diff --git a/clang/test/CodeGen/aarch64-sve-vector-bits-codegen.c b/clang/test/CodeGen/aarch64-sve-vector-bits-codegen.c
--- a/clang/test/CodeGen/aarch64-sve-vector-bits-codegen.c
+++ b/clang/test/CodeGen/aarch64-sve-vector-bits-codegen.c
@@ -1,7 +1,11 @@
-// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S -o - %s -mvscale-min=2 -mvscale-max=2  | FileCheck %s --check-prefixes=CHECK,CHECK256
-// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S -o - %s -mvscale-min=4 -mvscale-max=4  | FileCheck %s --check-prefixes=CHECK,CHECK512
-// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S -o - %s -mvscale-min=8 -mvscale-max=8 | FileCheck %s --check-prefixes=CHECK,CHECK1024
-// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S -o - %s -mvscale-min=16 -mvscale-max=16 | FileCheck %s --check-prefixes=CHECK,CHECK2048
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S \
+// RUN:   -mllvm -prefer-predicate-over-epilogue=scalar-epilogue -o - %s -mvscale-min=2 -mvscale-max=2  | FileCheck %s --check-prefixes=CHECK,CHECK256
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S \
+// RUN:   -mllvm -prefer-predicate-over-epilogue=scalar-epilogue -o - %s -mvscale-min=4 -mvscale-max=4  | FileCheck %s --check-prefixes=CHECK,CHECK512
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S \
+// RUN:   -mllvm -prefer-predicate-over-epilogue=scalar-epilogue -o - %s -mvscale-min=8 -mvscale-max=8 | FileCheck %s --check-prefixes=CHECK,CHECK1024
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -O2 -S \
+// RUN:   -mllvm -prefer-predicate-over-epilogue=scalar-epilogue -o - %s -mvscale-min=16 -mvscale-max=16 | FileCheck %s --check-prefixes=CHECK,CHECK2048
 
 // REQUIRES: aarch64-registered-target
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/gather-do-not-vectorize-addressing.ll b/llvm/test/Transforms/LoopVectorize/AArch64/gather-do-not-vectorize-addressing.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/gather-do-not-vectorize-addressing.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/gather-do-not-vectorize-addressing.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -loop-vectorize -mtriple=aarch64--linux-gnu -mattr=+neon -force-vector-width=2 -force-vector-interleave=1 -S -o - | FileCheck %s
-; RUN: opt < %s -loop-vectorize -mtriple=aarch64--linux-gnu -mattr=+sve -force-vector-width=2 -force-vector-interleave=1 -scalable-vectorization=on -S -o - | FileCheck --check-prefix=SVE %s
+; RUN: opt < %s -loop-vectorize -mtriple=aarch64--linux-gnu -mattr=+neon -force-vector-width=2 -force-vector-interleave=1 \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -S -o - | FileCheck %s
+; RUN: opt < %s -loop-vectorize -mtriple=aarch64--linux-gnu -mattr=+sve -force-vector-width=2 -force-vector-interleave=1 \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -scalable-vectorization=on -S -o - | FileCheck --check-prefix=SVE %s
 
 define dso_local double @test(ptr nocapture noundef readonly %data, ptr nocapture noundef readonly %offset, i32 noundef %size) local_unnamed_addr {
 ; CHECK-LABEL: @test(
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/i1-reg-usage.ll b/llvm/test/Transforms/LoopVectorize/AArch64/i1-reg-usage.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/i1-reg-usage.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/i1-reg-usage.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -debug-only=loop-vectorize -disable-output 2>&1 < %s | FileCheck %s
+; RUN: opt -loop-vectorize -debug-only=loop-vectorize -disable-output -prefer-predicate-over-epilogue=scalar-epilogue 2>&1 < %s | FileCheck %s
 ; REQUIRES: asserts
 
 target triple = "aarch64"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
@@ -1,8 +1,8 @@
 ; RUN: opt -S -loop-vectorize -force-vector-interleave=1 -instcombine -mattr=+sve -mtriple aarch64-unknown-linux-gnu \
-; RUN:     -pass-remarks-missed=loop-vectorize < %s 2>%t | FileCheck %s
+; RUN:     -prefer-predicate-over-epilogue=scalar-epilogue -pass-remarks-missed=loop-vectorize < %s 2>%t | FileCheck %s
 ; RUN: cat %t | FileCheck %s --check-prefix=CHECK-REMARKS
 ; RUN: opt -S -loop-vectorize -force-vector-interleave=1 -force-target-instruction-cost=1 -instcombine -mattr=+sve -mtriple aarch64-unknown-linux-gnu \
-; RUN:     -pass-remarks-missed=loop-vectorize < %s 2>%t | FileCheck %s
+; RUN:     -prefer-predicate-over-epilogue=scalar-epilogue -pass-remarks-missed=loop-vectorize < %s 2>%t | FileCheck %s
 ; RUN: cat %t | FileCheck %s --check-prefix=CHECK-REMARKS
 
 define void @vec_load(i64 %N, double* nocapture %a, double* nocapture readonly %b) {
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reduction-inloop-cond.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reduction-inloop-cond.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reduction-inloop-cond.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reduction-inloop-cond.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-vector-interleave=1 -force-vector-width=4 -prefer-inloop-reductions -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -prefer-predicate-over-epilogue=scalar-epilogue -mtriple aarch64-unknown-linux-gnu \
+; RUN:   -mattr=+sve -force-vector-interleave=1 -force-vector-width=4 -prefer-inloop-reductions -S | FileCheck %s
 
 define float @cond_fadd(float* noalias nocapture readonly %a, float* noalias nocapture readonly %cond, i64 %N){
 ; CHECK-LABEL: @cond_fadd(
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll
@@ -1,4 +1,5 @@
-; RUN: opt < %s -loop-vectorize -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve,+bf16 -S 2>%t | FileCheck %s -check-prefix=CHECK
+; RUN: opt < %s -loop-vectorize -prefer-predicate-over-epilogue=scalar-epilogue -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize \
+; RUN:   -pass-remarks-missed=loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve,+bf16 -S 2>%t | FileCheck %s -check-prefix=CHECK
 ; RUN: cat %t | FileCheck %s -check-prefix=CHECK-REMARK
 
 ; Reduction can be vectorized
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
@@ -1,10 +1,15 @@
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-ordered-reductions=false -hints-allow-reordering=false -S | FileCheck %s --check-prefix=CHECK-NOT-VECTORIZED
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-ordered-reductions=false -hints-allow-reordering=true  -S | FileCheck %s --check-prefix=CHECK-UNORDERED
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-ordered-reductions=true  -hints-allow-reordering=false -S | FileCheck %s --check-prefix=CHECK-ORDERED
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-ordered-reductions=true  -hints-allow-reordering=true  -S | FileCheck %s --check-prefix=CHECK-UNORDERED
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -hints-allow-reordering=false -S | FileCheck %s --check-prefix=CHECK-ORDERED
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -hints-allow-reordering=false \
-; RUN:   -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S | FileCheck %s --check-prefix=CHECK-ORDERED-TF
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -prefer-predicate-over-epilogue=scalar-epilogue \
+; RUN:   -force-ordered-reductions=false -hints-allow-reordering=false -S | FileCheck %s --check-prefix=CHECK-NOT-VECTORIZED
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -prefer-predicate-over-epilogue=scalar-epilogue \
+; RUN:   -force-ordered-reductions=false -hints-allow-reordering=true  -S | FileCheck %s --check-prefix=CHECK-UNORDERED
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -prefer-predicate-over-epilogue=scalar-epilogue \
+; RUN:   -force-ordered-reductions=true  -hints-allow-reordering=false -S | FileCheck %s --check-prefix=CHECK-ORDERED
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -prefer-predicate-over-epilogue=scalar-epilogue \
+; RUN:   -force-ordered-reductions=true  -hints-allow-reordering=true  -S | FileCheck %s --check-prefix=CHECK-UNORDERED
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -prefer-predicate-over-epilogue=scalar-epilogue \
+; RUN:   -hints-allow-reordering=false -S | FileCheck %s --check-prefix=CHECK-ORDERED
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
+; RUN:   -hints-allow-reordering=false -S | FileCheck %s --check-prefix=CHECK-ORDERED-TF
 
 define float @fadd_strict(float* noalias nocapture readonly %a, i64 %n) #0 {
 ; CHECK-ORDERED-LABEL: @fadd_strict
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalarize-store-with-predication.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalarize-store-with-predication.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalarize-store-with-predication.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalarize-store-with-predication.ll
@@ -1,5 +1,7 @@
-; RUN: opt -loop-vectorize -force-vector-width=1 -force-vector-interleave=2 -S -o - < %s | FileCheck %s
-; RUN: opt -mattr=+sve -loop-vectorize -force-vector-width=1 -force-vector-interleave=2 -S -o - < %s | FileCheck %s
+; RUN: opt -loop-vectorize -force-vector-width=1 -force-vector-interleave=2 \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -S -o - < %s | FileCheck %s
+; RUN: opt -mattr=+sve -loop-vectorize -force-vector-width=1 -force-vector-interleave=2 \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -S -o - < %s | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
@@ -1,4 +1,5 @@
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve < %s -S | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s -S | FileCheck %s
 
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -o - | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -S %s -o - | FileCheck %s
 
 define void @cond_inv_load_i32i32i16(i32* noalias nocapture %a, i32* noalias nocapture readonly %cond, i16* noalias nocapture readonly %inv, i64 %n) #0 {
 ; CHECK-LABEL: @cond_inv_load_i32i32i16(
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
@@ -1,8 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; REQUIRES: asserts
-; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 --debug-only=loop-vectorize -force-target-instruction-cost=1 -S 2>%t | FileCheck %s --check-prefix=CHECK
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 -prefer-predicate-over-epilogue=scalar-epilogue \
+; RUN:   -debug-only=loop-vectorize -force-target-instruction-cost=1 -S 2>%t | FileCheck %s --check-prefix=CHECK
 ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG
-; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-force-VF=8 --debug-only=loop-vectorize -S 2>%t | FileCheck %s --check-prefix=CHECK-VF8
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-force-VF=8 \
+; RUN:   -debug-only=loop-vectorize -S 2>%t | FileCheck %s --check-prefix=CHECK-VF8
 ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG-FORCED
 
 target triple = "aarch64-linux-gnu"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-fneg.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-fneg.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-fneg.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-fneg.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -loop-vectorize -dce -mtriple aarch64-linux-gnu -mattr=+sve < %s -S | FileCheck %s
+; RUN: opt -loop-vectorize -dce -mtriple aarch64-linux-gnu -mattr=+sve \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s -S | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
@@ -1,5 +1,6 @@
 ; REQUIRES: asserts
-; RUN: opt -loop-vectorize -mcpu=neoverse-v1 -disable-output %s -debug 2>&1 | FileCheck %s
+; RUN: opt -loop-vectorize -mcpu=neoverse-v1 -disable-output %s -debug \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue 2>&1 | FileCheck %s
 
 target triple="aarch64--linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -force-target-instruction-cost=1 -o - | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -S %s -force-target-instruction-cost=1 -o - | FileCheck %s
 
 define void @gather_nxv4i32_ind64(float* noalias nocapture readonly %a, i64* noalias nocapture readonly %b, float* noalias nocapture %c, i64 %n) #0 {
 ; CHECK-LABEL: @gather_nxv4i32_ind64(
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll
@@ -1,4 +1,5 @@
-; RUN: opt < %s -loop-vectorize -mattr=+sve -force-vector-width=4 -pass-remarks-analysis=loop-vectorize -S 2>%t | FileCheck %s
+; RUN: opt < %s -loop-vectorize -mattr=+sve -force-vector-width=4 -pass-remarks-analysis=loop-vectorize \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -S 2>%t | FileCheck %s
 ; RUN: cat %t | FileCheck %s -check-prefix=CHECK-REMARKS
 target triple = "aarch64-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
@@ -1,5 +1,5 @@
 ; REQUIRES: asserts
-; RUN: opt -loop-vectorize -S < %s -debug 2>%t | FileCheck %s
+; RUN: opt -loop-vectorize -S < %s -debug -prefer-predicate-over-epilogue=scalar-epilogue 2>%t | FileCheck %s
 ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG
 
 target triple = "aarch64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -loop-vectorize -force-target-instruction-cost=1 -dce -instcombine < %s -S | FileCheck %s
+; RUN: opt -loop-vectorize -force-target-instruction-cost=1 -dce -instcombine \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s -S | FileCheck %s
 
 target triple = "aarch64-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll
@@ -1,4 +1,5 @@
-; RUN: opt -S -loop-vectorize -mattr=+sve -mtriple aarch64-linux-gnu < %s | FileCheck %s
+; RUN: opt -S -loop-vectorize -mattr=+sve -mtriple aarch64-linux-gnu \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s
 
 define void @invariant_load(i64 %n, i32* noalias nocapture %a, i32* nocapture readonly %b) {
 ; CHECK-LABEL: @invariant_load
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-store.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-store.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-store.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-store.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -S -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll
@@ -1,4 +1,5 @@
-; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -dce -instcombine -S <%s | FileCheck %s
+; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -dce -instcombine -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue <%s | FileCheck %s
 
 define void @stride7_i32(i32* noalias nocapture %dst, i64 %n) #0 {
 ; CHECK-LABEL: @stride7_i32(
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll
@@ -1,4 +1,5 @@
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -o - | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -S %s -o - | FileCheck %s
 
 define void @mloadstore_f32(float* noalias nocapture %a, float* noalias nocapture readonly %b, i64 %n) {
 ; CHECK-LABEL: @mloadstore_f32
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-runtime-check-size-based-threshold.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-runtime-check-size-based-threshold.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-runtime-check-size-based-threshold.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-runtime-check-size-based-threshold.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -passes=loop-vectorize -mattr=+sve -S %s | FileCheck %s
+; RUN: opt -passes=loop-vectorize -mattr=+sve -prefer-predicate-over-epilogue=scalar-epilogue -S %s | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-select-cmp.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-select-cmp.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-select-cmp.ll
@@ -1,5 +1,7 @@
-; RUN: opt -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S < %s | FileCheck %s --check-prefix=CHECK-VF4IC1
-; RUN: opt -loop-vectorize -force-vector-interleave=4 -force-vector-width=4 -S < %s | FileCheck %s --check-prefix=CHECK-VF4IC4
+; RUN: opt -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s --check-prefix=CHECK-VF4IC1
+; RUN: opt -loop-vectorize -force-vector-interleave=4 -force-vector-width=4 -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s --check-prefix=CHECK-VF4IC4
 
 target triple = "aarch64-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll
@@ -1,10 +1,13 @@
 ; REQUIRES: asserts
 ; RUN: opt < %s -loop-vectorize -debug -disable-output -force-ordered-reductions=true -hints-allow-reordering=false \
-; RUN:   -force-vector-width=4 -force-vector-interleave=1 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF4
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -force-vector-width=4 -force-vector-interleave=1 \
+; RUN:   -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF4
 ; RUN: opt < %s -loop-vectorize -debug -disable-output -force-ordered-reductions=true -hints-allow-reordering=false \
-; RUN:   -force-vector-width=8 -force-vector-interleave=1 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF8
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -force-vector-width=8 -force-vector-interleave=1 \
+; RUN:   -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF8
 ; RUN: opt < %s -loop-vectorize -debug -disable-output -force-ordered-reductions=true -hints-allow-reordering=false \
-; RUN:   -force-vector-width=4 -force-vector-interleave=1 -mcpu=neoverse-n2 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF4-CPU-NEOVERSE-N2
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue -force-vector-width=4 -force-vector-interleave=1 \
+; RUN:   -mcpu=neoverse-n2 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF4-CPU-NEOVERSE-N2
 
 target triple="aarch64-unknown-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll
@@ -10,7 +10,8 @@
 
 ; The test checks if the mask is being correctly created, reverted and used
 
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
@@ -5,7 +5,8 @@
 ;  for (int i = N-1; i >= 0; --i)
 ;    a[i] = b[i] + 1.0;
 
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s
 
 define void @vector_reverse_f64(i64 %N, double* %a, double* %b) #0{
 ; CHECK-LABEL: @vector_reverse_f64(
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll
@@ -1,6 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; REQUIRES: asserts
-; RUN: opt -loop-vectorize -S -mtriple=aarch64 -mattr=+sve -debug-only=loop-vectorize < %s 2>&1 | FileCheck %s
+; RUN: opt -loop-vectorize -S -mtriple=aarch64 -mattr=+sve -debug-only=loop-vectorize \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s 2>&1 | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -dce -instcombine -S < %s | FileCheck %s
+; RUN: opt -mtriple aarch64-linux-gnu -mattr=+sve -loop-vectorize -dce -instcombine -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s
 
 ; Ensure that we can vectorize loops such as:
 ;   int *ptr = c;
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse-mask4.ll b/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse-mask4.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse-mask4.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse-mask4.ll
@@ -11,7 +11,8 @@
 
 ; The test checks if the mask is being correctly created, reverted  and used
 
-; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse.ll
--- a/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse.ll
@@ -5,7 +5,8 @@
 ;  for (int i = N-1; i >= 0; --i)
 ;    a[i] = b[i] + 1.0;
 
-; RUN: opt -loop-vectorize -dce  -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
+; RUN: opt -loop-vectorize -dce  -mtriple aarch64-linux-gnu -S \
+; RUN:   -prefer-predicate-over-epilogue=scalar-epilogue < %s | FileCheck %s
 
 define void @vector_reverse_f64(i64 %N, double* %a, double* %b) #0 {
 ; CHECK-LABEL: vector_reverse_f64