[LoopUnrollAndJam] Changed safety checks to consider more than 2-levels

loop nest. Summary: As discussed in https://reviews.llvm.org/D73129. Example Before unroll and jam: for A for B for C D E After unroll and jam (currently): for A A' for B for C D B' for C' D' E E' After unroll and jam (Ideal): for A A' for B B' for C C' D D' E E' This is the first patch to change unroll and jam to work in the ideal way. This patch change the safety checks needed to make sure is safe to unroll and jam in the ideal way. Reviewer: dmgreen, jdoerfert, Meinersbur, kbarton, bmahjour, etiotto Reviewed By: Meinersbur Subscribers: fhahn, hiraditya, zzheng, llvm-commits, anhtuyen, prithayan Tag: LLVM Differential Revision: https://reviews.llvm.org/D76132
YuriPlyakhin · May 6, 2020 · 0a52401 · 0a52401
1 parent 314f99e
commit 0a52401
Show file tree

Hide file tree

Showing 5 changed files with 504 additions and 142 deletions.
diff --git a/llvm/include/llvm/Transforms/Utils/UnrollLoop.h b/llvm/include/llvm/Transforms/Utils/UnrollLoop.h
@@ -110,7 +110,7 @@ LoopUnrollResult UnrollAndJamLoop(Loop *L, unsigned Count, unsigned TripCount,
                                   Loop **EpilogueLoop = nullptr);
 
 bool isSafeToUnrollAndJam(Loop *L, ScalarEvolution &SE, DominatorTree &DT,
-                          DependenceInfo &DI);
+                          DependenceInfo &DI, LoopInfo &LI);
 
 bool computeUnrollCount(Loop *L, const TargetTransformInfo &TTI,
                         DominatorTree &DT, LoopInfo *LI, ScalarEvolution &SE,

diff --git a/llvm/lib/Transforms/Scalar/LoopUnrollAndJamPass.cpp b/llvm/lib/Transforms/Scalar/LoopUnrollAndJamPass.cpp
@@ -280,21 +280,6 @@ tryToUnrollAndJamLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
                       ScalarEvolution &SE, const TargetTransformInfo &TTI,
                       AssumptionCache &AC, DependenceInfo &DI,
                       OptimizationRemarkEmitter &ORE, int OptLevel) {
-  // Quick checks of the correct loop form
-  if (!L->isLoopSimplifyForm() || L->getSubLoops().size() != 1)
-    return LoopUnrollResult::Unmodified;
-  Loop *SubLoop = L->getSubLoops()[0];
-  if (!SubLoop->isLoopSimplifyForm())
-    return LoopUnrollResult::Unmodified;
-
-  BasicBlock *Latch = L->getLoopLatch();
-  BasicBlock *Exit = L->getExitingBlock();
-  BasicBlock *SubLoopLatch = SubLoop->getLoopLatch();
-  BasicBlock *SubLoopExit = SubLoop->getExitingBlock();
-
-  if (Latch != Exit || SubLoopLatch != SubLoopExit)
-    return LoopUnrollResult::Unmodified;
-
   TargetTransformInfo::UnrollingPreferences UP =
       gatherUnrollingPreferences(L, SE, TTI, nullptr, nullptr, OptLevel, None,
                                  None, None, None, None, None, None, None);
@@ -324,7 +309,7 @@ tryToUnrollAndJamLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
     return LoopUnrollResult::Unmodified;
   }
 
-  if (!isSafeToUnrollAndJam(L, SE, DT, DI)) {
+  if (!isSafeToUnrollAndJam(L, SE, DT, DI, *LI)) {
     LLVM_DEBUG(dbgs() << "  Disabled due to not being safe.\n");
     return LoopUnrollResult::Unmodified;
   }
@@ -335,6 +320,7 @@ tryToUnrollAndJamLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
   bool Convergent;
   SmallPtrSet<const Value *, 32> EphValues;
   CodeMetrics::collectEphemeralValues(L, &AC, EphValues);
+  Loop *SubLoop = L->getSubLoops()[0];
   unsigned InnerLoopSize =
       ApproximateLoopSize(SubLoop, NumInlineCandidates, NotDuplicatable,
                           Convergent, TTI, EphValues, UP.BEInsns);
@@ -372,6 +358,8 @@ tryToUnrollAndJamLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
     SubLoop->setLoopID(NewInnerEpilogueLoopID.getValue());
 
   // Find trip count and trip multiple
+  BasicBlock *Latch = L->getLoopLatch();
+  BasicBlock *SubLoopLatch = SubLoop->getLoopLatch();
   unsigned OuterTripCount = SE.getSmallConstantTripCount(L, Latch);
   unsigned OuterTripMultiple = SE.getSmallConstantTripMultiple(L, Latch);
   unsigned InnerTripCount = SE.getSmallConstantTripCount(SubLoop, SubLoopLatch);