peel loops with runtime small trip counts

For Hexagon, peeling loops with small runtime trip count is beneficial for our
benchmarks. We set PeelCount in HexagonTargetInfo.cpp and we use PeelCount set
by the target for computing the desired peel count.

Differential Revision: https://reviews.llvm.org/D44880

llvm-svn: 329042

llvm/include/llvm/Transforms/Utils/UnrollLoop.h

@@ -73,6 +73,8 @@ void computePeelCount(Loop *L, unsigned LoopSize,
                       TargetTransformInfo::UnrollingPreferences &UP,
                       unsigned &TripCount, ScalarEvolution &SE);
 
+bool canPeel(Loop *L);
+
 bool peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI, ScalarEvolution *SE,
               DominatorTree *DT, AssumptionCache *AC, bool PreserveLCSSA);
 

llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp

@@ -44,6 +44,13 @@ HexagonTTIImpl::getPopcntSupport(unsigned IntTyWidthInBit) const {
 void HexagonTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                              TTI::UnrollingPreferences &UP) {
   UP.Runtime = UP.Partial = true;
+  // Only try to peel innermost loops with small runtime trip counts.
+  if (L && L->empty() &&
+      SE.getSmallConstantTripCount(L) == 0 &&
+      SE.getSmallConstantMaxTripCount(L) > 0 &&
+      SE.getSmallConstantMaxTripCount(L) <= 5) {
+    UP.PeelCount = 2;
+  }
 }
 
 bool HexagonTTIImpl::shouldFavorPostInc() const {

llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp

@@ -978,6 +978,9 @@ static LoopUnrollResult tryToUnrollLoop(
   if (UP.Threshold == 0 && (!UP.Partial || UP.PartialThreshold == 0))
     return LoopUnrollResult::Unmodified;
 
+  if (UP.PeelCount && !canPeel(L))
+    UP.PeelCount = 0;
+
   SmallPtrSet<const Value *, 32> EphValues;
   CodeMetrics::collectEphemeralValues(L, &AC, EphValues);
 

llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp

@@ -69,7 +69,7 @@ static const unsigned InfiniteIterationsToInvariance =
     std::numeric_limits<unsigned>::max();
 
 // Check whether we are capable of peeling this loop.
-static bool canPeel(Loop *L) {
+bool llvm::canPeel(Loop *L) {
   // Make sure the loop is in simplified form
   if (!L->isLoopSimplifyForm())
     return false;
@@ -221,6 +221,9 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
                             TargetTransformInfo::UnrollingPreferences &UP,
                             unsigned &TripCount, ScalarEvolution &SE) {
   assert(LoopSize > 0 && "Zero loop size is not allowed!");
+  // Save the UP.PeelCount value set by the target in
+  // TTI.getUnrollingPreferences or by the flag -unroll-peel-count.
+  unsigned TargetPeelCount = UP.PeelCount;
   UP.PeelCount = 0;
   if (!canPeel(L))
     return;
@@ -240,7 +243,9 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
     SmallDenseMap<PHINode *, unsigned> IterationsToInvariance;
     // Now go through all Phis to calculate their the number of iterations they
     // need to become invariants.
-    unsigned DesiredPeelCount = 0;
+    // Start the max computation with the UP.PeelCount value set by the target
+    // in TTI.getUnrollingPreferences or by the flag -unroll-peel-count.
+    unsigned DesiredPeelCount = TargetPeelCount;
     BasicBlock *BackEdge = L->getLoopLatch();
     assert(BackEdge && "Loop is not in simplified form?");
     for (auto BI = L->getHeader()->begin(); isa<PHINode>(&*BI); ++BI) {

llvm/test/Transforms/LoopUnroll/Hexagon/peel-small-loop.ll

@@ -0,0 +1,37 @@
+; RUN: opt -loop-unroll -mtriple=hexagon -S < %s | FileCheck %s
+; Check that the loop is peeled twice for Hexagon.
+; CHECK: while.body.peel
+; CHECK: while.body.peel2
+
+%struct.STREAM = type { %union.anon, i32, i32 }
+%union.anon = type { i32* }
+
+define void @function(%struct.STREAM* nocapture readonly %b) local_unnamed_addr {
+entry:
+  %bitPtr3 = getelementptr inbounds %struct.STREAM, %struct.STREAM* %b, i32 0, i32 2
+  %0 = load i32, i32* %bitPtr3, align 4
+  %cmp11 = icmp ult i32 %0, 32
+  br i1 %cmp11, label %while.body.preheader, label %do.end
+
+while.body.preheader:
+  %value2 = getelementptr inbounds %struct.STREAM, %struct.STREAM* %b, i32 0, i32 1
+  %1 = load i32, i32* %value2, align 4
+  %w = getelementptr inbounds %struct.STREAM, %struct.STREAM* %b, i32 0, i32 0, i32 0
+  %2 = load i32*, i32** %w, align 4
+  br label %while.body
+
+while.body:
+  %bitPtr.014 = phi i32 [ %add, %while.body ], [ %0, %while.body.preheader ]
+  %value.013 = phi i32 [ %shl, %while.body ], [ %1, %while.body.preheader ]
+  %ptr.012 = phi i32* [ %incdec.ptr, %while.body ], [ %2, %while.body.preheader ]
+  %add = add nuw i32 %bitPtr.014, 8
+  %shr = lshr i32 %value.013, 24
+  %incdec.ptr = getelementptr inbounds i32, i32* %ptr.012, i32 1
+  store i32 %shr, i32* %ptr.012, align 4
+  %shl = shl i32 %value.013, 8
+  %cmp = icmp ult i32 %add, 17
+  br i1 %cmp, label %while.body, label %do.end
+
+do.end:
+  ret void
+}