Index: lib/Target/ARM/ARMTargetTransformInfo.h
===================================================================
--- lib/Target/ARM/ARMTargetTransformInfo.h
+++ lib/Target/ARM/ARMTargetTransformInfo.h
@@ -122,6 +122,8 @@
                                  ArrayRef<unsigned> Indices, unsigned Alignment,
                                  unsigned AddressSpace);
 
+  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP);
+
   bool shouldBuildLookupTablesForConstant(Constant *C) const {
     // In the ROPI and RWPI relocation models we can't have pointers to global
     // variables or functions in constant data, so don't convert switches to
Index: lib/Target/ARM/ARMTargetTransformInfo.cpp
===================================================================
--- lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -544,3 +544,86 @@
   return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,
                                            Alignment, AddressSpace);
 }
+
+static Value *getTripCountValue(Loop *L) {
+  // Canonical loops will end with a 'cmp ne I, V', where I is the incremented
+  // canonical induction variable and V is the trip count of the loop.
+  PHINode *IV = L->getCanonicalInductionVariable();
+  if (!IV)
+    return nullptr;
+
+  BasicBlock *BackedgeBlock = L->getLoopLatch();
+  Value *Inc = IV->getIncomingValueForBlock(BackedgeBlock);
+
+  if (auto *BI = dyn_cast<BranchInst>(BackedgeBlock->getTerminator())) {
+    if (BI->isConditional()) {
+      if (auto *ICI = dyn_cast<ICmpInst>(BI->getCondition())) {
+        if (ICI->getOperand(0) == Inc) {
+          return ICI->getOperand(1);
+        }
+      }
+    }
+  }
+  return nullptr;
+}
+
+void ARMTTIImpl::getUnrollingPreferences(Loop *L,
+                                         TTI::UnrollingPreferences &UP) {
+  if (!ST->isThumb2() || !ST->isMClass() || (L->getNumBlocks() != 1)
+      || !L->getExitingBlock() || !L->getUniqueExitBlock())
+    return;
+
+  BasicBlock *BB = L->getLoopLatch();
+  UP.OptSizeThreshold = 0;
+  UP.PartialOptSizeThreshold = 0;
+
+  unsigned MemOps = 1;
+  // Scan the loop: don't unroll loops with calls.
+  for (auto &I : *BB) {
+    if (isa<CallInst>(I) || isa<InvokeInst>(I)) {
+      ImmutableCallSite CS(&I);
+      if (const Function *F = CS.getCalledFunction()) {
+        if (!isLoweredToCall(F))
+          continue;
+      }
+      return;
+    } else if (isa<LoadInst>(I) || isa<StoreInst>(I))
+      ++MemOps;
+  }
+
+  UP.Partial = true;
+  UP.Threshold = 150;
+  UP.PartialThreshold = 150;
+
+  // Increase the thresholds for multiple issue machines on more compute
+  // bound loops.
+  if (ST->getInstrItineraryData()->SchedModel.IssueWidth > 1) {
+    if (BB->size() / MemOps > 3) {
+      UP.PartialThreshold = 300;
+      UP.Threshold = 300;
+    }
+  }
+
+  // Enable runtime unrolling for non-nested loops.
+  if (L->getLoopDepth() == 1) {
+    UP.Runtime = true;
+    return;
+  }
+
+  // For nested loops, we want the trip count to be invariant in the outer
+  // loops.
+  Value *TripCount = getTripCountValue(L);
+  if (!TripCount)
+    return;
+
+  Loop *Parent = L->getParentLoop();
+  while (Parent) {
+    if (!Parent->isLoopInvariant(TripCount))
+      return;
+    Parent = Parent->getParentLoop();
+  }
+
+  // Lower the threshold for nested runtime loops.
+  UP.PartialThreshold /= 2;
+  UP.Runtime = true;
+}