diff --git a/llvm/lib/Target/ARM/ARMInstrMVE.td b/llvm/lib/Target/ARM/ARMInstrMVE.td
--- a/llvm/lib/Target/ARM/ARMInstrMVE.td
+++ b/llvm/lib/Target/ARM/ARMInstrMVE.td
@@ -4017,6 +4017,7 @@
   def : MVE_unpred_vector_store_typed<v4i32, RegImmInst, StoreKind, shift>;
   def : MVE_unpred_vector_store_typed<v4f32, RegImmInst, StoreKind, shift>;
   def : MVE_unpred_vector_store_typed<v2i64, RegImmInst, StoreKind, shift>;
+  def : MVE_unpred_vector_store_typed<v2f64, RegImmInst, StoreKind, shift>;
 }
 
 class MVE_unpred_vector_load_typed<ValueType Ty, Instruction RegImmInst,
@@ -4031,6 +4032,7 @@
   def : MVE_unpred_vector_load_typed<v4i32, RegImmInst, LoadKind, shift>;
   def : MVE_unpred_vector_load_typed<v4f32, RegImmInst, LoadKind, shift>;
   def : MVE_unpred_vector_load_typed<v2i64, RegImmInst, LoadKind, shift>;
+  def : MVE_unpred_vector_load_typed<v2f64, RegImmInst, LoadKind, shift>;
 }
 
 let Predicates = [HasMVEInt, IsLE] in {
diff --git a/llvm/test/CodeGen/Thumb2/mve-basic.ll b/llvm/test/CodeGen/Thumb2/mve-basic.ll
--- a/llvm/test/CodeGen/Thumb2/mve-basic.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-basic.ll
@@ -29,3 +29,27 @@
   store <4 x i32> %result, <4 x i32>* %resultp, align 16
   ret void
 }
+
+define arm_aapcs_vfpcc <16 x i8> @stack_slot_handling(<16 x i8> %a) #0 {
+; CHECK-LABEL: stack_slot_handling:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    push {r4, r6, r7, lr}
+; CHECK-NEXT:    add r7, sp, #8
+; CHECK-NEXT:    sub sp, #16
+; CHECK-NEXT:    mov r4, sp
+; CHECK-NEXT:    bfc r4, #0, #4
+; CHECK-NEXT:    mov sp, r4
+; CHECK-NEXT:    mov r0, sp
+; CHECK-NEXT:    vstrw.32 q0, [r0]
+; CHECK-NEXT:    vldrw.u32 q0, [r0]
+; CHECK-NEXT:    sub.w r4, r7, #8
+; CHECK-NEXT:    mov sp, r4
+; CHECK-NEXT:    pop {r4, r6, r7, pc}
+entry:
+  %a.addr = alloca <16 x i8>, align 8
+  store <16 x i8> %a, <16 x i8>* %a.addr, align 8
+  %0 = load <16 x i8>, <16 x i8>* %a.addr, align 8
+  ret <16 x i8> %0
+}
+
+attributes #0 = { noinline optnone }