diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
@@ -438,7 +438,7 @@
 
   Type *const Ty = I.getType();
   const unsigned TyBitWidth = DL->getTypeSizeInBits(Ty);
-  Type *const VecTy = VectorType::get(B.getInt32Ty(), 2);
+  auto *const VecTy = FixedVectorType::get(B.getInt32Ty(), 2);
 
   // This is the value in the atomic operation we need to combine in order to
   // reduce the number of atomic operations.
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp b/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
@@ -598,7 +598,7 @@
   if (Size <= 8)
     PtrElemTy = Type::getIntNTy(Ctx, Size * 8);
   else
-    PtrElemTy = VectorType::get(Type::getInt64Ty(Ctx), Size / 8);
+    PtrElemTy = FixedVectorType::get(Type::getInt64Ty(Ctx), Size / 8);
   unsigned PtrArgLoc = CI->getNumArgOperands() - 3;
   auto PtrArg = CI->getArgOperand(PtrArgLoc);
   unsigned PtrArgAS = PtrArg->getType()->getPointerAddressSpace();
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp b/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp
@@ -902,7 +902,7 @@
     return nullptr;
   }
   if (P.VectorSize > 1)
-    T = VectorType::get(T, P.VectorSize);
+    T = FixedVectorType::get(T, P.VectorSize);
   if (P.PtrKind != AMDGPULibFunc::BYVALUE)
     T = useAddrSpace ? T->getPointerTo((P.PtrKind & AMDGPULibFunc::ADDR_SPACE)
                                        - 1)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp
@@ -167,7 +167,7 @@
     }
 
     if (IsV3 && Size >= 32) {
-      V4Ty = VectorType::get(VT->getElementType(), 4);
+      V4Ty = FixedVectorType::get(VT->getElementType(), 4);
       // Use the hack that clang uses to avoid SelectionDAG ruining v3 loads
       AdjustedArgTy = V4Ty;
     }
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
@@ -516,7 +516,7 @@
             break;
           }
           if (EleCount > 1) {
-            IType = dyn_cast<Type>(VectorType::get(IType, EleCount));
+            IType = FixedVectorType::get(IType, EleCount);
           }
           Arg = new BitCastInst(Arg, IType, "PrintArgVect", Brnch);
           WhatToStore.push_back(Arg);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -334,12 +334,12 @@
       SrcAddrSpace == AMDGPUAS::REGION_ADDRESS ||
       DestAddrSpace == AMDGPUAS::LOCAL_ADDRESS ||
       DestAddrSpace == AMDGPUAS::REGION_ADDRESS) {
-    return VectorType::get(Type::getInt32Ty(Context), 2);
+    return FixedVectorType::get(Type::getInt32Ty(Context), 2);
   }
 
   // Global memory works best with 16-byte accesses. Private memory will also
   // hit this, although they'll be decomposed.
-  return VectorType::get(Type::getInt32Ty(Context), 4);
+  return FixedVectorType::get(Type::getInt32Ty(Context), 4);
 }
 
 void GCNTTIImpl::getMemcpyLoopResidualLoweringType(