[LoopUnroll] Allow unrolling if the unrolled size does not exceed loop size.

Summary:
In the following cases, unrolling can be beneficial, even when
optimizing for code size:
 1) very low trip counts
 2) potential to constant fold most instructions after fully unrolling.

We can unroll in those cases, by setting the unrolling threshold to the
loop size. This might highlight some cost modeling issues and fixing
them will have a positive impact in general.

Reviewers: vsk, efriedma, dmgreen, paquette

Reviewed By: paquette

Differential Revision: https://reviews.llvm.org/D60265

llvm-svn: 358586

1 files changed, 13 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
index c113e4d3166..53015d25842 100644
--- a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -207,6 +207,7 @@ TargetTransformInfo::UnrollingPreferences llvm::gatherUnrollingPreferences(
   if (OptForSize) {
     UP.Threshold = UP.OptSizeThreshold;
     UP.PartialThreshold = UP.PartialOptSizeThreshold;
+    UP.MaxPercentThresholdBoost = 100;
   }
 
   // Apply any user values specified by cl::opt
@@ -993,6 +994,7 @@ static LoopUnrollResult tryToUnrollLoop(
   if (OnlyWhenForced && !(TM & TM_Enable))
     return LoopUnrollResult::Unmodified;
 
+  bool OptForSize = L->getHeader()->getParent()->hasOptSize();
   unsigned NumInlineCandidates;
   bool NotDuplicatable;
   bool Convergent;
@@ -1000,8 +1002,11 @@ static LoopUnrollResult tryToUnrollLoop(
       L, SE, TTI, BFI, PSI, OptLevel, ProvidedThreshold, ProvidedCount,
       ProvidedAllowPartial, ProvidedRuntime, ProvidedUpperBound,
       ProvidedAllowPeeling);
-  // Exit early if unrolling is disabled.
-  if (UP.Threshold == 0 && (!UP.Partial || UP.PartialThreshold == 0))
+
+  // Exit early if unrolling is disabled. For OptForSize, we pick the loop size
+  // as threshold later on.
+  if (UP.Threshold == 0 && (!UP.Partial || UP.PartialThreshold == 0) &&
+      !OptForSize)
     return LoopUnrollResult::Unmodified;
 
   SmallPtrSet<const Value *, 32> EphValues;
@@ -1016,6 +1021,12 @@ static LoopUnrollResult tryToUnrollLoop(
                       << " instructions.\n");
     return LoopUnrollResult::Unmodified;
   }
+
+  // When optimizing for size, use LoopSize as threshold, to (fully) unroll
+  // loops, if it does not increase code size.
+  if (OptForSize)
+    UP.Threshold = std::max(UP.Threshold, LoopSize);
+
   if (NumInlineCandidates != 0) {
     LLVM_DEBUG(dbgs() << "  Not unrolling loop with inlinable calls.\n");
     return LoopUnrollResult::Unmodified;