8
+@ptr_to_func2 = internal local_unnamed_addr externally_initialized global void (i16)* @function_2, align 8
+@ptr_to_func3 = internal local_unnamed_addr externally_initialized global void (i8)* @function_3, align 8
+
+define internal void @function_3(i8 %c) {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_function_3, i32 0, i32 0
+  ret void
+}
+
+define internal void @function_2(i16 %i) {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_function_2, i32 0, i32 0
+  ret void
+}
+
+define internal void @function_1(float %f) {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:   %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* @lds_used_within_function_1, i32 0, i32 0
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_calls_function_3_and_1() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* @lds_used_within_function_3 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* @lds_used_within_function_1 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %fptr3 = load void (i8)*, void (i8)** @ptr_to_func3, align 8
+; CHECK:   %fptr1 = load void (float)*, void (float)** @ptr_to_func1, align 8
+; CHECK:   call void %fptr3(i8 1)
+; CHECK:   call void %fptr1(float 2.000000e+00)
+; CHECK:   ret void
+entry:
+  %fptr3 = load void (i8)*, void (i8)** @ptr_to_func3, align 8
+  %fptr1 = load void (float)*, void (float)** @ptr_to_func1, align 8
+  call void %fptr3(i8 1)
+  call void %fptr1(float 2.0)
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_calls_function_2_and_3() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* @lds_used_within_function_3 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* @lds_used_within_function_2 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   %fptr2 = load void (i16)*, void (i16)** @ptr_to_func2, align 8
+; CHECK:   %fptr3 = load void (i8)*, void (i8)** @ptr_to_func3, align 8
+; CHECK:   call void %fptr2(i16 3)
+; CHECK:   call void %fptr3(i8 4)
+; CHECK:   ret void
+entry:
+  %fptr2 = load void (i16)*, void (i16)** @ptr_to_func2, align 8
+  %fptr3 = load void (i8)*, void (i8)** @ptr_to_func3, align 8
+  call void %fptr2(i16 3)
+  call void %fptr3(i8 4)
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel_calls_function_1_and_2() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* @lds_used_within_function_2 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   store i16 ptrtoint ([4 x i32] addrspace(3)* @lds_used_within_function_1 to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %fptr1 = load void (float)*, void (float)** @ptr_to_func1, align 8
+; CHECK:   %fptr2 = load void (i16)*, void (i16)** @ptr_to_func2, align 8
+; CHECK:   call void %fptr1(float 5.000000e+00)
+; CHECK:   call void %fptr2(i16 6)
+; CHECK:   ret void
+entry:
+  %fptr1 = load void (float)*, void (float)** @ptr_to_func1, align 8
+  %fptr2 = load void (i16)*, void (i16)** @ptr_to_func2, align 8
+  call void %fptr1(float 5.0)
+  call void %fptr2(i16 6)
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-multiple-lds.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-multiple-lds.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-multiple-lds.ll
@@ -0,0 +1,58 @@
+; 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
+
+; All the three lds require pointer replacement since only function which access them is reachable.
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16, i16, i16 }
+; CHECK: %llvm.amdgcn.kernel.kernel.lds.t = type { [3 x i32], [2 x i32], [1 x i32] }
+
+; Original LDS should not exist.
+; CHECK-NOT: @lds1
+; CHECK-NOT: @lds2
+; CHECK-NOT: @lds3
+@lds1 = internal addrspace(3) global [1 x i32] undef, align 4
+@lds2 = internal addrspace(3) global [2 x i32] undef, align 4
+@lds3 = internal addrspace(3) global [3 x i32] undef, align 4
+
+; Pointers should not exist
+; CHECK-NOT: @lds1.pointer
+; CHECK-NOT: @lds2.pointer
+; CHECK-NOT: @lds3.pointer
+
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 2
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+; CHECK: @llvm.amdgcn.kernel.kernel.lds = internal addrspace(3) global %llvm.amdgcn.kernel.kernel.lds.t undef, align 4
+
+define internal void @function() {
+; CHECK-LABEL: entry:
+; CHECK:   %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:   %2 = bitcast i8 addrspace(3)* %1 to [3 x i32] addrspace(3)*
+; CHECK:   %3 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   %4 = getelementptr i8, i8 addrspace(3)* null, i16 %3
+; CHECK:   %5 = bitcast i8 addrspace(3)* %4 to [2 x i32] addrspace(3)*
+; CHECK:   %6 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %7 = getelementptr i8, i8 addrspace(3)* null, i16 %6
+; CHECK:   %8 = bitcast i8 addrspace(3)* %7 to [1 x i32] addrspace(3)*
+; CHECK:   %gep1 = getelementptr inbounds [1 x i32], [1 x i32] addrspace(3)* %8, i32 0, i32 0
+; CHECK:   %gep2 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* %5, i32 0, i32 0
+; CHECK:   %gep3 = getelementptr inbounds [3 x i32], [3 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:   ret void
+entry:
+  %gep1 = getelementptr inbounds [1 x i32], [1 x i32] addrspace(3)* @lds1, i32 0, i32 0
+  %gep2 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* @lds2, i32 0, i32 0
+  %gep3 = getelementptr inbounds [3 x i32], [3 x i32] addrspace(3)* @lds3, i32 0, i32 0
+  ret void
+}
+
+define protected amdgpu_kernel void @kernel() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint (%llvm.amdgcn.kernel.kernel.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel.lds to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 2), align 2
+; CHECK:   store i16 ptrtoint ([2 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.kernel.lds.t, %llvm.amdgcn.kernel.kernel.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel.lds, i32 0, i32 1) to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 1), align 2
+; CHECK:   store i16 ptrtoint ([1 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.kernel.lds.t, %llvm.amdgcn.kernel.kernel.lds.t addrspace(3)* @llvm.amdgcn.kernel.kernel.lds, i32 0, i32 2) to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   call void @function()
+; CHECK:   ret void
+entry:
+  call void @function()
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-use-within-func.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-use-within-func.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-use-within-func.ll
@@ -0,0 +1,46 @@
+; 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
+
+; Module struct should have pointer as a member instead of original LDS
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.kernel.k0.lds.t = type { [4 x i32] }
+
+; Original LDS should not exist.
+; CHECK-NOT: @used_only_within_func
+@used_only_within_func = addrspace(3) global [4 x i32] undef, align 4
+
+; Pointer should not exist.
+; CHECK-NOT: @used_only_within_func.pointer
+
+; Module and kernel LDS.
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 2
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+; CHECK: @llvm.amdgcn.kernel.k0.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k0.lds.t undef, align 4
+
+define void @f0(i32 %x) {
+; CHECK-LABEL: entry:
+; CHECK:  %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:  %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:  %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:  %3 = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:  %4 = addrspacecast i32 addrspace(3)* %3 to i32*
+; CHECK:  %5 = ptrtoint i32* %4 to i64
+; CHECK:  %6 = add i64 %5, %5
+; CHECK:  %7 = inttoptr i64 %6 to i32*
+; CHECK:  store i32 %x, i32* %7, align 4
+; CHECK:  ret void
+entry:
+  store i32 %x, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_func to i32 addrspace(3)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_func to i32 addrspace(3)*) to i32*) to i64)) to i32*), align 4
+  ret void
+}
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint (%llvm.amdgcn.kernel.k0.lds.t addrspace(3)* @llvm.amdgcn.kernel.k0.lds to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   call void @f0(i32 0)
+; CHECK:   ret void
+entry:
+  call void @f0(i32 0)
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-use-within-kern-and-func.ll b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-use-within-kern-and-func.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-use-within-kern-and-func.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
+
+; Module struct should have pointer as a member instead of original LDS @used_within_both_func_and_kern
+; CHECK: %llvm.amdgcn.module.lds.t = type { i16 }
+; CHECK: %llvm.amdgcn.kernel.k0.lds.t = type { [4 x i32], [4 x i32] }
+
+; Original LDS should not exist.
+; CHECK-NOT: @used_only_within_kern
+; CHECK-NOT: @used_within_both_func_and_kern
+@used_only_within_kern = addrspace(3) global [4 x i32] undef, align 4
+@used_within_both_func_and_kern = addrspace(3) global [4 x i32] undef, align 4
+
+; Pointer should not exist
+; CHECK-NOT: @used_only_within_kern.pointer
+; CHECK-NOT: @used_within_both_func_and_kern.pointer
+
+; Module and kernel LDS
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 2
+; CHECK: @llvm.compiler.used = appending global [1 x 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"
+; CHECK: @llvm.amdgcn.kernel.k0.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k0.lds.t undef, align 4
+
+define void @f0(i32 %x) {
+; CHECK-LABEL: entry:
+; CHECK:  %0 = load i16, i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:  %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
+; CHECK:  %2 = bitcast i8 addrspace(3)* %1 to [4 x i32] addrspace(3)*
+; CHECK:  %3 = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* %2, i32 0, i32 0
+; CHECK:  %4 = addrspacecast i32 addrspace(3)* %3 to i32*
+; CHECK:  %5 = ptrtoint i32* %4 to i64
+; CHECK:  %6 = add i64 %5, %5
+; CHECK:  %7 = inttoptr i64 %6 to i32*
+; CHECK:  store i32 %x, i32* %7, align 4
+; CHECK:  ret void
+entry:
+  store i32 %x, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_within_both_func_and_kern to i32 addrspace(3)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_within_both_func_and_kern to i32 addrspace(3)*) to i32*) to i64)) to i32*), align 4
+  ret void
+}
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: entry:
+; CHECK:   call void @llvm.donothing() [ "ExplicitUse"(%llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds) ]
+; CHECK:   store i16 ptrtoint ([4 x 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 1) to i16), i16 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0), align 2
+; CHECK:   %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (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 1, i32 0) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (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, i32 0) to i32*) to i64)) to i32*), align 4
+; CHECK:   %mul = mul i32 %ld, 2
+; CHECK:   store i32 %mul, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (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, i32 0) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (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 1, i32 0) to i32*) to i64)) to i32*), align 4
+; CHECK:   call void @f0(i32 0)
+; CHECK:   ret void
+entry:
+  %ld = load i32, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_within_both_func_and_kern to i32 addrspace(3)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_kern to i32 addrspace(3)*) to i32*) to i64)) to i32*), align 4
+  %mul = mul i32 %ld, 2
+  store i32 %mul, i32* inttoptr (i64 add (i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_only_within_kern to i32 addrspace(3)*) to i32*) to i64), i64 ptrtoint (i32* addrspacecast (i32 addrspace(3)* bitcast ([4 x i32] addrspace(3)* @used_within_both_func_and_kern to i32 addrspace(3)*) to i32*) to i64)) to i32*), align 4
+  call void @f0(i32 0)
+  ret void
+}