[LoopUnroll] Use Lazy strategy for DTU used for MergeBlockIntoPredecessor.

fhahn · fhahn · commit 3177b92231ae · 2019-08-29T04:26:29.000Z
We do not access the DT in the loop, so we do not have to apply updates eagerly. We can apply them lazyly and flush them after we are done merging blocks. As follow-up work, we might be able to use the DTU above as well, instead of manually updating the DT. This brings the example from PR43134 from ~100s to ~4s for a relase + assertions build on my machine. Reviewers: efriedma, kuhar, asbirlea, brzycki Reviewed By: kuhar, brzycki Differential Revision: https://reviews.llvm.org/D66911 llvm-svn: 370292
diff --git a/llvm/lib/Transforms/Utils/LoopUnroll.cpp b/llvm/lib/Transforms/Utils/LoopUnroll.cpp
@@ -870,7 +870,7 @@ LoopUnrollResult llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
   assert(!DT || !UnrollVerifyDomtree ||
          DT->verify(DominatorTree::VerificationLevel::Fast));
 
-  DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Eager);
+  DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Lazy);
   // Merge adjacent basic blocks, if possible.
   for (BasicBlock *Latch : Latches) {
     BranchInst *Term = dyn_cast<BranchInst>(Latch->getTerminator());
@@ -890,6 +890,8 @@ LoopUnrollResult llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
       }
     }
   }
+  // Apply updates to the DomTree.
+  DT = &DTU.getDomTree();
 
   // At this point, the code is well formed.  We now simplify the unrolled loop,
   // doing constant propagation and dead code elimination as we go.

Original file line number	Diff line number	Diff line change
`@@ -870,7 +870,7 @@ LoopUnrollResult llvm::UnrollLoop(Loop L, UnrollLoopOptions ULO, LoopInfo LI,`
`870`	`870`	`assert(!DT \|\| !UnrollVerifyDomtree \|\|`
`871`	`871`	`DT->verify(DominatorTree::VerificationLevel::Fast));`
`872`	`872`
`873`		`- DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Eager);`
	`873`	`+ DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Lazy);`
`874`	`874`	`// Merge adjacent basic blocks, if possible.`
`875`	`875`	`for (BasicBlock *Latch : Latches) {`
`876`	`876`	`BranchInst *Term = dyn_cast<BranchInst>(Latch->getTerminator());`
`@@ -890,6 +890,8 @@ LoopUnrollResult llvm::UnrollLoop(Loop L, UnrollLoopOptions ULO, LoopInfo LI,`
`890`	`890`	`}`
`891`	`891`	`}`
`892`	`892`	`}`
	`893`	`+ // Apply updates to the DomTree.`
	`894`	`+ DT = &DTU.getDomTree();`
`893`	`895`
`894`	`896`	`// At this point, the code is well formed. We now simplify the unrolled loop,`
`895`	`897`	`// doing constant propagation and dead code elimination as we go.`