diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
index 8bf2b13..5f05ce7 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
@@ -245,10 +245,10 @@
   // 32-bit and extract sequence is already present, and it is probably easier
   // to CSE this. The loads should be mergable later anyway.
   Value *GEPXY = Builder.CreateConstInBoundsGEP1_64(CastDispatchPtr, 1);
-  LoadInst *LoadXY = Builder.CreateAlignedLoad(GEPXY, 4);
+  LoadInst *LoadXY = Builder.CreateAlignedLoad(I32Ty, GEPXY, 4);
 
   Value *GEPZU = Builder.CreateConstInBoundsGEP1_64(CastDispatchPtr, 2);
-  LoadInst *LoadZU = Builder.CreateAlignedLoad(GEPZU, 4);
+  LoadInst *LoadZU = Builder.CreateAlignedLoad(I32Ty, GEPZU, 4);
 
   MDNode *MD = MDNode::get(Mod->getContext(), None);
   LoadXY->setMetadata(LLVMContext::MD_invariant_load, MD);
@@ -426,7 +426,7 @@
       Value *Index = calculateVectorIndex(Ptr, GEPVectorIdx);
 
       Value *BitCast = Builder.CreateBitCast(Alloca, VecPtrTy);
-      Value *VecValue = Builder.CreateLoad(BitCast);
+      Value *VecValue = Builder.CreateLoad(VectorTy, BitCast);
       Value *ExtractElement = Builder.CreateExtractElement(VecValue, Index);
       Inst->replaceAllUsesWith(ExtractElement);
       Inst->eraseFromParent();
@@ -441,7 +441,7 @@
       Value *Ptr = SI->getPointerOperand();
       Value *Index = calculateVectorIndex(Ptr, GEPVectorIdx);
       Value *BitCast = Builder.CreateBitCast(Alloca, VecPtrTy);
-      Value *VecValue = Builder.CreateLoad(BitCast);
+      Value *VecValue = Builder.CreateLoad(VectorTy, BitCast);
       Value *NewVecValue = Builder.CreateInsertElement(VecValue,
                                                        SI->getValueOperand(),
                                                        Index);