; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; This test verifies that the loop vectorizer will not vectorizes low trip count ; loops that require runtime checks (Trip count is computed with profile info). ; REQUIRES: asserts ; RUN: opt < %s -loop-vectorize -loop-vectorize-with-block-frequency -S | FileCheck %s target datalayout = "E-m:e-p:32:32-i64:32-f64:32:64-a:0:32-n32-S128" @tab = common global [32 x i8] zeroinitializer, align 1 define i32 @foo_low_trip_count1(i32 %bound) { ; Simple loop with low tripcount. Should not be vectorized. ; CHECK-LABEL: @foo_low_trip_count1( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[BOUND:%.*]], 1 ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 [[TMP0]], 3 ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], 4 ; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]] ; CHECK-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = sub i32 [[TMP0]], 1 ; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TRIP_COUNT_MINUS_1]], i32 0 ; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE12:%.*]] ] ; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ , [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE12]] ] ; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 0 ; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[INDEX]], 1 ; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[INDEX]], 2 ; CHECK-NEXT: [[TMP4:%.*]] = add i32 [[INDEX]], 3 ; CHECK-NEXT: [[TMP5:%.*]] = icmp ule <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]] ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP1]] ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP2]] ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP3]] ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP4]] ; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x i1> [[TMP5]], i32 0 ; CHECK-NEXT: br i1 [[TMP10]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]] ; CHECK: pred.load.if: ; CHECK-NEXT: [[TMP11:%.*]] = load i8, i8* [[TMP6]], align 1 ; CHECK-NEXT: [[TMP12:%.*]] = insertelement <4 x i8> poison, i8 [[TMP11]], i32 0 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]] ; CHECK: pred.load.continue: ; CHECK-NEXT: [[TMP13:%.*]] = phi <4 x i8> [ poison, [[VECTOR_BODY]] ], [ [[TMP12]], [[PRED_LOAD_IF]] ] ; CHECK-NEXT: [[TMP14:%.*]] = extractelement <4 x i1> [[TMP5]], i32 1 ; CHECK-NEXT: br i1 [[TMP14]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]] ; CHECK: pred.load.if1: ; CHECK-NEXT: [[TMP15:%.*]] = load i8, i8* [[TMP7]], align 1 ; CHECK-NEXT: [[TMP16:%.*]] = insertelement <4 x i8> [[TMP13]], i8 [[TMP15]], i32 1 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE2]] ; CHECK: pred.load.continue2: ; CHECK-NEXT: [[TMP17:%.*]] = phi <4 x i8> [ [[TMP13]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP16]], [[PRED_LOAD_IF1]] ] ; CHECK-NEXT: [[TMP18:%.*]] = extractelement <4 x i1> [[TMP5]], i32 2 ; CHECK-NEXT: br i1 [[TMP18]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]] ; CHECK: pred.load.if3: ; CHECK-NEXT: [[TMP19:%.*]] = load i8, i8* [[TMP8]], align 1 ; CHECK-NEXT: [[TMP20:%.*]] = insertelement <4 x i8> [[TMP17]], i8 [[TMP19]], i32 2 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE4]] ; CHECK: pred.load.continue4: ; CHECK-NEXT: [[TMP21:%.*]] = phi <4 x i8> [ [[TMP17]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP20]], [[PRED_LOAD_IF3]] ] ; CHECK-NEXT: [[TMP22:%.*]] = extractelement <4 x i1> [[TMP5]], i32 3 ; CHECK-NEXT: br i1 [[TMP22]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]] ; CHECK: pred.load.if5: ; CHECK-NEXT: [[TMP23:%.*]] = load i8, i8* [[TMP9]], align 1 ; CHECK-NEXT: [[TMP24:%.*]] = insertelement <4 x i8> [[TMP21]], i8 [[TMP23]], i32 3 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE6]] ; CHECK: pred.load.continue6: ; CHECK-NEXT: [[TMP25:%.*]] = phi <4 x i8> [ [[TMP21]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP24]], [[PRED_LOAD_IF5]] ] ; CHECK-NEXT: [[TMP26:%.*]] = icmp eq <4 x i8> [[TMP25]], zeroinitializer ; CHECK-NEXT: [[TMP27:%.*]] = select <4 x i1> [[TMP26]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i1> [[TMP5]], i32 0 ; CHECK-NEXT: br i1 [[TMP28]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]] ; CHECK: pred.store.if: ; CHECK-NEXT: [[TMP29:%.*]] = extractelement <4 x i8> [[TMP27]], i32 0 ; CHECK-NEXT: store i8 [[TMP29]], i8* [[TMP6]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]] ; CHECK: pred.store.continue: ; CHECK-NEXT: [[TMP30:%.*]] = extractelement <4 x i1> [[TMP5]], i32 1 ; CHECK-NEXT: br i1 [[TMP30]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]] ; CHECK: pred.store.if7: ; CHECK-NEXT: [[TMP31:%.*]] = extractelement <4 x i8> [[TMP27]], i32 1 ; CHECK-NEXT: store i8 [[TMP31]], i8* [[TMP7]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]] ; CHECK: pred.store.continue8: ; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i1> [[TMP5]], i32 2 ; CHECK-NEXT: br i1 [[TMP32]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10:%.*]] ; CHECK: pred.store.if9: ; CHECK-NEXT: [[TMP33:%.*]] = extractelement <4 x i8> [[TMP27]], i32 2 ; CHECK-NEXT: store i8 [[TMP33]], i8* [[TMP8]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE10]] ; CHECK: pred.store.continue10: ; CHECK-NEXT: [[TMP34:%.*]] = extractelement <4 x i1> [[TMP5]], i32 3 ; CHECK-NEXT: br i1 [[TMP34]], label [[PRED_STORE_IF11:%.*]], label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.if11: ; CHECK-NEXT: [[TMP35:%.*]] = extractelement <4 x i8> [[TMP27]], i32 3 ; CHECK-NEXT: store i8 [[TMP35]], i8* [[TMP9]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.continue12: ; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4 ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], ; CHECK-NEXT: [[TMP36:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] ; CHECK-NEXT: br i1 [[TMP36]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !prof [[PROF0:![0-9]+]], !llvm.loop [[LOOP1:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP37:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP37]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[I_08]], [[BOUND]] ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !prof [[PROF3:![0-9]+]], !llvm.loop [[LOOP4:![0-9]+]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 1 %exitcond = icmp eq i32 %i.08, %bound br i1 %exitcond, label %for.end, label %for.body, !prof !1 for.end: ; preds = %for.body ret i32 0 } define i32 @foo_low_trip_count2(i32 %bound) !prof !0 { ; The loop has a same invocation count with the function, but has a low ; trip_count per invocation and not worth to vectorize. ; CHECK-LABEL: @foo_low_trip_count2( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[BOUND:%.*]], 1 ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 [[TMP0]], 3 ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], 4 ; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]] ; CHECK-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = sub i32 [[TMP0]], 1 ; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TRIP_COUNT_MINUS_1]], i32 0 ; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE12:%.*]] ] ; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ , [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE12]] ] ; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 0 ; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[INDEX]], 1 ; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[INDEX]], 2 ; CHECK-NEXT: [[TMP4:%.*]] = add i32 [[INDEX]], 3 ; CHECK-NEXT: [[TMP5:%.*]] = icmp ule <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]] ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP1]] ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP2]] ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP3]] ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP4]] ; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x i1> [[TMP5]], i32 0 ; CHECK-NEXT: br i1 [[TMP10]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]] ; CHECK: pred.load.if: ; CHECK-NEXT: [[TMP11:%.*]] = load i8, i8* [[TMP6]], align 1 ; CHECK-NEXT: [[TMP12:%.*]] = insertelement <4 x i8> poison, i8 [[TMP11]], i32 0 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]] ; CHECK: pred.load.continue: ; CHECK-NEXT: [[TMP13:%.*]] = phi <4 x i8> [ poison, [[VECTOR_BODY]] ], [ [[TMP12]], [[PRED_LOAD_IF]] ] ; CHECK-NEXT: [[TMP14:%.*]] = extractelement <4 x i1> [[TMP5]], i32 1 ; CHECK-NEXT: br i1 [[TMP14]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]] ; CHECK: pred.load.if1: ; CHECK-NEXT: [[TMP15:%.*]] = load i8, i8* [[TMP7]], align 1 ; CHECK-NEXT: [[TMP16:%.*]] = insertelement <4 x i8> [[TMP13]], i8 [[TMP15]], i32 1 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE2]] ; CHECK: pred.load.continue2: ; CHECK-NEXT: [[TMP17:%.*]] = phi <4 x i8> [ [[TMP13]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP16]], [[PRED_LOAD_IF1]] ] ; CHECK-NEXT: [[TMP18:%.*]] = extractelement <4 x i1> [[TMP5]], i32 2 ; CHECK-NEXT: br i1 [[TMP18]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]] ; CHECK: pred.load.if3: ; CHECK-NEXT: [[TMP19:%.*]] = load i8, i8* [[TMP8]], align 1 ; CHECK-NEXT: [[TMP20:%.*]] = insertelement <4 x i8> [[TMP17]], i8 [[TMP19]], i32 2 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE4]] ; CHECK: pred.load.continue4: ; CHECK-NEXT: [[TMP21:%.*]] = phi <4 x i8> [ [[TMP17]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP20]], [[PRED_LOAD_IF3]] ] ; CHECK-NEXT: [[TMP22:%.*]] = extractelement <4 x i1> [[TMP5]], i32 3 ; CHECK-NEXT: br i1 [[TMP22]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]] ; CHECK: pred.load.if5: ; CHECK-NEXT: [[TMP23:%.*]] = load i8, i8* [[TMP9]], align 1 ; CHECK-NEXT: [[TMP24:%.*]] = insertelement <4 x i8> [[TMP21]], i8 [[TMP23]], i32 3 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE6]] ; CHECK: pred.load.continue6: ; CHECK-NEXT: [[TMP25:%.*]] = phi <4 x i8> [ [[TMP21]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP24]], [[PRED_LOAD_IF5]] ] ; CHECK-NEXT: [[TMP26:%.*]] = icmp eq <4 x i8> [[TMP25]], zeroinitializer ; CHECK-NEXT: [[TMP27:%.*]] = select <4 x i1> [[TMP26]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i1> [[TMP5]], i32 0 ; CHECK-NEXT: br i1 [[TMP28]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]] ; CHECK: pred.store.if: ; CHECK-NEXT: [[TMP29:%.*]] = extractelement <4 x i8> [[TMP27]], i32 0 ; CHECK-NEXT: store i8 [[TMP29]], i8* [[TMP6]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]] ; CHECK: pred.store.continue: ; CHECK-NEXT: [[TMP30:%.*]] = extractelement <4 x i1> [[TMP5]], i32 1 ; CHECK-NEXT: br i1 [[TMP30]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]] ; CHECK: pred.store.if7: ; CHECK-NEXT: [[TMP31:%.*]] = extractelement <4 x i8> [[TMP27]], i32 1 ; CHECK-NEXT: store i8 [[TMP31]], i8* [[TMP7]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]] ; CHECK: pred.store.continue8: ; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i1> [[TMP5]], i32 2 ; CHECK-NEXT: br i1 [[TMP32]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10:%.*]] ; CHECK: pred.store.if9: ; CHECK-NEXT: [[TMP33:%.*]] = extractelement <4 x i8> [[TMP27]], i32 2 ; CHECK-NEXT: store i8 [[TMP33]], i8* [[TMP8]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE10]] ; CHECK: pred.store.continue10: ; CHECK-NEXT: [[TMP34:%.*]] = extractelement <4 x i1> [[TMP5]], i32 3 ; CHECK-NEXT: br i1 [[TMP34]], label [[PRED_STORE_IF11:%.*]], label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.if11: ; CHECK-NEXT: [[TMP35:%.*]] = extractelement <4 x i8> [[TMP27]], i32 3 ; CHECK-NEXT: store i8 [[TMP35]], i8* [[TMP9]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.continue12: ; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4 ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], ; CHECK-NEXT: [[TMP36:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] ; CHECK-NEXT: br i1 [[TMP36]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !prof [[PROF0]], !llvm.loop [[LOOP7:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP37:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP37]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[I_08]], [[BOUND]] ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !prof [[PROF3]], !llvm.loop [[LOOP8:![0-9]+]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 1 %exitcond = icmp eq i32 %i.08, %bound br i1 %exitcond, label %for.end, label %for.body, !prof !1 for.end: ; preds = %for.body ret i32 0 } define i32 @foo_low_trip_count3(i1 %cond, i32 %bound) !prof !0 { ; The loop has low invocation count compare to the function invocation count, ; but has a high trip count per invocation. Vectorize it. ; CHECK-LABEL: @foo_low_trip_count3( ; CHECK-NEXT: entry: ; CHECK-NEXT: br i1 [[COND:%.*]], label [[FOR_PREHEADER:%.*]], label [[FOR_END:%.*]], !prof [[PROF9:![0-9]+]] ; CHECK: for.preheader: ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[BOUND:%.*]], 1 ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP0]], 4 ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP0]], 4 ; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP0]], [[N_MOD_VF]] ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 0 ; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[TMP2]], i32 0 ; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <4 x i8>* ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP4]], align 1 ; CHECK-NEXT: [[TMP5:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], zeroinitializer ; CHECK-NEXT: [[TMP6:%.*]] = select <4 x i1> [[TMP5]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP3]] to <4 x i8>* ; CHECK-NEXT: store <4 x i8> [[TMP6]], <4 x i8>* [[TMP7]], align 1 ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4 ; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] ; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !prof [[PROF10:![0-9]+]], !llvm.loop [[LOOP11:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP0]], [[N_VEC]] ; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END_LOOPEXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_PREHEADER]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP9:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP9]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[I_08]], [[BOUND]] ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT]], label [[FOR_BODY]], !prof [[PROF12:![0-9]+]], !llvm.loop [[LOOP13:![0-9]+]] ; CHECK: for.end.loopexit: ; CHECK-NEXT: br label [[FOR_END]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br i1 %cond, label %for.preheader, label %for.end, !prof !2 for.preheader: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %for.preheader ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 1 %exitcond = icmp eq i32 %i.08, %bound br i1 %exitcond, label %for.end, label %for.body, !prof !3 for.end: ; preds = %for.body ret i32 0 } define i32 @foo_low_trip_count_icmp_sgt(i32 %bound) { ; Simple loop with low tripcount and inequality test for exit. ; Should not be vectorized. ; CHECK-LABEL: @foo_low_trip_count_icmp_sgt( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[SMAX:%.*]] = call i32 @llvm.smax.i32(i32 [[BOUND:%.*]], i32 -1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[SMAX]], 2 ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 [[TMP0]], 3 ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], 4 ; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]] ; CHECK-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = sub i32 [[TMP0]], 1 ; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TRIP_COUNT_MINUS_1]], i32 0 ; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE12:%.*]] ] ; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ , [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE12]] ] ; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 0 ; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[INDEX]], 1 ; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[INDEX]], 2 ; CHECK-NEXT: [[TMP4:%.*]] = add i32 [[INDEX]], 3 ; CHECK-NEXT: [[TMP5:%.*]] = icmp ule <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]] ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP1]] ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP2]] ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP3]] ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP4]] ; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x i1> [[TMP5]], i32 0 ; CHECK-NEXT: br i1 [[TMP10]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]] ; CHECK: pred.load.if: ; CHECK-NEXT: [[TMP11:%.*]] = load i8, i8* [[TMP6]], align 1 ; CHECK-NEXT: [[TMP12:%.*]] = insertelement <4 x i8> poison, i8 [[TMP11]], i32 0 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]] ; CHECK: pred.load.continue: ; CHECK-NEXT: [[TMP13:%.*]] = phi <4 x i8> [ poison, [[VECTOR_BODY]] ], [ [[TMP12]], [[PRED_LOAD_IF]] ] ; CHECK-NEXT: [[TMP14:%.*]] = extractelement <4 x i1> [[TMP5]], i32 1 ; CHECK-NEXT: br i1 [[TMP14]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]] ; CHECK: pred.load.if1: ; CHECK-NEXT: [[TMP15:%.*]] = load i8, i8* [[TMP7]], align 1 ; CHECK-NEXT: [[TMP16:%.*]] = insertelement <4 x i8> [[TMP13]], i8 [[TMP15]], i32 1 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE2]] ; CHECK: pred.load.continue2: ; CHECK-NEXT: [[TMP17:%.*]] = phi <4 x i8> [ [[TMP13]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP16]], [[PRED_LOAD_IF1]] ] ; CHECK-NEXT: [[TMP18:%.*]] = extractelement <4 x i1> [[TMP5]], i32 2 ; CHECK-NEXT: br i1 [[TMP18]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]] ; CHECK: pred.load.if3: ; CHECK-NEXT: [[TMP19:%.*]] = load i8, i8* [[TMP8]], align 1 ; CHECK-NEXT: [[TMP20:%.*]] = insertelement <4 x i8> [[TMP17]], i8 [[TMP19]], i32 2 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE4]] ; CHECK: pred.load.continue4: ; CHECK-NEXT: [[TMP21:%.*]] = phi <4 x i8> [ [[TMP17]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP20]], [[PRED_LOAD_IF3]] ] ; CHECK-NEXT: [[TMP22:%.*]] = extractelement <4 x i1> [[TMP5]], i32 3 ; CHECK-NEXT: br i1 [[TMP22]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]] ; CHECK: pred.load.if5: ; CHECK-NEXT: [[TMP23:%.*]] = load i8, i8* [[TMP9]], align 1 ; CHECK-NEXT: [[TMP24:%.*]] = insertelement <4 x i8> [[TMP21]], i8 [[TMP23]], i32 3 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE6]] ; CHECK: pred.load.continue6: ; CHECK-NEXT: [[TMP25:%.*]] = phi <4 x i8> [ [[TMP21]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP24]], [[PRED_LOAD_IF5]] ] ; CHECK-NEXT: [[TMP26:%.*]] = icmp eq <4 x i8> [[TMP25]], zeroinitializer ; CHECK-NEXT: [[TMP27:%.*]] = select <4 x i1> [[TMP26]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i1> [[TMP5]], i32 0 ; CHECK-NEXT: br i1 [[TMP28]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]] ; CHECK: pred.store.if: ; CHECK-NEXT: [[TMP29:%.*]] = extractelement <4 x i8> [[TMP27]], i32 0 ; CHECK-NEXT: store i8 [[TMP29]], i8* [[TMP6]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]] ; CHECK: pred.store.continue: ; CHECK-NEXT: [[TMP30:%.*]] = extractelement <4 x i1> [[TMP5]], i32 1 ; CHECK-NEXT: br i1 [[TMP30]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]] ; CHECK: pred.store.if7: ; CHECK-NEXT: [[TMP31:%.*]] = extractelement <4 x i8> [[TMP27]], i32 1 ; CHECK-NEXT: store i8 [[TMP31]], i8* [[TMP7]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]] ; CHECK: pred.store.continue8: ; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i1> [[TMP5]], i32 2 ; CHECK-NEXT: br i1 [[TMP32]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10:%.*]] ; CHECK: pred.store.if9: ; CHECK-NEXT: [[TMP33:%.*]] = extractelement <4 x i8> [[TMP27]], i32 2 ; CHECK-NEXT: store i8 [[TMP33]], i8* [[TMP8]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE10]] ; CHECK: pred.store.continue10: ; CHECK-NEXT: [[TMP34:%.*]] = extractelement <4 x i1> [[TMP5]], i32 3 ; CHECK-NEXT: br i1 [[TMP34]], label [[PRED_STORE_IF11:%.*]], label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.if11: ; CHECK-NEXT: [[TMP35:%.*]] = extractelement <4 x i8> [[TMP27]], i32 3 ; CHECK-NEXT: store i8 [[TMP35]], i8* [[TMP9]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.continue12: ; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4 ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], ; CHECK-NEXT: [[TMP36:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] ; CHECK-NEXT: br i1 [[TMP36]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !prof [[PROF0]], !llvm.loop [[LOOP14:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP37:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP37]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp sgt i32 [[I_08]], [[BOUND]] ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !prof [[PROF3]], !llvm.loop [[LOOP15:![0-9]+]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 1 %exitcond = icmp sgt i32 %i.08, %bound br i1 %exitcond, label %for.end, label %for.body, !prof !1 for.end: ; preds = %for.body ret i32 0 } define i32 @const_low_trip_count() { ; Simple loop with constant, small trip count and no profiling info. ; CHECK-LABEL: @const_low_trip_count( ; CHECK-NEXT: entry: ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE12:%.*]] ] ; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ , [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE12]] ] ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[INDEX]], 2 ; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[INDEX]], 3 ; CHECK-NEXT: [[TMP4:%.*]] = icmp ule <4 x i32> [[VEC_IND]], ; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]] ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP1]] ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP2]] ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP3]] ; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0 ; CHECK-NEXT: br i1 [[TMP9]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]] ; CHECK: pred.load.if: ; CHECK-NEXT: [[TMP10:%.*]] = load i8, i8* [[TMP5]], align 1 ; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i8> poison, i8 [[TMP10]], i32 0 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]] ; CHECK: pred.load.continue: ; CHECK-NEXT: [[TMP12:%.*]] = phi <4 x i8> [ poison, [[VECTOR_BODY]] ], [ [[TMP11]], [[PRED_LOAD_IF]] ] ; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1 ; CHECK-NEXT: br i1 [[TMP13]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]] ; CHECK: pred.load.if1: ; CHECK-NEXT: [[TMP14:%.*]] = load i8, i8* [[TMP6]], align 1 ; CHECK-NEXT: [[TMP15:%.*]] = insertelement <4 x i8> [[TMP12]], i8 [[TMP14]], i32 1 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE2]] ; CHECK: pred.load.continue2: ; CHECK-NEXT: [[TMP16:%.*]] = phi <4 x i8> [ [[TMP12]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP15]], [[PRED_LOAD_IF1]] ] ; CHECK-NEXT: [[TMP17:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2 ; CHECK-NEXT: br i1 [[TMP17]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]] ; CHECK: pred.load.if3: ; CHECK-NEXT: [[TMP18:%.*]] = load i8, i8* [[TMP7]], align 1 ; CHECK-NEXT: [[TMP19:%.*]] = insertelement <4 x i8> [[TMP16]], i8 [[TMP18]], i32 2 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE4]] ; CHECK: pred.load.continue4: ; CHECK-NEXT: [[TMP20:%.*]] = phi <4 x i8> [ [[TMP16]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP19]], [[PRED_LOAD_IF3]] ] ; CHECK-NEXT: [[TMP21:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3 ; CHECK-NEXT: br i1 [[TMP21]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]] ; CHECK: pred.load.if5: ; CHECK-NEXT: [[TMP22:%.*]] = load i8, i8* [[TMP8]], align 1 ; CHECK-NEXT: [[TMP23:%.*]] = insertelement <4 x i8> [[TMP20]], i8 [[TMP22]], i32 3 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE6]] ; CHECK: pred.load.continue6: ; CHECK-NEXT: [[TMP24:%.*]] = phi <4 x i8> [ [[TMP20]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP23]], [[PRED_LOAD_IF5]] ] ; CHECK-NEXT: [[TMP25:%.*]] = icmp eq <4 x i8> [[TMP24]], zeroinitializer ; CHECK-NEXT: [[TMP26:%.*]] = select <4 x i1> [[TMP25]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP27:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0 ; CHECK-NEXT: br i1 [[TMP27]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]] ; CHECK: pred.store.if: ; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i8> [[TMP26]], i32 0 ; CHECK-NEXT: store i8 [[TMP28]], i8* [[TMP5]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]] ; CHECK: pred.store.continue: ; CHECK-NEXT: [[TMP29:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1 ; CHECK-NEXT: br i1 [[TMP29]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]] ; CHECK: pred.store.if7: ; CHECK-NEXT: [[TMP30:%.*]] = extractelement <4 x i8> [[TMP26]], i32 1 ; CHECK-NEXT: store i8 [[TMP30]], i8* [[TMP6]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]] ; CHECK: pred.store.continue8: ; CHECK-NEXT: [[TMP31:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2 ; CHECK-NEXT: br i1 [[TMP31]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10:%.*]] ; CHECK: pred.store.if9: ; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i8> [[TMP26]], i32 2 ; CHECK-NEXT: store i8 [[TMP32]], i8* [[TMP7]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE10]] ; CHECK: pred.store.continue10: ; CHECK-NEXT: [[TMP33:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3 ; CHECK-NEXT: br i1 [[TMP33]], label [[PRED_STORE_IF11:%.*]], label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.if11: ; CHECK-NEXT: [[TMP34:%.*]] = extractelement <4 x i8> [[TMP26]], i32 3 ; CHECK-NEXT: store i8 [[TMP34]], i8* [[TMP8]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.continue12: ; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4 ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], ; CHECK-NEXT: [[TMP35:%.*]] = icmp eq i32 [[INDEX_NEXT]], 4 ; CHECK-NEXT: br i1 [[TMP35]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 4, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP36:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP36]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 2 ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP17:![0-9]+]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 1 %exitcond = icmp slt i32 %i.08, 2 br i1 %exitcond, label %for.body, label %for.end for.end: ; preds = %for.body ret i32 0 } define i32 @const_large_trip_count() { ; Simple loop with constant large trip count and no profiling info. ; CHECK-LABEL: @const_large_trip_count( ; CHECK-NEXT: entry: ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]] ; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0 ; CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>* ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP3]], align 1 ; CHECK-NEXT: [[TMP4:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], zeroinitializer ; CHECK-NEXT: [[TMP5:%.*]] = select <4 x i1> [[TMP4]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP6:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>* ; CHECK-NEXT: store <4 x i8> [[TMP5]], <4 x i8>* [[TMP6]], align 1 ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4 ; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000 ; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 1001, 1000 ; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 1000, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP8:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP8]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 1000 ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP19:![0-9]+]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 1 %exitcond = icmp slt i32 %i.08, 1000 br i1 %exitcond, label %for.body, label %for.end for.end: ; preds = %for.body ret i32 0 } define i32 @const_small_trip_count_step() { ; Simple loop with static, small trip count and no profiling info. ; CHECK-LABEL: @const_small_trip_count_step( ; CHECK-NEXT: entry: ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE12:%.*]] ] ; CHECK-NEXT: [[OFFSET_IDX:%.*]] = mul i32 [[INDEX]], 5 ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[OFFSET_IDX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[OFFSET_IDX]], 5 ; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[OFFSET_IDX]], 10 ; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[OFFSET_IDX]], 15 ; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[INDEX]], i32 0 ; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: [[VEC_IV:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP4:%.*]] = icmp ule <4 x i32> [[VEC_IV]], ; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]] ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP1]] ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP2]] ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP3]] ; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0 ; CHECK-NEXT: br i1 [[TMP9]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]] ; CHECK: pred.load.if: ; CHECK-NEXT: [[TMP10:%.*]] = load i8, i8* [[TMP5]], align 1 ; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i8> poison, i8 [[TMP10]], i32 0 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]] ; CHECK: pred.load.continue: ; CHECK-NEXT: [[TMP12:%.*]] = phi <4 x i8> [ poison, [[VECTOR_BODY]] ], [ [[TMP11]], [[PRED_LOAD_IF]] ] ; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1 ; CHECK-NEXT: br i1 [[TMP13]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]] ; CHECK: pred.load.if1: ; CHECK-NEXT: [[TMP14:%.*]] = load i8, i8* [[TMP6]], align 1 ; CHECK-NEXT: [[TMP15:%.*]] = insertelement <4 x i8> [[TMP12]], i8 [[TMP14]], i32 1 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE2]] ; CHECK: pred.load.continue2: ; CHECK-NEXT: [[TMP16:%.*]] = phi <4 x i8> [ [[TMP12]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP15]], [[PRED_LOAD_IF1]] ] ; CHECK-NEXT: [[TMP17:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2 ; CHECK-NEXT: br i1 [[TMP17]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]] ; CHECK: pred.load.if3: ; CHECK-NEXT: [[TMP18:%.*]] = load i8, i8* [[TMP7]], align 1 ; CHECK-NEXT: [[TMP19:%.*]] = insertelement <4 x i8> [[TMP16]], i8 [[TMP18]], i32 2 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE4]] ; CHECK: pred.load.continue4: ; CHECK-NEXT: [[TMP20:%.*]] = phi <4 x i8> [ [[TMP16]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP19]], [[PRED_LOAD_IF3]] ] ; CHECK-NEXT: [[TMP21:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3 ; CHECK-NEXT: br i1 [[TMP21]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]] ; CHECK: pred.load.if5: ; CHECK-NEXT: [[TMP22:%.*]] = load i8, i8* [[TMP8]], align 1 ; CHECK-NEXT: [[TMP23:%.*]] = insertelement <4 x i8> [[TMP20]], i8 [[TMP22]], i32 3 ; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE6]] ; CHECK: pred.load.continue6: ; CHECK-NEXT: [[TMP24:%.*]] = phi <4 x i8> [ [[TMP20]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP23]], [[PRED_LOAD_IF5]] ] ; CHECK-NEXT: [[TMP25:%.*]] = icmp eq <4 x i8> [[TMP24]], zeroinitializer ; CHECK-NEXT: [[TMP26:%.*]] = select <4 x i1> [[TMP25]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP27:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0 ; CHECK-NEXT: br i1 [[TMP27]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]] ; CHECK: pred.store.if: ; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i8> [[TMP26]], i32 0 ; CHECK-NEXT: store i8 [[TMP28]], i8* [[TMP5]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]] ; CHECK: pred.store.continue: ; CHECK-NEXT: [[TMP29:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1 ; CHECK-NEXT: br i1 [[TMP29]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]] ; CHECK: pred.store.if7: ; CHECK-NEXT: [[TMP30:%.*]] = extractelement <4 x i8> [[TMP26]], i32 1 ; CHECK-NEXT: store i8 [[TMP30]], i8* [[TMP6]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]] ; CHECK: pred.store.continue8: ; CHECK-NEXT: [[TMP31:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2 ; CHECK-NEXT: br i1 [[TMP31]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10:%.*]] ; CHECK: pred.store.if9: ; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i8> [[TMP26]], i32 2 ; CHECK-NEXT: store i8 [[TMP32]], i8* [[TMP7]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE10]] ; CHECK: pred.store.continue10: ; CHECK-NEXT: [[TMP33:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3 ; CHECK-NEXT: br i1 [[TMP33]], label [[PRED_STORE_IF11:%.*]], label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.if11: ; CHECK-NEXT: [[TMP34:%.*]] = extractelement <4 x i8> [[TMP26]], i32 3 ; CHECK-NEXT: store i8 [[TMP34]], i8* [[TMP8]], align 1 ; CHECK-NEXT: br label [[PRED_STORE_CONTINUE12]] ; CHECK: pred.store.continue12: ; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4 ; CHECK-NEXT: [[TMP35:%.*]] = icmp eq i32 [[INDEX_NEXT]], 4 ; CHECK-NEXT: br i1 [[TMP35]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 20, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP36:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP36]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 5 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 10 ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP21:![0-9]+]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 5 %exitcond = icmp slt i32 %i.08, 10 br i1 %exitcond, label %for.body, label %for.end for.end: ; preds = %for.body ret i32 0 } define i32 @const_trip_over_profile() { ; constant trip count takes precedence over profile data ; CHECK-LABEL: @const_trip_over_profile( ; CHECK-NEXT: entry: ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]] ; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0 ; CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>* ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP3]], align 1 ; CHECK-NEXT: [[TMP4:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], zeroinitializer ; CHECK-NEXT: [[TMP5:%.*]] = select <4 x i1> [[TMP4]], <4 x i8> , <4 x i8> ; CHECK-NEXT: [[TMP6:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>* ; CHECK-NEXT: store <4 x i8> [[TMP5]], <4 x i8>* [[TMP6]], align 1 ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4 ; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000 ; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP22:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 1001, 1000 ; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 1000, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]] ; CHECK-NEXT: [[TMP8:%.*]] = load i8, i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP8]], 0 ; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1 ; CHECK-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1 ; CHECK-NEXT: [[INC]] = add nsw i32 [[I_08]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp slt i32 [[I_08]], 1000 ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !prof [[PROF3]], !llvm.loop [[LOOP23:![0-9]+]] ; CHECK: for.end: ; CHECK-NEXT: ret i32 0 ; entry: br label %for.body for.body: ; preds = %for.body, %entry %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ] %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08 %0 = load i8, i8* %arrayidx, align 1 %cmp1 = icmp eq i8 %0, 0 %. = select i1 %cmp1, i8 2, i8 1 store i8 %., i8* %arrayidx, align 1 %inc = add nsw i32 %i.08, 1 %exitcond = icmp slt i32 %i.08, 1000 br i1 %exitcond, label %for.body, label %for.end, !prof !1 for.end: ; preds = %for.body ret i32 0 } ; original loop has latchExitWeight=10 and backedgeTakenWeight=10,000, ; therefore estimatedBackedgeTakenCount=1,000 and estimatedTripCount=1,001. ; Vectorizing by 4 produces estimatedTripCounts of 1,001/4=250 and 1,001%4=1 ; for vectorized and remainder loops, respectively, therefore their ; estimatedBackedgeTakenCounts are 249 and 0, and so the weights recorded with ; loop invocation weights of 10 are the above {10, 2490} and {10, 0}. !0 = !{!"function_entry_count", i64 100} !1 = !{!"branch_weights", i32 100, i32 0} !2 = !{!"branch_weights", i32 10, i32 90} !3 = !{!"branch_weights", i32 10, i32 10000}