diff --git a/llvm/test/CodeGen/Thumb2/aligned-nonfallthrough.ll b/llvm/test/CodeGen/Thumb2/aligned-nonfallthrough.ll
new file mode 100644
index 000000000000..90bf4df53f30
--- /dev/null
+++ b/llvm/test/CodeGen/Thumb2/aligned-nonfallthrough.ll
@@ -0,0 +1,88 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1-m.main-none-eabi -mcpu=cortex-m55 -O3 < %s | FileCheck %s
+
+define i32 @loop(i32* nocapture readonly %x) {
+; CHECK-LABEL: loop:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    .save {r7, lr}
+; CHECK-NEXT:    push {r7, lr}
+; CHECK-NEXT:    mov.w lr, #500
+; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    movs r1, #0
+; CHECK-NEXT:    .p2align 2
+; CHECK-NEXT:  .LBB0_1: @ %for.body
+; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    ldr r2, [r0], #4
+; CHECK-NEXT:    add r1, r2
+; CHECK-NEXT:    le lr, .LBB0_1
+; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
+; CHECK-NEXT:    mov r0, r1
+; CHECK-NEXT:    pop {r7, pc}
+entry:
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body
+  ret i32 %add
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.07 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %s.06 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.07
+  %0 = load i32, i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %s.06
+  %inc = add nuw nsw i32 %i.07, 1
+  %exitcond.not = icmp eq i32 %inc, 500
+  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+define i64 @loopif(i32* nocapture readonly %x, i32 %y, i32 %n) {
+; CHECK-LABEL: loopif:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    .save {r7, lr}
+; CHECK-NEXT:    push {r7, lr}
+; CHECK-NEXT:    cmp r2, #1
+; CHECK-NEXT:    blt .LBB1_4
+; CHECK-NEXT:  @ %bb.1: @ %for.body.lr.ph
+; CHECK-NEXT:    mov lr, r2
+; CHECK-NEXT:    dls lr, r2
+; CHECK-NEXT:    mov r12, r0
+; CHECK-NEXT:    movs r0, #0
+; CHECK-NEXT:    movs r3, #0
+; CHECK-NEXT:    .p2align 2
+; CHECK-NEXT:  .LBB1_2: @ %for.body
+; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    ldr r2, [r12], #4
+; CHECK-NEXT:    smlal r0, r3, r2, r1
+; CHECK-NEXT:    le lr, .LBB1_2
+; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
+; CHECK-NEXT:    mov r1, r3
+; CHECK-NEXT:    pop {r7, pc}
+; CHECK-NEXT:  .LBB1_4:
+; CHECK-NEXT:    movs r0, #0
+; CHECK-NEXT:    movs r3, #0
+; CHECK-NEXT:    mov r1, r3
+; CHECK-NEXT:    pop {r7, pc}
+entry:
+  %cmp7 = icmp sgt i32 %n, 0
+  br i1 %cmp7, label %for.body.lr.ph, label %for.cond.cleanup
+
+for.body.lr.ph:                                   ; preds = %entry
+  %conv1 = sext i32 %y to i64
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body, %entry
+  %s.0.lcssa = phi i64 [ 0, %entry ], [ %add, %for.body ]
+  ret i64 %s.0.lcssa
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.body
+  %i.09 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
+  %s.08 = phi i64 [ 0, %for.body.lr.ph ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.09
+  %0 = load i32, i32* %arrayidx, align 4
+  %conv = sext i32 %0 to i64
+  %mul = mul nsw i64 %conv, %conv1
+  %add = add nsw i64 %mul, %s.08
+  %inc = add nuw nsw i32 %i.09, 1
+  %exitcond.not = icmp eq i32 %inc, %n
+  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}