diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
index bf76b4d08c6e2f..d4906fd0dbbd70 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
@@ -1,18 +1,109 @@
-; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -instsimplify -S | FileCheck %s --check-prefixes=CHECK,LV
-; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -instsimplify -S | FileCheck %s --check-prefixes=CHECK,TFALWAYS
-; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -instsimplify -S | FileCheck %s --check-prefixes=CHECK,TFFALLBACK
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -instsimplify -S | FileCheck %s --check-prefixes=TFNONE
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -instsimplify -S | FileCheck %s --check-prefixes=TFALWAYS
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -instsimplify -S | FileCheck %s --check-prefixes=TFFALLBACK
 
 target triple = "aarch64-unknown-linux-gnu"
 
 ; A call whose argument must be widened. We check that tail folding uses the
 ; primary mask, and that without tail folding we synthesize an all-true mask.
 define void @test_widen(i64* noalias %a, i64* readnone %b) #4 {
-; CHECK-LABEL: @test_widen(
-; LV-NOT: call <vscale x 2 x i64> @foo_vector
-; TFALWAYS-NOT: vector.body
-; TFALWAYS-NOT: call <vscale x 2 x i64> @foo_vector
-; TFFALLBACK-NOT: call <vscale x 2 x i64> @foo_vector
-; CHECK: ret void
+; TFNONE-LABEL: @test_widen(
+; TFNONE-NEXT:  entry:
+; TFNONE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE:       vector.ph:
+; TFNONE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; TFNONE:       vector.body:
+; TFNONE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFNONE-NEXT:    [[TMP0:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT:    [[TMP1:%.*]] = bitcast i64* [[TMP0]] to <2 x i64>*
+; TFNONE-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 4
+; TFNONE-NEXT:    [[TMP2:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 0
+; TFNONE-NEXT:    [[TMP3:%.*]] = call i64 @foo(i64 [[TMP2]]) #[[ATTR2:[0-9]+]]
+; TFNONE-NEXT:    [[TMP4:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 1
+; TFNONE-NEXT:    [[TMP5:%.*]] = call i64 @foo(i64 [[TMP4]]) #[[ATTR2]]
+; TFNONE-NEXT:    [[TMP6:%.*]] = insertelement <2 x i64> poison, i64 [[TMP3]], i32 0
+; TFNONE-NEXT:    [[TMP7:%.*]] = insertelement <2 x i64> [[TMP6]], i64 [[TMP5]], i32 1
+; TFNONE-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT:    [[TMP9:%.*]] = bitcast i64* [[TMP8]] to <2 x i64>*
+; TFNONE-NEXT:    store <2 x i64> [[TMP7]], <2 x i64>* [[TMP9]], align 4
+; TFNONE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
+; TFNONE-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
+; TFNONE-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; TFNONE:       middle.block:
+; TFNONE-NEXT:    br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFNONE:       scalar.ph:
+; TFNONE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFNONE-NEXT:    br label [[FOR_BODY:%.*]]
+; TFNONE:       for.body:
+; TFNONE-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFNONE-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFNONE-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR2]]
+; TFNONE-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFNONE-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFNONE-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFNONE-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
+; TFNONE:       for.cond.cleanup:
+; TFNONE-NEXT:    ret void
+;
+; TFALWAYS-LABEL: @test_widen(
+; TFALWAYS-NEXT:  entry:
+; TFALWAYS-NEXT:    br label [[FOR_BODY:%.*]]
+; TFALWAYS:       for.body:
+; TFALWAYS-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFALWAYS-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFALWAYS-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR1:[0-9]+]]
+; TFALWAYS-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFALWAYS-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFALWAYS-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFALWAYS-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFALWAYS:       for.cond.cleanup:
+; TFALWAYS-NEXT:    ret void
+;
+; TFFALLBACK-LABEL: @test_widen(
+; TFFALLBACK-NEXT:  entry:
+; TFFALLBACK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFFALLBACK:       vector.ph:
+; TFFALLBACK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; TFFALLBACK:       vector.body:
+; TFFALLBACK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[TMP0:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT:    [[TMP1:%.*]] = bitcast i64* [[TMP0]] to <2 x i64>*
+; TFFALLBACK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 4
+; TFFALLBACK-NEXT:    [[TMP2:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 0
+; TFFALLBACK-NEXT:    [[TMP3:%.*]] = call i64 @foo(i64 [[TMP2]]) #[[ATTR2:[0-9]+]]
+; TFFALLBACK-NEXT:    [[TMP4:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 1
+; TFFALLBACK-NEXT:    [[TMP5:%.*]] = call i64 @foo(i64 [[TMP4]]) #[[ATTR2]]
+; TFFALLBACK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i64> poison, i64 [[TMP3]], i32 0
+; TFFALLBACK-NEXT:    [[TMP7:%.*]] = insertelement <2 x i64> [[TMP6]], i64 [[TMP5]], i32 1
+; TFFALLBACK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT:    [[TMP9:%.*]] = bitcast i64* [[TMP8]] to <2 x i64>*
+; TFFALLBACK-NEXT:    store <2 x i64> [[TMP7]], <2 x i64>* [[TMP9]], align 4
+; TFFALLBACK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
+; TFFALLBACK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
+; TFFALLBACK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; TFFALLBACK:       middle.block:
+; TFFALLBACK-NEXT:    br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFFALLBACK:       scalar.ph:
+; TFFALLBACK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFFALLBACK-NEXT:    br label [[FOR_BODY:%.*]]
+; TFFALLBACK:       for.body:
+; TFFALLBACK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFFALLBACK-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR2]]
+; TFFALLBACK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFFALLBACK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFFALLBACK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFFALLBACK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
+; TFFALLBACK:       for.cond.cleanup:
+; TFFALLBACK-NEXT:    ret void
+;
 entry:
   br label %for.body
 
@@ -33,11 +124,72 @@ for.cond.cleanup:
 
 ; Check that a simple conditional call can be vectorized.
 define void @test_if_then(i64* noalias %a, i64* readnone %b) #4 {
-; CHECK-LABEL: @test_if_then(
-; LV-NOT: call <vscale x 2 x i64> @foo_vector
-; TFALWAYS-NOT: call <vscale x 2 x i64> @foo_vector
-; TFFALLBACK-NOT: call <vscale x 2 x i64> @foo_vector
-; CHECK: ret void
+; TFNONE-LABEL: @test_if_then(
+; TFNONE-NEXT:  entry:
+; TFNONE-NEXT:    br label [[FOR_BODY:%.*]]
+; TFNONE:       for.body:
+; TFNONE-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; TFNONE-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; TFNONE-NEXT:    [[CMP:%.*]] = icmp ugt i64 [[TMP0]], 50
+; TFNONE-NEXT:    br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END]]
+; TFNONE:       if.then:
+; TFNONE-NEXT:    [[TMP1:%.*]] = call i64 @foo(i64 [[TMP0]]) #[[ATTR2]]
+; TFNONE-NEXT:    br label [[IF_END]]
+; TFNONE:       if.end:
+; TFNONE-NEXT:    [[TMP2:%.*]] = phi i64 [ [[TMP1]], [[IF_THEN]] ], [ 0, [[FOR_BODY]] ]
+; TFNONE-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    store i64 [[TMP2]], i64* [[ARRAYIDX1]], align 8
+; TFNONE-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFNONE-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFNONE-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFNONE:       for.cond.cleanup:
+; TFNONE-NEXT:    ret void
+;
+; TFALWAYS-LABEL: @test_if_then(
+; TFALWAYS-NEXT:  entry:
+; TFALWAYS-NEXT:    br label [[FOR_BODY:%.*]]
+; TFALWAYS:       for.body:
+; TFALWAYS-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; TFALWAYS-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; TFALWAYS-NEXT:    [[CMP:%.*]] = icmp ugt i64 [[TMP0]], 50
+; TFALWAYS-NEXT:    br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END]]
+; TFALWAYS:       if.then:
+; TFALWAYS-NEXT:    [[TMP1:%.*]] = call i64 @foo(i64 [[TMP0]]) #[[ATTR1]]
+; TFALWAYS-NEXT:    br label [[IF_END]]
+; TFALWAYS:       if.end:
+; TFALWAYS-NEXT:    [[TMP2:%.*]] = phi i64 [ [[TMP1]], [[IF_THEN]] ], [ 0, [[FOR_BODY]] ]
+; TFALWAYS-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    store i64 [[TMP2]], i64* [[ARRAYIDX1]], align 8
+; TFALWAYS-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFALWAYS-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFALWAYS-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFALWAYS:       for.cond.cleanup:
+; TFALWAYS-NEXT:    ret void
+;
+; TFFALLBACK-LABEL: @test_if_then(
+; TFFALLBACK-NEXT:  entry:
+; TFFALLBACK-NEXT:    br label [[FOR_BODY:%.*]]
+; TFFALLBACK:       for.body:
+; TFFALLBACK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; TFFALLBACK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; TFFALLBACK-NEXT:    [[CMP:%.*]] = icmp ugt i64 [[TMP0]], 50
+; TFFALLBACK-NEXT:    br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END]]
+; TFFALLBACK:       if.then:
+; TFFALLBACK-NEXT:    [[TMP1:%.*]] = call i64 @foo(i64 [[TMP0]]) #[[ATTR2]]
+; TFFALLBACK-NEXT:    br label [[IF_END]]
+; TFFALLBACK:       if.end:
+; TFFALLBACK-NEXT:    [[TMP2:%.*]] = phi i64 [ [[TMP1]], [[IF_THEN]] ], [ 0, [[FOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    store i64 [[TMP2]], i64* [[ARRAYIDX1]], align 8
+; TFFALLBACK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFFALLBACK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFFALLBACK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFFALLBACK:       for.cond.cleanup:
+; TFFALLBACK-NEXT:    ret void
+;
 entry:
   br label %for.body
 
@@ -69,14 +221,81 @@ for.cond.cleanup:
 ; uniform parameter and the metadata lists a uniform variant, right now
 ; we just see a splat of the parameter instead. More work needed.
 define void @test_widen_if_then_else(i64* noalias %a, i64* readnone %b) #4 {
-; CHECK-LABEL: @test_widen_if_then_else
-; LV-NOT: call <vscale x 2 x i64> @foo_vector
-; LV-NOT: call <vscale x 2 x i64> @foo_uniform
-; TFALWAYS-NOT: call <vscale x 2 x i64> @foo_vector
-; TFALWAYS-NOT: call <vscale x 2 x i64> @foo_uniform
-; TFFALLBACK-NOT: call <vscale x 2 x i64> @foo_vector
-; TFFALLBACK-NOT: call <vscale x 2 x i64> @foo_uniform
-; CHECK: ret void
+; TFNONE-LABEL: @test_widen_if_then_else(
+; TFNONE-NEXT:  entry:
+; TFNONE-NEXT:    br label [[FOR_BODY:%.*]]
+; TFNONE:       for.body:
+; TFNONE-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; TFNONE-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; TFNONE-NEXT:    [[CMP:%.*]] = icmp ugt i64 [[TMP0]], 50
+; TFNONE-NEXT:    br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; TFNONE:       if.then:
+; TFNONE-NEXT:    [[TMP1:%.*]] = call i64 @foo(i64 [[TMP0]]) #[[ATTR3:[0-9]+]]
+; TFNONE-NEXT:    br label [[IF_END]]
+; TFNONE:       if.else:
+; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @foo(i64 0) #[[ATTR3]]
+; TFNONE-NEXT:    br label [[IF_END]]
+; TFNONE:       if.end:
+; TFNONE-NEXT:    [[TMP3:%.*]] = phi i64 [ [[TMP1]], [[IF_THEN]] ], [ [[TMP2]], [[IF_ELSE]] ]
+; TFNONE-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    store i64 [[TMP3]], i64* [[ARRAYIDX1]], align 8
+; TFNONE-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFNONE-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFNONE-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFNONE:       for.cond.cleanup:
+; TFNONE-NEXT:    ret void
+;
+; TFALWAYS-LABEL: @test_widen_if_then_else(
+; TFALWAYS-NEXT:  entry:
+; TFALWAYS-NEXT:    br label [[FOR_BODY:%.*]]
+; TFALWAYS:       for.body:
+; TFALWAYS-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; TFALWAYS-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; TFALWAYS-NEXT:    [[CMP:%.*]] = icmp ugt i64 [[TMP0]], 50
+; TFALWAYS-NEXT:    br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; TFALWAYS:       if.then:
+; TFALWAYS-NEXT:    [[TMP1:%.*]] = call i64 @foo(i64 [[TMP0]]) #[[ATTR2:[0-9]+]]
+; TFALWAYS-NEXT:    br label [[IF_END]]
+; TFALWAYS:       if.else:
+; TFALWAYS-NEXT:    [[TMP2:%.*]] = call i64 @foo(i64 0) #[[ATTR2]]
+; TFALWAYS-NEXT:    br label [[IF_END]]
+; TFALWAYS:       if.end:
+; TFALWAYS-NEXT:    [[TMP3:%.*]] = phi i64 [ [[TMP1]], [[IF_THEN]] ], [ [[TMP2]], [[IF_ELSE]] ]
+; TFALWAYS-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    store i64 [[TMP3]], i64* [[ARRAYIDX1]], align 8
+; TFALWAYS-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFALWAYS-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFALWAYS-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFALWAYS:       for.cond.cleanup:
+; TFALWAYS-NEXT:    ret void
+;
+; TFFALLBACK-LABEL: @test_widen_if_then_else(
+; TFFALLBACK-NEXT:  entry:
+; TFFALLBACK-NEXT:    br label [[FOR_BODY:%.*]]
+; TFFALLBACK:       for.body:
+; TFFALLBACK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; TFFALLBACK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; TFFALLBACK-NEXT:    [[CMP:%.*]] = icmp ugt i64 [[TMP0]], 50
+; TFFALLBACK-NEXT:    br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; TFFALLBACK:       if.then:
+; TFFALLBACK-NEXT:    [[TMP1:%.*]] = call i64 @foo(i64 [[TMP0]]) #[[ATTR3:[0-9]+]]
+; TFFALLBACK-NEXT:    br label [[IF_END]]
+; TFFALLBACK:       if.else:
+; TFFALLBACK-NEXT:    [[TMP2:%.*]] = call i64 @foo(i64 0) #[[ATTR3]]
+; TFFALLBACK-NEXT:    br label [[IF_END]]
+; TFFALLBACK:       if.end:
+; TFFALLBACK-NEXT:    [[TMP3:%.*]] = phi i64 [ [[TMP1]], [[IF_THEN]] ], [ [[TMP2]], [[IF_ELSE]] ]
+; TFFALLBACK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    store i64 [[TMP3]], i64* [[ARRAYIDX1]], align 8
+; TFFALLBACK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFFALLBACK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFFALLBACK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFFALLBACK:       for.cond.cleanup:
+; TFFALLBACK-NEXT:    ret void
+;
 entry:
   br label %for.body
 
@@ -111,12 +330,112 @@ for.cond.cleanup:
 ; a mask. Forcing tail folding results in no vectorized call, whereas an
 ; unpredicated body with scalar tail can use the unmasked variant.
 define void @test_widen_nomask(i64* noalias %a, i64* readnone %b) #4 {
-; CHECK-LABEL: @test_widen_nomask(
-; LV: call <vscale x 2 x i64> @foo_vector_nomask
-; TFALWAYS-NOT: vector.body
-; TFALWAYS-NOT: call <vscale x 2 x i64> @foo_vector_nomask
-; TFFALLBACK: call <vscale x 2 x i64> @foo_vector_nomask
-; CHECK: ret void
+; TFNONE-LABEL: @test_widen_nomask(
+; TFNONE-NEXT:  entry:
+; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE:       vector.ph:
+; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFNONE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; TFNONE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; TFNONE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; TFNONE:       vector.body:
+; TFNONE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFNONE-NEXT:    [[TMP4:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT:    [[TMP5:%.*]] = bitcast i64* [[TMP4]] to <vscale x 2 x i64>*
+; TFNONE-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP5]], align 4
+; TFNONE-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector_nomask(<vscale x 2 x i64> [[WIDE_LOAD]])
+; TFNONE-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT:    [[TMP8:%.*]] = bitcast i64* [[TMP7]] to <vscale x 2 x i64>*
+; TFNONE-NEXT:    store <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64>* [[TMP8]], align 4
+; TFNONE-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 2
+; TFNONE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP10]]
+; TFNONE-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; TFNONE-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; TFNONE:       middle.block:
+; TFNONE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; TFNONE-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFNONE:       scalar.ph:
+; TFNONE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFNONE-NEXT:    br label [[FOR_BODY:%.*]]
+; TFNONE:       for.body:
+; TFNONE-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFNONE-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFNONE-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR4:[0-9]+]]
+; TFNONE-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFNONE-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFNONE-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFNONE-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; TFNONE:       for.cond.cleanup:
+; TFNONE-NEXT:    ret void
+;
+; TFALWAYS-LABEL: @test_widen_nomask(
+; TFALWAYS-NEXT:  entry:
+; TFALWAYS-NEXT:    br label [[FOR_BODY:%.*]]
+; TFALWAYS:       for.body:
+; TFALWAYS-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFALWAYS-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFALWAYS-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR3:[0-9]+]]
+; TFALWAYS-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFALWAYS-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFALWAYS-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFALWAYS-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFALWAYS:       for.cond.cleanup:
+; TFALWAYS-NEXT:    ret void
+;
+; TFFALLBACK-LABEL: @test_widen_nomask(
+; TFFALLBACK-NEXT:  entry:
+; TFFALLBACK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFFALLBACK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; TFFALLBACK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFFALLBACK:       vector.ph:
+; TFFALLBACK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFFALLBACK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; TFFALLBACK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; TFFALLBACK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; TFFALLBACK:       vector.body:
+; TFFALLBACK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[TMP4:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[TMP4]] to <vscale x 2 x i64>*
+; TFFALLBACK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP5]], align 4
+; TFFALLBACK-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector_nomask(<vscale x 2 x i64> [[WIDE_LOAD]])
+; TFFALLBACK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT:    [[TMP8:%.*]] = bitcast i64* [[TMP7]] to <vscale x 2 x i64>*
+; TFFALLBACK-NEXT:    store <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64>* [[TMP8]], align 4
+; TFFALLBACK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 2
+; TFFALLBACK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP10]]
+; TFFALLBACK-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; TFFALLBACK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; TFFALLBACK:       middle.block:
+; TFFALLBACK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; TFFALLBACK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFFALLBACK:       scalar.ph:
+; TFFALLBACK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFFALLBACK-NEXT:    br label [[FOR_BODY:%.*]]
+; TFFALLBACK:       for.body:
+; TFFALLBACK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFFALLBACK-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR4:[0-9]+]]
+; TFFALLBACK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFFALLBACK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFFALLBACK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFFALLBACK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; TFFALLBACK:       for.cond.cleanup:
+; TFFALLBACK-NEXT:    ret void
+;
 entry:
   br label %for.body
 
@@ -139,12 +458,112 @@ for.cond.cleanup:
 ; use the masked version and unpredicated body with scalar tail use the unmasked
 ; version.
 define void @test_widen_optmask(i64* noalias %a, i64* readnone %b) #4 {
-; CHECK-LABEL: @test_widen_optmask(
-; LV: call <vscale x 2 x i64> @foo_vector_nomask
-; TFALWAYS-NOT: vector.body
-; TFALWAYS-NOT: call <vscale x 2 x i64> @foo_vector
-; TFFALLBACK: call <vscale x 2 x i64> @foo_vector_nomask
-; CHECK: ret void
+; TFNONE-LABEL: @test_widen_optmask(
+; TFNONE-NEXT:  entry:
+; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE:       vector.ph:
+; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFNONE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; TFNONE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; TFNONE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; TFNONE:       vector.body:
+; TFNONE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFNONE-NEXT:    [[TMP4:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT:    [[TMP5:%.*]] = bitcast i64* [[TMP4]] to <vscale x 2 x i64>*
+; TFNONE-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP5]], align 4
+; TFNONE-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector_nomask(<vscale x 2 x i64> [[WIDE_LOAD]])
+; TFNONE-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT:    [[TMP8:%.*]] = bitcast i64* [[TMP7]] to <vscale x 2 x i64>*
+; TFNONE-NEXT:    store <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64>* [[TMP8]], align 4
+; TFNONE-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 2
+; TFNONE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP10]]
+; TFNONE-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; TFNONE-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; TFNONE:       middle.block:
+; TFNONE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; TFNONE-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFNONE:       scalar.ph:
+; TFNONE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFNONE-NEXT:    br label [[FOR_BODY:%.*]]
+; TFNONE:       for.body:
+; TFNONE-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFNONE-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFNONE-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR5:[0-9]+]]
+; TFNONE-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFNONE-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFNONE-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFNONE-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; TFNONE:       for.cond.cleanup:
+; TFNONE-NEXT:    ret void
+;
+; TFALWAYS-LABEL: @test_widen_optmask(
+; TFALWAYS-NEXT:  entry:
+; TFALWAYS-NEXT:    br label [[FOR_BODY:%.*]]
+; TFALWAYS:       for.body:
+; TFALWAYS-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFALWAYS-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFALWAYS-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR4:[0-9]+]]
+; TFALWAYS-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDVARS_IV]]
+; TFALWAYS-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFALWAYS-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFALWAYS-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFALWAYS-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; TFALWAYS:       for.cond.cleanup:
+; TFALWAYS-NEXT:    ret void
+;
+; TFFALLBACK-LABEL: @test_widen_optmask(
+; TFFALLBACK-NEXT:  entry:
+; TFFALLBACK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFFALLBACK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; TFFALLBACK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFFALLBACK:       vector.ph:
+; TFFALLBACK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFFALLBACK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; TFFALLBACK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; TFFALLBACK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; TFFALLBACK:       vector.body:
+; TFFALLBACK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[TMP4:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[TMP4]] to <vscale x 2 x i64>*
+; TFFALLBACK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP5]], align 4
+; TFFALLBACK-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector_nomask(<vscale x 2 x i64> [[WIDE_LOAD]])
+; TFFALLBACK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT:    [[TMP8:%.*]] = bitcast i64* [[TMP7]] to <vscale x 2 x i64>*
+; TFFALLBACK-NEXT:    store <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64>* [[TMP8]], align 4
+; TFFALLBACK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 2
+; TFFALLBACK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP10]]
+; TFFALLBACK-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; TFFALLBACK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; TFFALLBACK:       middle.block:
+; TFFALLBACK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; TFFALLBACK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFFALLBACK:       scalar.ph:
+; TFFALLBACK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFFALLBACK-NEXT:    br label [[FOR_BODY:%.*]]
+; TFFALLBACK:       for.body:
+; TFFALLBACK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[GEP:%.*]] = getelementptr i64, i64* [[B]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    [[LOAD:%.*]] = load i64, i64* [[GEP]], align 4
+; TFFALLBACK-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR5:[0-9]+]]
+; TFFALLBACK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[INDVARS_IV]]
+; TFFALLBACK-NEXT:    store i64 [[CALL]], i64* [[ARRAYIDX]], align 4
+; TFFALLBACK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFFALLBACK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1024
+; TFFALLBACK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; TFFALLBACK:       for.cond.cleanup:
+; TFFALLBACK-NEXT:    ret void
+;
 entry:
   br label %for.body