diff --git a/llvm/lib/Target/DirectX/DXILDataScalarization.cpp b/llvm/lib/Target/DirectX/DXILDataScalarization.cpp
index d9d9b36d0b739..7c8a41b05f805 100644
--- a/llvm/lib/Target/DirectX/DXILDataScalarization.cpp
+++ b/llvm/lib/Target/DirectX/DXILDataScalarization.cpp
@@ -305,6 +305,33 @@ bool DataScalarizerVisitor::visitGetElementPtrInst(GetElementPtrInst &GEPI) {
   Type *OrigGEPType = GEPI.getSourceElementType();
   Type *NewGEPType = OrigGEPType;
   bool NeedsTransform = false;
+  // Check if the pointer operand is a ConstantExpr GEP
+  if (auto *PtrOpGEPCE = dyn_cast<ConstantExpr>(PtrOperand);
+      PtrOpGEPCE && PtrOpGEPCE->getOpcode() == Instruction::GetElementPtr) {
+    if (GlobalVariable *NewGlobal =
+            lookupReplacementGlobal(PtrOpGEPCE->getOperand(0))) {
+      GetElementPtrInst *NestedGEP =
+          cast<GetElementPtrInst>(PtrOpGEPCE->getAsInstruction());
+      NestedGEP->insertBefore(GEPI.getIterator());
+
+      // Create a new GEP with the replaced global directly
+      IRBuilder<> Builder(&GEPI);
+      Type *NewNestedGEPType = NewGlobal->getValueType();
+
+      // Extract indices from the ConstantExpr GEP
+      SmallVector<Value *, MaxVecSize> NestedIndices(NestedGEP->indices());
+      Value *NewNestedGEP =
+          Builder.CreateGEP(NewNestedGEPType, NewGlobal, NestedIndices,
+                            NestedGEP->getName(), NestedGEP->getNoWrapFlags());
+
+      // Update the outer GEP to use the new nested GEP
+      GEPI.setOperand(GEPI.getPointerOperandIndex(), NewNestedGEP);
+      NestedGEP->replaceAllUsesWith(NewNestedGEP);
+      NestedGEP->eraseFromParent();
+      // Return true to indicate that we've modified the instruction
+      return true;
+    }
+  }
 
   if (GlobalVariable *NewGlobal = lookupReplacementGlobal(PtrOperand)) {
     NewGEPType = NewGlobal->getValueType();
diff --git a/llvm/test/CodeGen/DirectX/bugfix_139023_data_scalarize_const_gep.ll b/llvm/test/CodeGen/DirectX/bugfix_139023_data_scalarize_const_gep.ll
new file mode 100644
index 0000000000000..2decb3d6e19ee
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/bugfix_139023_data_scalarize_const_gep.ll
@@ -0,0 +1,39 @@
+; RUN: opt -S -passes='dxil-data-scalarization' -mtriple=dxil-pc-shadermodel6.4-library %s | FileCheck %s --check-prefixes=SCHECK,CHECK
+; RUN: opt -S -passes='dxil-data-scalarization,dxil-flatten-arrays' -mtriple=dxil-pc-shadermodel6.4-library %s | FileCheck %s --check-prefixes=FCHECK,CHECK
+
+@aTile = hidden addrspace(3) global [10 x [10 x <4 x i32>]] zeroinitializer, align 16
+@bTile = hidden addrspace(3) global [10 x [10 x i32]] zeroinitializer, align 16
+
+define void @CSMain() {
+; CHECK-LABEL: define void @CSMain() {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:  [[AFRAGPACKED_I_SCALARIZE:%.*]] = alloca [4 x i32], align 16
+; SCHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [10 x <4 x i32>], ptr addrspace(3) getelementptr inbounds ([10 x [10 x [4 x i32]]], ptr addrspace(3) @aTile.scalarized, i32 0, i32 1), i32 0, i32 2
+; FCHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, ptr addrspace(3) getelementptr inbounds ([400 x i32], ptr addrspace(3) @aTile.scalarized.1dim, i32 0, i32 48), align 16
+; SCHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, ptr addrspace(3) [[TMP0]], align 16
+; SCHECK-NEXT:    store <4 x i32> [[TMP1]], ptr [[AFRAGPACKED_I_SCALARIZE]], align 16
+; SCHECK-NEXT:    ret void
+;
+entry:
+  %aFragPacked.i = alloca <4 x i32>, align 16
+  %0 = load <4 x i32>, ptr addrspace(3) getelementptr inbounds ([10 x <4 x i32>], ptr addrspace(3) getelementptr inbounds ([10 x [10 x <4 x i32>]], ptr addrspace(3) @aTile, i32 0, i32 1), i32 0, i32 2), align 16
+  store <4 x i32> %0, ptr %aFragPacked.i, align 16
+  ret void
+}
+
+define void @Main() {
+; CHECK-LABEL: define void @Main() {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:  [[BFRAGPACKED_I:%.*]] = alloca i32, align 16
+; SCHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [10 x i32], ptr addrspace(3) getelementptr inbounds ([10 x [10 x i32]], ptr addrspace(3) @bTile, i32 0, i32 1), i32 0, i32 2
+; FCHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([100 x i32], ptr addrspace(3) @bTile.1dim, i32 0, i32 12), align 16
+; SCHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr addrspace(3) [[TMP0]], align 16
+; SCHECK-NEXT:    store i32 [[TMP1]], ptr [[BFRAGPACKED_I]], align 16
+; SCHECK-NEXT:    ret void
+;
+entry:
+  %bFragPacked.i = alloca i32, align 16
+  %0 = load i32, ptr addrspace(3) getelementptr inbounds ([10 x i32], ptr addrspace(3) getelementptr inbounds ([10 x [10 x i32]], ptr addrspace(3) @bTile, i32 0, i32 1), i32 0, i32 2), align 16
+  store i32 %0, ptr %bFragPacked.i, align 16
+  ret void
+}