[VPlan] Print live-in backedge taken count as part of plan.

[fhahn]

Summary

At the moment, a VPValue is created for the backedge-taken count, which
is used by some recipes. To make it easier to identify the operands of
recipes using the backedge-taken count, print it at the beginning of the
VPlan if it is used.

[a.elovikov]

LGTM other than a minor nit.

llvm/lib/Transforms/Vectorize/VPlan.cpp

891

This looks strange. Why extra space? What's more interesting is that I don't see it in the CHECKs below.

[fhahn]

remove extra space, thanks!

[fhahn]

llvm/lib/Transforms/Vectorize/VPlan.cpp

891

Thanks, I missed the extra space. Removed!

[a.elovikov]

Thanks!

llvm/lib/Transforms/Vectorize/VPlan.cpp

 }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 LLVM_DUMP_METHOD
 void VPlan::print(raw_ostream &O) const {
   VPSlotTracker SlotTracker(this);
 
   O << "VPlan '" << Name << "' {";
+
+  if (BackedgeTakenCount && BackedgeTakenCount->getNumUsers()) {
+    O << "\nLive-in ";
+    BackedgeTakenCount->printAsOperand(O, SlotTracker);
+    O << " = backedge-taken count\n";
+  }
+
   for (const VPBlockBase *Block : depth_first(getEntry())) {
     O << '\n';
     Block->print(O, "", SlotTracker);
   }
   O << "}\n";
 }
 
 LLVM_DUMP_METHOD

llvm/test/Transforms/LoopVectorize/first-order-recurrence-sink-replicate-region.ll

 ; REQUIRES: asserts
 ; RUN: opt < %s -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -disable-output -debug-only=loop-vectorize 2>&1 | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 
 ; Test cases for PR50009, which require sinking a replicate-region due to a
 ; first-order recurrence.
 
 define void @sink_replicate_region_1(i32 %x, i8* %ptr) optsize {
 ; CHECK-LABEL: sink_replicate_region_1
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   FIRST-ORDER-RECURRENCE-PHI ir<%0> = phi ir<0>, ir<%conv>
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<{{.+}}>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT: Successor(s): loop.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0:
 ; CHECK-NEXT: Successor(s): pred.load
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK]]>

 
 exit:
   ret void
 }
 
 define void @sink_replicate_region_2(i32 %x, i8 %y, i32* %ptr) optsize {
 ; CHECK-LABEL: sink_replicate_region_2
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   FIRST-ORDER-RECURRENCE-PHI ir<%recur> = phi ir<0>, ir<%recur.next>
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<{{.+}}>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT: Successor(s): loop.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0:
 ; CHECK-NEXT:   WIDEN ir<%recur.next> = sext ir<%y>
 ; CHECK-NEXT:   EMIT vp<[[SPLICE:%.+]]> = first-order splice ir<%recur> ir<%recur.next>
 ; CHECK-NEXT: Successor(s): loop.0.split
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0.split:

 
 exit:
   ret void
 }
 
 define i32 @sink_replicate_region_3_reduction(i32 %x, i8 %y, i32* %ptr) optsize {
 ; CHECK-LABEL: sink_replicate_region_3_reduction
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   FIRST-ORDER-RECURRENCE-PHI ir<%recur> = phi ir<0>, ir<%recur.next>
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
 ; CHECK-NEXT:   WIDEN-REDUCTION-PHI ir<%and.red> = phi ir<1234>, ir<%and.red.next>
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<{{.+}}>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT: Successor(s): loop.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0:
 ; CHECK-NEXT:   WIDEN ir<%recur.next> = sext ir<%y>
 ; CHECK-NEXT:   EMIT vp<[[SPLICE:%.+]]> = first-order splice ir<%recur> ir<%recur.next>
 ; CHECK-NEXT: Successor(s): pred.srem
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.srem: {
exit:
   ret i32 %res
 }
 
 ; To sink the replicate region containing %rem, we need to split the block
 ; containing %conv at the end, because %conv is the last recipe in the block.
 define void @sink_replicate_region_4_requires_split_at_end_of_block(i32 %x, i8* %ptr) optsize {
 ; CHECK-LABEL: sink_replicate_region_4_requires_split_at_end_of_block
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   FIRST-ORDER-RECURRENCE-PHI ir<%0> = phi ir<0>, ir<%conv>
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<{{.+}}>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT:   REPLICATE ir<%gep> = getelementptr ir<%ptr>, ir<%iv>
 ; CHECK-NEXT: Successor(s): loop.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0:
 ; CHECK-NEXT: Successor(s): pred.load
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:

 exit:
   ret void
 }
 
 ; Test case that requires sinking a recipe in a replicate region after another replicate region.
 define void @sink_replicate_region_after_replicate_region(i32* %ptr, i32 %x, i8 %y) optsize {
 ; CHECK-LABEL: sink_replicate_region_after_replicate_region
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   FIRST-ORDER-RECURRENCE-PHI ir<%recur> = phi ir<0>, ir<%recur.next>
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<{{.+}}>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT: Successor(s): loop.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0:
 ; CHECK-NEXT: Successor(s): loop.1
 ; CHECK-EMPTY:
 ; CHECK-NEXT:  loop.1:
 ; CHECK-NEXT:   WIDEN ir<%recur.next> = sext ir<%y>
 ; CHECK-NEXT:   EMIT vp<[[SPLICE:%.+]]> = first-order splice ir<%recur> ir<%recur.next>

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

 ; REQUIRES: asserts
 
 ; RUN: opt -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -debug -disable-output %s 2>&1 | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 
 @a = common global [2048 x i32] zeroinitializer, align 16
 @b = common global [2048 x i32] zeroinitializer, align 16
 @c = common global [2048 x i32] zeroinitializer, align 16
 
 
 ; CHECK-LABEL: LV: Checking a loop in "sink1"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT: Successor(s): loop.0
 
 ; CHECK:      loop.0:
 ; CHECK-NEXT: Successor(s): pred.store
 
 ; CHECK:      <xVFxUF> pred.store: {
 ; CHECK-NEXT:   pred.store.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK]]>
loop:
   br i1 %realexit, label %exit, label %loop
 
 exit:
   ret void
 }
 
 ; CHECK-LABEL: LV: Checking a loop in "sink2"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT: Successor(s): pred.load
 
 ; CHECK:      <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK]]>
 ; CHECK-NEXT:   Successor(s): pred.load.if, pred.load.continue
 ; CHECK-NEXT:   CondBit: vp<[[MASK]]> (loop)
 
loop:
   br i1 %realexit, label %exit, label %loop
 
 exit:
   ret void
 }
 
 ; CHECK-LABEL: LV: Checking a loop in "sink3"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT: Successor(s): pred.load
 
 ; CHECK:      <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK]]>
 ; CHECK-NEXT:   Successor(s): pred.load.if, pred.load.continue
 ; CHECK-NEXT:   CondBit: vp<[[MASK]]> (loop)
 

 exit:
   ret void
 }
 
 ; Make sure we do not sink uniform instructions.
 define void @uniform_gep(i64 %k, i16* noalias %A, i16* noalias %B) {
 ; CHECK-LABEL: LV: Checking a loop in "uniform_gep"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 21, %iv.next
 ; CHECK-NEXT:   EMIT vp<[[CAN_IV:%.+]]> = WIDEN-CANONICAL-INDUCTION
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule vp<[[CAN_IV]]> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule vp<[[CAN_IV]]> vp<[[BTC]]>
 ; CHECK-NEXT:   CLONE ir<%gep.A.uniform> = getelementptr ir<%A>, ir<0>
 ; CHECK-NEXT: Successor(s): pred.load
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK]]>
 ; CHECK-NEXT:   Successor(s): pred.load.if, pred.load.continue
 ; CHECK-NEXT:   CondBit: vp<[[MASK]]> (loop)

 exit:
   ret void
 }
 
 ; Loop with predicated load.
 define void @pred_cfg1(i32 %k, i32 %j) {
 ; CHECK-LABEL: LV: Checking a loop in "pred_cfg1"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
 ; CHECK-NEXT:   WIDEN ir<%c.1> = icmp ir<%iv>, ir<%j>
 ; CHECK-NEXT:   WIDEN ir<%mul> = mul ir<%iv>, ir<10>
 ; CHECK-NEXT: Successor(s): then.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: then.0:
-; CHECK-NEXT:   EMIT vp<[[MASK1:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK1:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT:   EMIT vp<[[MASK2:%.+]]> = select vp<[[MASK1]]> ir<%c.1> ir<false>
 ; CHECK-NEXT: Successor(s): pred.load
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK2]]>
 ; CHECK-NEXT:   Successor(s): pred.load.if, pred.load.continue
 ; CHECK-NEXT:   CondBit: vp<[[MASK2]]> (then.0)
exit:
   ret void
 }
 
 ; Loop with predicated load and store in separate blocks, store depends on
 ; loaded value.
 define void @pred_cfg2(i32 %k, i32 %j) {
 ; CHECK-LABEL: LV: Checking a loop in "pred_cfg2"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
 ; CHECK-NEXT:   WIDEN ir<%mul> = mul ir<%iv>, ir<10>
 ; CHECK-NEXT:   WIDEN ir<%c.0> = icmp ir<%iv>, ir<%j>
 ; CHECK-NEXT:   WIDEN ir<%c.1> = icmp ir<%iv>, ir<%j>
 ; CHECK-NEXT: Successor(s): then.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: then.0:
-; CHECK-NEXT:   EMIT vp<[[MASK1:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK1:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT:   EMIT vp<[[MASK2:%.+]]> = select vp<[[MASK1]]> ir<%c.0> ir<false>
 ; CHECK-NEXT: Successor(s): pred.load
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK2]]>
 ; CHECK-NEXT:   Successor(s): pred.load.if, pred.load.continue
 ; CHECK-NEXT:   CondBit: vp<[[MASK2]]> (then.0)
exit:
   ret void
 }
 
 ; Loop with predicated load and store in separate blocks, store does not depend
 ; on loaded value.
 define void @pred_cfg3(i32 %k, i32 %j) {
 ; CHECK-LABEL: LV: Checking a loop in "pred_cfg3"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
 ; CHECK-NEXT:   WIDEN ir<%mul> = mul ir<%iv>, ir<10>
 ; CHECK-NEXT:   WIDEN ir<%c.0> = icmp ir<%iv>, ir<%j>
 ; CHECK-NEXT: Successor(s): then.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: then.0:
-; CHECK-NEXT:   EMIT vp<[[MASK1:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK1:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT:   EMIT vp<[[MASK2:%.+]]> = select vp<[[MASK1:%.+]]> ir<%c.0> ir<false>
 ; CHECK-NEXT: Successor(s): pred.load
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK2]]>
 ; CHECK-NEXT:   Successor(s): pred.load.if, pred.load.continue
 ; CHECK-NEXT:   CondBit: vp<[[MASK2]]> (then.0)

 
 exit:
   ret void
 }
 
 define void @merge_3_replicate_region(i32 %k, i32 %j) {
 ; CHECK-LABEL: LV: Checking a loop in "merge_3_replicate_region"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT:   REPLICATE ir<%gep.a> = getelementptr ir<@a>, ir<0>, ir<%iv>
 ; CHECK-NEXT: Successor(s): loop.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0:
 ; CHECK-NEXT: Successor(s): loop.1
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.1:
 ; CHECK-NEXT: Successor(s): loop.2

 exit:
   ret void
 }
 
 
 define void @update_2_uses_in_same_recipe_in_merged_block(i32 %k) {
 ; CHECK-LABEL: LV: Checking a loop in "update_2_uses_in_same_recipe_in_merged_block"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT:   REPLICATE ir<%gep.a> = getelementptr ir<@a>, ir<0>, ir<%iv>
 ; CHECK-NEXT: Successor(s): loop.0
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.0:
 ; CHECK-NEXT: Successor(s): loop.1
 ; CHECK-EMPTY:
 ; CHECK-NEXT: loop.1:
 ; CHECK-NEXT: Successor(s): pred.store

 
 exit:
   ret void
 }
 
 define void @recipe_in_merge_candidate_used_by_first_order_recurrence(i32 %k) {
 ; CHECK-LABEL: LV: Checking a loop in "recipe_in_merge_candidate_used_by_first_order_recurrence"
 ; CHECK:      VPlan 'Initial VPlan for VF={2},UF>=1' {
+; CHECK-NEXT: Live-in vp<[[BTC:%.+]]> = backedge-taken count
+; CHECK-EMPTY:
 ; CHECK-NEXT: loop:
 ; CHECK-NEXT:   WIDEN-INDUCTION %iv = phi 0, %iv.next
 ; CHECK-NEXT:   FIRST-ORDER-RECURRENCE-PHI ir<%for> = phi ir<0>, ir<%lv.a>
-; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<%0>
+; CHECK-NEXT:   EMIT vp<[[MASK:%.+]]> = icmp ule ir<%iv> vp<[[BTC]]>
 ; CHECK-NEXT:   REPLICATE ir<%gep.a> = getelementptr ir<@a>, ir<0>, ir<%iv>
 ; CHECK-NEXT: Successor(s): pred.load
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <xVFxUF> pred.load: {
 ; CHECK-NEXT:   pred.load.entry:
 ; CHECK-NEXT:     BRANCH-ON-MASK vp<[[MASK]]>
 ; CHECK-NEXT:   Successor(s): pred.load.if, pred.load.continue
 ; CHECK-NEXT:   CondBit: vp<[[MASK]]> (loop)