diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -1305,6 +1305,18 @@
   GlobalAddressSDNode *G = cast<GlobalAddressSDNode>(Op);
   const GlobalValue *GV = G->getGlobal();
 
+  if (G->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS) {
+    if (!MFI->isModuleEntryFunction()) {
+      if (const GlobalVariable *GVar = dyn_cast<GlobalVariable>(GV)) {
+        if (AMDGPUMachineFunction::isKnownAddressLDSGlobal(*GVar)) {
+          unsigned Offset =
+              AMDGPUMachineFunction::calculateKnownAddressOfLDSGlobal(*GVar);
+          return DAG.getConstant(Offset, SDLoc(Op), Op.getValueType());
+        }
+      }
+    }
+  }
+
   if (G->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS ||
       G->getAddressSpace() == AMDGPUAS::REGION_ADDRESS) {
     if (!MFI->isModuleEntryFunction() &&
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -162,7 +162,7 @@
 cl::opt<LoweringKind> LoweringKindLoc(
     "amdgpu-lower-module-lds-strategy",
     cl::desc("Specify lowering strategy for function LDS access:"), cl::Hidden,
-    cl::init(LoweringKind::module),
+    cl::init(LoweringKind::hybrid),
     cl::values(
         clEnumValN(LoweringKind::table, "table", "Lower via table lookup"),
         clEnumValN(LoweringKind::module, "module", "Lower via module struct"),