[LAA] Prevent invalid IR for loop-invariant bound in loop body

[loladiro]

Summary

If LAA expands a bound that is loop invariant, but not hoisted out
of the loop body, it used to use that value anyway, causing a
non-domination error, because the memcheck block is of course not
dominated by the scalar loop body. Detect this situation and expand
the SCEV expression instead.

Fixes PR31251

Please note, I don't know this part of the code base at all, so while
I patched up the symptoms, there may be something more fundamental at
play here that I'm oblivious to.

[anemet]

LGTM with the comments below. Thanks for the fix!

test/Analysis/LoopAccessAnalysis/loop-invariant-bound.ll

1

This test should probably be formulated with -loop-versioning under Transform/LoopVersioning

4

No need to specify the target triple.

lib/Analysis/LoopAccessAnalysis.cpp

 /// in \p TheLoop.  \return the values for the bounds.
 static PointerBounds
 expandBounds(const RuntimePointerChecking::CheckingPtrGroup *CG, Loop *TheLoop,
              Instruction *Loc, SCEVExpander &Exp, ScalarEvolution *SE,
              const RuntimePointerChecking &PtrRtChecking) {
   Value *Ptr = PtrRtChecking.Pointers[CG->Members[0]].PointerValue;
   const SCEV *Sc = SE->getSCEV(Ptr);
 
-  if (SE->isLoopInvariant(Sc, TheLoop)) {
-    DEBUG(dbgs() << "LAA: Adding RT check for a loop invariant ptr:" << *Ptr
-                 << "\n");
-    return {Ptr, Ptr};
-  } else {
-    unsigned AS = Ptr->getType()->getPointerAddressSpace();
-    LLVMContext &Ctx = Loc->getContext();
 
-    // Use this type for pointer arithmetic.
-    Type *PtrArithTy = Type::getInt8PtrTy(Ctx, AS);
-    Value *Start = nullptr, *End = nullptr;
 
+  if (SE->isLoopInvariant(Sc, TheLoop)) {
+    DEBUG(dbgs() << "LAA: Adding RT check for a loop invariant ptr:" << *Ptr
+                 << "\n");
+    // Ptr could be in the loop body. If so, expand a new one at the correct
+    // location.
+    Instruction *Inst = dyn_cast<Instruction>(Ptr);
+    Value *NewPtr = (Inst && TheLoop->contains(Inst))
+                        ? Exp.expandCodeFor(Sc, PtrArithTy, Loc)
+                        : Ptr;
+    return {NewPtr, NewPtr};
+  } else {
+    Value *Start = nullptr, *End = nullptr;
     DEBUG(dbgs() << "LAA: Adding RT check for range:\n");
     Start = Exp.expandCodeFor(CG->Low, PtrArithTy, Loc);
     End = Exp.expandCodeFor(CG->High, PtrArithTy, Loc);
     DEBUG(dbgs() << "Start: " << *CG->Low << " End: " << *CG->High << "\n");
     return {Start, End};
   }
 }
 

test/Analysis/LoopAccessAnalysis/loop-invariant-bound.ll

+; RUN: opt -loop-vectorize -S < %s | FileCheck %s
+; Checks that when introducing memcheck, LAA does not accidentally introduce non-dominating instructions
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%Dual.212 = type { %Dual.213, %Partials.215 }
+%Dual.213 = type { double, %Partials.214 }
+%Partials.214 = type { [2 x double] }
+%Partials.215 = type { [2 x %Dual.213] }
+
+; CHECK: vector.memcheck
+
+; Function Attrs: sspreq
+define void @"julia_axpy!_65480"(%Dual.212*) #0 {
+top:
+  br label %if24
+
+if24:                                             ; preds = %if24, %top
+  %"#temp#1.sroa.3.02" = phi i64 [ undef, %top ], [ %2, %if24 ]
+  %"#temp#1.sroa.0.01" = phi i64 [ undef, %top ], [ %1, %if24 ]
+  %1 = add i64 %"#temp#1.sroa.0.01", 1
+  %2 = add i64 %"#temp#1.sroa.3.02", 1
+  ; This pointer is loop invariant. LAA used to re-use it from memcheck, even though it didn't dominate.
+  %v2.sroa.0.0..sroa_cast = bitcast %Dual.212* %0 to i64*
+  %v2.sroa.0.0.copyload = load i64, i64* %v2.sroa.0.0..sroa_cast, align 1
+  %3 = add i64 %"#temp#1.sroa.0.01", -1
+  %4 = getelementptr inbounds %Dual.212, %Dual.212* undef, i64 %3, i32 1, i32 0, i64 0, i32 1, i32 0, i64 0
+  %5 = bitcast double* %4 to i64*
+  store i64 undef, i64* %5, align 8
+  %notlhs27 = icmp eq i64 %2, undef
+  %notrhs28 = icmp eq i64 %1, undef
+  %6 = or i1 %notrhs28, %notlhs27
+  br i1 %6, label %L41.L335_crit_edge, label %if24
+
+L41.L335_crit_edge:                               ; preds = %if24
+  ret void
+}
+
+attributes #0 = { sspreq "no-frame-pointer-elim"="true" "target-cpu"="knl" }