Index: llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
+++ llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
@@ -1530,19 +1530,23 @@
         // TODO: We could be producing more VPT blocks than necessary and could
         // fold the newly created one into a proceeding one.
         MachineInstr *Divergent = VPTState::getDivergent(Block);
-        for (auto I = ++MachineBasicBlock::iterator(Insts.front()),
-             E = ++MachineBasicBlock::iterator(Divergent); I != E; ++I)
+        MachineInstr *VPST = Insts.front();
+        auto DivergentNext = ++MachineBasicBlock::iterator(Divergent);
+        bool DivergentNextIsPredicated =
+            getVPTInstrPredicate(*DivergentNext) != ARMVCC::None;
+
+        for (auto I = ++MachineBasicBlock::iterator(VPST), E = DivergentNext;
+             I != E; ++I)
           RemovePredicate(&*I);
 
         // Check if the instruction defining vpr is a vcmp so it can be combined
         // with the VPST This should be the divergent instruction
-        MachineInstr *VCMP = VCMPOpcodeToVPT(Divergent->getOpcode()) != 0
-          ? Divergent
-          : nullptr;
+        MachineInstr *VCMP =
+            VCMPOpcodeToVPT(Divergent->getOpcode()) != 0 ? Divergent : nullptr;
 
         MachineInstrBuilder MIB;
-        if (VCMP) {
-          // Combine the VPST and VCMP into a VPT
+        auto ReplaceVCMPWithVPT = [&]() {
+          // Replace the VCMP with a VPT
           MIB = BuildMI(*Divergent->getParent(), Divergent,
                         Divergent->getDebugLoc(),
                         TII->get(VCMPOpcodeToVPT(VCMP->getOpcode())));
@@ -1555,18 +1559,36 @@
           MIB.add(VCMP->getOperand(3));
           LLVM_DEBUG(dbgs()
                      << "ARM Loops: Combining with VCMP to VPT: " << *MIB);
+          LoLoop.BlockMasksToRecompute.insert(MIB.getInstr());
           LoLoop.ToRemove.insert(VCMP);
-        } else {
-          // Create a VPST (with a null mask for now, we'll recompute it later)
-          // or a VPT in case there was a VCMP right before it
-          MIB = BuildMI(*Divergent->getParent(), Divergent,
-                        Divergent->getDebugLoc(), TII->get(ARM::MVE_VPST));
-          MIB.addImm(0);
-          LLVM_DEBUG(dbgs() << "ARM Loops: Created VPST: " << *MIB);
+        };
+
+        // If the VCMP exists and it has the same register values as the VPST,
+        // replace both with a VPT
+        if (VCMP &&
+            RDA->hasSameReachingDef(VCMP, VPST, VCMP->getOperand(1).getReg()) &&
+            RDA->hasSameReachingDef(VCMP, VPST, VCMP->getOperand(2).getReg())) {
+          ReplaceVCMPWithVPT();
+        } else if (DivergentNextIsPredicated) {
+          // Otherwise insert a VPST at the divergent only if the next
+          // instruction would actually use it. A VCMP following a VPST can be
+          // merged into a VPT so do that instead if the VCMP exists.
+          if (!VCMP) {
+            // Create a VPST (with a null mask for now, we'll recompute it
+            // later)
+            MIB = BuildMI(*Divergent->getParent(), Divergent,
+                          Divergent->getDebugLoc(), TII->get(ARM::MVE_VPST));
+            MIB.addImm(0);
+            LLVM_DEBUG(dbgs() << "ARM Loops: Created VPST: " << *MIB);
+            LoLoop.BlockMasksToRecompute.insert(MIB.getInstr());
+          } else {
+            // No RDA checks are necessary here since the VPST would have been
+            // directly before the VCMP
+            ReplaceVCMPWithVPT();
+          }
         }
-        LLVM_DEBUG(dbgs() << "ARM Loops: Removing VPST: " << *Insts.front());
-        LoLoop.ToRemove.insert(Insts.front());
-        LoLoop.BlockMasksToRecompute.insert(MIB.getInstr());
+        LLVM_DEBUG(dbgs() << "ARM Loops: Removing VPST: " << *VPST);
+        LoLoop.ToRemove.insert(VPST);
       }
     } else if (Block.containsVCTP()) {
       // The vctp will be removed, so the block mask of the vp(s)t will need
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/vcmp-vpst-combination.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/LowOverheadLoops/vcmp-vpst-combination.ll
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/vcmp-vpst-combination.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -tail-predication=force-enabled-no-reductions -o - %s | FileCheck %s
 
 define arm_aapcs_vfpcc <16 x i8> @vcmp_vpst_combination(<16 x i8>* %pSrc, i16 zeroext %blockSize, i8* nocapture %pResult, i32* nocapture %pIndex) {
@@ -40,6 +41,70 @@
   ret <16 x i8> %6
 }
 
+define hidden i32 @vcmp_new_vpst_combination(i32 %len, i32* nocapture readonly %arr) local_unnamed_addr #0 {
+; CHECK-LABEL: vcmp_new_vpst_combination:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    .save {r7, lr}
+; CHECK-NEXT:    push {r7, lr}
+; CHECK-NEXT:    cmp r0, #1
+; CHECK-NEXT:    blt .LBB1_4
+; CHECK-NEXT:  @ %bb.1: @ %vector.ph
+; CHECK-NEXT:    vmov.i32 q0, #0x0
+; CHECK-NEXT:    vmov.i32 q1, #0x1
+; CHECK-NEXT:    movs r2, #0
+; CHECK-NEXT:    dlstp.32 lr, r0
+; CHECK-NEXT:  .LBB1_2: @ %vector.body
+; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
+; CHECK-NEXT:    vcmp.i32 ne, q2, zr
+; CHECK-NEXT:    vmov q2, q0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmovt q2, q1
+; CHECK-NEXT:    vaddva.u32 r2, q2
+; CHECK-NEXT:    letp lr, .LBB1_2
+; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
+; CHECK-NEXT:    mov r0, r2
+; CHECK-NEXT:    pop {r7, pc}
+; CHECK-NEXT:  .LBB1_4:
+; CHECK-NEXT:    movs r2, #0
+; CHECK-NEXT:    mov r0, r2
+; CHECK-NEXT:    pop {r7, pc}
+entry:
+  %cmp7 = icmp sgt i32 %len, 0
+  br i1 %cmp7, label %vector.ph, label %for.cond.cleanup
+
+vector.ph:                                        ; preds = %entry
+  %n.rnd.up = add i32 %len, 3
+  %n.vec = and i32 %n.rnd.up, -4
+  br label %vector.body
+
+vector.body:                                      ; preds = %vector.body, %vector.ph
+  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+  %vec.phi = phi i32 [ 0, %vector.ph ], [ %5, %vector.body ]
+  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %len)
+  %0 = getelementptr inbounds i32, i32* %arr, i32 %index
+  %1 = bitcast i32* %0 to <4 x i32>*
+  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
+  %2 = icmp ne <4 x i32> %wide.masked.load, zeroinitializer
+  %narrow = and <4 x i1> %active.lane.mask, %2
+  %3 = zext <4 x i1> %narrow to <4 x i32>
+  %4 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %3)
+  %5 = add i32 %4, %vec.phi
+  %index.next = add i32 %index, 4
+  %6 = icmp eq i32 %index.next, %n.vec
+  br i1 %6, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup:                                 ; preds = %vector.body, %entry
+  %count.0.lcssa = phi i32 [ 0, %entry ], [ %5, %vector.body ]
+  ret i32 %count.0.lcssa
+}
+
+declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
+
+declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
+
+declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
+
 declare { <16 x i8>, i32 } @llvm.arm.mve.vidup.v16i8(i32, i32)
 
 declare <16 x i1> @llvm.arm.mve.vctp8(i32)