[LV][NFC] Update test checks using utils/update_test_checks.py

[ebrevnov]

Summary

Regenerate checks using update_test_checks.py to simplify future updates

[ebrevnov]

Ping

[lebedev.ri]

llvm/test/Transforms/LoopVectorize/tripcount.ll

2–4

While there, do you have any insights into this test?
In D114779 i'm strongly guessing that this test is completely broken.

[ebrevnov]

llvm/test/Transforms/LoopVectorize/tripcount.ll

2–4

Don't have any insights, sorry.

[lebedev.ri]

I'll end up doing this autogeneration for D114779 anyways, so i think this should be fine?

llvm/test/Transforms/LoopVectorize/tripcount.ll

386–388

I think you may want to run with the update script with --check-globals

[ebrevnov]

rebase

llvm/test/Transforms/LoopVectorize/tripcount.ll

+; 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 -passes=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-NOT: <{{[0-9]+}} x i8>
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP0]], 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 [[PROF0:![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-NOT: <{{[0-9]+}} x i8>
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP0]], 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 [[PROF0]]
+; 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:  [[VECTOR_BODY:vector\.body]]:
-; CHECK:    br i1 [[TMP9:%.*]], label [[MIDDLE_BLOCK:%.*]], label %[[VECTOR_BODY]], !prof [[LP3:\!.*]],
-; CHECK:  [[FOR_BODY:for\.body]]:
-; CHECK:    br i1 [[EXITCOND:%.*]], label [[FOR_END_LOOPEXIT:%.*]], label %[[FOR_BODY]], !prof [[LP6:\!.*]],
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[FOR_PREHEADER:%.*]], label [[FOR_END:%.*]], !prof [[PROF2:![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> <i8 2, i8 2, i8 2, i8 2>, <4 x i8> <i8 1, i8 1, i8 1, i8 1>
+; 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 [[PROF3:![0-9]+]], !llvm.loop [[LOOP4:![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 [[PROF6:![0-9]+]], !llvm.loop [[LOOP7:![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-NOT: <{{[0-9]+}} x i8>
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP0]], 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 [[PROF0]]
+; 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-NOT: <{{[0-9]+}} x i8>
+; CHECK-LABEL: @const_low_trip_count(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP0]], 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:%.*]]
+; 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: <{{[0-9]+}} x i8>
+; 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> <i8 2, i8 2, i8 2, i8 2>, <4 x i8> <i8 1, i8 1, i8 1, i8 1>
+; 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 [[LOOP9:![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 [[LOOP10:![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-NOT: <{{[0-9]+}} x i8>
+; CHECK-LABEL: @const_small_trip_count_step(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i8 [[TMP0]], 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:%.*]]
+; 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: <{{[0-9]+}} x i8>
+; 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> <i8 2, i8 2, i8 2, i8 2>, <4 x i8> <i8 1, i8 1, i8 1, i8 1>
+; 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 [[LOOP11:![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 [[PROF0]], !llvm.loop [[LOOP12:![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
 }
 
-; CHECK: [[LP3]] = !{!"branch_weights", i32 10, i32 2490}
-; CHECK: [[LP6]] = !{!"branch_weights", i32 10, i32 0}
+; CHECK: [[PROF3]] = !{!"branch_weights", i32 10, i32 2490}
+; CHECK: [[PROF6]] = !{!"branch_weights", i32 10, 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}