[LV] Use IVUpdateMayOverflow to set HasNUW.

If IVUpdateMayOverflow is false, we proved that the induction increment
cannot overflow in the vector loop. This allows setting NUW in some
cases when folding the tail.

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -9014,9 +9014,12 @@ LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range) {
 
   DebugLoc DL = getDebugLocFromInstOrOperands(Legal->getPrimaryInduction());
   TailFoldingStyle Style = CM.getTailFoldingStyle(IVUpdateMayOverflow);
-  // When not folding the tail, we know that the induction increment will not
-  // overflow.
-  bool HasNUW = Style == TailFoldingStyle::None;
+  // Use NUW for the induction increment if we proved that it won't overflow in
+  // the vector loop or when not folding the tail. Then we know that the
+  // induction increment will not overflow as the vector trip count is >=
+  // increment and a multiple of the increment.
+  bool HasNUW = !IVUpdateMayOverflow || Style == TailFoldingStyle::None;
+  ;
   addCanonicalIVRecipes(*Plan, Legal->getWidestInductionType(), HasNUW, DL);
 
   VPRecipeBuilder RecipeBuilder(*Plan, OrigLoop, TLI, Legal, CM, PSE, Builder);

llvm/test/Transforms/LoopVectorize/ARM/tail-folding-loop-hint.ll

@@ -50,7 +50,7 @@ define dso_local void @predicate_loop_hint(ptr noalias nocapture %A, ptr noalias
 ; CHECK:         %[[WML2:.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0({{.*}}<4 x i1> %active.lane.mask
 ; CHECK:         %[[ADD:.*]] = add nsw <4 x i32> %[[WML2]], %[[WML1]]
 ; CHECK:         call void @llvm.masked.store.v4i32.p0(<4 x i32> %[[ADD]], {{.*}}<4 x i1> %active.lane.mask
-; CHECK:         %index.next = add i64 %index, 4
+; CHECK:         %index.next = add nuw i64 %index, 4
 ; CHECK:         br i1 %{{.*}}, label %{{.*}}, label %vector.body, !llvm.loop [[VEC_LOOP2:![0-9]+]]
 ;
 ; CHECK:         br i1 %{{.*}}, label %{{.*}}, label %for.body, !llvm.loop [[SCALAR_LOOP2:![0-9]+]]

llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll

@@ -55,7 +55,7 @@ define void @test(ptr %p, i64 %a, i8 %b) {
 ; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE8]]
 ; CHECK:       pred.store.continue8:
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
 ; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY1]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]

llvm/test/Transforms/LoopVectorize/X86/pr81872.ll

@@ -35,7 +35,7 @@ define void @test(ptr noundef align 8 dereferenceable_or_null(16) %arr) #0 {
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 -3
 ; CHECK-NEXT:    [[REVERSE:%.*]] = shufflevector <4 x i1> [[TMP4]], <4 x i1> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; CHECK-NEXT:    call void @llvm.masked.store.v4i64.p0(<4 x i64> <i64 1, i64 1, i64 1, i64 1>, ptr [[TMP8]], i32 8, <4 x i1> [[REVERSE]])
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 -4, i64 -4, i64 -4, i64 -4>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 12
 ; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !prof [[PROF1:![0-9]+]], !llvm.loop [[LOOP2:![0-9]+]]