[IndVars] IV user should not prevent use widening

[mkazantsev]

Summary

Sometimes the an instruction we are trying to widen is used by the IV
(which means the instruction is the IV increment). Currently this may
prevent its widening. We should ignore such user because it will be
dead once the transform is done anyways.

[fhahn]

LGTM thanks.

llvm/lib/Transforms/Utils/SimplifyIndVar.cpp

1572

nit: maybe add the same comment as below?

llvm/lib/Transforms/Utils/SimplifyIndVar.cpp

bool WidenIV::widenWithVariantUse(WidenIV::NarrowIVDefUse DU) {
   }
 
   // Verifying that Defining operand is an AddRec
   const SCEV *Op1 = SE->getSCEV(WideDef);
   const SCEVAddRecExpr *AddRecOp1 = dyn_cast<SCEVAddRecExpr>(Op1);
   if (!AddRecOp1 || AddRecOp1->getLoop() != L)
     return false;
 
+  // Check that all uses are either s/zext, or narrow def (in case of we are
+  // widening the IV increment).
   for (Use &U : NarrowUse->uses()) {
+    if (U.getUser() == NarrowDef)
+      continue;
     Instruction *User = nullptr;
     if (ExtKind == SignExtended)
       User = dyn_cast<SExtInst>(U.getUser());
     else
       User = dyn_cast<ZExtInst>(U.getUser());
     if (!User || User->getType() != WideType)
       return false;
   }
bool WidenIV::widenWithVariantUse(WidenIV::NarrowIVDefUse DU) {
   auto *WideBO = BinaryOperator::Create(NarrowBO->getOpcode(), LHS, RHS,
                                         NarrowBO->getName());
   IRBuilder<> Builder(NarrowUse);
   Builder.Insert(WideBO);
   WideBO->copyIRFlags(NarrowBO);
   ExtendKindMap[NarrowUse] = ExtKind;
 
   for (Use &U : NarrowUse->uses()) {
+    // Ignore narrow def: it will be removed after the transform.
+    if (U.getUser() == NarrowDef)
+      continue;
     Instruction *User = nullptr;
     if (ExtKind == SignExtended)
       User = cast<SExtInst>(U.getUser());
     else
       User = cast<ZExtInst>(U.getUser());
     assert(User->getType() == WideType && "Checked before!");
     LLVM_DEBUG(dbgs() << "INDVARS: eliminating " << *User << " replaced by "
                       << *WideBO << "\n");

llvm/test/Transforms/IndVarSimplify/widen-loop-comp.ll

 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = zext i32 [[START:%.*]] to i64
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ [[TMP0]], [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[COND:%.*]] = icmp eq i64 [[INDVARS_IV]], 0
 ; CHECK-NEXT:    br i1 [[COND]], label [[EXIT:%.*]], label [[BACKEDGE]]
 ; CHECK:       backedge:
-; CHECK-NEXT:    [[TMP1:%.*]] = trunc i64 [[INDVARS_IV]] to i32
-; CHECK-NEXT:    [[IV_NEXT:%.*]] = add i32 [[TMP1]], -1
-; CHECK-NEXT:    [[INDEX:%.*]] = zext i32 [[IV_NEXT]] to i64
-; CHECK-NEXT:    [[STORE_ADDR:%.*]] = getelementptr i32, i32* [[P:%.*]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add nsw i64 [[INDVARS_IV]], -1
+; CHECK-NEXT:    [[STORE_ADDR:%.*]] = getelementptr i32, i32* [[P:%.*]], i64 [[TMP1]]
 ; CHECK-NEXT:    store i32 1, i32* [[STORE_ADDR]], align 4
-; CHECK-NEXT:    [[LOAD_ADDR:%.*]] = getelementptr i32, i32* [[Q:%.*]], i64 [[INDEX]]
-; CHECK-NEXT:    [[STOP:%.*]] = load i32, i32* [[Q]], align 4
+; CHECK-NEXT:    [[STOP:%.*]] = load i32, i32* [[Q:%.*]], align 4
 ; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp eq i32 [[STOP]], 0
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nsw i64 [[INDVARS_IV]], -1
 ; CHECK-NEXT:    br i1 [[LOOP_COND]], label [[LOOP]], label [[FAILURE:%.*]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret i32 0
 ; CHECK:       failure:
 ; CHECK-NEXT:    unreachable
 ;