[LoopPeel] Implement initial peeling off the last loop iteration.

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -680,6 +680,9 @@ class TargetTransformInfo {
     /// If the value is true the peeling cost model can decide to peel only
     /// some iterations and in this case it will set this to false.
     bool PeelProfiledIterations;
+
+    /// Peel off the last PeelCount loop iterations.
+    bool PeelLast;
   };
 
   /// Get target-customized preferences for the generic loop peeling

llvm/include/llvm/Transforms/Utils/LoopPeel.h

@@ -21,11 +21,18 @@ namespace llvm {
 
 bool canPeel(const Loop *L);
 
+/// Returns true if the last iteration of \p L can be peeled off. It makes sure
+/// the loop exit condition can be adjusted when peeling and that the loop
+/// executes at least 2 iterations.
+bool canPeelLastIteration(const Loop &L, ScalarEvolution &SE);
+
 /// VMap is the value-map that maps instructions from the original loop to
-/// instructions in the last peeled-off iteration.
-bool peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI, ScalarEvolution *SE,
-              DominatorTree &DT, AssumptionCache *AC, bool PreserveLCSSA,
-              ValueToValueMapTy &VMap);
+/// instructions in the last peeled-off iteration. If \p PeelLast is true, peel
+/// off the last \p PeelCount iterations from \p L (canPeelLastIteration must be
+/// true for \p L), otherwise peel off the first \p PeelCount iterations.
+bool peelLoop(Loop *L, unsigned PeelCount, bool PeelLast, LoopInfo *LI,
+              ScalarEvolution *SE, DominatorTree &DT, AssumptionCache *AC,
+              bool PreserveLCSSA, ValueToValueMapTy &VMap);
 
 TargetTransformInfo::PeelingPreferences
 gatherPeelingPreferences(Loop *L, ScalarEvolution &SE,

llvm/lib/Transforms/Scalar/LoopFuse.cpp

@@ -790,7 +790,8 @@ struct LoopFuser {
                       << " iterations of the first loop. \n");
 
     ValueToValueMapTy VMap;
-    FC0.Peeled = peelLoop(FC0.L, PeelCount, &LI, &SE, DT, &AC, true, VMap);
+    FC0.Peeled =
+        peelLoop(FC0.L, PeelCount, false, &LI, &SE, DT, &AC, true, VMap);
     if (FC0.Peeled) {
       LLVM_DEBUG(dbgs() << "Done Peeling\n");
 

llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp

@@ -1314,7 +1314,8 @@ tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI, ScalarEvolution &SE,
     });
 
     ValueToValueMapTy VMap;
-    if (peelLoop(L, PP.PeelCount, LI, &SE, DT, &AC, PreserveLCSSA, VMap)) {
+    if (peelLoop(L, PP.PeelCount, PP.PeelLast, LI, &SE, DT, &AC, PreserveLCSSA,
+                 VMap)) {
       simplifyLoopAfterUnroll(L, true, LI, &SE, &DT, &AC, &TTI, nullptr);
       // If the loop was peeled, we already "used up" the profile information
       // we had, so we don't want to unroll or peel again.