[PATCH] D136643: [LoopPeeling] Add flag to disable support for peeling loops with non-latch exits

[Alina Sbirlea via Phabricator via llvm-commits]

asbirlea updated this revision to Diff 470552.
asbirlea added a comment.

Simplified to only the changes in `canPeel`.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D136643/new/

https://reviews.llvm.org/D136643

Files:
  llvm/lib/Transforms/Utils/LoopPeel.cpp
  llvm/test/Transforms/LoopUnroll/peel-branch-weights.ll


Index: llvm/test/Transforms/LoopUnroll/peel-branch-weights.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/peel-branch-weights.ll
+++ llvm/test/Transforms/LoopUnroll/peel-branch-weights.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals
 ; RUN: opt < %s -S -loop-unroll -unroll-force-peel-count=2 2>&1 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -unroll-force-peel-count=2 -disable-advanced-peeling 2>&1 | FileCheck %s --check-prefix=DISABLEADV
 
 declare i32 @get.x()
 
@@ -50,7 +51,22 @@
 ; CHECK-NEXT:    br label [[LOOP_EXIT]]
 ; CHECK:       loop.exit:
 ; CHECK-NEXT:    ret void
-;
+
+; DISABLEADV-LABEL: @test()
+; DISABLEADV-NEXT: entry:
+; DISABLEADV-NEXT:  br label %loop
+; DISABLEADV: loop
+; DISABLEADV-NEXT:  %x = call i32 @get.x()
+; DISABLEADV-NEXT:  switch i32 %x, label %loop.latch [
+; DISABLEADV-NEXT:    i32 0, label %loop.latch
+; DISABLEADV-NEXT:    i32 1, label %loop.exit
+; DISABLEADV-NEXT:    i32 2, label %loop.exit
+; DISABLEADV-NEXT:  ], !prof !0
+; DISABLEADV: loop.latch:
+; DISABLEADV-NEXT:  br label %loop
+; DISABLEADV: loop.exit:
+; DISABLEADV-NEXT:  ret void
+
 entry:
   br label %loop
 
Index: llvm/lib/Transforms/Utils/LoopPeel.cpp
===================================================================
--- llvm/lib/Transforms/Utils/LoopPeel.cpp
+++ llvm/lib/Transforms/Utils/LoopPeel.cpp
@@ -72,12 +72,44 @@
     "unroll-force-peel-count", cl::init(0), cl::Hidden,
     cl::desc("Force a peel count regardless of profiling information."));
 
+static cl::opt<bool> DisableAdvancedPeeling(
+    "disable-advanced-peeling", cl::init(false), cl::Hidden,
+    cl::desc(
+        "Disable advance peeling. Issues for convergent targets (D134803)."));
+
 static const char *PeeledCountMetaData = "llvm.loop.peeled.count";
 
 // Check whether we are capable of peeling this loop.
 bool llvm::canPeel(Loop *L) {
   // Make sure the loop is in simplified form
-  return L->isLoopSimplifyForm();
+  if (!L->isLoopSimplifyForm())
+    return false;
+  if (!DisableAdvancedPeeling)
+    return true;
+
+  // Don't try to peel loops where the latch is not the exiting block.
+  // This can be an indication of two different things:
+  // 1) The loop is not rotated.
+  // 2) The loop contains irreducible control flow that involves the latch.
+  const BasicBlock *Latch = L->getLoopLatch();
+  if (!L->isLoopExiting(Latch))
+    return false;
+
+  // Peeling is only supported if the latch is a branch.
+  if (!isa<BranchInst>(Latch->getTerminator()))
+    return false;
+
+  SmallVector<BasicBlock *, 4> Exits;
+  L->getUniqueNonLatchExitBlocks(Exits);
+  // The latch must either be the only exiting block or all non-latch exit
+  // blocks have either a deopt or unreachable terminator or compose a chain of
+  // blocks where the last one is either deopt or unreachable terminated. Both
+  // deopt and unreachable terminators are a strong indication they are not
+  // taken. Note that this is a profitability check, not a legality check. Also
+  // note that LoopPeeling currently can only update the branch weights of latch
+  // blocks and branch weights to blocks with deopt or unreachable do not need
+  // updating.
+  return llvm::all_of(Exits, IsBlockFollowedByDeoptOrUnreachable);
 }
 
 // This function calculates the number of iterations after which the given Phi
@@ -545,6 +577,7 @@
                     MDB.createBranchWeights(Info.Weights));
 }
 
+
 /// Clones the body of the loop L, putting it between \p InsertTop and \p
 /// InsertBot.
 /// \param IterNumber The serial number of the iteration currently being


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D136643.470552.patch
Type: text/x-patch
Size: 3689 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221025/579fbc89/attachment.bin>