[clang] ceb6c23 - [NFC][LoopVectorize] Explicitly disable tail-folding on some SVE tests
David Sherwood via cfe-commits
cfe-commits at lists.llvm.org
Thu Jul 21 07:23:06 PDT 2022
Author: David Sherwood
Date: 2022-07-21T15:23:00+01:00
New Revision: ceb6c23b708d4cae3fbb0a569c5ac14069524a63
URL: https://github.com/llvm/llvm-project/commit/ceb6c23b708d4cae3fbb0a569c5ac14069524a63
DIFF: https://github.com/llvm/llvm-project/commit/ceb6c23b708d4cae3fbb0a569c5ac14069524a63.diff
LOG: [NFC][LoopVectorize] Explicitly disable tail-folding on some SVE tests
This patch is in preparation for enabling vectorisation with tail-folding
by default for SVE targets. Once we do that many existing tests will
break that depend upon having normal unpredicated vector loops. For
all such tests I have added the flag:
-prefer-predicate-over-epilogue=scalar-epilogue
Differential Revision: https://reviews.llvm.org/D129137
Added:
Modified:
clang/test/CodeGen/aarch64-sve-vector-bits-codegen.c
llvm/test/Transforms/LoopVectorize/AArch64/gather-do-not-vectorize-addressing.ll
llvm/test/Transforms/LoopVectorize/AArch64/i1-reg-usage.ll
llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
llvm/test/Transforms/LoopVectorize/AArch64/scalable-reduction-inloop-cond.ll
llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll
llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
llvm/test/Transforms/LoopVectorize/AArch64/scalarize-store-with-predication.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-cond-inv-loads.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-fneg.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-loads.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-store.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-large-strides.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-masked-loadstore.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-runtime-check-size-based-threshold.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-select-cmp.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse-mask4.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-phi.ll
llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse-mask4.ll
llvm/test/Transforms/LoopVectorize/AArch64/vector-reverse.ll
Removed:
################################################################################
diff --git a/clang/test/CodeGen/aarch64-sve-vector-bits-codegen.c b/clang/test/CodeGen/aarch64-sve-vector-bits-codegen.c
index bccd328f0ccad..e306f44c27fb3 100644
--- 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
index 6e934dd989a49..6c62b8765c132 100644
--- 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
index f0dc8e502769d..3124c9df4330b 100644
--- 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
index 7675a568051e6..d270450f1f6ed 100644
--- 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
index d6f73c8e9f5ef..091b117c182ac 100644
--- 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
index 86f1f553d8217..6bafe5629cc4f 100644
--- 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
index 96bc8b0530612..5130a49cf2244 100644
--- 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
index cf0dbb30d0d37..71f554edf53a3 100644
--- 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
index 1021791a0dfb1..a6109903b42ad 100644
--- 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
index b01ee1d4b9526..ab07bff24bd14 100644
--- 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
index 0ebb017204129..bedb6e85af8fd 100644
--- 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
index 2fc3b300fd0b3..d26f18451caec 100644
--- 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
index 96e3108458bd4..9e19ec4643edc 100644
--- 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
index 81c5c9e4dfa91..60c82ab64bc87 100644
--- 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
index 43ef43c11507d..e49acbe9d4dab 100644
--- 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
index 1f9964b04457d..6ea9ee6e160f2 100644
--- 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
index 3898580f2b3e8..0bdbcc605d50a 100644
--- 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
index a12ec7f29c42b..ca9a42a8ff540 100644
--- 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
index 3d78b6f1f0ff1..c7f3fb759d58a 100644
--- 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
index a8ec7f9d7ec64..a2782e7b27530 100644
--- 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
index 1e40638703583..367c8c435edc4 100644
--- 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
index 3371a84425fae..62213b15869cd 100644
--- 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
index 38456ad1da9d5..6faf661fdc5e4 100644
--- 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
index 8fe55ea45631d..ae3ed96555f76 100644
--- 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
index 660eda6dc567b..408c80c3d93d7 100644
--- 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
index 569e7fccd7cec..481425bf02db8 100644
--- 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
index 6b4cc3f83464b..bb36224db1505 100644
--- 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
index 3b9aa409b960a..658bcce1555cb 100644
--- 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
index c7656994d2dfb..8a8abf67e5766 100644
--- 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
index 311dfdb068ca5..eec6c68832cd5 100644
--- 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
More information about the cfe-commits
mailing list