[LV] Add test for tail fold by masking with external IV users. (#82329)

Test case for #76069

Author: niwinanto

llvm/test/Transforms/LoopVectorize/no-fold-tail-by-masking-iv-external-uses.ll

@@ -0,0 +1,159 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S | FileCheck %s
+
+; FIXME: The vectorizer should refuse to fold the tail by masking because
+; %conv is used outside of the loop. Test for this by checking that
+; %n.vec, the vector trip count, is rounded down to the next multiple of
+; 4. If folding the tail, it would have been rounded up instead.
+; Test case for #76069(https://github.com/llvm/llvm-project/issues/76069).
+define i32 @test(ptr %arr, i64 %n) {
+; CHECK-LABEL: define i32 @test(
+; CHECK-SAME: ptr [[ARR:%.*]], i64 [[N:%.*]]) {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp ugt i64 [[N]], 1
+; CHECK-NEXT:    br i1 [[CMP1]], label [[PREHEADER:%.*]], label [[DONE:%.*]]
+; CHECK:       preheader:
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[N]], -1
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; CHECK:       vector.scevcheck:
+; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[N]], -2
+; CHECK-NEXT:    [[TMP2:%.*]] = trunc i64 [[TMP1]] to i8
+; CHECK-NEXT:    [[TMP3:%.*]] = add i8 1, [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp ult i8 [[TMP3]], 1
+; CHECK-NEXT:    [[TMP5:%.*]] = icmp ugt i64 [[TMP1]], 255
+; CHECK-NEXT:    [[TMP6:%.*]] = or i1 [[TMP4]], [[TMP5]]
+; CHECK-NEXT:    [[TMP7:%.*]] = trunc i64 [[TMP1]] to i8
+; CHECK-NEXT:    [[TMP8:%.*]] = add i8 2, [[TMP7]]
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp ult i8 [[TMP8]], 2
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp ugt i64 [[TMP1]], 255
+; CHECK-NEXT:    [[TMP11:%.*]] = or i1 [[TMP9]], [[TMP10]]
+; CHECK-NEXT:    [[TMP12:%.*]] = or i1 [[TMP6]], [[TMP11]]
+; CHECK-NEXT:    br i1 [[TMP12]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[TMP0]], 3
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[IND_END:%.*]] = add i64 1, [[N_VEC]]
+; CHECK-NEXT:    [[DOTCAST:%.*]] = trunc i64 [[N_VEC]] to i8
+; CHECK-NEXT:    [[IND_END1:%.*]] = add i8 1, [[DOTCAST]]
+; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[TMP0]], 1
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE10:%.*]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 1, i64 2, i64 3, i64 4>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE10]] ]
+; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 1, [[INDEX]]
+; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[OFFSET_IDX]], 0
+; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[OFFSET_IDX]], 1
+; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[OFFSET_IDX]], 2
+; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[OFFSET_IDX]], 3
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <4 x i64> poison, i64 [[INDEX]], i64 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT3]], <4 x i64> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[VEC_IV:%.*]] = add <4 x i64> [[BROADCAST_SPLAT4]], <i64 0, i64 1, i64 2, i64 3>
+; CHECK-NEXT:    [[TMP17:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[TMP18:%.*]] = add nsw <4 x i64> [[VEC_IND]], <i64 -1, i64 -1, i64 -1, i64 -1>
+; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <4 x i1> [[TMP17]], i32 0
+; CHECK-NEXT:    br i1 [[TMP19]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
+; CHECK:       pred.store.if:
+; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i64> [[TMP18]], i32 0
+; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, ptr [[ARR]], i64 [[TMP20]]
+; CHECK-NEXT:    store i32 65, ptr [[TMP21]], align 4
+; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE]]
+; CHECK:       pred.store.continue:
+; CHECK-NEXT:    [[TMP22:%.*]] = extractelement <4 x i1> [[TMP17]], i32 1
+; CHECK-NEXT:    br i1 [[TMP22]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6:%.*]]
+; CHECK:       pred.store.if5:
+; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <4 x i64> [[TMP18]], i32 1
+; CHECK-NEXT:    [[TMP24:%.*]] = getelementptr inbounds i32, ptr [[ARR]], i64 [[TMP23]]
+; CHECK-NEXT:    store i32 65, ptr [[TMP24]], align 4
+; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE6]]
+; CHECK:       pred.store.continue6:
+; CHECK-NEXT:    [[TMP25:%.*]] = extractelement <4 x i1> [[TMP17]], i32 2
+; CHECK-NEXT:    br i1 [[TMP25]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]]
+; CHECK:       pred.store.if7:
+; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <4 x i64> [[TMP18]], i32 2
+; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds i32, ptr [[ARR]], i64 [[TMP26]]
+; CHECK-NEXT:    store i32 65, ptr [[TMP27]], align 4
+; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE8]]
+; CHECK:       pred.store.continue8:
+; CHECK-NEXT:    [[TMP28:%.*]] = extractelement <4 x i1> [[TMP17]], i32 3
+; CHECK-NEXT:    br i1 [[TMP28]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10]]
+; CHECK:       pred.store.if9:
+; CHECK-NEXT:    [[TMP29:%.*]] = extractelement <4 x i64> [[TMP18]], i32 3
+; CHECK-NEXT:    [[TMP30:%.*]] = getelementptr inbounds i32, ptr [[ARR]], i64 [[TMP29]]
+; CHECK-NEXT:    store i32 65, ptr [[TMP30]], align 4
+; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE10]]
+; CHECK:       pred.store.continue10:
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
+; CHECK-NEXT:    [[TMP31:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP31]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMO:%.*]] = sub i64 [[N_VEC]], 1
+; CHECK-NEXT:    [[IND_ESCAPE:%.*]] = add i64 1, [[CMO]]
+; CHECK-NEXT:    br i1 true, label [[LOAD_VAL:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 1, [[PREHEADER]] ], [ 1, [[VECTOR_SCEVCHECK]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL2:%.*]] = phi i8 [ [[IND_END1]], [[MIDDLE_BLOCK]] ], [ 1, [[PREHEADER]] ], [ 1, [[VECTOR_SCEVCHECK]] ]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[CONV:%.*]] = phi i64 [ [[CONV2:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i8 [ [[INC:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL2]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[SUB:%.*]] = add nsw i64 [[CONV]], -1
+; CHECK-NEXT:    [[PTR:%.*]] = getelementptr inbounds i32, ptr [[ARR]], i64 [[SUB]]
+; CHECK-NEXT:    store i32 65, ptr [[PTR]], align 4
+; CHECK-NEXT:    [[INC]] = add i8 [[I]], 1
+; CHECK-NEXT:    [[CONV2]] = zext i8 [[INC]] to i64
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp ult i64 [[CONV2]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP2]], label [[LOOP]], label [[LOAD_VAL]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK:       load_val:
+; CHECK-NEXT:    [[FINAL:%.*]] = phi i64 [ [[CONV]], [[LOOP]] ], [ [[IND_ESCAPE]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    [[PTR2:%.*]] = getelementptr inbounds i32, ptr [[ARR]], i64 [[FINAL]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, ptr [[PTR2]], align 4
+; CHECK-NEXT:    br label [[DONE]]
+; CHECK:       done:
+; CHECK-NEXT:    [[VALUE:%.*]] = phi i32 [ [[VAL]], [[LOAD_VAL]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    ret i32 [[VALUE]]
+;
+entry:
+  %cmp1 = icmp ugt i64 %n, 1
+  br i1 %cmp1, label %preheader, label %done
+
+preheader:
+  br label %loop
+
+loop:
+  %conv = phi i64 [ %conv2, %loop ], [ 1, %preheader ]
+  %i = phi i8 [ %inc, %loop ], [ 1, %preheader ]
+  %sub = add nsw i64 %conv, -1
+  %ptr = getelementptr inbounds i32, ptr %arr, i64 %sub
+  store i32 65, ptr %ptr, align 4
+  %inc = add i8 %i, 1
+  %conv2 = zext i8 %inc to i64
+  %cmp2 = icmp ult i64 %conv2, %n
+  br i1 %cmp2, label %loop, label %load_val, !llvm.loop !0
+
+load_val:
+  %final = phi i64 [ %conv, %loop ]
+  %ptr2 = getelementptr inbounds i32, ptr %arr, i64 %final
+  %val = load i32, ptr %ptr2, align 4
+  br label %done
+
+done:
+  %value = phi i32 [ %val, %load_val ], [ 0, %entry ]
+  ret i32 %value
+
+}
+
+!0 = distinct !{!0, !1, !2, !3}
+!1 = !{!"llvm.loop.unroll.disable"}
+!2 = !{!"llvm.loop.vectorize.predicate.enable", i1 true}
+!3 = !{!"llvm.loop.vectorize.enable", i1 true}
+;.
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]], [[META3:![0-9]+]]}
+; CHECK: [[META1]] = !{!"llvm.loop.unroll.disable"}
+; CHECK: [[META2]] = !{!"llvm.loop.isvectorized", i32 1}
+; CHECK: [[META3]] = !{!"llvm.loop.unroll.runtime.disable"}
+; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
+;.