[Loop Peeling] Separate the Loop Peeling Utilities from the Loop Unrolling Utilities

Summary: This patch separates the Loop Peeling Utilities from Loop Unrolling.
The reason for this change is that Loop Peeling is no longer only being used by
loop unrolling; Patch D82927 introduces loop peeling with fusion, such that
loops can be modified to have to same trip count, making them legal to be
peeled.

Reviewed By: Meinersbur

Differential Revision: https://reviews.llvm.org/D83056

include/llvm/Transforms/Utils/LoopPeel.h

@@ -0,0 +1,40 @@
+//===- llvm/Transforms/Utils/LoopPeel.h ----- Peeling utilities -*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines some loop peeling utilities. It does not define any
+// actual pass or policy.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TRANSFORMS_UTILS_LOOPPEEL_H
+#define LLVM_TRANSFORMS_UTILS_LOOPPEEL_H
+
+#include "llvm/Analysis/TargetTransformInfo.h"
+
+namespace llvm {
+
+bool canPeel(Loop *L);
+
+bool peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI, ScalarEvolution *SE,
+              DominatorTree *DT, AssumptionCache *AC, bool PreserveLCSSA);
+
+TargetTransformInfo::PeelingPreferences
+gatherPeelingPreferences(Loop *L, ScalarEvolution &SE,
+                         const TargetTransformInfo &TTI,
+                         Optional<bool> UserAllowPeeling,
+                         Optional<bool> UserAllowProfileBasedPeeling,
+                         bool UnrollingSpecficValues = false);
+
+void computePeelCount(Loop *L, unsigned LoopSize,
+                      TargetTransformInfo::PeelingPreferences &PP,
+                      unsigned &TripCount, ScalarEvolution &SE,
+                      unsigned Threshold = UINT_MAX);
+
+} // end namespace llvm
+
+#endif // LLVM_TRANSFORMS_UTILS_LOOPPEEL_H

include/llvm/Transforms/Utils/UnrollLoop.h

@@ -92,16 +92,6 @@ bool UnrollRuntimeLoopRemainder(
     const TargetTransformInfo *TTI, bool PreserveLCSSA,
     Loop **ResultLoop = nullptr);
 
-void computePeelCount(Loop *L, unsigned LoopSize,
-                      TargetTransformInfo::UnrollingPreferences &UP,
-                      TargetTransformInfo::PeelingPreferences &PP,
-                      unsigned &TripCount, ScalarEvolution &SE);
-
-bool canPeel(Loop *L);
-
-bool peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI, ScalarEvolution *SE,
-              DominatorTree *DT, AssumptionCache *AC, bool PreserveLCSSA);
-
 LoopUnrollResult UnrollAndJamLoop(Loop *L, unsigned Count, unsigned TripCount,
                                   unsigned TripMultiple, bool UnrollRemainder,
                                   LoopInfo *LI, ScalarEvolution *SE,
@@ -121,7 +111,6 @@ bool computeUnrollCount(Loop *L, const TargetTransformInfo &TTI,
                         unsigned &TripMultiple, unsigned LoopSize,
                         TargetTransformInfo::UnrollingPreferences &UP,
                         TargetTransformInfo::PeelingPreferences &PP,
-
                         bool &UseUpperBound);
 
 void simplifyLoopAfterUnroll(Loop *L, bool SimplifyIVs, LoopInfo *LI,
@@ -138,12 +127,6 @@ TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
     Optional<bool> UserAllowPartial, Optional<bool> UserRuntime,
     Optional<bool> UserUpperBound, Optional<unsigned> UserFullUnrollMaxCount);
 
-TargetTransformInfo::PeelingPreferences
-gatherPeelingPreferences(Loop *L, ScalarEvolution &SE,
-                         const TargetTransformInfo &TTI,
-                         Optional<bool> UserAllowPeeling,
-                         Optional<bool> UserAllowProfileBasedPeeling);
-
 unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls,
                              bool &NotDuplicatable, bool &Convergent,
                              const TargetTransformInfo &TTI,

lib/Target/Hexagon/HexagonTargetTransformInfo.cpp

@@ -21,6 +21,7 @@
 #include "llvm/IR/User.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
+#include "llvm/Transforms/Utils/LoopPeel.h"
 #include "llvm/Transforms/Utils/UnrollLoop.h"
 
 using namespace llvm;

lib/Transforms/Scalar/LoopFuse.cpp

@@ -66,7 +66,7 @@
 #include "llvm/Transforms/Utils.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/CodeMoverUtils.h"
-#include "llvm/Transforms/Utils/UnrollLoop.h"
+#include "llvm/Transforms/Utils/LoopPeel.h"
 
 using namespace llvm;
 

lib/Transforms/Scalar/LoopUnrollAndJamPass.cpp

@@ -41,6 +41,7 @@
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Transforms/Scalar.h"
+#include "llvm/Transforms/Utils/LoopPeel.h"
 #include "llvm/Transforms/Utils/LoopSimplify.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
 #include "llvm/Transforms/Utils/UnrollLoop.h"

lib/Transforms/Scalar/LoopUnrollPass.cpp

@@ -56,6 +56,7 @@
 #include "llvm/Transforms/Scalar.h"
 #include "llvm/Transforms/Scalar/LoopPassManager.h"
 #include "llvm/Transforms/Utils.h"
+#include "llvm/Transforms/Utils/LoopPeel.h"
 #include "llvm/Transforms/Utils/LoopSimplify.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
 #include "llvm/Transforms/Utils/SizeOpts.h"
@@ -115,10 +116,6 @@ static cl::opt<unsigned> UnrollFullMaxCount(
     cl::desc(
         "Set the max unroll count for full unrolling, for testing purposes"));
 
-static cl::opt<unsigned> UnrollPeelCount(
-    "unroll-peel-count", cl::Hidden,
-    cl::desc("Set the unroll peeling count, for testing purposes"));
-
 static cl::opt<bool>
     UnrollAllowPartial("unroll-allow-partial", cl::Hidden,
                        cl::desc("Allows loops to be partially unrolled until "
@@ -149,15 +146,6 @@ static cl::opt<unsigned> FlatLoopTripCountThreshold(
              "threshold, the loop is considered as flat and will be less "
              "aggressively unrolled."));
 
-static cl::opt<bool>
-    UnrollAllowPeeling("unroll-allow-peeling", cl::init(true), cl::Hidden,
-                       cl::desc("Allows loops to be peeled when the dynamic "
-                                "trip count is known to be low."));
-
-static cl::opt<bool> UnrollAllowLoopNestsPeeling(
-    "unroll-allow-loop-nests-peeling", cl::init(false), cl::Hidden,
-    cl::desc("Allows loop nests to be peeled."));
-
 static cl::opt<bool> UnrollUnrollRemainder(
   "unroll-remainder", cl::Hidden,
   cl::desc("Allow the loop remainder to be unrolled."));
@@ -275,39 +263,6 @@ TargetTransformInfo::UnrollingPreferences llvm::gatherUnrollingPreferences(
   return UP;
 }
 
-TargetTransformInfo::PeelingPreferences
-llvm::gatherPeelingPreferences(Loop *L, ScalarEvolution &SE,
-                               const TargetTransformInfo &TTI,
-                               Optional<bool> UserAllowPeeling,
-                               Optional<bool> UserAllowProfileBasedPeeling) {
-  TargetTransformInfo::PeelingPreferences PP;
-
-  // Default values
-  PP.PeelCount = 0;
-  PP.AllowPeeling = true;
-  PP.AllowLoopNestsPeeling = false;
-  PP.PeelProfiledIterations = true;
-
-  // Get Target Specifc Values
-  TTI.getPeelingPreferences(L, SE, PP);
-
-  // User Specified Values using cl::opt
-  if (UnrollPeelCount.getNumOccurrences() > 0)
-    PP.PeelCount = UnrollPeelCount;
-  if (UnrollAllowPeeling.getNumOccurrences() > 0)
-    PP.AllowPeeling = UnrollAllowPeeling;
-  if (UnrollAllowLoopNestsPeeling.getNumOccurrences() > 0)
-    PP.AllowLoopNestsPeeling = UnrollAllowLoopNestsPeeling;
-
-  // User Specifed values provided by argument
-  if (UserAllowPeeling.hasValue())
-    PP.AllowPeeling = *UserAllowPeeling;
-  if (UserAllowProfileBasedPeeling.hasValue())
-    PP.PeelProfiledIterations = *UserAllowProfileBasedPeeling;
-
-  return PP;
-}
-
 namespace {
 
 /// A struct to densely store the state of an instruction after unrolling at
@@ -881,7 +836,7 @@ bool llvm::computeUnrollCount(
   }
 
   // 4th priority is loop peeling.
-  computePeelCount(L, LoopSize, UP, PP, TripCount, SE);
+  computePeelCount(L, LoopSize, PP, TripCount, SE, UP.Threshold);
   if (PP.PeelCount) {
     UP.Runtime = false;
     UP.Count = 1;
@@ -1087,7 +1042,7 @@ static LoopUnrollResult tryToUnrollLoop(
       ProvidedAllowPartial, ProvidedRuntime, ProvidedUpperBound,
       ProvidedFullUnrollMaxCount);
   TargetTransformInfo::PeelingPreferences PP = gatherPeelingPreferences(
-      L, SE, TTI, ProvidedAllowPeeling, ProvidedAllowProfileBasedPeeling);
+      L, SE, TTI, ProvidedAllowPeeling, ProvidedAllowProfileBasedPeeling, true);
 
   // Exit early if unrolling is disabled. For OptForSize, we pick the loop size
   // as threshold later on.

lib/Transforms/Utils/CMakeLists.txt

@@ -35,11 +35,11 @@ add_llvm_component_library(LLVMTransformUtils
   LCSSA.cpp
   LibCallsShrinkWrap.cpp
   Local.cpp
+  LoopPeel.cpp
   LoopRotationUtils.cpp
   LoopSimplify.cpp
   LoopUnroll.cpp
   LoopUnrollAndJam.cpp
-  LoopUnrollPeel.cpp
   LoopUnrollRuntime.cpp
   LoopUtils.cpp
   LoopVersioning.cpp

lib/Transforms/Utils/LoopPeel.cpp

@@ -1,4 +1,4 @@
-//===- UnrollLoopPeel.cpp - Loop peeling utilities ------------------------===//
+//===- LoopPeel.cpp -------------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
@@ -6,12 +6,10 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements some loop unrolling utilities for peeling loops
+// Loop Peeling Utilities.
-// with dynamically inferred (from PGO) trip counts. See LoopUnroll.cpp for
-// unrolling loops with compile-time constant trip counts.
-//
 //===----------------------------------------------------------------------===//
 
+#include "llvm/Transforms/Utils/LoopPeel.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/SmallVector.h"
@@ -49,10 +47,24 @@
 using namespace llvm;
 using namespace llvm::PatternMatch;
 
-#define DEBUG_TYPE "loop-unroll"
+#define DEBUG_TYPE "loop-peel"
 
 STATISTIC(NumPeeled, "Number of loops peeled");
 
+static cl::opt<unsigned> UnrollPeelCount(
+    "unroll-peel-count", cl::Hidden,
+    cl::desc("Set the unroll peeling count, for testing purposes"));
+
+static cl::opt<bool>
+    UnrollAllowPeeling("unroll-allow-peeling", cl::init(true), cl::Hidden,
+                       cl::desc("Allows loops to be peeled when the dynamic "
+                                "trip count is known to be low."));
+
+static cl::opt<bool>
+    UnrollAllowLoopNestsPeeling("unroll-allow-loop-nests-peeling",
+                                cl::init(false), cl::Hidden,
+                                cl::desc("Allows loop nests to be peeled."));
+
 static cl::opt<unsigned> UnrollPeelMaxCount(
     "unroll-peel-max-count", cl::init(7), cl::Hidden,
     cl::desc("Max average trip count which will cause loop peeling."));
@@ -278,9 +290,9 @@ static unsigned countToEliminateCompares(Loop &L, unsigned MaxPeelCount,
 
 // Return the number of iterations we want to peel off.
 void llvm::computePeelCount(Loop *L, unsigned LoopSize,
-                            TargetTransformInfo::UnrollingPreferences &UP,
                             TargetTransformInfo::PeelingPreferences &PP,
-                            unsigned &TripCount, ScalarEvolution &SE) {
+                            unsigned &TripCount, ScalarEvolution &SE,
+                            unsigned Threshold) {
   assert(LoopSize > 0 && "Zero loop size is not allowed!");
   // Save the PP.PeelCount value set by the target in
   // TTI.getPeelingPreferences or by the flag -unroll-peel-count.
@@ -322,7 +334,7 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
   // maximum number of iterations among these values, thus turning all those
   // Phis into invariants.
   // First, check that we can peel at least one iteration.
-  if (2 * LoopSize <= UP.Threshold && UnrollPeelMaxCount > 0) {
+  if (2 * LoopSize <= Threshold && UnrollPeelMaxCount > 0) {
     // Store the pre-calculated values here.
     SmallDenseMap<PHINode *, unsigned> IterationsToInvariance;
     // Now go through all Phis to calculate their the number of iterations they
@@ -342,7 +354,7 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
 
     // Pay respect to limitations implied by loop size and the max peel count.
     unsigned MaxPeelCount = UnrollPeelMaxCount;
-    MaxPeelCount = std::min(MaxPeelCount, UP.Threshold / LoopSize - 1);
+    MaxPeelCount = std::min(MaxPeelCount, Threshold / LoopSize - 1);
 
     DesiredPeelCount = std::max(DesiredPeelCount,
                                 countToEliminateCompares(*L, MaxPeelCount, SE));
@@ -385,7 +397,7 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
 
     if (*PeelCount) {
       if ((*PeelCount + AlreadyPeeled <= UnrollPeelMaxCount) &&
-          (LoopSize * (*PeelCount + 1) <= UP.Threshold)) {
+          (LoopSize * (*PeelCount + 1) <= Threshold)) {
         LLVM_DEBUG(dbgs() << "Peeling first " << *PeelCount
                           << " iterations.\n");
         PP.PeelCount = *PeelCount;
@@ -396,7 +408,7 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
       LLVM_DEBUG(dbgs() << "Max peel count: " << UnrollPeelMaxCount << "\n");
       LLVM_DEBUG(dbgs() << "Peel cost: " << LoopSize * (*PeelCount + 1)
                         << "\n");
-      LLVM_DEBUG(dbgs() << "Max peel cost: " << UP.Threshold << "\n");
+      LLVM_DEBUG(dbgs() << "Max peel cost: " << Threshold << "\n");
     }
   }
 }
@@ -491,7 +503,7 @@ static void fixupBranchWeights(BasicBlock *Header, BranchInst *LatchBR,
 /// instructions in the last peeled-off iteration.
 static void cloneLoopBlocks(
     Loop *L, unsigned IterNumber, BasicBlock *InsertTop, BasicBlock *InsertBot,
-    SmallVectorImpl<std::pair<BasicBlock *, BasicBlock *> > &ExitEdges,
+    SmallVectorImpl<std::pair<BasicBlock *, BasicBlock *>> &ExitEdges,
     SmallVectorImpl<BasicBlock *> &NewBlocks, LoopBlocksDFS &LoopBlocks,
     ValueToValueMapTy &VMap, ValueToValueMapTy &LVMap, DominatorTree *DT,
     LoopInfo *LI) {
@@ -599,6 +611,40 @@ static void cloneLoopBlocks(
     LVMap[KV.first] = KV.second;
 }
 
+TargetTransformInfo::PeelingPreferences llvm::gatherPeelingPreferences(
+    Loop *L, ScalarEvolution &SE, const TargetTransformInfo &TTI,
+    Optional<bool> UserAllowPeeling,
+    Optional<bool> UserAllowProfileBasedPeeling, bool UnrollingSpecficValues) {
+  TargetTransformInfo::PeelingPreferences PP;
+
+  // Set the default values.
+  PP.PeelCount = 0;
+  PP.AllowPeeling = true;
+  PP.AllowLoopNestsPeeling = false;
+  PP.PeelProfiledIterations = true;
+
+  // Get the target specifc values.
+  TTI.getPeelingPreferences(L, SE, PP);
+
+  // User specified values using cl::opt.
+  if (UnrollingSpecficValues) {
+    if (UnrollPeelCount.getNumOccurrences() > 0)
+      PP.PeelCount = UnrollPeelCount;
+    if (UnrollAllowPeeling.getNumOccurrences() > 0)
+      PP.AllowPeeling = UnrollAllowPeeling;
+    if (UnrollAllowLoopNestsPeeling.getNumOccurrences() > 0)
+      PP.AllowLoopNestsPeeling = UnrollAllowLoopNestsPeeling;
+  }
+
+  // User specifed values provided by argument.
+  if (UserAllowPeeling.hasValue())
+    PP.AllowPeeling = *UserAllowPeeling;
+  if (UserAllowProfileBasedPeeling.hasValue())
+    PP.PeelProfiledIterations = *UserAllowProfileBasedPeeling;
+
+  return PP;
+}
+
 /// Peel off the first \p PeelCount iterations of loop \p L.
 ///
 /// Note that this does not peel them off as a single straight-line block.
@@ -609,8 +655,8 @@ static void cloneLoopBlocks(
 /// for the bulk of dynamic execution, can be further simplified by scalar
 /// optimizations.
 bool llvm::peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI,
-                    ScalarEvolution *SE, DominatorTree *DT,
+                    ScalarEvolution *SE, DominatorTree *DT, AssumptionCache *AC,
-                    AssumptionCache *AC, bool PreserveLCSSA) {
+                    bool PreserveLCSSA) {
   assert(PeelCount > 0 && "Attempt to peel out zero iterations?");
   assert(canPeel(L) && "Attempt to peel a loop which is not peelable?");
 

lib/Transforms/Utils/LoopUnroll.cpp

@@ -59,6 +59,7 @@
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/Cloning.h"
 #include "llvm/Transforms/Utils/Local.h"
+#include "llvm/Transforms/Utils/LoopPeel.h"
 #include "llvm/Transforms/Utils/LoopSimplify.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
 #include "llvm/Transforms/Utils/SimplifyIndVar.h"