Index: llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
+++ llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
@@ -789,6 +789,21 @@
       ToRemove.insert(ElementChain.begin(), ElementChain.end());
     }
   }
+  // If we converted the LoopStart to a t2DoLoopStartTP, we can also remove any
+  // extra instructions in the preheader, which often includes a now unused MOV.
+  if (Start->getOpcode() == ARM::t2DoLoopStartTP && Preheader &&
+      !Preheader->empty() &&
+      !RDA.hasLocalDefBefore(VCTP, VCTP->getOperand(1).getReg())) {
+    if (auto *Def = RDA.getUniqueReachingMIDef(
+            &Preheader->back(), VCTP->getOperand(1).getReg().asMCReg())) {
+      SmallPtrSet<MachineInstr*, 2> ElementChain;
+      SmallPtrSet<MachineInstr*, 2> Ignore;
+      Ignore.insert(VCTPs.begin(), VCTPs.end());
+      if (TryRemove(Def, RDA, ElementChain, Ignore)) {
+        ToRemove.insert(ElementChain.begin(), ElementChain.end());
+      }
+    }
+  }
   return true;
 }
 
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/exitcount.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/LowOverheadLoops/exitcount.ll
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/exitcount.ll
@@ -10,7 +10,6 @@
 ; CHECK-NEXT:    ldrd r12, r2, [r0]
 ; CHECK-NEXT:    ldrd r4, r3, [r0, #8]
 ; CHECK-NEXT:    rsb r12, r12, r2, lsl #1
-; CHECK-NEXT:    mov r2, r12
 ; CHECK-NEXT:    dlstp.16 lr, r12
 ; CHECK-NEXT:  .LBB0_1: @ %do.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/mov-operand.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/LowOverheadLoops/mov-operand.ll
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/mov-operand.ll
@@ -7,7 +7,6 @@
 ; CHECK-NEXT:    .save {r7, lr}
 ; CHECK-NEXT:    push {r7, lr}
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
-; CHECK-NEXT:    mov r3, r1
 ; CHECK-NEXT:    mov r12, r0
 ; CHECK-NEXT:    dlstp.32 lr, r1
 ; CHECK-NEXT:  .LBB0_1: @ %do.body.i
@@ -19,7 +18,6 @@
 ; CHECK-NEXT:    vmov s4, r1
 ; CHECK-NEXT:    vadd.f32 s0, s3, s3
 ; CHECK-NEXT:    vcvt.f32.u32 s4, s4
-; CHECK-NEXT:    mov r3, r1
 ; CHECK-NEXT:    vdiv.f32 s0, s0, s4
 ; CHECK-NEXT:    vmov r12, s0
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/while-loops.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/LowOverheadLoops/while-loops.ll
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/while-loops.ll
@@ -78,7 +78,6 @@
 ; CHECK-NEXT:  @ %bb.5: @ %do.body.preheader
 ; CHECK-NEXT:    @ in Loop: Header=BB1_4 Depth=1
 ; CHECK-NEXT:    bic r9, r7, #3
-; CHECK-NEXT:    mov r7, r5
 ; CHECK-NEXT:    mov r4, r3
 ; CHECK-NEXT:    add.w r8, r0, r9, lsl #2
 ; CHECK-NEXT:    dlstp.32 lr, r5
Index: llvm/test/CodeGen/Thumb2/mve-postinc-dct.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-postinc-dct.ll
+++ llvm/test/CodeGen/Thumb2/mve-postinc-dct.ll
@@ -24,7 +24,6 @@
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    mov r6, r1
 ; CHECK-NEXT:    mov r7, r3
-; CHECK-NEXT:    mov r4, r5
 ; CHECK-NEXT:    dlstp.32 lr, r5
 ; CHECK-NEXT:  .LBB0_3: @ %vector.body
 ; CHECK-NEXT:    @ Parent Loop BB0_2 Depth=1
@@ -127,7 +126,6 @@
 ; CHECK-NEXT:    mov r3, r11
 ; CHECK-NEXT:    mov r0, r7
 ; CHECK-NEXT:    vmov q1, q0
-; CHECK-NEXT:    mov r6, r12
 ; CHECK-NEXT:    dlstp.32 lr, r12
 ; CHECK-NEXT:  .LBB1_3: @ %vector.body
 ; CHECK-NEXT:    @ Parent Loop BB1_2 Depth=1
@@ -272,7 +270,6 @@
 ; CHECK-NEXT:    mov r4, r10
 ; CHECK-NEXT:    vmov q2, q0
 ; CHECK-NEXT:    vmov q1, q0
-; CHECK-NEXT:    mov r8, r7
 ; CHECK-NEXT:    dlstp.32 lr, r7
 ; CHECK-NEXT:  .LBB2_3: @ %vector.body
 ; CHECK-NEXT:    @ Parent Loop BB2_2 Depth=1
@@ -448,7 +445,6 @@
 ; CHECK-NEXT:    vmov q1, q0
 ; CHECK-NEXT:    vmov q2, q0
 ; CHECK-NEXT:    vmov q3, q0
-; CHECK-NEXT:    mov r10, r7
 ; CHECK-NEXT:    dlstp.32 lr, r7
 ; CHECK-NEXT:  .LBB3_3: @ %vector.body
 ; CHECK-NEXT:    @ Parent Loop BB3_2 Depth=1
@@ -645,7 +641,6 @@
 ; CHECK-NEXT:    vmov q3, q1
 ; CHECK-NEXT:    vmov q2, q1
 ; CHECK-NEXT:    vmov q4, q1
-; CHECK-NEXT:    mov r1, r7
 ; CHECK-NEXT:    dlstp.32 lr, r7
 ; CHECK-NEXT:  .LBB4_3: @ %vector.body
 ; CHECK-NEXT:    @ Parent Loop BB4_2 Depth=1
@@ -864,7 +859,6 @@
 ; CHECK-NEXT:    vmov q0, q1
 ; CHECK-NEXT:    vmov q5, q1
 ; CHECK-NEXT:    vmov q2, q1
-; CHECK-NEXT:    mov r9, r7
 ; CHECK-NEXT:    dlstp.32 lr, r7
 ; CHECK-NEXT:  .LBB5_3: @ %vector.body
 ; CHECK-NEXT:    @ Parent Loop BB5_2 Depth=1
Index: llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll
+++ llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll
@@ -740,7 +740,6 @@
 ; CHECK-NEXT:    ldr r1, [sp, #16] @ 4-byte Reload
 ; CHECK-NEXT:    mov r8, r12
 ; CHECK-NEXT:    mla r3, r11, r2, r0
-; CHECK-NEXT:    mov r9, r2
 ; CHECK-NEXT:    mov r10, r12
 ; CHECK-NEXT:    ldm.w sp, {r0, r5, r7} @ 12-byte Folded Reload
 ; CHECK-NEXT:    dlstp.16 lr, r2
@@ -913,7 +912,6 @@
 ; CHECK-NEXT:    ldr r1, [sp, #16] @ 4-byte Reload
 ; CHECK-NEXT:    mov r8, r12
 ; CHECK-NEXT:    mla r3, r11, r2, r0
-; CHECK-NEXT:    mov r9, r2
 ; CHECK-NEXT:    mov r10, r12
 ; CHECK-NEXT:    ldm.w sp, {r0, r5, r7} @ 12-byte Folded Reload
 ; CHECK-NEXT:    dlstp.16 lr, r2
Index: llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
+++ llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
@@ -14,7 +14,6 @@
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    vldrw.u32 q1, [r4]
 ; CHECK-NEXT:    vmov.i32 q3, #0x4
-; CHECK-NEXT:    mov r12, r1
 ; CHECK-NEXT:    dlstp.32 lr, r1
 ; CHECK-NEXT:  .LBB0_1: @ %do.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1