[VPlan] Address review

Author: artagnon

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -2405,7 +2405,9 @@ void VPWidenIntOrFpInductionRecipe::print(raw_ostream &O, const Twine &Indent,
                                           VPSlotTracker &SlotTracker) const {
   O << Indent;
   printAsOperand(O, SlotTracker);
-  O << " = WIDEN-INDUCTION  ";
+  O << " = WIDEN-INDUCTION";
+  printFlags(O);
+  O << " ";
   printOperands(O, SlotTracker);
 
   if (auto *TI = getTruncInst())

llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp

@@ -547,7 +547,9 @@ static void removeRedundantCanonicalIVs(VPlan &Plan) {
     // only.
     if (!vputils::onlyScalarValuesUsed(WidenOriginalIV) ||
         vputils::onlyFirstLaneUsed(WidenNewIV)) {
-      // Drop poison-generating flags when performing replacement.
+      // We are replacing a wide canonical iv with a suitable wide induction.
+      // This is used to compute header mask, and may sign-wrap, and not
+      // unsigned-wrap, so drop no-wrap flags before performing a replacement.
       WidenOriginalIV->dropPoisonGeneratingFlags();
       WidenNewIV->replaceAllUsesWith(WidenOriginalIV);
       WidenNewIV->eraseFromParent();

llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll

@@ -11,7 +11,7 @@ define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst)
 ; CHECK:  Cost of 0 for VF 2: induction instruction %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop.latch ]
 ; CHECK:  Cost of 1 for VF 2: exit condition instruction %exitcond = icmp eq i64 %iv.next, 32
 ; CHECK:  Cost of 0 for VF 2: EMIT vp<%3> = CANONICAL-INDUCTION ir<0>, vp<%index.next>
-; CHECK:  Cost of 0 for VF 2: ir<%iv> = WIDEN-INDUCTION ir<0>, ir<1>, vp<%0>
+; CHECK:  Cost of 0 for VF 2: ir<%iv> = WIDEN-INDUCTION nuw nsw ir<0>, ir<1>, vp<%0>
 ; CHECK:  Cost of 0 for VF 2: vp<%4> = SCALAR-STEPS vp<%3>, ir<1>
 ; CHECK:  Cost of 0 for VF 2: CLONE ir<%g.src> = getelementptr inbounds ir<%src>, vp<%4>
 ; CHECK:  Cost of 0 for VF 2: vp<%5> = vector-pointer ir<%g.src>
@@ -29,7 +29,7 @@ define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst)
 ; CHECK:  Cost of 0 for VF 4: induction instruction %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop.latch ]
 ; CHECK:  Cost of 1 for VF 4: exit condition instruction %exitcond = icmp eq i64 %iv.next, 32
 ; CHECK:  Cost of 0 for VF 4: EMIT vp<%3> = CANONICAL-INDUCTION ir<0>, vp<%index.next>
-; CHECK:  Cost of 0 for VF 4: ir<%iv> = WIDEN-INDUCTION ir<0>, ir<1>, vp<%0>
+; CHECK:  Cost of 0 for VF 4: ir<%iv> = WIDEN-INDUCTION nuw nsw ir<0>, ir<1>, vp<%0>
 ; CHECK:  Cost of 0 for VF 4: vp<%4> = SCALAR-STEPS vp<%3>, ir<1>
 ; CHECK:  Cost of 0 for VF 4: CLONE ir<%g.src> = getelementptr inbounds ir<%src>, vp<%4>
 ; CHECK:  Cost of 0 for VF 4: vp<%5> = vector-pointer ir<%g.src>

llvm/test/Transforms/LoopVectorize/vplan-printing-reductions.ll

@@ -223,7 +223,7 @@ define i64 @find_last_iv(ptr %a, i64 %n, i64 %start) {
 ; CHECK:        <x1> vector loop: {
 ; CHECK-NEXT:     vector.body:
 ; CHECK-NEXT:     EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ir<0>, vp<%index.next>
-; CHECK-NEXT:     ir<%iv> = WIDEN-INDUCTION ir<0>, ir<1>, vp<{{.+}}>
+; CHECK-NEXT:     ir<%iv> = WIDEN-INDUCTION nuw nsw ir<0>, ir<1>, vp<{{.+}}>
 ; CHECK-NEXT:     WIDEN-REDUCTION-PHI ir<%rdx> = phi ir<-9223372036854775808>, ir<%cond>
 ; CHECK-NEXT:     vp<[[SCALAR_STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>
 ; CHECK-NEXT:     CLONE ir<%gep.a> = getelementptr inbounds ir<%a>, vp<[[SCALAR_STEPS]]>

llvm/test/Transforms/LoopVectorize/vplan-printing.ll

@@ -165,7 +165,7 @@ define void @print_replicate_predicated_phi(i64 %n, ptr %x) {
 ; CHECK-NEXT: <x1> vector loop: {
 ; CHECK-NEXT: vector.body:
 ; CHECK-NEXT:   EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ir<0>, vp<[[CAN_IV_NEXT:%.+]]>
-; CHECK-NEXT:   ir<%i> = WIDEN-INDUCTION ir<0>, ir<1>, vp<[[VF]]>
+; CHECK-NEXT:   ir<%i> = WIDEN-INDUCTION nuw nsw ir<0>, ir<1>, vp<[[VF]]>
 ; CHECK-NEXT:   vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>
 ; CHECK-NEXT:   WIDEN ir<%cmp> = icmp ult ir<%i>, ir<5>
 ; CHECK-NEXT: Successor(s): pred.udiv
@@ -523,7 +523,7 @@ define i32 @print_exit_value(ptr %ptr, i32 %off) {
 ; CHECK-NEXT: <x1> vector loop: {
 ; CHECK-NEXT:   vector.body:
 ; CHECK-NEXT:    EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ir<0>, vp<[[CAN_IV_NEXT:%.+]]>
-; CHECK-NEXT:     ir<%iv> = WIDEN-INDUCTION ir<0>, ir<1>, vp<[[VF]]>
+; CHECK-NEXT:     ir<%iv> = WIDEN-INDUCTION nsw ir<0>, ir<1>, vp<[[VF]]>
 ; CHECK-NEXT:     vp<[[STEPS:%.+]]>    = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>
 ; CHECK-NEXT:     CLONE ir<%gep> = getelementptr inbounds ir<%ptr>, vp<[[STEPS]]>
 ; CHECK-NEXT:     WIDEN ir<%add> = add ir<%iv>, ir<%off>

llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll

@@ -276,7 +276,7 @@ define void @uniform_gep(i64 %k, ptr noalias %A, ptr noalias %B) {
 ; CHECK-NEXT: <x1> vector loop: {
 ; CHECK-NEXT: vector.body:
 ; CHECK-NEXT:   EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
-; CHECK-NEXT:   ir<%iv> = WIDEN-INDUCTION ir<21>, ir<1>, vp<[[VF]]>
+; CHECK-NEXT:   ir<%iv> = WIDEN-INDUCTION nsw ir<21>, ir<1>, vp<[[VF]]>
 ; CHECK-NEXT:   vp<[[DERIVED_IV:%.+]]> = DERIVED-IV ir<21> + vp<[[CAN_IV]]> * ir<1>
 ; CHECK-NEXT:   EMIT vp<[[WIDE_CAN_IV:%.+]]> = WIDEN-CANONICAL-INDUCTION vp<[[CAN_IV]]>
 ; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule vp<[[WIDE_CAN_IV]]>, vp<[[BTC]]>
@@ -1060,7 +1060,7 @@ define void @merge_with_dead_gep_between_regions(i32 %n, i32 %k, ptr noalias %sr
 ; CHECK-NEXT: <x1> vector loop: {
 ; CHECK-NEXT:   vector.body:
 ; CHECK-NEXT:     EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
-; CHECK-NEXT:     ir<%iv> = WIDEN-INDUCTION ir<%n>, ir<-1>, vp<[[VF]]>
+; CHECK-NEXT:     ir<%iv> = WIDEN-INDUCTION nsw ir<%n>, ir<-1>, vp<[[VF]]>
 ; CHECK-NEXT:     vp<[[DERIVED_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
 ; CHECK-NEXT:     WIDEN ir<%cond> = icmp ult ir<%iv>, ir<%k>
 ; CHECK-NEXT:   Successor(s): pred.store