Index: lib/Target/ARM/ARMTargetTransformInfo.cpp
===================================================================
--- lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -1054,14 +1054,17 @@
   UP.Partial = true;
   UP.Runtime = true;
   UP.UpperBound = true;
-  UP.UnrollRemainder = true;
+  // Hopefully we'll be able to generate a low-overhead loop for both the
+  // unrolled loop and the remainder loop.
+  UP.UnrollRemainder = ST->hasLOB() ? false : true;
   UP.DefaultUnrollRuntimeCount = 4;
   UP.UnrollAndJam = true;
   UP.UnrollAndJamInnerLoopThreshold = 60;
 
   // Force unrolling small loops can be very useful because of the branch
-  // taken cost of the backedge.
-  if (Cost < 12)
+  // taken cost of the backedge, but generally shouldn't be required if we
+  // have low-overhead branches.
+  if (Cost < 12 && !ST->hasLOB())
     UP.Force = true;
 }
 
Index: test/Transforms/LoopUnroll/ARM/loop-unrolling.ll
===================================================================
--- test/Transforms/LoopUnroll/ARM/loop-unrolling.ll
+++ test/Transforms/LoopUnroll/ARM/loop-unrolling.ll
@@ -1,9 +1,10 @@
-; RUN: opt -mtriple=armv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A
-; RUN: opt -mtriple=thumbv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A
-; RUN: opt -mtriple=thumbv7 -mcpu=cortex-a72 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A
-; RUN: opt -mtriple=thumbv8m -mcpu=cortex-m23 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T1
-; RUN: opt -mtriple=thumbv8m.main -mcpu=cortex-m33 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2
-; RUN: opt -mtriple=thumbv7em -mcpu=cortex-m7 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2
+; RUN: opt -mtriple=armv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A --check-prefix=CHECK
+; RUN: opt -mtriple=thumbv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A --check-prefix=CHECK
+; RUN: opt -mtriple=thumbv7 -mcpu=cortex-a72 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A --check-prefix=CHECK
+; RUN: opt -mtriple=thumbv8m -mcpu=cortex-m23 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T1 --check-prefix=CHECK
+; RUN: opt -mtriple=thumbv8m.main -mcpu=cortex-m33 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2 --check-prefix=CHECK
+; RUN: opt -mtriple=thumbv7em -mcpu=cortex-m7 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2 --check-prefix=CHECK
+; RUN: opt -mtriple=thumbv8.1m.main -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-LOB --check-prefix=CHECK
 
 ; CHECK-LABEL: partial
 define arm_aapcs_vfpcc void @partial(i32* nocapture %C, i32* nocapture readonly %A, i32* nocapture readonly %B) local_unnamed_addr #0 {
@@ -44,6 +45,26 @@
 ; CHECK-UNROLL-T2: [[CMP:%[a-z.0-9]+]] = icmp eq i32 [[IV16]], 1024
 ; CHECK-UNROLL-T2: br i1 [[CMP]], label [[END:%[a-z.]+]], label %for.body
 
+; CHECK-UNROLL-LOB: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV16:%[a-z.0-9]+]], %for.body ]
+; CHECK-UNROLL-LOB: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
+; CHECK-UNROLL-LOB: [[IV2:%[a-z.0-9]+]] = add nuw nsw i32 [[IV1]], 1
+; CHECK-UNROLL-LOB: [[IV3:%[a-z.0-9]+]] = add nuw nsw i32 [[IV2]], 1
+; CHECK-UNROLL-LOB: [[IV4:%[a-z.0-9]+]] = add nuw nsw i32 [[IV3]], 1
+; CHECK-UNROLL-LOB: [[IV5:%[a-z.0-9]+]] = add nuw nsw i32 [[IV4]], 1
+; CHECK-UNROLL-LOB: [[IV6:%[a-z.0-9]+]] = add nuw nsw i32 [[IV5]], 1
+; CHECK-UNROLL-LOB: [[IV7:%[a-z.0-9]+]] = add nuw nsw i32 [[IV6]], 1
+; CHECK-UNROLL-LOB: [[IV8:%[a-z.0-9]+]] = add nuw nsw i32 [[IV7]], 1
+; CHECK-UNROLL-LOB: [[IV9:%[a-z.0-9]+]] = add nuw nsw i32 [[IV8]], 1
+; CHECK-UNROLL-LOB: [[IV10:%[a-z.0-9]+]] = add nuw nsw i32 [[IV9]], 1
+; CHECK-UNROLL-LOB: [[IV11:%[a-z.0-9]+]] = add nuw nsw i32 [[IV10]], 1
+; CHECK-UNROLL-LOB: [[IV12:%[a-z.0-9]+]] = add nuw nsw i32 [[IV11]], 1
+; CHECK-UNROLL-LOB: [[IV13:%[a-z.0-9]+]] = add nuw nsw i32 [[IV12]], 1
+; CHECK-UNROLL-LOB: [[IV14:%[a-z.0-9]+]] = add nuw nsw i32 [[IV13]], 1
+; CHECK-UNROLL-LOB: [[IV15:%[a-z.0-9]+]] = add nuw nsw i32 [[IV14]], 1
+; CHECK-UNROLL-LOB: [[IV16]] = add nuw nsw i32 [[IV15]], 1
+; CHECK-UNROLL-LOB: [[CMP:%[a-z.0-9]+]] = icmp eq i32 [[IV16]], 1024
+; CHECK-UNROLL-LOB: br i1 [[CMP]], label [[END:%[a-z.]+]], label %for.body
+
   %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
   %arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.08
   %0 = load i32, i32* %arrayidx, align 4
@@ -89,6 +110,16 @@
 ; CHECK-UNROLL-T2: for.body.epil.1:
 ; CHECK-UNROLL-T2: for.body.epil.2:
 
+; CHECK-UNROLL-LOB: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, [[PRE:%[a-z.0-9]+]] ], [ [[IV4:%[a-z.0-9]+]], %for.body ]
+; CHECK-UNROLL-LOB: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
+; CHECK-UNROLL-LOB: [[IV2:%[a-z.0-9]+]] = add nuw nsw i32 [[IV1]], 1
+; CHECK-UNROLL-LOB: [[IV3:%[a-z.0-9]+]] = add nuw nsw i32 [[IV2]], 1
+; CHECK-UNROLL-LOB: [[IV4]] = add nuw i32 [[IV3]], 1
+; CHECK-UNROLL-LOB: br
+
+; CHECK-UNROLL-LOB: for.body.epil:
+; CHECK-UNROLL-LOB-NOT: for.body.epil.1:
+
   %i.09 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
   %arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.09
   %0 = load i32, i32* %arrayidx, align 4
@@ -140,6 +171,15 @@
 ; CHECK-UNROLL-T2: for.body4.epil.1:
 ; CHECK-UNROLL-T2: for.body4.epil.2:
 
+; CHECK-UNROLL-LOB: for.body4.epil:
+; CHECK-UNROLL-LOB: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, [[PRE:%[a-z0-9.]+]] ], [ [[IV4:%[a-z.0-9]+]], %for.body4 ]
+; CHECK-UNROLL-LOB: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
+; CHECK-UNROLL-LOB: [[IV2:%[a-z.0-9]+]] = add nuw nsw i32 [[IV1]], 1
+; CHECK-UNROLL-LOB: [[IV3:%[a-z.0-9]+]] = add nuw nsw i32 [[IV2]], 1
+; CHECK-UNROLL-LOB: [[IV4]] = add nuw i32 [[IV3]], 1
+; CHECK-UNROLL-LOB: br
+; CHECK-UNROLL-LOB-NOT: for.body4.epil.1:
+
   %w.024 = phi i32 [ 0, %for.body4.lr.ph ], [ %inc, %for.body4 ]
   %add = add i32 %w.024, %mul
   %arrayidx = getelementptr inbounds i16, i16* %A, i32 %add
@@ -207,6 +247,11 @@
 ; CHECK-UNROLL-T1: br i1 %tobool
 ; CHECK-UNROLL-T1-NOT: load
 
+; CHECK-UNROLL-LOB: %n.addr.04 = phi %struct.Node* [ %1, %while.body ], [ %n, %while.body.preheader ]
+; CHECK-UNROLL-LOB: %tobool = icmp eq %struct.Node* %1, null
+; CHECK-UNROLL-LOB: br i1 %tobool
+; CHECK-UNROLL-LOB-NOT: load
+
 ; CHECK-UNROLL-T2: [[CMP0:%[a-z.0-9]+]] = icmp eq %struct.Node* [[VAR0:%[a-z.0-9]+]], null
 ; CHECK-UNROLL-T2: br i1 [[CMP0]], label [[END:%[a-z.0-9]+]]
 ; CHECK-UNROLL-T2: [[CMP1:%[a-z.0-9]+]] = icmp eq %struct.Node* [[VAR1:%[a-z.0-9]+]], null