[LoopVersioning] Add a check to see if the input loop is in LCSSA form (#116443)

Loop Optimizations expect the input loop to be in LCSSA form. But it
seems that LoopVersioning doesn't have any check to see if the loop is
actually in LCSSA form. As a result, if we give it a loop which is not
in LCSSA form but still correct semantically, the resulting
transformation fails to pass through verifier pass with the following
error.

Instruction does not dominate all uses!
%inc = add nsw i16 undef, 1
store i16 %inc, ptr @c, align 1

As the loop is not in LCSSA form, LoopVersioning's transformations leads
to invalid IR! As some instructions do not dominate all their uses.

This patch checks if a loop is in LCSSA form, if not it will call
formLCSSARecursively on the loop before passing it to LoopVersioning.

Fixes: #36998

Author: VedantParanjape

llvm/lib/Transforms/Utils/LoopVersioning.cpp

@@ -26,6 +26,7 @@
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/Cloning.h"
+#include "llvm/Transforms/Utils/LoopUtils.h"
 #include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"
 
 using namespace llvm;
@@ -278,6 +279,9 @@ bool runImpl(LoopInfo *LI, LoopAccessInfoManager &LAIs, DominatorTree *DT,
     if (!LAI.hasConvergentOp() &&
         (LAI.getNumRuntimePointerChecks() ||
          !LAI.getPSE().getPredicate().isAlwaysTrue())) {
+      if (!L->isLCSSAForm(*DT))
+       formLCSSARecursively(*L, *DT, LI, SE);
+
       LoopVersioning LVer(LAI, LAI.getRuntimePointerChecking()->getChecks(), L,
                           LI, DT, SE);
       LVer.versionLoop();

llvm/test/Transforms/LoopVersioning/crash-36998.ll

@@ -0,0 +1,64 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes=loop-versioning -aa-pipeline='' -S < %s | FileCheck %s
+
+@a = external global i16, align 1
+@b = external global i16, align 1
+@c = external global i16, align 1
+
+define i16 @f2(i16 %a) {
+; CHECK-LABEL: define i16 @f2(
+; CHECK-SAME: i16 [[A:%.*]]) {
+; CHECK-NEXT:  [[FOR_BODY_LVER_CHECK:.*:]]
+; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ult ptr @b, getelementptr inbounds nuw (i8, ptr @a, i64 2)
+; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ult ptr @a, getelementptr inbounds nuw (i8, ptr @b, i64 2)
+; CHECK-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT:    br i1 [[FOUND_CONFLICT]], label %[[FOR_BODY_PH_LVER_ORIG:.*]], label %[[FOR_BODY_PH:.*]]
+; CHECK:       [[FOR_BODY_PH_LVER_ORIG]]:
+; CHECK-NEXT:    br label %[[FOR_BODY_LVER_ORIG:.*]]
+; CHECK:       [[FOR_BODY_LVER_ORIG]]:
+; CHECK-NEXT:    [[TMP0:%.*]] = load i16, ptr @a, align 1
+; CHECK-NEXT:    store i16 [[TMP0]], ptr @b, align 1
+; CHECK-NEXT:    [[INC_LVER_ORIG:%.*]] = add nsw i16 [[A]], 1
+; CHECK-NEXT:    br i1 false, label %[[FOR_BODY_LVER_ORIG]], label %[[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT:.*]]
+; CHECK:       [[FOR_BODY_PH]]:
+; CHECK-NEXT:    br label %[[FOR_BODY:.*]]
+; CHECK:       [[FOR_BODY]]:
+; CHECK-NEXT:    [[TMP1:%.*]] = load i16, ptr @a, align 1, !alias.scope [[META0:![0-9]+]]
+; CHECK-NEXT:    store i16 [[TMP1]], ptr @b, align 1, !alias.scope [[META3:![0-9]+]], !noalias [[META0]]
+; CHECK-NEXT:    [[INC:%.*]] = add nsw i16 [[A]], 1
+; CHECK-NEXT:    br i1 false, label %[[FOR_BODY]], label %[[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT1:.*]]
+; CHECK:       [[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT]]:
+; CHECK-NEXT:    [[INC_LCSSA_PH:%.*]] = phi i16 [ [[INC_LVER_ORIG]], %[[FOR_BODY_LVER_ORIG]] ]
+; CHECK-NEXT:    [[SPLIT2_PH:%.*]] = phi i16 [ [[INC_LVER_ORIG]], %[[FOR_BODY_LVER_ORIG]] ]
+; CHECK-NEXT:    br label %[[FOR_COND_FOR_END_CRIT_EDGE:.*]]
+; CHECK:       [[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT1]]:
+; CHECK-NEXT:    [[INC_LCSSA_PH2:%.*]] = phi i16 [ [[INC]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    [[SPLIT2_PH3:%.*]] = phi i16 [ [[INC]], %[[FOR_BODY]] ]
+; CHECK-NEXT:    br label %[[FOR_COND_FOR_END_CRIT_EDGE]]
+; CHECK:       [[FOR_COND_FOR_END_CRIT_EDGE]]:
+; CHECK-NEXT:    [[INC_LCSSA:%.*]] = phi i16 [ [[INC_LCSSA_PH]], %[[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT]] ], [ [[INC_LCSSA_PH2]], %[[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT1]] ]
+; CHECK-NEXT:    [[SPLIT2:%.*]] = phi i16 [ [[SPLIT2_PH]], %[[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT]] ], [ [[SPLIT2_PH3]], %[[FOR_COND_FOR_END_CRIT_EDGE_LOOPEXIT1]] ]
+; CHECK-NEXT:    store i16 [[INC_LCSSA]], ptr @c, align 1
+; CHECK-NEXT:    ret i16 [[SPLIT2]]
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %0 = load i16, ptr @a, align 1
+  store i16 %0, ptr @b, align 1
+  %inc = add nsw i16 %a, 1
+  br i1 false, label %for.body, label %for.cond.for.end_crit_edge
+
+for.cond.for.end_crit_edge:                       ; preds = %for.body
+  %split2 = phi i16 [ %inc, %for.body ]
+  store i16 %inc, ptr @c, align 1
+  ret i16 %split2
+}
+;.
+; CHECK: [[META0]] = !{[[META1:![0-9]+]]}
+; CHECK: [[META1]] = distinct !{[[META1]], [[META2:![0-9]+]]}
+; CHECK: [[META2]] = distinct !{[[META2]], !"LVerDomain"}
+; CHECK: [[META3]] = !{[[META4:![0-9]+]]}
+; CHECK: [[META4]] = distinct !{[[META4]], [[META2]]}
+;.