[llvm] [AMDGPU] Introduce "amdgpu-sw-lower-lds" pass to lower LDS accesses to use device global memory. (PR #87265)

via llvm-commits llvm-commits at lists.llvm.org
Thu May 9 04:25:33 PDT 2024


https://github.com/skc7 updated https://github.com/llvm/llvm-project/pull/87265

>From 9d9e0230826eafa2eb9861bda877d7c2b3d95da8 Mon Sep 17 00:00:00 2001
From: skc7 <Krishna.Sankisa at amd.com>
Date: Thu, 7 Mar 2024 12:40:41 +0530
Subject: [PATCH] [AMDGPU] Enable amdgpu-sw-lower-lds pass to lower LDS
 accesses to use device global memory. (#87265)

---
 llvm/lib/Target/AMDGPU/AMDGPU.h               |   9 +
 .../AMDGPU/AMDGPULowerModuleLDSPass.cpp       | 230 +----
 llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def |   1 +
 llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp   | 876 ++++++++++++++++++
 .../lib/Target/AMDGPU/AMDGPUTargetMachine.cpp |   1 +
 llvm/lib/Target/AMDGPU/CMakeLists.txt         |   1 +
 .../Target/AMDGPU/Utils/AMDGPUMemoryUtils.cpp | 216 +++++
 .../Target/AMDGPU/Utils/AMDGPUMemoryUtils.h   |  29 +
 ...pu-sw-lower-lds-dynamic-indirect-access.ll | 100 ++
 .../amdgpu-sw-lower-lds-dynamic-lds-test.ll   |  63 ++
 ...ds-multi-static-dynamic-indirect-access.ll | 194 ++++
 ...gpu-sw-lower-lds-multiple-blocks-return.ll |  79 ++
 ...ower-lds-static-dynamic-indirect-access.ll | 101 ++
 ...pu-sw-lower-lds-static-dynamic-lds-test.ll |  88 ++
 ...s-static-indirect-access-function-param.ll |  61 ++
 ...lower-lds-static-indirect-access-nested.ll | 220 +++++
 ...gpu-sw-lower-lds-static-indirect-access.ll |  85 ++
 .../amdgpu-sw-lower-lds-static-lds-test.ll    |  58 ++
 18 files changed, 2184 insertions(+), 228 deletions(-)
 create mode 100644 llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-indirect-access.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-lds-test.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multi-static-dynamic-indirect-access.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multiple-blocks-return.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-indirect-access.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-lds-test.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-function-param.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-nested.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access.ll
 create mode 100644 llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-test.ll

diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.h b/llvm/lib/Target/AMDGPU/AMDGPU.h
index 6016bd5187d88..15ff74f7c53af 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.h
@@ -263,6 +263,15 @@ struct AMDGPUAlwaysInlinePass : PassInfoMixin<AMDGPUAlwaysInlinePass> {
   bool GlobalOpt;
 };
 
+void initializeAMDGPUSwLowerLDSLegacyPass(PassRegistry &);
+extern char &AMDGPUSwLowerLDSLegacyPassID;
+ModulePass *createAMDGPUSwLowerLDSLegacyPass();
+
+struct AMDGPUSwLowerLDSPass : PassInfoMixin<AMDGPUSwLowerLDSPass> {
+  AMDGPUSwLowerLDSPass() {}
+  PreservedAnalyses run(Module &M, ModuleAnalysisManager &AM);
+};
+
 class AMDGPUCodeGenPreparePass
     : public PassInfoMixin<AMDGPUCodeGenPreparePass> {
 private:
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
index c8bf9dd39e389..625ac0230f160 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -212,6 +212,7 @@
 #define DEBUG_TYPE "amdgpu-lower-module-lds"
 
 using namespace llvm;
+using namespace AMDGPU;
 
 namespace {
 
@@ -234,17 +235,6 @@ cl::opt<LoweringKind> LoweringKindLoc(
         clEnumValN(LoweringKind::hybrid, "hybrid",
                    "Lower via mixture of above strategies")));
 
-bool isKernelLDS(const Function *F) {
-  // Some weirdness here. AMDGPU::isKernelCC does not call into
-  // AMDGPU::isKernel with the calling conv, it instead calls into
-  // isModuleEntryFunction which returns true for more calling conventions
-  // than AMDGPU::isKernel does. There's a FIXME on AMDGPU::isKernel.
-  // There's also a test that checks that the LDS lowering does not hit on
-  // a graphics shader, denoted amdgpu_ps, so stay with the limited case.
-  // Putting LDS in the name of the function to draw attention to this.
-  return AMDGPU::isKernel(F->getCallingConv());
-}
-
 template <typename T> std::vector<T> sortByName(std::vector<T> &&V) {
   llvm::sort(V.begin(), V.end(), [](const auto *L, const auto *R) {
     return L->getName() < R->getName();
@@ -305,183 +295,9 @@ class AMDGPULowerModuleLDS {
         Decl, {}, {OperandBundleDefT<Value *>("ExplicitUse", UseInstance)});
   }
 
-  static bool eliminateConstantExprUsesOfLDSFromAllInstructions(Module &M) {
-    // Constants are uniqued within LLVM. A ConstantExpr referring to a LDS
-    // global may have uses from multiple different functions as a result.
-    // This pass specialises LDS variables with respect to the kernel that
-    // allocates them.
-
-    // This is semantically equivalent to (the unimplemented as slow):
-    // for (auto &F : M.functions())
-    //   for (auto &BB : F)
-    //     for (auto &I : BB)
-    //       for (Use &Op : I.operands())
-    //         if (constantExprUsesLDS(Op))
-    //           replaceConstantExprInFunction(I, Op);
-
-    SmallVector<Constant *> LDSGlobals;
-    for (auto &GV : M.globals())
-      if (AMDGPU::isLDSVariableToLower(GV))
-        LDSGlobals.push_back(&GV);
-
-    return convertUsersOfConstantsToInstructions(LDSGlobals);
-  }
-
 public:
   AMDGPULowerModuleLDS(const AMDGPUTargetMachine &TM_) : TM(TM_) {}
 
-  using FunctionVariableMap = DenseMap<Function *, DenseSet<GlobalVariable *>>;
-
-  using VariableFunctionMap = DenseMap<GlobalVariable *, DenseSet<Function *>>;
-
-  static void getUsesOfLDSByFunction(CallGraph const &CG, Module &M,
-                                     FunctionVariableMap &kernels,
-                                     FunctionVariableMap &functions) {
-
-    // Get uses from the current function, excluding uses by called functions
-    // Two output variables to avoid walking the globals list twice
-    for (auto &GV : M.globals()) {
-      if (!AMDGPU::isLDSVariableToLower(GV)) {
-        continue;
-      }
-
-      for (User *V : GV.users()) {
-        if (auto *I = dyn_cast<Instruction>(V)) {
-          Function *F = I->getFunction();
-          if (isKernelLDS(F)) {
-            kernels[F].insert(&GV);
-          } else {
-            functions[F].insert(&GV);
-          }
-        }
-      }
-    }
-  }
-
-  struct LDSUsesInfoTy {
-    FunctionVariableMap direct_access;
-    FunctionVariableMap indirect_access;
-  };
-
-  static LDSUsesInfoTy getTransitiveUsesOfLDS(CallGraph const &CG, Module &M) {
-
-    FunctionVariableMap direct_map_kernel;
-    FunctionVariableMap direct_map_function;
-    getUsesOfLDSByFunction(CG, M, direct_map_kernel, direct_map_function);
-
-    // Collect variables that are used by functions whose address has escaped
-    DenseSet<GlobalVariable *> VariablesReachableThroughFunctionPointer;
-    for (Function &F : M.functions()) {
-      if (!isKernelLDS(&F))
-        if (F.hasAddressTaken(nullptr,
-                              /* IgnoreCallbackUses */ false,
-                              /* IgnoreAssumeLikeCalls */ false,
-                              /* IgnoreLLVMUsed */ true,
-                              /* IgnoreArcAttachedCall */ false)) {
-          set_union(VariablesReachableThroughFunctionPointer,
-                    direct_map_function[&F]);
-        }
-    }
-
-    auto functionMakesUnknownCall = [&](const Function *F) -> bool {
-      assert(!F->isDeclaration());
-      for (const CallGraphNode::CallRecord &R : *CG[F]) {
-        if (!R.second->getFunction()) {
-          return true;
-        }
-      }
-      return false;
-    };
-
-    // Work out which variables are reachable through function calls
-    FunctionVariableMap transitive_map_function = direct_map_function;
-
-    // If the function makes any unknown call, assume the worst case that it can
-    // access all variables accessed by functions whose address escaped
-    for (Function &F : M.functions()) {
-      if (!F.isDeclaration() && functionMakesUnknownCall(&F)) {
-        if (!isKernelLDS(&F)) {
-          set_union(transitive_map_function[&F],
-                    VariablesReachableThroughFunctionPointer);
-        }
-      }
-    }
-
-    // Direct implementation of collecting all variables reachable from each
-    // function
-    for (Function &Func : M.functions()) {
-      if (Func.isDeclaration() || isKernelLDS(&Func))
-        continue;
-
-      DenseSet<Function *> seen; // catches cycles
-      SmallVector<Function *, 4> wip{&Func};
-
-      while (!wip.empty()) {
-        Function *F = wip.pop_back_val();
-
-        // Can accelerate this by referring to transitive map for functions that
-        // have already been computed, with more care than this
-        set_union(transitive_map_function[&Func], direct_map_function[F]);
-
-        for (const CallGraphNode::CallRecord &R : *CG[F]) {
-          Function *ith = R.second->getFunction();
-          if (ith) {
-            if (!seen.contains(ith)) {
-              seen.insert(ith);
-              wip.push_back(ith);
-            }
-          }
-        }
-      }
-    }
-
-    // direct_map_kernel lists which variables are used by the kernel
-    // find the variables which are used through a function call
-    FunctionVariableMap indirect_map_kernel;
-
-    for (Function &Func : M.functions()) {
-      if (Func.isDeclaration() || !isKernelLDS(&Func))
-        continue;
-
-      for (const CallGraphNode::CallRecord &R : *CG[&Func]) {
-        Function *ith = R.second->getFunction();
-        if (ith) {
-          set_union(indirect_map_kernel[&Func], transitive_map_function[ith]);
-        } else {
-          set_union(indirect_map_kernel[&Func],
-                    VariablesReachableThroughFunctionPointer);
-        }
-      }
-    }
-
-    // Verify that we fall into one of 2 cases:
-    //    - All variables are absolute: this is a re-run of the pass
-    //      so we don't have anything to do.
-    //    - No variables are absolute.
-    std::optional<bool> HasAbsoluteGVs;
-    for (auto &Map : {direct_map_kernel, indirect_map_kernel}) {
-      for (auto &[Fn, GVs] : Map) {
-        for (auto *GV : GVs) {
-          bool IsAbsolute = GV->isAbsoluteSymbolRef();
-          if (HasAbsoluteGVs.has_value()) {
-            if (*HasAbsoluteGVs != IsAbsolute) {
-              report_fatal_error(
-                  "Module cannot mix absolute and non-absolute LDS GVs");
-            }
-          } else
-            HasAbsoluteGVs = IsAbsolute;
-        }
-      }
-    }
-
-    // If we only had absolute GVs, we have nothing to do, return an empty
-    // result.
-    if (HasAbsoluteGVs && *HasAbsoluteGVs)
-      return {FunctionVariableMap(), FunctionVariableMap()};
-
-    return {std::move(direct_map_kernel), std::move(indirect_map_kernel)};
-  }
-
   struct LDSVariableReplacement {
     GlobalVariable *SGV = nullptr;
     DenseMap<GlobalVariable *, Constant *> LDSVarsToConstantGEP;
@@ -1046,48 +862,6 @@ class AMDGPULowerModuleLDS {
     return N;
   }
 
-  /// Strip "amdgpu-no-lds-kernel-id" from any functions where we may have
-  /// introduced its use. If AMDGPUAttributor ran prior to the pass, we inferred
-  /// the lack of llvm.amdgcn.lds.kernel.id calls.
-  void removeNoLdsKernelIdFromReachable(CallGraph &CG, Function *KernelRoot) {
-    KernelRoot->removeFnAttr("amdgpu-no-lds-kernel-id");
-
-    SmallVector<Function *> WorkList({CG[KernelRoot]->getFunction()});
-    SmallPtrSet<Function *, 8> Visited;
-    bool SeenUnknownCall = false;
-
-    while (!WorkList.empty()) {
-      Function *F = WorkList.pop_back_val();
-
-      for (auto &CallRecord : *CG[F]) {
-        if (!CallRecord.second)
-          continue;
-
-        Function *Callee = CallRecord.second->getFunction();
-        if (!Callee) {
-          if (!SeenUnknownCall) {
-            SeenUnknownCall = true;
-
-            // If we see any indirect calls, assume nothing about potential
-            // targets.
-            // TODO: This could be refined to possible LDS global users.
-            for (auto &ExternalCallRecord : *CG.getExternalCallingNode()) {
-              Function *PotentialCallee =
-                  ExternalCallRecord.second->getFunction();
-              assert(PotentialCallee);
-              if (!isKernelLDS(PotentialCallee))
-                PotentialCallee->removeFnAttr("amdgpu-no-lds-kernel-id");
-            }
-          }
-        } else {
-          Callee->removeFnAttr("amdgpu-no-lds-kernel-id");
-          if (Visited.insert(Callee).second)
-            WorkList.push_back(Callee);
-        }
-      }
-    }
-  }
-
   DenseMap<Function *, GlobalVariable *> lowerDynamicLDSVariables(
       Module &M, LDSUsesInfoTy &LDSUsesInfo,
       DenseSet<Function *> const &KernelsThatIndirectlyAllocateDynamicLDS,
@@ -1243,7 +1017,7 @@ class AMDGPULowerModuleLDS {
       //
       // TODO: We could filter out subgraphs that do not access LDS globals.
       for (Function *F : KernelsThatAllocateTableLDS)
-        removeNoLdsKernelIdFromReachable(CG, F);
+        removeFnAttrFromReachable(CG, F, "amdgpu-no-lds-kernel-id");
     }
 
     DenseMap<Function *, GlobalVariable *> KernelToCreatedDynamicLDS =
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
index 90f36fadf3590..eda4949d0296d 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
@@ -22,6 +22,7 @@ MODULE_PASS("amdgpu-lower-buffer-fat-pointers",
             AMDGPULowerBufferFatPointersPass(*this))
 MODULE_PASS("amdgpu-lower-ctor-dtor", AMDGPUCtorDtorLoweringPass())
 MODULE_PASS("amdgpu-lower-module-lds", AMDGPULowerModuleLDSPass(*this))
+MODULE_PASS("amdgpu-sw-lower-lds", AMDGPUSwLowerLDSPass())
 MODULE_PASS("amdgpu-printf-runtime-binding", AMDGPUPrintfRuntimeBindingPass())
 MODULE_PASS("amdgpu-unify-metadata", AMDGPUUnifyMetadataPass())
 #undef MODULE_PASS
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
new file mode 100644
index 0000000000000..3b951e72aabed
--- /dev/null
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSwLowerLDS.cpp
@@ -0,0 +1,876 @@
+//===-- AMDGPUSwLowerLDS.cpp -----------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This pass lowers the local data store, LDS, uses in kernel and non-kernel
+// functions in module with dynamically allocated device global memory.
+//
+// Replacement of Kernel LDS accesses:
+//    For a kernel, LDS access can be static or dynamic which are direct
+//    (accessed within kernel) and indirect (accessed through non-kernels).
+//    A device global memory equal to size of all these LDS globals will be
+//    allocated. At the prologue of the kernel, a single work-item from the
+//    work-group, does a "malloc" and stores the pointer of the allocation in
+//    new LDS global that will be created for the kernel. This will be called
+//    "SW LDS" in this pass.
+//    Each LDS access corresponds to an offset in the allocated memory.
+//    All static LDS accesses will be allocated first and then dynamic LDS
+//    will occupy the device global memory.
+//    To store the offsets corresponding to all LDS accesses, another global
+//    variable is created which will be called "SW LDS metadata" in this pass.
+//    - SW LDS Global:
+//        It is LDS global of ptr type with name
+//        "llvm.amdgcn.sw.lds.<kernel-name>".
+//    - Metadata Global:
+//        It is of struct type, with n members. n equals the number of LDS
+//        globals accessed by the kernel(direct and indirect). Each member of
+//        struct is another struct of type {i32, i32, i32}. First member
+//        corresponds to offset, second member corresponds to size of LDS global
+//        being replaced and third represents the total aligned size. It will
+//        have name "llvm.amdgcn.sw.lds.<kernel-name>.md". This global will have
+//        an intializer with static LDS related offsets and sizes initialized.
+//        But for dynamic LDS related entries, offsets will be intialized to
+//        previous static LDS allocation end offset. Sizes for them will be zero
+//        initially. These dynamic LDS offset and size values will be updated
+//        with in the kernel, since kernel can read the dynamic LDS size
+//        allocation done at runtime with query to "hidden_dynamic_lds_size"
+//        hidden kernel argument.
+//
+//    LDS accesses within the kernel will be replaced by "gep" ptr to
+//    corresponding offset into allocated device global memory for the kernel.
+//    At the epilogue of kernel, allocated memory would be made free by the same
+//    single work-item.
+//
+// Replacement of non-kernel LDS accesses:
+//    Multiple kernels can access the same non-kernel function.
+//    All the kernels accessing LDS through non-kernels are sorted and
+//    assigned a kernel-id. All the LDS globals accessed by non-kernels
+//    are sorted. This information is used to build two tables:
+//    - Base table:
+//        Base table will have single row, with elements of the row
+//        placed as per kernel ID. Each element in the row corresponds
+//        to addresss of "SW LDS" variable created for
+//        that kernel.
+//    - Offset table:
+//        Offset table will have multiple rows and columns.
+//        Rows are assumed to be from 0 to (n-1). n is total number
+//        of kernels accessing the LDS through non-kernels.
+//        Each row will have m elements. m is the total number of
+//        unique LDS globals accessed by all non-kernels.
+//        Each element in the row correspond to the address of
+//        the replacement of LDS global done by that particular kernel.
+//    A LDS variable in non-kernel will be replaced based on the information
+//    from base and offset tables. Based on kernel-id query, address of "SW
+//    LDS" for that corresponding kernel is obtained from base table.
+//    The Offset into the base "SW LDS" is obtained from
+//    corresponding element in offset table. With this information, replacement
+//    value is obtained.
+//===----------------------------------------------------------------------===//
+
+#include "AMDGPU.h"
+#include "Utils/AMDGPUMemoryUtils.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/SetOperations.h"
+#include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Analysis/CallGraph.h"
+#include "llvm/Analysis/DomTreeUpdater.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
+#include "llvm/IR/MDBuilder.h"
+#include "llvm/IR/ReplaceConstant.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Pass.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Transforms/Utils/ModuleUtils.h"
+
+#include <algorithm>
+
+#define DEBUG_TYPE "amdgpu-sw-lower-lds"
+
+using namespace llvm;
+using namespace AMDGPU;
+
+namespace {
+
+using DomTreeCallback = function_ref<DominatorTree *(Function &F)>;
+
+struct LDSAccessTypeInfo {
+  SetVector<GlobalVariable *> StaticLDSGlobals;
+  SetVector<GlobalVariable *> DynamicLDSGlobals;
+};
+
+// Struct to hold all the Metadata required for a kernel
+// to replace a LDS global uses with corresponding offset
+// in to device global memory.
+struct KernelLDSParameters {
+  GlobalVariable *SwLDS = nullptr;
+  GlobalVariable *SwLDSMetadata = nullptr;
+  LDSAccessTypeInfo DirectAccess;
+  LDSAccessTypeInfo IndirectAccess;
+  DenseMap<GlobalVariable *, SmallVector<uint32_t, 3>>
+      LDSToReplacementIndicesMap;
+};
+
+// Struct to store infor for creation of offset table
+// for all the non-kernel LDS accesses.
+struct NonKernelLDSParameters {
+  GlobalVariable *LDSBaseTable{nullptr};
+  GlobalVariable *LDSOffsetTable{nullptr};
+  SetVector<Function *> OrderedKernels;
+  SetVector<GlobalVariable *> OrdereLDSGlobals;
+};
+
+class AMDGPUSwLowerLDS {
+public:
+  AMDGPUSwLowerLDS(Module &Mod, DomTreeCallback Callback)
+      : M(Mod), IRB(M.getContext()), DTCallback(Callback) {}
+  bool run();
+  void getUsesOfLDSByNonKernels(const CallGraph &CG,
+                                FunctionVariableMap &Functions);
+  SetVector<Function *>
+  getOrderedIndirectLDSAccessingKernels(SetVector<Function *> &&Kernels);
+  SetVector<GlobalVariable *>
+  getOrderedNonKernelAllLDSGlobals(SetVector<GlobalVariable *> &&Variables);
+  void populateSwLDSGlobal(Function *Func);
+  void populateSwMetadataGlobal(Function *Func);
+  void populateLDSToReplacementIndicesMap(Function *Func);
+  void replaceKernelLDSAccesses(Function *Func);
+  void lowerKernelLDSAccesses(Function *Func, DomTreeUpdater &DTU);
+  void buildNonKernelLDSOffsetTable(NonKernelLDSParameters &NKLDSParams);
+  void buildNonKernelLDSBaseTable(NonKernelLDSParameters &NKLDSParams);
+  Constant *
+  getAddressesOfVariablesInKernel(Function *Func,
+                                  SetVector<GlobalVariable *> &Variables);
+  void lowerNonKernelLDSAccesses(Function *Func,
+                                 SetVector<GlobalVariable *> &LDSGlobals,
+                                 NonKernelLDSParameters &NKLDSParams);
+
+private:
+  Module &M;
+  IRBuilder<> IRB;
+  DomTreeCallback DTCallback;
+  DenseMap<Function *, KernelLDSParameters> KernelToLDSParametersMap;
+};
+
+template <typename T> SetVector<T> sortByName(std::vector<T> &&V) {
+  // Sort the vector of globals or Functions based on their name.
+  // Returns a SetVector of globals/Functions.
+  sort(V, [](const auto *L, const auto *R) {
+    return L->getName() < R->getName();
+  });
+  return {SetVector<T>(V.begin(), V.end())};
+}
+
+SetVector<GlobalVariable *> AMDGPUSwLowerLDS::getOrderedNonKernelAllLDSGlobals(
+    SetVector<GlobalVariable *> &&Variables) {
+  // Sort all the non-kernel LDS accesses based on their name.
+  return sortByName(
+      std::vector<GlobalVariable *>(Variables.begin(), Variables.end()));
+}
+
+SetVector<Function *> AMDGPUSwLowerLDS::getOrderedIndirectLDSAccessingKernels(
+    SetVector<Function *> &&Kernels) {
+  // Sort the non-kernels accessing LDS based on their name.
+  // Also assign a kernel ID metadata based on the sorted order.
+  LLVMContext &Ctx = M.getContext();
+  if (Kernels.size() > UINT32_MAX) {
+    // 32 bit keeps it in one SGPR. > 2**32 kernels won't fit on the GPU
+    report_fatal_error("Unimplemented SW LDS lowering for > 2**32 kernels");
+  }
+  SetVector<Function *> OrderedKernels =
+      sortByName(std::vector<Function *>(Kernels.begin(), Kernels.end()));
+  for (size_t i = 0; i < Kernels.size(); i++) {
+    Metadata *AttrMDArgs[1] = {
+        ConstantAsMetadata::get(IRB.getInt32(i)),
+    };
+    Function *Func = OrderedKernels[i];
+    Func->setMetadata("llvm.amdgcn.lds.kernel.id",
+                      MDNode::get(Ctx, AttrMDArgs));
+    auto &LDSParams = KernelToLDSParametersMap[Func];
+  }
+  return std::move(OrderedKernels);
+}
+
+void AMDGPUSwLowerLDS::getUsesOfLDSByNonKernels(
+    const CallGraph &CG, FunctionVariableMap &functions) {
+  // Get uses from the current function, excluding uses by called functions
+  // Two output variables to avoid walking the globals list twice
+  for (auto &GV : M.globals()) {
+    if (!AMDGPU::isLDSVariableToLower(GV))
+      continue;
+
+    if (GV.isAbsoluteSymbolRef()) {
+      report_fatal_error(
+          "LDS variables with absolute addresses are unimplemented.");
+    }
+
+    for (User *V : GV.users()) {
+      if (auto *I = dyn_cast<Instruction>(V)) {
+        Function *F = I->getFunction();
+        if (!isKernelLDS(F))
+          functions[F].insert(&GV);
+      }
+    }
+  }
+}
+
+void AMDGPUSwLowerLDS::populateSwLDSGlobal(Function *Func) {
+  // Create new LDS global required for each kernel to store
+  // device global memory pointer.
+  auto &LDSParams = KernelToLDSParametersMap[Func];
+  // create new global pointer variable
+  LDSParams.SwLDS = new GlobalVariable(
+      M, IRB.getPtrTy(), false, GlobalValue::InternalLinkage,
+      PoisonValue::get(IRB.getPtrTy()), "llvm.amdgcn.sw.lds." + Func->getName(),
+      nullptr, GlobalValue::NotThreadLocal, AMDGPUAS::LOCAL_ADDRESS, false);
+  return;
+}
+
+void AMDGPUSwLowerLDS::populateSwMetadataGlobal(Function *Func) {
+  // Create new metadata global for every kernel and initialize the
+  // start offsets and sizes corresponding to each LDS accesses.
+  auto &LDSParams = KernelToLDSParametersMap[Func];
+  auto &Ctx = M.getContext();
+  auto &DL = M.getDataLayout();
+  std::vector<Type *> Items;
+  Type *Int32Ty = IRB.getInt32Ty();
+  std::vector<Constant *> Initializers;
+  Align MaxAlignment(1);
+  auto UpdateMaxAlignment = [&MaxAlignment, &DL](GlobalVariable *GV) {
+    Align GVAlign = AMDGPU::getAlign(DL, GV);
+    MaxAlignment = std::max(MaxAlignment, GVAlign);
+  };
+
+  for (GlobalVariable *GV : LDSParams.DirectAccess.StaticLDSGlobals)
+    UpdateMaxAlignment(GV);
+
+  for (GlobalVariable *GV : LDSParams.DirectAccess.DynamicLDSGlobals)
+    UpdateMaxAlignment(GV);
+
+  for (GlobalVariable *GV : LDSParams.IndirectAccess.StaticLDSGlobals)
+    UpdateMaxAlignment(GV);
+
+  for (GlobalVariable *GV : LDSParams.IndirectAccess.DynamicLDSGlobals)
+    UpdateMaxAlignment(GV);
+
+  //{StartOffset, AlignedSizeInBytes}
+  SmallString<128> MDItemStr;
+  raw_svector_ostream MDItemOS(MDItemStr);
+  MDItemOS << "llvm.amdgcn.sw.lds." << Func->getName().str() << ".md.item";
+
+  StructType *LDSItemTy =
+      StructType::create(Ctx, {Int32Ty, Int32Ty, Int32Ty}, MDItemOS.str());
+  uint32_t MallocSize = 0;
+  auto buildInitializerForSwLDSMD =
+      [&](SetVector<GlobalVariable *> &LDSGlobals) {
+        for (auto &GV : LDSGlobals) {
+          Type *Ty = GV->getValueType();
+          const uint64_t SizeInBytes = DL.getTypeAllocSize(Ty);
+          Items.push_back(LDSItemTy);
+          Constant *ItemStartOffset = ConstantInt::get(Int32Ty, MallocSize);
+          Constant *SizeInBytesConst = ConstantInt::get(Int32Ty, SizeInBytes);
+          uint64_t AlignedSize = alignTo(SizeInBytes, MaxAlignment);
+          Constant *AlignedSizeInBytesConst =
+              ConstantInt::get(Int32Ty, AlignedSize);
+          MallocSize += AlignedSize;
+          Constant *InitItem =
+              ConstantStruct::get(LDSItemTy, {ItemStartOffset, SizeInBytesConst,
+                                              AlignedSizeInBytesConst});
+          Initializers.push_back(InitItem);
+        }
+      };
+
+  buildInitializerForSwLDSMD(LDSParams.DirectAccess.StaticLDSGlobals);
+  buildInitializerForSwLDSMD(LDSParams.IndirectAccess.StaticLDSGlobals);
+  buildInitializerForSwLDSMD(LDSParams.DirectAccess.DynamicLDSGlobals);
+  buildInitializerForSwLDSMD(LDSParams.IndirectAccess.DynamicLDSGlobals);
+
+  SmallString<128> MDTypeStr;
+  raw_svector_ostream MDTypeOS(MDTypeStr);
+  MDTypeOS << "llvm.amdgcn.sw.lds." << Func->getName().str() << ".md.type";
+
+  StructType *MetadataStructType =
+      StructType::create(Ctx, Items, MDTypeOS.str());
+  SmallString<128> MDStr;
+  raw_svector_ostream MDOS(MDStr);
+  MDOS << "llvm.amdgcn.sw.lds." << Func->getName().str() << ".md";
+  LDSParams.SwLDSMetadata = new GlobalVariable(
+      M, MetadataStructType, false, GlobalValue::InternalLinkage,
+      PoisonValue::get(MetadataStructType), MDOS.str(), nullptr,
+      GlobalValue::NotThreadLocal, AMDGPUAS::GLOBAL_ADDRESS, false);
+  Constant *data = ConstantStruct::get(MetadataStructType, Initializers);
+  LDSParams.SwLDSMetadata->setInitializer(data);
+  assert(LDSParams.SwLDS);
+  // Set the alignment to MaxAlignment for SwLDS.
+  LDSParams.SwLDS->setAlignment(MaxAlignment);
+  GlobalValue::SanitizerMetadata MD;
+  MD.NoAddress = true;
+  LDSParams.SwLDSMetadata->setSanitizerMetadata(MD);
+  return;
+}
+
+void AMDGPUSwLowerLDS::populateLDSToReplacementIndicesMap(Function *Func) {
+  // Fill the corresponding LDS replacement indices for each LDS access
+  // related to this kernel.
+  auto &LDSParams = KernelToLDSParametersMap[Func];
+  auto PopulateIndices = [&](SetVector<GlobalVariable *> &LDSGlobals,
+                             uint32_t &Idx) {
+    for (auto &GV : LDSGlobals) {
+      LDSParams.LDSToReplacementIndicesMap[GV] = {0, Idx, 0};
+      ++Idx;
+    }
+  };
+  uint32_t Idx = 0;
+  PopulateIndices(LDSParams.DirectAccess.StaticLDSGlobals, Idx);
+  PopulateIndices(LDSParams.IndirectAccess.StaticLDSGlobals, Idx);
+  PopulateIndices(LDSParams.DirectAccess.DynamicLDSGlobals, Idx);
+  PopulateIndices(LDSParams.IndirectAccess.DynamicLDSGlobals, Idx);
+  return;
+}
+
+static void replacesUsesOfGlobalInFunction(Function *Func, GlobalVariable *GV,
+                                           Value *Replacement) {
+  // Replace all uses of LDS global in this Function with a Replacement.
+  auto ReplaceUsesLambda = [Func](const Use &U) -> bool {
+    auto *V = U.getUser();
+    if (auto *Inst = dyn_cast<Instruction>(V)) {
+      auto *Func1 = Inst->getParent()->getParent();
+      if (Func == Func1)
+        return true;
+    }
+    return false;
+  };
+  GV->replaceUsesWithIf(Replacement, ReplaceUsesLambda);
+}
+
+void AMDGPUSwLowerLDS::replaceKernelLDSAccesses(Function *Func) {
+  auto &LDSParams = KernelToLDSParametersMap[Func];
+  GlobalVariable *SwLDS = LDSParams.SwLDS;
+  assert(SwLDS);
+  GlobalVariable *SwLDSMetadata = LDSParams.SwLDSMetadata;
+  assert(SwLDSMetadata);
+  StructType *SwLDSMetadataStructType =
+      cast<StructType>(SwLDSMetadata->getValueType());
+  Type *Int32Ty = IRB.getInt32Ty();
+
+  auto &IndirectAccess = LDSParams.IndirectAccess;
+  auto &DirectAccess = LDSParams.DirectAccess;
+  // Replace all uses of LDS global in this Function with a Replacement.
+  auto ReplaceLDSGlobalUses = [&](SetVector<GlobalVariable *> &LDSGlobals) {
+    for (auto &GV : LDSGlobals) {
+      // Do not generate instructions if LDS access is in non-kernel
+      // i.e indirect-access.
+      if ((IndirectAccess.StaticLDSGlobals.contains(GV) ||
+           IndirectAccess.DynamicLDSGlobals.contains(GV)) &&
+          (!DirectAccess.StaticLDSGlobals.contains(GV) &&
+           !DirectAccess.DynamicLDSGlobals.contains(GV)))
+        continue;
+      auto &Indices = LDSParams.LDSToReplacementIndicesMap[GV];
+      assert(Indices.size() == 3);
+      uint32_t Idx0 = Indices[0];
+      uint32_t Idx1 = Indices[1];
+      uint32_t Idx2 = Indices[2];
+      Constant *GEPIdx[] = {ConstantInt::get(Int32Ty, Idx0),
+                            ConstantInt::get(Int32Ty, Idx1),
+                            ConstantInt::get(Int32Ty, Idx2)};
+      Constant *GEP = ConstantExpr::getGetElementPtr(
+          SwLDSMetadataStructType, SwLDSMetadata, GEPIdx, true);
+      Value *Load = IRB.CreateLoad(Int32Ty, GEP);
+      Value *BasePlusOffset =
+          IRB.CreateInBoundsGEP(IRB.getInt8Ty(), SwLDS, {Load});
+      LLVM_DEBUG(dbgs() << "Sw LDS Lowering, Replacing LDS "
+                        << GV->getName().str());
+      replacesUsesOfGlobalInFunction(Func, GV, BasePlusOffset);
+    }
+  };
+  ReplaceLDSGlobalUses(DirectAccess.StaticLDSGlobals);
+  ReplaceLDSGlobalUses(IndirectAccess.StaticLDSGlobals);
+  ReplaceLDSGlobalUses(DirectAccess.DynamicLDSGlobals);
+  ReplaceLDSGlobalUses(IndirectAccess.DynamicLDSGlobals);
+}
+
+void AMDGPUSwLowerLDS::lowerKernelLDSAccesses(Function *Func,
+                                              DomTreeUpdater &DTU) {
+  LLVM_DEBUG(dbgs() << "Sw Lowering Kernel LDS for : "
+                    << Func->getName().str());
+  auto &LDSParams = KernelToLDSParametersMap[Func];
+  auto &Ctx = M.getContext();
+  auto *PrevEntryBlock = &Func->getEntryBlock();
+
+  // Create malloc block.
+  auto *MallocBlock = BasicBlock::Create(Ctx, "Malloc", Func, PrevEntryBlock);
+
+  // Create WIdBlock block which has instructions related to selection of
+  // {0,0,0} indiex work item in the work group.
+  auto *WIdBlock = BasicBlock::Create(Ctx, "WId", Func, MallocBlock);
+  IRB.SetInsertPoint(WIdBlock, WIdBlock->begin());
+  auto *const WIdx =
+      IRB.CreateIntrinsic(Intrinsic::amdgcn_workitem_id_x, {}, {});
+  auto *const WIdy =
+      IRB.CreateIntrinsic(Intrinsic::amdgcn_workitem_id_y, {}, {});
+  auto *const WIdz =
+      IRB.CreateIntrinsic(Intrinsic::amdgcn_workitem_id_z, {}, {});
+  auto *const XYOr = IRB.CreateOr(WIdx, WIdy);
+  auto *const XYZOr = IRB.CreateOr(XYOr, WIdz);
+  auto *const WIdzCond = IRB.CreateICmpEQ(XYZOr, IRB.getInt32(0));
+
+  GlobalVariable *SwLDS = LDSParams.SwLDS;
+  GlobalVariable *SwLDSMetadata = LDSParams.SwLDSMetadata;
+  assert(SwLDS && SwLDSMetadata);
+  StructType *MetadataStructType =
+      cast<StructType>(SwLDSMetadata->getValueType());
+
+  // All work items will branch to PrevEntryBlock except {0,0,0} index
+  // work item which will branch to malloc block.
+  IRB.CreateCondBr(WIdzCond, MallocBlock, PrevEntryBlock);
+
+  // Malloc block
+  IRB.SetInsertPoint(MallocBlock, MallocBlock->begin());
+
+  // If Dynamic LDS globals are accessed by the kernel,
+  // Get the size of dyn lds from hidden dyn_lds_size kernel arg.
+  // Update the corresponding metadata global entries for this dyn lds global.
+  uint32_t MallocSize = 0;
+  Value *CurrMallocSize;
+
+  unsigned NumStaticLDS = LDSParams.DirectAccess.StaticLDSGlobals.size() +
+                          LDSParams.IndirectAccess.StaticLDSGlobals.size();
+  unsigned NumDynLDS = LDSParams.DirectAccess.DynamicLDSGlobals.size() +
+                       LDSParams.IndirectAccess.DynamicLDSGlobals.size();
+
+  if (NumStaticLDS) {
+    auto *GEPForEndStaticLDSOffset = IRB.CreateInBoundsGEP(
+        MetadataStructType, SwLDSMetadata,
+        {IRB.getInt32(0), IRB.getInt32(NumStaticLDS - 1), IRB.getInt32(0)});
+
+    auto *GEPForEndStaticLDSSize = IRB.CreateInBoundsGEP(
+        MetadataStructType, SwLDSMetadata,
+        {IRB.getInt32(0), IRB.getInt32(NumStaticLDS - 1), IRB.getInt32(2)});
+
+    Value *EndStaticLDSOffset =
+        IRB.CreateLoad(IRB.getInt64Ty(), GEPForEndStaticLDSOffset);
+    Value *EndStaticLDSSize =
+        IRB.CreateLoad(IRB.getInt64Ty(), GEPForEndStaticLDSSize);
+    CurrMallocSize = IRB.CreateAdd(EndStaticLDSOffset, EndStaticLDSSize);
+  } else
+    CurrMallocSize = IRB.getInt64(MallocSize);
+
+  if (NumDynLDS) {
+    unsigned MaxAlignment = SwLDS->getAlignment();
+    Value *MaxAlignValue = IRB.getInt64(MaxAlignment);
+    Value *MaxAlignValueMinusOne = IRB.getInt64(MaxAlignment - 1);
+
+    Value *ImplicitArg =
+        IRB.CreateIntrinsic(Intrinsic::amdgcn_implicitarg_ptr, {}, {});
+    Value *HiddenDynLDSSize = IRB.CreateInBoundsGEP(
+        ImplicitArg->getType(), ImplicitArg, {IRB.getInt32(15)});
+
+    auto MallocSizeCalcLambda =
+        [&](SetVector<GlobalVariable *> &DynamicLDSGlobals) {
+          for (GlobalVariable *DynGV : DynamicLDSGlobals) {
+            auto &Indices = LDSParams.LDSToReplacementIndicesMap[DynGV];
+
+            // Update the Offset metadata.
+            auto *GEPForOffset = IRB.CreateInBoundsGEP(
+                MetadataStructType, SwLDSMetadata,
+                {IRB.getInt32(0), IRB.getInt32(Indices[1]), IRB.getInt32(0)});
+            IRB.CreateStore(CurrMallocSize, GEPForOffset);
+
+            // Get size from hidden dyn_lds_size argument of kernel
+            // Update the size and Aligned Size metadata.
+            auto *GEPForSize = IRB.CreateInBoundsGEP(
+                MetadataStructType, SwLDSMetadata,
+                {IRB.getInt32(0), IRB.getInt32(Indices[1]), IRB.getInt32(1)});
+            Value *CurrDynLDSSize =
+                IRB.CreateLoad(IRB.getInt64Ty(), HiddenDynLDSSize);
+            IRB.CreateStore(CurrDynLDSSize, GEPForSize);
+
+            auto *GEPForAlignedSize = IRB.CreateInBoundsGEP(
+                MetadataStructType, SwLDSMetadata,
+                {IRB.getInt32(0), IRB.getInt32(Indices[1]), IRB.getInt32(2)});
+            Value *AlignedDynLDSSize =
+                IRB.CreateAdd(CurrDynLDSSize, MaxAlignValueMinusOne);
+            AlignedDynLDSSize =
+                IRB.CreateUDiv(AlignedDynLDSSize, MaxAlignValue);
+            AlignedDynLDSSize = IRB.CreateMul(AlignedDynLDSSize, MaxAlignValue);
+            IRB.CreateStore(AlignedDynLDSSize, GEPForAlignedSize);
+
+            // Update the Current Malloc Size
+            CurrMallocSize = IRB.CreateAdd(CurrMallocSize, AlignedDynLDSSize);
+          }
+        };
+    MallocSizeCalcLambda(LDSParams.DirectAccess.DynamicLDSGlobals);
+    MallocSizeCalcLambda(LDSParams.IndirectAccess.DynamicLDSGlobals);
+  }
+
+  // Create a call to malloc function which does device global memory allocation
+  // with size equals to all LDS global accesses size  in this kernel.
+  FunctionCallee AMDGPUMallocFunc = M.getOrInsertFunction(
+      StringRef("malloc"),
+      FunctionType::get(IRB.getPtrTy(1), {IRB.getInt64Ty()}, false));
+  Value *MCI = IRB.CreateCall(AMDGPUMallocFunc, {CurrMallocSize});
+
+  // create store of malloc to new global
+  IRB.CreateStore(MCI, SwLDS);
+
+  // Create branch to PrevEntryBlock
+  IRB.CreateBr(PrevEntryBlock);
+
+  // Create wave-group barrier at the starting of Previous entry block
+  Type *Int1Ty = IRB.getInt1Ty();
+  IRB.SetInsertPoint(PrevEntryBlock, PrevEntryBlock->begin());
+  auto *XYZCondPhi = IRB.CreatePHI(Int1Ty, 2, "xyzCond");
+  XYZCondPhi->addIncoming(IRB.getInt1(0), WIdBlock);
+  XYZCondPhi->addIncoming(IRB.getInt1(1), MallocBlock);
+
+  IRB.CreateIntrinsic(Intrinsic::amdgcn_s_barrier, {}, {});
+
+  replaceKernelLDSAccesses(Func);
+
+  auto *CondFreeBlock = BasicBlock::Create(Ctx, "CondFree", Func);
+  auto *FreeBlock = BasicBlock::Create(Ctx, "Free", Func);
+  auto *EndBlock = BasicBlock::Create(Ctx, "End", Func);
+  for (BasicBlock &BB : *Func) {
+    if (!BB.empty()) {
+      if (ReturnInst *RI = dyn_cast<ReturnInst>(&BB.back())) {
+        RI->eraseFromParent();
+        IRB.SetInsertPoint(&BB, BB.end());
+        IRB.CreateBr(CondFreeBlock);
+      }
+    }
+  }
+
+  // Cond Free Block
+  IRB.SetInsertPoint(CondFreeBlock, CondFreeBlock->begin());
+  IRB.CreateIntrinsic(Intrinsic::amdgcn_s_barrier, {}, {});
+  IRB.CreateCondBr(XYZCondPhi, FreeBlock, EndBlock);
+
+  // Free Block
+  IRB.SetInsertPoint(FreeBlock, FreeBlock->begin());
+
+  // Free the previously allocate device global memory.
+  FunctionCallee AMDGPUFreeReturn = M.getOrInsertFunction(
+      StringRef("free"),
+      FunctionType::get(IRB.getVoidTy(), {IRB.getPtrTy()}, false));
+
+  Value *MallocPtr = IRB.CreateLoad(IRB.getPtrTy(), SwLDS);
+  IRB.CreateCall(AMDGPUFreeReturn, {MallocPtr});
+  IRB.CreateBr(EndBlock);
+
+  // End Block
+  IRB.SetInsertPoint(EndBlock, EndBlock->begin());
+  IRB.CreateRetVoid();
+  // Update the DomTree with corresponding links to basic blocks.
+  DTU.applyUpdates({{DominatorTree::Insert, WIdBlock, MallocBlock},
+                    {DominatorTree::Insert, MallocBlock, PrevEntryBlock},
+                    {DominatorTree::Insert, CondFreeBlock, FreeBlock},
+                    {DominatorTree::Insert, FreeBlock, EndBlock}});
+}
+
+Constant *AMDGPUSwLowerLDS::getAddressesOfVariablesInKernel(
+    Function *Func, SetVector<GlobalVariable *> &Variables) {
+  Type *Int32Ty = IRB.getInt32Ty();
+  auto &LDSParams = KernelToLDSParametersMap[Func];
+
+  GlobalVariable *SwLDSMetadata = LDSParams.SwLDSMetadata;
+  assert(SwLDSMetadata);
+  auto *SwLDSMetadataStructType =
+      cast<StructType>(SwLDSMetadata->getValueType());
+  ArrayType *KernelOffsetsType = ArrayType::get(Int32Ty, Variables.size());
+
+  SmallVector<Constant *> Elements;
+  for (size_t i = 0; i < Variables.size(); i++) {
+    GlobalVariable *GV = Variables[i];
+    if (!LDSParams.LDSToReplacementIndicesMap.contains(GV)) {
+      Elements.push_back(PoisonValue::get(Int32Ty));
+      continue;
+    }
+    auto &Indices = LDSParams.LDSToReplacementIndicesMap[GV];
+    uint32_t Idx0 = Indices[0];
+    uint32_t Idx1 = Indices[1];
+    uint32_t Idx2 = Indices[2];
+    Constant *GEPIdx[] = {ConstantInt::get(Int32Ty, Idx0),
+                          ConstantInt::get(Int32Ty, Idx1),
+                          ConstantInt::get(Int32Ty, Idx2)};
+    Constant *GEP = ConstantExpr::getGetElementPtr(SwLDSMetadataStructType,
+                                                   SwLDSMetadata, GEPIdx, true);
+    auto elt = ConstantExpr::getPtrToInt(GEP, Int32Ty);
+    Elements.push_back(elt);
+  }
+  return ConstantArray::get(KernelOffsetsType, Elements);
+}
+
+void AMDGPUSwLowerLDS::buildNonKernelLDSBaseTable(
+    NonKernelLDSParameters &NKLDSParams) {
+  // Base table will have single row, with elements of the row
+  // placed as per kernel ID. Each element in the row corresponds
+  // to addresss of "SW LDS" global of the kernel.
+  auto &Kernels = NKLDSParams.OrderedKernels;
+  Type *Int32Ty = IRB.getInt32Ty();
+  const size_t NumberKernels = Kernels.size();
+  ArrayType *AllKernelsOffsetsType = ArrayType::get(Int32Ty, NumberKernels);
+  std::vector<Constant *> OverallConstantExprElts(NumberKernels);
+  for (size_t i = 0; i < NumberKernels; i++) {
+    Function *Func = Kernels[i];
+    auto &LDSParams = KernelToLDSParametersMap[Func];
+    GlobalVariable *SwLDS = LDSParams.SwLDS;
+    assert(SwLDS);
+    Constant *GEPIdx[] = {ConstantInt::get(Int32Ty, 0)};
+    Constant *GEP =
+        ConstantExpr::getGetElementPtr(SwLDS->getType(), SwLDS, GEPIdx, true);
+    auto Elt = ConstantExpr::getPtrToInt(GEP, Int32Ty);
+    OverallConstantExprElts[i] = Elt;
+  }
+  Constant *init =
+      ConstantArray::get(AllKernelsOffsetsType, OverallConstantExprElts);
+  NKLDSParams.LDSBaseTable = new GlobalVariable(
+      M, AllKernelsOffsetsType, true, GlobalValue::InternalLinkage, init,
+      "llvm.amdgcn.sw.lds.base.table", nullptr, GlobalValue::NotThreadLocal,
+      AMDGPUAS::CONSTANT_ADDRESS);
+}
+
+void AMDGPUSwLowerLDS::buildNonKernelLDSOffsetTable(
+    NonKernelLDSParameters &NKLDSParams) {
+  // Offset table will have multiple rows and columns.
+  // Rows are assumed to be from 0 to (n-1). n is total number
+  // of kernels accessing the LDS through non-kernels.
+  // Each row will have m elements. m is the total number of
+  // unique LDS globals accessed by non-kernels.
+  // Each element in the row correspond to the address of
+  // the replacement of LDS global done by that particular kernel.
+  auto &Variables = NKLDSParams.OrdereLDSGlobals;
+  auto &Kernels = NKLDSParams.OrderedKernels;
+  assert(!Variables.empty());
+  assert(!Kernels.empty());
+  const size_t NumberVariables = Variables.size();
+  const size_t NumberKernels = Kernels.size();
+
+  ArrayType *KernelOffsetsType =
+      ArrayType::get(IRB.getInt32Ty(), NumberVariables);
+
+  ArrayType *AllKernelsOffsetsType =
+      ArrayType::get(KernelOffsetsType, NumberKernels);
+  std::vector<Constant *> overallConstantExprElts(NumberKernels);
+  for (size_t i = 0; i < NumberKernels; i++) {
+    Function *Func = Kernels[i];
+    overallConstantExprElts[i] =
+        getAddressesOfVariablesInKernel(Func, Variables);
+  }
+  Constant *Init =
+      ConstantArray::get(AllKernelsOffsetsType, overallConstantExprElts);
+  NKLDSParams.LDSOffsetTable = new GlobalVariable(
+      M, AllKernelsOffsetsType, true, GlobalValue::InternalLinkage, Init,
+      "llvm.amdgcn.sw.lds.offset.table", nullptr, GlobalValue::NotThreadLocal,
+      AMDGPUAS::CONSTANT_ADDRESS);
+}
+
+void AMDGPUSwLowerLDS::lowerNonKernelLDSAccesses(
+    Function *Func, SetVector<GlobalVariable *> &LDSGlobals,
+    NonKernelLDSParameters &NKLDSParams) {
+  // Replace LDS access in non-kernel with replacement queried from
+  // Base table and offset from offset table.
+  LLVM_DEBUG(dbgs() << "Sw LDS lowering, lower non-kernel access for : "
+                    << Func->getName().str());
+  auto *EntryBlock = &Func->getEntryBlock();
+  IRB.SetInsertPoint(EntryBlock, EntryBlock->begin());
+  Function *Decl =
+      Intrinsic::getDeclaration(&M, Intrinsic::amdgcn_lds_kernel_id, {});
+  auto *KernelId = IRB.CreateCall(Decl, {});
+  GlobalVariable *LDSBaseTable = NKLDSParams.LDSBaseTable;
+  GlobalVariable *LDSOffsetTable = NKLDSParams.LDSOffsetTable;
+  auto &OrdereLDSGlobals = NKLDSParams.OrdereLDSGlobals;
+  assert(LDSBaseTable && LDSOffsetTable);
+  Value *BaseGEP = IRB.CreateInBoundsGEP(
+      LDSBaseTable->getValueType(), LDSBaseTable, {IRB.getInt32(0), KernelId});
+  Value *BaseLoad = IRB.CreateLoad(IRB.getInt32Ty(), BaseGEP);
+
+  for (GlobalVariable *GV : LDSGlobals) {
+    Value *BasePtr = IRB.CreateIntToPtr(BaseLoad, GV->getType());
+    auto GVIt = std::find(OrdereLDSGlobals.begin(), OrdereLDSGlobals.end(), GV);
+    assert(GVIt != OrdereLDSGlobals.end());
+    uint32_t GVOffset = std::distance(OrdereLDSGlobals.begin(), GVIt);
+    Value *OffsetGEP = IRB.CreateInBoundsGEP(
+        LDSOffsetTable->getValueType(), LDSOffsetTable,
+        {IRB.getInt32(0), KernelId, IRB.getInt32(GVOffset)});
+    Value *OffsetLoad = IRB.CreateLoad(IRB.getInt32Ty(), OffsetGEP);
+    OffsetLoad = IRB.CreateIntToPtr(OffsetLoad, GV->getType());
+    OffsetLoad = IRB.CreateLoad(IRB.getInt32Ty(), OffsetLoad);
+    Value *BasePlusOffset =
+        IRB.CreateInBoundsGEP(IRB.getInt8Ty(), BasePtr, {OffsetLoad});
+    LLVM_DEBUG(dbgs() << "Sw LDS Lowering, Replace non-kernel LDS for "
+                      << GV->getName().str());
+    replacesUsesOfGlobalInFunction(Func, GV, BasePlusOffset);
+  }
+}
+
+static void reorderStaticDynamicIndirectLDSSet(KernelLDSParameters &LDSParams) {
+  // Sort Static, dynamic LDS globals which are either
+  // direct or indirect access on basis of name.
+  auto &DirectAccess = LDSParams.DirectAccess;
+  auto &IndirectAccess = LDSParams.IndirectAccess;
+  LDSParams.DirectAccess.StaticLDSGlobals = sortByName(
+      std::vector<GlobalVariable *>(DirectAccess.StaticLDSGlobals.begin(),
+                                    DirectAccess.StaticLDSGlobals.end()));
+  LDSParams.DirectAccess.DynamicLDSGlobals = sortByName(
+      std::vector<GlobalVariable *>(DirectAccess.DynamicLDSGlobals.begin(),
+                                    DirectAccess.DynamicLDSGlobals.end()));
+  LDSParams.IndirectAccess.StaticLDSGlobals = sortByName(
+      std::vector<GlobalVariable *>(IndirectAccess.StaticLDSGlobals.begin(),
+                                    IndirectAccess.StaticLDSGlobals.end()));
+  LDSParams.IndirectAccess.DynamicLDSGlobals = sortByName(
+      std::vector<GlobalVariable *>(IndirectAccess.DynamicLDSGlobals.begin(),
+                                    IndirectAccess.DynamicLDSGlobals.end()));
+}
+
+bool AMDGPUSwLowerLDS::run() {
+  bool Changed = false;
+  CallGraph CG = CallGraph(M);
+  SetVector<Function *> KernelsWithIndirectLDSAccess;
+  FunctionVariableMap NonKernelToLDSAccessMap;
+  SetVector<GlobalVariable *> AllNonKernelLDSAccess;
+
+  Changed |= eliminateConstantExprUsesOfLDSFromAllInstructions(M);
+
+  // Get all the direct and indirect access of LDS for all the kernels.
+  LDSUsesInfoTy LDSUsesInfo = getTransitiveUsesOfLDS(CG, M);
+
+  // Get the Uses of LDS from non-kernels.
+  getUsesOfLDSByNonKernels(CG, NonKernelToLDSAccessMap);
+
+  // Utility to group LDS access into direct, indirect, static and dynamic.
+  auto PopulateKernelStaticDynamicLDS = [&](FunctionVariableMap &LDSAccesses,
+                                            bool DirectAccess) {
+    for (auto &K : LDSAccesses) {
+      Function *F = K.first;
+      assert(isKernelLDS(F));
+
+      if (!KernelToLDSParametersMap.contains(F)) {
+        KernelLDSParameters KernelLDSParams;
+        KernelToLDSParametersMap[F] = KernelLDSParams;
+      }
+
+      auto &LDSParams = KernelToLDSParametersMap[F];
+      if (!DirectAccess)
+        KernelsWithIndirectLDSAccess.insert(F);
+      for (GlobalVariable *GV : K.second) {
+        if (!DirectAccess) {
+          if (AMDGPU::isDynamicLDS(*GV))
+            LDSParams.IndirectAccess.DynamicLDSGlobals.insert(GV);
+          else
+            LDSParams.IndirectAccess.StaticLDSGlobals.insert(GV);
+          AllNonKernelLDSAccess.insert(GV);
+        } else {
+          if (AMDGPU::isDynamicLDS(*GV))
+            LDSParams.DirectAccess.DynamicLDSGlobals.insert(GV);
+          else
+            LDSParams.DirectAccess.StaticLDSGlobals.insert(GV);
+        }
+      }
+    }
+  };
+
+  PopulateKernelStaticDynamicLDS(LDSUsesInfo.direct_access, true);
+  PopulateKernelStaticDynamicLDS(LDSUsesInfo.indirect_access, false);
+
+  for (auto &K : KernelToLDSParametersMap) {
+    Function *Func = K.first;
+    auto &LDSParams = KernelToLDSParametersMap[Func];
+    if (LDSParams.DirectAccess.StaticLDSGlobals.empty() &&
+        LDSParams.DirectAccess.DynamicLDSGlobals.empty() &&
+        LDSParams.IndirectAccess.StaticLDSGlobals.empty() &&
+        LDSParams.IndirectAccess.DynamicLDSGlobals.empty()) {
+      Changed = false;
+    } else {
+      removeFnAttrFromReachable(CG, Func, "amdgpu-no-workitem-id-x");
+      removeFnAttrFromReachable(CG, Func, "amdgpu-no-workitem-id-y");
+      removeFnAttrFromReachable(CG, Func, "amdgpu-no-workitem-id-z");
+      reorderStaticDynamicIndirectLDSSet(LDSParams);
+      populateSwLDSGlobal(Func);
+      populateSwMetadataGlobal(Func);
+      populateLDSToReplacementIndicesMap(Func);
+      DomTreeUpdater DTU(DTCallback(*Func),
+                         DomTreeUpdater::UpdateStrategy::Lazy);
+      lowerKernelLDSAccesses(Func, DTU);
+      Changed = true;
+    }
+  }
+
+  NonKernelLDSParameters NKLDSParams;
+  if (!NonKernelToLDSAccessMap.empty()) {
+    NKLDSParams.OrderedKernels = getOrderedIndirectLDSAccessingKernels(
+        std::move(KernelsWithIndirectLDSAccess));
+    NKLDSParams.OrdereLDSGlobals =
+        getOrderedNonKernelAllLDSGlobals(std::move(AllNonKernelLDSAccess));
+    assert(!NKLDSParams.OrderedKernels.empty());
+    assert(!NKLDSParams.OrdereLDSGlobals.empty());
+    buildNonKernelLDSBaseTable(NKLDSParams);
+    buildNonKernelLDSOffsetTable(NKLDSParams);
+    for (auto &K : NonKernelToLDSAccessMap) {
+      Function *Func = K.first;
+      DenseSet<GlobalVariable *> &LDSGlobals = K.second;
+      SetVector<GlobalVariable *> OrderedLDSGlobals = sortByName(
+          std::vector<GlobalVariable *>(LDSGlobals.begin(), LDSGlobals.end()));
+      lowerNonKernelLDSAccesses(Func, OrderedLDSGlobals, NKLDSParams);
+    }
+  }
+  return Changed;
+}
+
+class AMDGPUSwLowerLDSLegacy : public ModulePass {
+public:
+  static char ID;
+  AMDGPUSwLowerLDSLegacy() : ModulePass(ID) {}
+  bool runOnModule(Module &M) override;
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addPreserved<DominatorTreeWrapperPass>();
+  }
+};
+} // namespace
+
+char AMDGPUSwLowerLDSLegacy::ID = 0;
+char &llvm::AMDGPUSwLowerLDSLegacyPassID = AMDGPUSwLowerLDSLegacy::ID;
+
+INITIALIZE_PASS(AMDGPUSwLowerLDSLegacy, "amdgpu-sw-lower-lds",
+                "AMDGPU Software lowering of LDS", false, false)
+
+bool AMDGPUSwLowerLDSLegacy::runOnModule(Module &M) {
+  DominatorTreeWrapperPass *const DTW =
+      getAnalysisIfAvailable<DominatorTreeWrapperPass>();
+  auto DTCallback = [&DTW](Function &F) -> DominatorTree * {
+    return DTW ? &DTW->getDomTree() : nullptr;
+  };
+  bool IsChanged = false;
+  AMDGPUSwLowerLDS SwLowerLDSImpl(M, DTCallback);
+  IsChanged |= SwLowerLDSImpl.run();
+  return IsChanged;
+}
+
+ModulePass *llvm::createAMDGPUSwLowerLDSLegacyPass() {
+  return new AMDGPUSwLowerLDSLegacy();
+}
+
+PreservedAnalyses AMDGPUSwLowerLDSPass::run(Module &M,
+                                            ModuleAnalysisManager &AM) {
+  auto &FAM = AM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
+  auto DTCallback = [&FAM](Function &F) -> DominatorTree * {
+    return &FAM.getResult<DominatorTreeAnalysis>(F);
+  };
+  bool IsChanged = false;
+  AMDGPUSwLowerLDS SwLowerLDSImpl(M, DTCallback);
+  IsChanged |= SwLowerLDSImpl.run();
+  if (!IsChanged)
+    return PreservedAnalyses::all();
+
+  PreservedAnalyses PA;
+  PA.preserve<DominatorTreeAnalysis>();
+  return PA;
+}
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 305a6c8c3b926..6d75a634c82f0 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -402,6 +402,7 @@ extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
   initializeSILoadStoreOptimizerPass(*PR);
   initializeAMDGPUCtorDtorLoweringLegacyPass(*PR);
   initializeAMDGPUAlwaysInlinePass(*PR);
+  initializeAMDGPUSwLowerLDSLegacyPass(*PR);
   initializeAMDGPUAttributorLegacyPass(*PR);
   initializeAMDGPUAnnotateKernelFeaturesPass(*PR);
   initializeAMDGPUAnnotateUniformValuesPass(*PR);
diff --git a/llvm/lib/Target/AMDGPU/CMakeLists.txt b/llvm/lib/Target/AMDGPU/CMakeLists.txt
index 48325a0928f93..139a416d50f29 100644
--- a/llvm/lib/Target/AMDGPU/CMakeLists.txt
+++ b/llvm/lib/Target/AMDGPU/CMakeLists.txt
@@ -73,6 +73,7 @@ add_llvm_target(AMDGPUCodeGen
   AMDGPULowerKernelArguments.cpp
   AMDGPULowerKernelAttributes.cpp
   AMDGPULowerModuleLDSPass.cpp
+  AMDGPUSwLowerLDS.cpp
   AMDGPUMachineCFGStructurizer.cpp
   AMDGPUMachineFunction.cpp
   AMDGPUMachineModuleInfo.cpp
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.cpp
index 79c359a575545..8ff041ee14b40 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.cpp
@@ -9,13 +9,16 @@
 #include "AMDGPUMemoryUtils.h"
 #include "AMDGPU.h"
 #include "AMDGPUBaseInfo.h"
+#include "llvm/ADT/SetOperations.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/Analysis/AliasAnalysis.h"
+#include "llvm/Analysis/CallGraph.h"
 #include "llvm/Analysis/MemorySSA.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/IntrinsicsAMDGPU.h"
+#include "llvm/IR/Operator.h"
 #include "llvm/IR/ReplaceConstant.h"
 
 #define DEBUG_TYPE "amdgpu-memory-utils"
@@ -61,6 +64,219 @@ bool isLDSVariableToLower(const GlobalVariable &GV) {
   return true;
 }
 
+bool eliminateConstantExprUsesOfLDSFromAllInstructions(Module &M) {
+  // Constants are uniqued within LLVM. A ConstantExpr referring to a LDS
+  // global may have uses from multiple different functions as a result.
+  // This pass specialises LDS variables with respect to the kernel that
+  // allocates them.
+
+  // This is semantically equivalent to (the unimplemented as slow):
+  // for (auto &F : M.functions())
+  //   for (auto &BB : F)
+  //     for (auto &I : BB)
+  //       for (Use &Op : I.operands())
+  //         if (constantExprUsesLDS(Op))
+  //           replaceConstantExprInFunction(I, Op);
+
+  SmallVector<Constant *> LDSGlobals;
+  for (auto &GV : M.globals())
+    if (AMDGPU::isLDSVariableToLower(GV))
+      LDSGlobals.push_back(&GV);
+  return convertUsersOfConstantsToInstructions(LDSGlobals);
+}
+
+void getUsesOfLDSByFunction(CallGraph const &CG, Module &M,
+                            FunctionVariableMap &kernels,
+                            FunctionVariableMap &functions) {
+  // Get uses from the current function, excluding uses by called functions
+  // Two output variables to avoid walking the globals list twice
+  for (auto &GV : M.globals()) {
+    if (!AMDGPU::isLDSVariableToLower(GV)) {
+      continue;
+    }
+    for (User *V : GV.users()) {
+      if (auto *I = dyn_cast<Instruction>(V)) {
+        Function *F = I->getFunction();
+        if (isKernelLDS(F)) {
+          kernels[F].insert(&GV);
+        } else {
+          functions[F].insert(&GV);
+        }
+      }
+    }
+  }
+}
+
+bool isKernelLDS(const Function *F) {
+  // Some weirdness here. AMDGPU::isKernelCC does not call into
+  // AMDGPU::isKernel with the calling conv, it instead calls into
+  // isModuleEntryFunction which returns true for more calling conventions
+  // than AMDGPU::isKernel does. There's a FIXME on AMDGPU::isKernel.
+  // There's also a test that checks that the LDS lowering does not hit on
+  // a graphics shader, denoted amdgpu_ps, so stay with the limited case.
+  // Putting LDS in the name of the function to draw attention to this.
+  return AMDGPU::isKernel(F->getCallingConv());
+}
+
+LDSUsesInfoTy getTransitiveUsesOfLDS(CallGraph const &CG, Module &M) {
+
+  FunctionVariableMap direct_map_kernel;
+  FunctionVariableMap direct_map_function;
+  getUsesOfLDSByFunction(CG, M, direct_map_kernel, direct_map_function);
+
+  // Collect variables that are used by functions whose address has escaped
+  DenseSet<GlobalVariable *> VariablesReachableThroughFunctionPointer;
+  for (Function &F : M.functions()) {
+    if (!isKernelLDS(&F))
+      if (F.hasAddressTaken(nullptr,
+                            /* IgnoreCallbackUses */ false,
+                            /* IgnoreAssumeLikeCalls */ false,
+                            /* IgnoreLLVMUsed */ true,
+                            /* IgnoreArcAttachedCall */ false)) {
+        set_union(VariablesReachableThroughFunctionPointer,
+                  direct_map_function[&F]);
+      }
+  }
+
+  auto functionMakesUnknownCall = [&](const Function *F) -> bool {
+    assert(!F->isDeclaration());
+    for (const CallGraphNode::CallRecord &R : *CG[F]) {
+      if (!R.second->getFunction()) {
+        return true;
+      }
+    }
+    return false;
+  };
+
+  // Work out which variables are reachable through function calls
+  FunctionVariableMap transitive_map_function = direct_map_function;
+
+  // If the function makes any unknown call, assume the worst case that it can
+  // access all variables accessed by functions whose address escaped
+  for (Function &F : M.functions()) {
+    if (!F.isDeclaration() && functionMakesUnknownCall(&F)) {
+      if (!isKernelLDS(&F)) {
+        set_union(transitive_map_function[&F],
+                  VariablesReachableThroughFunctionPointer);
+      }
+    }
+  }
+
+  // Direct implementation of collecting all variables reachable from each
+  // function
+  for (Function &Func : M.functions()) {
+    if (Func.isDeclaration() || isKernelLDS(&Func))
+      continue;
+
+    DenseSet<Function *> seen; // catches cycles
+    SmallVector<Function *, 4> wip{&Func};
+
+    while (!wip.empty()) {
+      Function *F = wip.pop_back_val();
+
+      // Can accelerate this by referring to transitive map for functions that
+      // have already been computed, with more care than this
+      set_union(transitive_map_function[&Func], direct_map_function[F]);
+
+      for (const CallGraphNode::CallRecord &R : *CG[F]) {
+        Function *ith = R.second->getFunction();
+        if (ith) {
+          if (!seen.contains(ith)) {
+            seen.insert(ith);
+            wip.push_back(ith);
+          }
+        }
+      }
+    }
+  }
+
+  // direct_map_kernel lists which variables are used by the kernel
+  // find the variables which are used through a function call
+  FunctionVariableMap indirect_map_kernel;
+
+  for (Function &Func : M.functions()) {
+    if (Func.isDeclaration() || !isKernelLDS(&Func))
+      continue;
+
+    for (const CallGraphNode::CallRecord &R : *CG[&Func]) {
+      Function *ith = R.second->getFunction();
+      if (ith) {
+        set_union(indirect_map_kernel[&Func], transitive_map_function[ith]);
+      } else {
+        set_union(indirect_map_kernel[&Func],
+                  VariablesReachableThroughFunctionPointer);
+      }
+    }
+  }
+
+  // Verify that we fall into one of 2 cases:
+  //    - All variables are absolute: this is a re-run of the pass
+  //      so we don't have anything to do.
+  //    - No variables are absolute.
+  std::optional<bool> HasAbsoluteGVs;
+  for (auto &Map : {direct_map_kernel, indirect_map_kernel}) {
+    for (auto &[Fn, GVs] : Map) {
+      for (auto *GV : GVs) {
+        bool IsAbsolute = GV->isAbsoluteSymbolRef();
+        if (HasAbsoluteGVs.has_value()) {
+          if (*HasAbsoluteGVs != IsAbsolute) {
+            report_fatal_error(
+                "Module cannot mix absolute and non-absolute LDS GVs");
+          }
+        } else
+          HasAbsoluteGVs = IsAbsolute;
+      }
+    }
+  }
+
+  // If we only had absolute GVs, we have nothing to do, return an empty
+  // result.
+  if (HasAbsoluteGVs && *HasAbsoluteGVs)
+    return {FunctionVariableMap(), FunctionVariableMap()};
+
+  return {std::move(direct_map_kernel), std::move(indirect_map_kernel)};
+}
+
+void removeFnAttrFromReachable(CallGraph &CG, Function *KernelRoot,
+                               StringRef FnAttr) {
+  KernelRoot->removeFnAttr(FnAttr);
+
+  SmallVector<Function *> WorkList({CG[KernelRoot]->getFunction()});
+  SmallPtrSet<Function *, 8> Visited;
+  bool SeenUnknownCall = false;
+
+  while (!WorkList.empty()) {
+    Function *F = WorkList.pop_back_val();
+
+    for (auto &CallRecord : *CG[F]) {
+      if (!CallRecord.second)
+        continue;
+
+      Function *Callee = CallRecord.second->getFunction();
+      if (!Callee) {
+        if (!SeenUnknownCall) {
+          SeenUnknownCall = true;
+
+          // If we see any indirect calls, assume nothing about potential
+          // targets.
+          // TODO: This could be refined to possible LDS global users.
+          for (auto &ExternalCallRecord : *CG.getExternalCallingNode()) {
+            Function *PotentialCallee =
+                ExternalCallRecord.second->getFunction();
+            assert(PotentialCallee);
+            if (!isKernelLDS(PotentialCallee))
+              PotentialCallee->removeFnAttr(FnAttr);
+          }
+        }
+      } else {
+        Callee->removeFnAttr(FnAttr);
+        if (Visited.insert(Callee).second)
+          WorkList.push_back(Callee);
+      }
+    }
+  }
+}
+
 bool isReallyAClobber(const Value *Ptr, MemoryDef *Def, AAResults *AA) {
   Instruction *DefInst = Def->getMemoryInst();
 
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.h
index e42b27f8e09e1..1df9c28e65888 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.h
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUMemoryUtils.h
@@ -9,6 +9,9 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUMEMORYUTILS_H
 #define LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUMEMORYUTILS_H
 
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/DenseSet.h"
+
 namespace llvm {
 
 struct Align;
@@ -19,14 +22,40 @@ class LoadInst;
 class MemoryDef;
 class MemorySSA;
 class Value;
+class Function;
+class CallGraph;
+class Module;
 
 namespace AMDGPU {
 
+using FunctionVariableMap = DenseMap<Function *, DenseSet<GlobalVariable *>>;
+using VariableFunctionMap = DenseMap<GlobalVariable *, DenseSet<Function *>>;
+
 Align getAlign(DataLayout const &DL, const GlobalVariable *GV);
 
 bool isDynamicLDS(const GlobalVariable &GV);
 bool isLDSVariableToLower(const GlobalVariable &GV);
 
+struct LDSUsesInfoTy {
+  FunctionVariableMap direct_access;
+  FunctionVariableMap indirect_access;
+};
+
+bool eliminateConstantExprUsesOfLDSFromAllInstructions(Module &M);
+
+void getUsesOfLDSByFunction(CallGraph const &CG, Module &M,
+                            FunctionVariableMap &kernels,
+                            FunctionVariableMap &functions);
+
+bool isKernelLDS(const Function *F);
+
+LDSUsesInfoTy getTransitiveUsesOfLDS(CallGraph const &CG, Module &M);
+
+/// Strip FnAttr attribute from any functions where we may have
+/// introduced its use.
+void removeFnAttrFromReachable(CallGraph &CG, Function *KernelRoot,
+                               StringRef FnAttr);
+
 /// Given a \p Def clobbering a load from \p Ptr according to the MSSA check
 /// if this is actually a memory update or an artificial clobber to facilitate
 /// ordering constraints.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-indirect-access.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-indirect-access.ll
new file mode 100644
index 0000000000000..3ac43caebd918
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-indirect-access.ll
@@ -0,0 +1,100 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check indirect dynamic LDS access through a non-kernel from kernel is lowered correctly.
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 1
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, align 2
+ at lds_3 = external addrspace(3) global [0 x i8], align 4
+ at lds_4 = external addrspace(3) global [0 x i8], align 8
+
+define void @use_variables() {
+; CHECK-LABEL: define void @use_variables() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [1 x i32], ptr addrspace(4) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr addrspace(4) [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [1 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(4) [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr i32 [[TMP6]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [1 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
+; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(4) [[TMP11]], align 4
+; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i32 [[TMP12]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP10]], i32 [[TMP14]]
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP9]], align 4
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP15]], align 8
+; CHECK-NEXT:    ret void
+;
+  store i8 3, ptr addrspace(3) @lds_3, align 4
+  store i8 3, ptr addrspace(3) @lds_4, align 8
+  ret void
+}
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META0:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP21:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP13:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP27:%.*]] = add i64 [[TMP13]], [[TMP14]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP6]], i32 15
+; CHECK-NEXT:    store i64 [[TMP27]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP11]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 1), align 8
+; CHECK-NEXT:    [[TMP19:%.*]] = add i64 [[TMP11]], 7
+; CHECK-NEXT:    [[TMP28:%.*]] = udiv i64 [[TMP19]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP28]], 8
+; CHECK-NEXT:    store i64 [[TMP8]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 2), align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP27]], [[TMP8]]
+; CHECK-NEXT:    store i64 [[TMP12]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 0), align 8
+; CHECK-NEXT:    [[TMP29:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP29]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 1), align 8
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[TMP29]], 7
+; CHECK-NEXT:    [[TMP18:%.*]] = udiv i64 [[TMP17]], 8
+; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP18]], 8
+; CHECK-NEXT:    store i64 [[TMP15]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 2), align 8
+; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[TMP12]], [[TMP15]]
+; CHECK-NEXT:    [[TMP20:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP16]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP20]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    br label [[TMP21]]
+; CHECK:       22:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP22:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 4
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP22]]
+; CHECK-NEXT:    [[TMP24:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP24]]
+; CHECK-NEXT:    call void @use_variables()
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP23]], align 1
+; CHECK-NEXT:    store i32 8, ptr addrspace(3) [[TMP25]], align 2
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP26:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP26]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  call void @use_variables()
+  store i8 7, ptr addrspace(3) @lds_1, align 1
+  store i32 8, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+;.
+; CHECK: [[META0]] = !{i32 0}
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-lds-test.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-lds-test.ll
new file mode 100644
index 0000000000000..ecb02d5cb5ebc
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-dynamic-lds-test.ll
@@ -0,0 +1,63 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if direct access of dynamic LDS in kernel is lowered correctly.
+ at lds_1 = external addrspace(3) global [0 x i8]
+ at lds_2 = external addrspace(3) global [0 x i8]
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0() {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP7:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP20:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP20]], i32 15
+; CHECK-NEXT:    store i64 0, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 8
+; CHECK-NEXT:    [[TMP16:%.*]] = load i64, ptr addrspace(4) [[TMP21]], align 8
+; CHECK-NEXT:    store i64 [[TMP16]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 0, i32 1), align 8
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[TMP16]], 0
+; CHECK-NEXT:    [[TMP18:%.*]] = udiv i64 [[TMP17]], 1
+; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP18]], 1
+; CHECK-NEXT:    store i64 [[TMP22]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 0, i32 2), align 8
+; CHECK-NEXT:    [[TMP23:%.*]] = add i64 0, [[TMP22]]
+; CHECK-NEXT:    store i64 [[TMP23]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP13:%.*]] = load i64, ptr addrspace(4) [[TMP21]], align 8
+; CHECK-NEXT:    store i64 [[TMP13]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 1), align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[TMP13]], 0
+; CHECK-NEXT:    [[TMP24:%.*]] = udiv i64 [[TMP14]], 1
+; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP24]], 1
+; CHECK-NEXT:    store i64 [[TMP15]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP19:%.*]] = add i64 [[TMP23]], [[TMP15]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP19]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    br label [[TMP7]]
+; CHECK:       19:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP10]]
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP9]], align 4
+; CHECK-NEXT:    store i8 8, ptr addrspace(3) [[TMP11]], align 8
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP12:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP12]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  store i8 7, ptr addrspace(3) @lds_1, align 4
+  store i8 8, ptr addrspace(3) @lds_2, align 8
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multi-static-dynamic-indirect-access.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multi-static-dynamic-indirect-access.ll
new file mode 100644
index 0000000000000..a31553a98138b
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multi-static-dynamic-indirect-access.ll
@@ -0,0 +1,194 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check when multiple  kernels access the same non-kernel, LDS accesses are lowere correctly.
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 1
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, align 2
+ at lds_3 = external addrspace(3) global [0 x i8], align 4
+ at lds_4 = external addrspace(3) global [0 x i8], align 8
+
+define void @use_variables_1() {
+; CHECK-LABEL: define void @use_variables_1() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [2 x i32], ptr addrspace(4) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr addrspace(4) [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [2 x [4 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 2
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(4) [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr i32 [[TMP6]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [2 x [4 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 3
+; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(4) [[TMP11]], align 4
+; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i32 [[TMP12]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP10]], i32 [[TMP14]]
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP9]], align 4
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP15]], align 8
+; CHECK-NEXT:    ret void
+;
+  store i8 3, ptr addrspace(3) @lds_3, align 4
+  store i8 3, ptr addrspace(3) @lds_4, align 8
+  ret void
+}
+
+define void @use_variables_2() {
+; CHECK-LABEL: define void @use_variables_2() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [2 x i32], ptr addrspace(4) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr addrspace(4) [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [2 x [4 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(4) [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr i32 [[TMP6]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [2 x [4 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
+; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(4) [[TMP11]], align 4
+; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i32 [[TMP12]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP10]], i32 [[TMP14]]
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP9]], align 1
+; CHECK-NEXT:    store i32 8, ptr addrspace(3) [[TMP15]], align 2
+; CHECK-NEXT:    ret void
+;
+  store i8 7, ptr addrspace(3) @lds_1, align 1
+  store i32 8, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META0:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP21:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP13:%.*]] = load i64, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 0, i32 2), align 8
+; CHECK-NEXT:    [[TMP25:%.*]] = add i64 [[TMP13]], [[TMP14]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP6]], i32 15
+; CHECK-NEXT:    store i64 [[TMP25]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP11]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 1), align 8
+; CHECK-NEXT:    [[TMP19:%.*]] = add i64 [[TMP11]], 7
+; CHECK-NEXT:    [[TMP26:%.*]] = udiv i64 [[TMP19]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP26]], 8
+; CHECK-NEXT:    store i64 [[TMP8]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP25]], [[TMP8]]
+; CHECK-NEXT:    store i64 [[TMP12]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 8
+; CHECK-NEXT:    [[TMP27:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP27]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 1), align 8
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[TMP27]], 7
+; CHECK-NEXT:    [[TMP18:%.*]] = udiv i64 [[TMP17]], 8
+; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP18]], 8
+; CHECK-NEXT:    store i64 [[TMP15]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 2), align 8
+; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[TMP12]], [[TMP15]]
+; CHECK-NEXT:    [[TMP20:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP16]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP20]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    br label [[TMP21]]
+; CHECK:       22:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP22:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 4
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP22]]
+; CHECK-NEXT:    call void @use_variables_1()
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP23]], align 1
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP24:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP24]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  call void @use_variables_1()
+  store i8 7, ptr addrspace(3) @lds_1, align 1
+  ret void
+}
+
+define amdgpu_kernel void @k1() {
+; CHECK-LABEL: define amdgpu_kernel void @k1(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META1:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP14:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP20:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP21:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP27:%.*]] = add i64 [[TMP20]], [[TMP21]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP6]], i32 15
+; CHECK-NEXT:    store i64 [[TMP27]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 0), align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP11]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 1), align 8
+; CHECK-NEXT:    [[TMP19:%.*]] = add i64 [[TMP11]], 7
+; CHECK-NEXT:    [[TMP24:%.*]] = udiv i64 [[TMP19]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP24]], 8
+; CHECK-NEXT:    store i64 [[TMP8]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 2), align 8
+; CHECK-NEXT:    [[TMP26:%.*]] = add i64 [[TMP27]], [[TMP8]]
+; CHECK-NEXT:    store i64 [[TMP26]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 0), align 8
+; CHECK-NEXT:    [[TMP25:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP25]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 1), align 8
+; CHECK-NEXT:    [[TMP28:%.*]] = add i64 [[TMP25]], 7
+; CHECK-NEXT:    [[TMP18:%.*]] = udiv i64 [[TMP28]], 8
+; CHECK-NEXT:    [[TMP29:%.*]] = mul i64 [[TMP18]], 8
+; CHECK-NEXT:    store i64 [[TMP29]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 2), align 8
+; CHECK-NEXT:    [[TMP30:%.*]] = add i64 [[TMP26]], [[TMP29]]
+; CHECK-NEXT:    store i64 [[TMP30]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 4, i32 0), align 8
+; CHECK-NEXT:    [[TMP33:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP33]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 4, i32 1), align 8
+; CHECK-NEXT:    [[TMP34:%.*]] = add i64 [[TMP33]], 7
+; CHECK-NEXT:    [[TMP23:%.*]] = udiv i64 [[TMP34]], 8
+; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP23]], 8
+; CHECK-NEXT:    store i64 [[TMP22]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 4, i32 2), align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP30]], [[TMP22]]
+; CHECK-NEXT:    [[TMP13:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP12]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP13]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k1, align 8
+; CHECK-NEXT:    br label [[TMP14]]
+; CHECK:       27:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP15:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 0), align 4
+; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k1, i32 [[TMP15]]
+; CHECK-NEXT:    [[TMP31:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k1.md, i32 0, i32 3, i32 0), align 4
+; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k1, i32 [[TMP31]]
+; CHECK-NEXT:    call void @use_variables_1()
+; CHECK-NEXT:    call void @use_variables_2()
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP16]], align 4
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP17:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k1, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP17]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  call void @use_variables_1()
+  call void @use_variables_2()
+  store i8 3, ptr addrspace(3) @lds_3, align 4
+  ret void
+}
+;.
+; CHECK: [[META0]] = !{i32 0}
+; CHECK: [[META1]] = !{i32 1}
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multiple-blocks-return.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multiple-blocks-return.ll
new file mode 100644
index 0000000000000..5222c3ae528cc
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-multiple-blocks-return.ll
@@ -0,0 +1,79 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check malloc and free blocks are placed correctly when multiple
+; blocks and branching is present in the function with LDS accesses lowered correctly.
+
+ at lds_1 = internal addrspace(3) global i32 poison
+ at lds_2 = internal addrspace(3) global i32 poison
+
+define amdgpu_kernel void @test_kernel() {
+; CHECK-LABEL: define amdgpu_kernel void @test_kernel() {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP7:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP15:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_TEST_KERNEL_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.test_kernel.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP16:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_TEST_KERNEL_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.test_kernel.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[TMP15]], [[TMP16]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP17]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.test_kernel, align 8
+; CHECK-NEXT:    br label [[TMP7]]
+; CHECK:       10:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.test_kernel.md, align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.test_kernel, i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_TEST_KERNEL_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.test_kernel.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.test_kernel, i32 [[TMP10]]
+; CHECK-NEXT:    [[TMP12:%.*]] = addrspacecast ptr addrspace(3) [[TMP9]] to ptr addrspace(1)
+; CHECK-NEXT:    [[VAL1:%.*]] = load i32, ptr addrspace(1) [[TMP12]], align 4
+; CHECK-NEXT:    [[TMP13:%.*]] = addrspacecast ptr addrspace(3) [[TMP11]] to ptr addrspace(1)
+; CHECK-NEXT:    [[VAL2:%.*]] = load i32, ptr addrspace(1) [[TMP13]], align 4
+; CHECK-NEXT:    [[RESULT:%.*]] = add i32 [[VAL1]], [[VAL2]]
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[RESULT]], 0
+; CHECK-NEXT:    br i1 [[CMP]], label [[POSITIVE:%.*]], label [[NEGATIVE:%.*]]
+; CHECK:       positive:
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       negative:
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp sgt i32 [[VAL1]], 0
+; CHECK-NEXT:    br i1 [[CMP2]], label [[VAL1_POSITIVE:%.*]], label [[VAL1_NEGATIVE:%.*]]
+; CHECK:       val1_positive:
+; CHECK-NEXT:    br label [[CONDFREE]]
+; CHECK:       val1_negative:
+; CHECK-NEXT:    br label [[CONDFREE]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP14:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.test_kernel, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP14]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+%val1 = load i32, ptr addrspace(1) addrspacecast (ptr addrspace(3) @lds_1 to ptr addrspace(1))
+%val2 = load i32, ptr addrspace(1) addrspacecast (ptr addrspace(3) @lds_2 to ptr addrspace(1))
+
+%result = add i32 %val1, %val2
+%cmp = icmp sgt i32 %result, 0
+br i1 %cmp, label %positive, label %negative
+
+positive:
+ret void
+
+negative:
+%cmp2 = icmp sgt i32 %val1, 0
+br i1 %cmp2, label %val1_positive, label %val1_negative
+
+val1_positive:
+ret void
+
+val1_negative:
+ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-indirect-access.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-indirect-access.ll
new file mode 100644
index 0000000000000..a275314d8f6b5
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-indirect-access.ll
@@ -0,0 +1,101 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if static and dynamic LDS accesses are lowered correctly when a non-kernel
+; is called from kernel.
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 1
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, align 2
+ at lds_3 = external addrspace(3) global [0 x i8], align 4
+ at lds_4 = external addrspace(3) global [0 x i8], align 8
+
+define void @use_variables() {
+; CHECK-LABEL: define void @use_variables() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [1 x i32], ptr addrspace(4) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr addrspace(4) [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [1 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(4) [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr i32 [[TMP6]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [1 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
+; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(4) [[TMP11]], align 4
+; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i32 [[TMP12]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP10]], i32 [[TMP14]]
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP9]], align 4
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP15]], align 8
+; CHECK-NEXT:    ret void
+;
+  store i8 3, ptr addrspace(3) @lds_3, align 4
+  store i8 3, ptr addrspace(3) @lds_4, align 8
+  ret void
+}
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META0:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP21:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP13:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP27:%.*]] = add i64 [[TMP13]], [[TMP14]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP6]], i32 15
+; CHECK-NEXT:    store i64 [[TMP27]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP11]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 1), align 8
+; CHECK-NEXT:    [[TMP19:%.*]] = add i64 [[TMP11]], 7
+; CHECK-NEXT:    [[TMP28:%.*]] = udiv i64 [[TMP19]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP28]], 8
+; CHECK-NEXT:    store i64 [[TMP8]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 2), align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP27]], [[TMP8]]
+; CHECK-NEXT:    store i64 [[TMP12]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 0), align 8
+; CHECK-NEXT:    [[TMP29:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP29]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 1), align 8
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[TMP29]], 7
+; CHECK-NEXT:    [[TMP18:%.*]] = udiv i64 [[TMP17]], 8
+; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP18]], 8
+; CHECK-NEXT:    store i64 [[TMP15]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 2), align 8
+; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[TMP12]], [[TMP15]]
+; CHECK-NEXT:    [[TMP20:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP16]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP20]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    br label [[TMP21]]
+; CHECK:       22:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP22:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 4
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP22]]
+; CHECK-NEXT:    [[TMP24:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP24]]
+; CHECK-NEXT:    call void @use_variables()
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP23]], align 1
+; CHECK-NEXT:    store i32 8, ptr addrspace(3) [[TMP25]], align 2
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP26:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP26]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  call void @use_variables()
+  store i8 7, ptr addrspace(3) @lds_1, align 1
+  store i32 8, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+;.
+; CHECK: [[META0]] = !{i32 0}
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-lds-test.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-lds-test.ll
new file mode 100644
index 0000000000000..188e494da119e
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-dynamic-lds-test.ll
@@ -0,0 +1,88 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if static and dynamic LDS accesses are lowered correctly in kernel.
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, align 8
+ at lds_3 = external addrspace(3) global [0 x i8], align 4
+ at lds_4 = external addrspace(3) global [0 x i8], align 8
+
+;.
+; CHECK: @lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+; CHECK: @lds_2 = internal addrspace(3) global [1 x i32] poison, align 8
+; CHECK: @lds_3 = external addrspace(3) global [0 x i8], align 4
+; CHECK: @lds_4 = external addrspace(3) global [0 x i8], align 8
+; CHECK: @llvm.amdgcn.sw.lds.k0 = internal addrspace(3) global ptr poison, align 8
+; CHECK: @llvm.amdgcn.sw.lds.k0.md = internal addrspace(1) global %llvm.amdgcn.sw.lds.k0.md.type { %llvm.amdgcn.sw.lds.k0.md.item { i32 0, i32 1, i32 8 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 8, i32 4, i32 8 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 16, i32 0, i32 0 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 16, i32 0, i32 0 } }, no_sanitize_address
+;.
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0() {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP21:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP13:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP31:%.*]] = add i64 [[TMP13]], [[TMP14]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP6]], i32 15
+; CHECK-NEXT:    store i64 [[TMP31]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP11]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 1), align 8
+; CHECK-NEXT:    [[TMP19:%.*]] = add i64 [[TMP11]], 7
+; CHECK-NEXT:    [[TMP32:%.*]] = udiv i64 [[TMP19]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP32]], 8
+; CHECK-NEXT:    store i64 [[TMP8]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 2), align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP31]], [[TMP8]]
+; CHECK-NEXT:    store i64 [[TMP12]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 0), align 8
+; CHECK-NEXT:    [[TMP33:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP33]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 1), align 8
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[TMP33]], 7
+; CHECK-NEXT:    [[TMP18:%.*]] = udiv i64 [[TMP17]], 8
+; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP18]], 8
+; CHECK-NEXT:    store i64 [[TMP15]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 2), align 8
+; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[TMP12]], [[TMP15]]
+; CHECK-NEXT:    [[TMP20:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP16]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP20]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    br label [[TMP21]]
+; CHECK:       22:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP22:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 4
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP22]]
+; CHECK-NEXT:    [[TMP24:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP24]]
+; CHECK-NEXT:    [[TMP26:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 2, i32 0), align 4
+; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP26]]
+; CHECK-NEXT:    [[TMP28:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 0), align 4
+; CHECK-NEXT:    [[TMP29:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP28]]
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP23]], align 4
+; CHECK-NEXT:    store i32 8, ptr addrspace(3) [[TMP25]], align 8
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP27]], align 4
+; CHECK-NEXT:    store i8 8, ptr addrspace(3) [[TMP29]], align 8
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP30:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP30]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  store i8 7, ptr addrspace(3) @lds_1, align 4
+  store i32 8, ptr addrspace(3) @lds_2, align 8
+  store i8 7, ptr addrspace(3) @lds_3, align 4
+  store i8 8, ptr addrspace(3) @lds_4, align 8
+  ret void
+}
+;.
+; CHECK: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+; CHECK: attributes #[[ATTR1:[0-9]+]] = { convergent nocallback nofree nounwind willreturn }
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-function-param.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-function-param.ll
new file mode 100644
index 0000000000000..3a3950c007cd3
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-function-param.ll
@@ -0,0 +1,61 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if LDS accesses are lowered correctly when LDS is passed as function
+; argument to non-kernel.
+
+ at lds_var = internal addrspace(3) global [1024 x i32] poison, align 4
+
+define void @my_function(ptr addrspace(3) %lds_arg) {
+; CHECK-LABEL: define void @my_function(
+; CHECK-SAME: ptr addrspace(3) [[LDS_ARG:%.*]]) {
+; CHECK-NEXT:    [[LDS_VAL:%.*]] = load i32, ptr addrspace(3) [[LDS_ARG]], align 4
+; CHECK-NEXT:    [[NEW_LDS_VAL:%.*]] = add i32 [[LDS_VAL]], 1
+; CHECK-NEXT:    store i32 [[NEW_LDS_VAL]], ptr addrspace(3) [[LDS_ARG]], align 4
+; CHECK-NEXT:    ret void
+;
+  %lds_val = load i32, ptr addrspace(3) %lds_arg, align 4
+  %new_lds_val = add i32 %lds_val, 1
+  store i32 %new_lds_val, ptr addrspace(3) %lds_arg, align 4
+  ret void
+}
+
+define amdgpu_kernel void @my_kernel() {
+; CHECK-LABEL: define amdgpu_kernel void @my_kernel() {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP7:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(1) @llvm.amdgcn.sw.lds.my_kernel.md, align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_MY_KERNEL_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.my_kernel.md, i32 0, i32 0, i32 2), align 8
+; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[TMP11]], [[TMP12]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP13]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.my_kernel, align 8
+; CHECK-NEXT:    br label [[TMP7]]
+; CHECK:       10:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.my_kernel.md, align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.my_kernel, i32 [[TMP8]]
+; CHECK-NEXT:    [[LDS_PTR:%.*]] = getelementptr [1024 x i32], ptr addrspace(3) [[TMP9]], i32 0, i32 0
+; CHECK-NEXT:    call void @my_function(ptr addrspace(3) [[LDS_PTR]])
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP10:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.my_kernel, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP10]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  %lds_ptr = getelementptr [1024 x i32], ptr addrspace(3) @lds_var, i32 0, i32 0
+  call void @my_function(ptr addrspace(3) %lds_ptr)
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-nested.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-nested.ll
new file mode 100644
index 0000000000000..f5114a8554248
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access-nested.ll
@@ -0,0 +1,220 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if LDS accesses are lowered correctly when a call is made to nested non-kernel.
+
+ at A = external addrspace(3) global [8 x ptr]
+ at B = external addrspace(3) global [0 x i32]
+
+define amdgpu_kernel void @kernel_0() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_0(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META0:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP7:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP9:%.*]] = load i64, ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_0.md, align 8
+; CHECK-NEXT:    [[TMP10:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_KERNEL_0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_0.md, i32 0, i32 0, i32 2), align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = add i64 [[TMP9]], [[TMP10]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP11]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_0, align 8
+; CHECK-NEXT:    br label [[TMP7]]
+; CHECK:       10:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    call void @call_store_A()
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP8:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP8]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  call void @call_store_A()
+  ret void
+}
+
+define amdgpu_kernel void @kernel_1() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_1(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META1:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP14:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP6]], i32 15
+; CHECK-NEXT:    store i64 0, ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_1.md, align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP11]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_KERNEL_1_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_1.md, i32 0, i32 0, i32 1), align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP11]], 3
+; CHECK-NEXT:    [[TMP10:%.*]] = udiv i64 [[TMP12]], 4
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP10]], 4
+; CHECK-NEXT:    store i64 [[TMP8]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_KERNEL_1_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_1.md, i32 0, i32 0, i32 2), align 8
+; CHECK-NEXT:    [[TMP9:%.*]] = add i64 0, [[TMP8]]
+; CHECK-NEXT:    [[TMP13:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP9]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP13]], ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_1, align 8
+; CHECK-NEXT:    br label [[TMP14]]
+; CHECK:       14:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[PTR:%.*]] = call ptr @get_B_ptr()
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP15:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_1, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP15]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  %ptr = call ptr @get_B_ptr()
+  ret void
+}
+
+define amdgpu_kernel void @kernel_2() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_2(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META2:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP7:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP9:%.*]] = load i64, ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_2.md, align 8
+; CHECK-NEXT:    [[TMP10:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_KERNEL_2_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_2.md, i32 0, i32 0, i32 2), align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = add i64 [[TMP9]], [[TMP10]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP11]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_2, align 8
+; CHECK-NEXT:    br label [[TMP7]]
+; CHECK:       10:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    call void @store_A()
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP8:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_2, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP8]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  call void @store_A()
+  ret void
+}
+
+define amdgpu_kernel void @kernel_3() {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_3(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META3:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP14:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr addrspace(4), ptr addrspace(4) [[TMP6]], i32 15
+; CHECK-NEXT:    store i64 0, ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_3.md, align 8
+; CHECK-NEXT:    [[TMP11:%.*]] = load i64, ptr addrspace(4) [[TMP7]], align 8
+; CHECK-NEXT:    store i64 [[TMP11]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_KERNEL_3_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_3.md, i32 0, i32 0, i32 1), align 8
+; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP11]], 3
+; CHECK-NEXT:    [[TMP10:%.*]] = udiv i64 [[TMP12]], 4
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP10]], 4
+; CHECK-NEXT:    store i64 [[TMP8]], ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_KERNEL_3_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.kernel_3.md, i32 0, i32 0, i32 2), align 8
+; CHECK-NEXT:    [[TMP9:%.*]] = add i64 0, [[TMP8]]
+; CHECK-NEXT:    [[TMP13:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP9]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP13]], ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_3, align 8
+; CHECK-NEXT:    br label [[TMP14]]
+; CHECK:       14:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[PTR:%.*]] = call ptr @get_B_ptr()
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP15:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.kernel_3, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP15]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  %ptr = call ptr @get_B_ptr()
+  ret void
+}
+
+define private void @call_store_A() {
+; CHECK-LABEL: define private void @call_store_A() {
+; CHECK-NEXT:    call void @store_A()
+; CHECK-NEXT:    ret void
+;
+  call void @store_A()
+  ret void
+}
+
+define private void @store_A() {
+; CHECK-LABEL: define private void @store_A() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [4 x i32], ptr addrspace(4) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr addrspace(4) [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [4 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(4) [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr i32 [[TMP6]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = addrspacecast ptr addrspace(3) [[TMP9]] to ptr
+; CHECK-NEXT:    store ptr [[TMP10]], ptr null, align 8
+; CHECK-NEXT:    ret void
+;
+  store ptr addrspacecast (ptr addrspace(3) @A to ptr), ptr null
+  ret void
+}
+
+define private ptr @get_B_ptr() {
+; CHECK-LABEL: define private ptr @get_B_ptr() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [4 x i32], ptr addrspace(4) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr addrspace(4) [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [4 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(4) [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr i32 [[TMP6]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = addrspacecast ptr addrspace(3) [[TMP9]] to ptr
+; CHECK-NEXT:    ret ptr [[TMP10]]
+;
+  ret ptr addrspacecast (ptr addrspace(3) @B to ptr)
+}
+;.
+; CHECK: [[META0]] = !{i32 0}
+; CHECK: [[META1]] = !{i32 1}
+; CHECK: [[META2]] = !{i32 2}
+; CHECK: [[META3]] = !{i32 3}
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access.ll
new file mode 100644
index 0000000000000..ac082dda0f10a
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-indirect-access.ll
@@ -0,0 +1,85 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if static LDS is lowered correctly when a non-kernel with LDS accesses is called from kernel.
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 1
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, align 2
+ at lds_3 = external addrspace(3) global [3 x i8], align 4
+ at lds_4 = external addrspace(3) global [4 x i8], align 8
+
+define void @use_variables() {
+; CHECK-LABEL: define void @use_variables() {
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [1 x i32], ptr addrspace(4) @llvm.amdgcn.sw.lds.base.table, i32 0, i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr addrspace(4) [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [1 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr addrspace(4) [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP7:%.*]] = inttoptr i32 [[TMP6]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(3) [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP4]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [1 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.sw.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
+; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr addrspace(4) [[TMP11]], align 4
+; CHECK-NEXT:    [[TMP13:%.*]] = inttoptr i32 [[TMP12]] to ptr addrspace(3)
+; CHECK-NEXT:    [[TMP14:%.*]] = load i32, ptr addrspace(3) [[TMP13]], align 4
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr addrspace(3) [[TMP10]], i32 [[TMP14]]
+; CHECK-NEXT:    [[X:%.*]] = addrspacecast ptr addrspace(3) [[TMP9]] to ptr
+; CHECK-NEXT:    [[TMP16:%.*]] = addrspacecast ptr addrspace(3) [[TMP9]] to ptr
+; CHECK-NEXT:    store i8 3, ptr [[TMP16]], align 4
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) [[TMP15]], align 8
+; CHECK-NEXT:    ret void
+;
+  %X = addrspacecast ptr addrspace(3) @lds_3 to ptr
+  store i8 3, ptr addrspacecast( ptr addrspace(3) @lds_3 to ptr), align 4
+  store i8 3, ptr addrspace(3) @lds_4, align 8
+  ret void
+}
+
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0(
+; CHECK-SAME: ) !llvm.amdgcn.lds.kernel.id [[META0:![0-9]+]] {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP7:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP13:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 0), align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 3, i32 2), align 8
+; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[TMP13]], [[TMP14]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP15]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    br label [[TMP7]]
+; CHECK:       10:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP10]]
+; CHECK-NEXT:    call void @use_variables()
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP9]], align 1
+; CHECK-NEXT:    store i32 8, ptr addrspace(3) [[TMP11]], align 2
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP12:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP12]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  call void @use_variables()
+  store i8 7, ptr addrspace(3) @lds_1, align 1
+  store i32 8, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+;.
+; CHECK: [[META0]] = !{i32 0}
+;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-test.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-test.ll
new file mode 100644
index 0000000000000..928e83a1f30b5
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-sw-lower-lds-static-lds-test.ll
@@ -0,0 +1,58 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if static LDS accesses in kernel are lowered correctly.
+ at lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+ at lds_2 = internal addrspace(3) global [1 x i32] poison, align 8
+
+;.
+; CHECK: @lds_1 = internal addrspace(3) global [1 x i8] poison, align 4
+; CHECK: @lds_2 = internal addrspace(3) global [1 x i32] poison, align 8
+; CHECK: @llvm.amdgcn.sw.lds.k0 = internal addrspace(3) global ptr poison, align 8
+; CHECK: @llvm.amdgcn.sw.lds.k0.md = internal addrspace(1) global %llvm.amdgcn.sw.lds.k0.md.type { %llvm.amdgcn.sw.lds.k0.md.item { i32 0, i32 1, i32 8 }, %llvm.amdgcn.sw.lds.k0.md.item { i32 8, i32 4, i32 8 } }, no_sanitize_address
+;.
+define amdgpu_kernel void @k0() {
+; CHECK-LABEL: define amdgpu_kernel void @k0() {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = or i32 [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[TMP4]], 0
+; CHECK-NEXT:    br i1 [[TMP5]], label [[MALLOC:%.*]], label [[TMP7:%.*]]
+; CHECK:       Malloc:
+; CHECK-NEXT:    [[TMP13:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE:%.*]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = load i64, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 2), align 8
+; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[TMP13]], [[TMP14]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call ptr addrspace(1) @malloc(i64 [[TMP15]])
+; CHECK-NEXT:    store ptr addrspace(1) [[TMP6]], ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    br label [[TMP7]]
+; CHECK:       10:
+; CHECK-NEXT:    [[XYZCOND:%.*]] = phi i1 [ false, [[WID:%.*]] ], [ true, [[MALLOC]] ]
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, align 4
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = load i32, ptr addrspace(1) getelementptr inbounds ([[LLVM_AMDGCN_SW_LDS_K0_MD_TYPE]], ptr addrspace(1) @llvm.amdgcn.sw.lds.k0.md, i32 0, i32 1, i32 0), align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, i32 [[TMP10]]
+; CHECK-NEXT:    store i8 7, ptr addrspace(3) [[TMP9]], align 4
+; CHECK-NEXT:    store i32 8, ptr addrspace(3) [[TMP11]], align 2
+; CHECK-NEXT:    br label [[CONDFREE:%.*]]
+; CHECK:       CondFree:
+; CHECK-NEXT:    call void @llvm.amdgcn.s.barrier()
+; CHECK-NEXT:    br i1 [[XYZCOND]], label [[FREE:%.*]], label [[END:%.*]]
+; CHECK:       Free:
+; CHECK-NEXT:    [[TMP12:%.*]] = load ptr, ptr addrspace(3) @llvm.amdgcn.sw.lds.k0, align 8
+; CHECK-NEXT:    call void @free(ptr [[TMP12]])
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       End:
+; CHECK-NEXT:    ret void
+;
+  store i8 7, ptr addrspace(3) @lds_1, align 4
+  store i32 8, ptr addrspace(3) @lds_2, align 2
+  ret void
+}
+;.
+; CHECK: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+; CHECK: attributes #[[ATTR1:[0-9]+]] = { convergent nocallback nofree nounwind willreturn }
+;.



More information about the llvm-commits mailing list