RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00
Code Issues Projects Releases Wiki Activity

Revert "[NewPM][opt] Run the "default" AA pipeline by default"

Browse Source 
This reverts commit be611431cd1f5c826a55b531db92a63e84323866.

Other/new-pm-lto-defaults.ll failing
This commit is contained in:
Arthur Eubanks 2021-01-21 20:16:34 -08:00
parent d6b74b6a39
commit f6943821ec
36 changed files with 640 additions and 585 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
test/Analysis/MemorySSA/pr43569.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -pgo-kind=pgo-instr-gen-pipeline -passes="default<O3>" -enable-nontrivial-unswitch -S < %s | FileCheck %s
; RUN: opt -pgo-kind=pgo-instr-gen-pipeline -aa-pipeline=default -passes="default<O3>" -enable-nontrivial-unswitch -S < %s | FileCheck %s
; REQUIRES: asserts
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"

2
test/CodeGen/Hexagon/loop-idiom/pmpy-mod.ll
View File

@ -3,7 +3,7 @@
; get this opportunity regardless of what happens before.
; RUN: opt -O2 -march=hexagon -S < %s | FileCheck %s
; RUN: opt -passes='default<O2>' -march=hexagon -S < %s | FileCheck %s
; RUN: opt -aa-pipeline=default -passes='default<O2>' -march=hexagon -S < %s | FileCheck %s
target triple = "hexagon"
target datalayout = "e-m:e-p:32:32:32-a:0-n16:32-i64:64:64-i32:32:32-i16:16:16-i1:8:8-f32:32:32-f64:64:64-v32:32:32-v64:64:64-v512:512:512-v1024:1024:1024-v2048:2048:2048"

6
test/Other/loop-pm-invalidation.ll
View File

@ -2,18 +2,18 @@
;
; Check that we always nuke the LPM stuff when the loops themselves are
; invalidated.
; RUN: opt -disable-output -disable-verify -debug-pass-manager -aa-pipeline= %s 2>&1 \
; RUN: opt -disable-output -disable-verify -debug-pass-manager %s 2>&1 \
; RUN: -passes='loop(no-op-loop),invalidate<loops>,loop(no-op-loop)' \
; RUN: | FileCheck %s --check-prefix=CHECK-LOOP-INV
;
; If we ended up building the standard analyses, their invalidation should nuke
; stuff as well.
; RUN: opt -disable-output -disable-verify -debug-pass-manager %s -aa-pipeline= 2>&1 \
; RUN: opt -disable-output -disable-verify -debug-pass-manager %s 2>&1 \
; RUN: -passes='loop(no-op-loop),invalidate<scalar-evolution>,loop(no-op-loop)' \
; RUN: | FileCheck %s --check-prefix=CHECK-SCEV-INV
;
; Also provide a test that can delete loops after populating analyses for them.
; RUN: opt -disable-output -disable-verify -debug-pass-manager %s -aa-pipeline= 2>&1 \
; RUN: opt -disable-output -disable-verify -debug-pass-manager %s 2>&1 \
; RUN: -passes='loop(no-op-loop,loop-deletion),invalidate<scalar-evolution>,loop(no-op-loop)' \
; RUN: | FileCheck %s --check-prefix=CHECK-SCEV-INV-AFTER-DELETE

4
test/Other/new-pass-manager.ll
View File

@ -445,10 +445,6 @@
; CHECK-REPEAT-LOOP-PASS-NEXT: Finished llvm::Function pass manager run
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: AAManager
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: TargetLibraryAnalysis
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: BasicAA
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: TypeBasedAA
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: ScalarEvolutionAnalysis
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: TargetIRAnalysis
; CHECK-REPEAT-LOOP-PASS-NEXT: Running analysis: InnerAnalysisManagerProxy<{{.*}}>

3
test/Other/new-pm-defaults.ll
View File

@ -98,9 +98,6 @@
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis
; CHECK-O-NEXT: Running analysis: AAManager
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-EP-PEEPHOLE-NEXT: Running pass: NoOpFunctionPass
; CHECK-O-NEXT: Running pass: SimplifyCFGPass

7
test/Other/new-pm-lto-defaults.ll
View File

@ -49,12 +49,6 @@
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph{{.*}}>
; CHECK-O-NEXT: Running pass: PostOrderFunctionAttrsPass
; CHECK-O-NEXT: Running analysis: AAManager
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O1-NEXT: Running analysis: AssumptionAnalysis on foo
; CHECK-O1-NEXT: Running analysis: DominatorTreeAnalysis
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: ReversePostOrderFunctionAttrsPass
; CHECK-O-NEXT: Running analysis: CallGraphAnalysis
; CHECK-O-NEXT: Running pass: GlobalSplitPass
@ -67,6 +61,7 @@
; CHECK-O2-NEXT: Starting llvm::Function pass manager run.
; CHECK-O3-NEXT: Running pass: AggressiveInstCombinePass
; CHECK-O2-NEXT: Running pass: InstCombinePass
; CHECK-O2-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-EP-Peephole-NEXT: Running pass: NoOpFunctionPass
; CHECK-O2-NEXT: Finished llvm::Function pass manager run.
; CHECK-O2-NEXT: Running pass: ModuleInlinerWrapperPass

2
test/Other/new-pm-pr42726-cgscc.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -passes="default<O1>" %s -S | FileCheck %s
; RUN: opt -aa-pipeline=default -passes="default<O1>" %s -S | FileCheck %s
; REQUIRES: asserts
declare void @bar()

3
test/Other/new-pm-thinlto-defaults.ll
View File

@ -84,9 +84,6 @@
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-PRELINK-O-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis
; CHECK-O-NEXT: Running analysis: AAManager
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Finished llvm::Function pass manager run.

3
test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
View File

@ -53,9 +53,6 @@
; CHECK-O-NEXT: Starting {{.*}}Function pass manager run.
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running analysis: AAManager
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running analysis: BlockFrequencyAnalysis on foo
; These next two can appear in any order since they are accessed as parameters

3
test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
View File

@ -48,9 +48,6 @@
; CHECK-O-NEXT: Running pass: InstCombinePass on foo
; CHECK-O-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis on foo
; CHECK-O-NEXT: Running analysis: AAManager on foo
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Finished {{.*}}Function pass manager run.
; CHECK-O-NEXT: Running pass: SampleProfileLoaderPass

16
test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
View File

@ -54,9 +54,6 @@
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis
; CHECK-O-NEXT: Running analysis: AAManager
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Finished {{.*}}Function pass manager run.
@ -107,19 +104,17 @@
; CHECK-O-NEXT: Running pass: InlinerPass
; CHECK-O-NEXT: Running pass: InlinerPass
; CHECK-O-NEXT: Running pass: PostOrderFunctionAttrsPass
; CHECK-O-NEXT: Running analysis: AAManager
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O-NEXT: Running analysis: AssumptionAnalysis
; CHECK-O-NEXT: Running analysis: DominatorTreeAnalysis
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running analysis: AAManager on foo
; CHECK-O3-NEXT: Running pass: ArgumentPromotionPass
; CHECK-O3-NEXT: Running analysis: TargetIRAnalysis
; CHECK-O2-NEXT: Running pass: OpenMPOptPass
; CHECK-O3-NEXT: Running pass: OpenMPOptPass
; CHECK-O-NEXT: Starting {{.*}}Function pass manager run.
; CHECK-O-NEXT: Running pass: SROA
; These next two can appear in any order since they are accessed as parameters
; on the same call to SROA::runImpl
; CHECK-O-DAG: Running analysis: DominatorTreeAnalysis on foo
; CHECK-O-DAG: Running analysis: AssumptionAnalysis on foo
; CHECK-O-NEXT: Running pass: EarlyCSEPass
; CHECK-O1-NEXT: Running analysis: TargetIRAnalysis on foo
; CHECK-O2-NEXT: Running analysis: TargetIRAnalysis on foo
@ -134,6 +129,7 @@
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O3-NEXT: Running pass: AggressiveInstCombinePass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running analysis: BlockFrequencyAnalysis on foo
; These next two can appear in any order since they are accessed as parameters
; on the same call to BlockFrequencyInfo::calculate.

3
test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
View File

@ -46,9 +46,6 @@
; CHECK-O-NEXT: Running pass: InstCombinePass on foo
; CHECK-O-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis on foo
; CHECK-O-NEXT: Running analysis: AAManager on foo
; CHECK-O-NEXT: Running analysis: BasicAA
; CHECK-O-NEXT: Running analysis: ScopedNoAliasAA
; CHECK-O-NEXT: Running analysis: TypeBasedAA
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Finished {{.*}}Function pass manager run.
; CHECK-O-NEXT: Running pass: SampleProfileLoaderPass

27
test/Other/pass-pipeline-parsing.ll
View File

@ -46,33 +46,6 @@
; CHECK-MIXED-FP-AND-MP: Running pass: NoOpModulePass
; CHECK-MIXED-FP-AND-MP: Finished llvm::Module pass manager run
; RUN: opt -disable-output -debug-pass-manager \
; RUN: -aa-pipeline= -passes='require<aa>' %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=CHECK-EMPTY-AA
; CHECK-EMPTY-AA: Running analysis: AAManager
; CHECK-EMPTY-AA-NOT: Running analysis: BasicAA
; RUN: opt -disable-output -debug-pass-manager \
; RUN: -aa-pipeline=basic-aa -passes='require<aa>' %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=CHECK-BASIC-AA
; CHECK-BASIC-AA: Running analysis: AAManager
; CHECK-BASIC-AA: Running analysis: BasicAA
; CHECK-BASIC-AA-NOT: Running analysis: TypeBasedAA
; RUN: opt -disable-output -debug-pass-manager \
; RUN: -aa-pipeline=basic-aa,tbaa -passes='require<aa>' %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=CHECK-TWO-AA
; CHECK-TWO-AA: Running analysis: AAManager
; CHECK-TWO-AA: Running analysis: BasicAA
; CHECK-TWO-AA: Running analysis: TypeBasedAA
; RUN: opt -disable-output -debug-pass-manager \
; RUN: -aa-pipeline=default -passes='require<aa>' %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=CHECK-DEFAULT-AA
; CHECK-DEFAULT-AA: Running analysis: AAManager
; CHECK-DEFAULT-AA-DAG: Running analysis: BasicAA
; CHECK-DEFAULT-AA-DAG: Running analysis: TypeBasedAA
; RUN: not opt -disable-output -debug-pass-manager \
; RUN: -passes='no-op-module)' %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=CHECK-UNBALANCED1

6
test/Transforms/Coroutines/coro-elide-musttail.ll
View File

@ -17,7 +17,7 @@ declare dso_local fastcc void @"bar.resume"(%"bar.Frame"*) align 2
define internal fastcc void @foo.resume_musttail(%"foo.Frame"* %FramePtr) {
; CHECK-LABEL: @foo.resume_musttail(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = tail call token @llvm.coro.id(i32 16, i8* null, i8* bitcast (void ()* @bar to i8*), i8* bitcast ([3 x void (%bar.Frame*)*]* @bar.resumers to i8*))
; CHECK-NEXT: [[TMP0:%.*]] = tail call token @llvm.coro.id
; CHECK-NEXT: [[TMP1:%.*]] = tail call i1 @llvm.coro.alloc(token [[TMP0]])
; CHECK-NEXT: [[TMP2:%.*]] = tail call i8* @llvm.coro.begin(token [[TMP0]], i8* null)
; CHECK-NEXT: [[CALL34:%.*]] = call i8* undef()
@ -39,9 +39,9 @@ define internal fastcc void @foo.resume_no_musttail(%"foo.Frame"* %FramePtr) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = alloca [24 x i8], align 8
; CHECK-NEXT: [[VFRAME:%.*]] = bitcast [24 x i8]* [[TMP0]] to i8*
; CHECK-NEXT: [[TMP1:%.*]] = tail call token @llvm.coro.id(i32 16, i8* null, i8* bitcast (void ()* @bar to i8*), i8* bitcast ([3 x void (%bar.Frame*)*]* @bar.resumers to i8*))
; CHECK-NEXT: [[TMP1:%.*]] = call token @llvm.coro.id
; CHECK-NEXT: [[CALL34:%.*]] = call i8* undef()
; CHECK-NEXT: tail call fastcc void undef(i8* [[CALL34]])
; CHECK-NEXT: call fastcc void undef(i8* [[CALL34]])
; CHECK-NEXT: ret void
;
entry:

2
test/Transforms/Coroutines/coro-retcon.ll
View File

@ -1,6 +1,6 @@
; First example from Doc/Coroutines.rst (two block loop) converted to retcon
; RUN: opt < %s -enable-coroutines -O2 -S -enable-new-pm=0 | FileCheck %s
; RUN: opt < %s -enable-coroutines -passes='default<O2>' -S | FileCheck %s
; RUN: opt < %s -enable-coroutines -aa-pipeline=default -passes='default<O2>' -S | FileCheck %s
define i8* @f(i8* %buffer, i32 %n) {
entry:

2
test/Transforms/Inline/cgscc-incremental-invalidate.ll
View File

@ -1,7 +1,7 @@
; Test for a subtle bug when computing analyses during inlining and mutating
; the SCC structure. Without care, this can fail to invalidate analyses.
;
; RUN: opt < %s -aa-pipeline= -passes='cgscc(inline,function(verify<domtree>))' -debug-pass-manager -S 2>&1 | FileCheck %s
; RUN: opt < %s -passes='cgscc(inline,function(verify<domtree>))' -debug-pass-manager -S 2>&1 | FileCheck %s
; First we check that the passes run in the way we expect. Otherwise this test
; may stop testing anything.

4
test/Transforms/LoopRotate/pr35210.ll
View File

@ -1,5 +1,5 @@
;RUN: opt %s -aa-pipeline= -passes='adce,loop(loop-rotate),adce' -S -debug-pass-manager -debug-only=loop-rotate 2>&1 | FileCheck %s
;RUN: opt %s -aa-pipeline= -passes='adce,loop-mssa(loop-rotate),adce' -S -debug-pass-manager -debug-only=loop-rotate -verify-memoryssa 2>&1 | FileCheck %s --check-prefix=MSSA
;RUN: opt %s -passes='adce,loop(loop-rotate),adce' -S -debug-pass-manager -debug-only=loop-rotate 2>&1 | FileCheck %s
;RUN: opt %s -passes='adce,loop-mssa(loop-rotate),adce' -S -debug-pass-manager -debug-only=loop-rotate -verify-memoryssa 2>&1 | FileCheck %s --check-prefix=MSSA
;REQUIRES: asserts
; This test is to make sure we invalidate the post dominator pass after loop rotate simplifies the loop latch.

892
test/Transforms/LoopVectorize/PowerPC/optimal-epilog-vectorization.ll
View File

File diff suppressed because it is too large Load Diff

200
test/Transforms/LoopVectorize/optimal-epilog-vectorization.ll
View File

@ -15,15 +15,34 @@ target datalayout = "e-m:e-i64:64-n32:64-v128:128:128"
define dso_local void @f1(float* noalias %aa, float* noalias %bb, float* noalias %cc, i32 signext %N) {
; CHECK-LABEL: @f1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[AA1:%.*]] = bitcast float* [[AA:%.*]] to i8*
; CHECK-NEXT: [[BB3:%.*]] = bitcast float* [[BB:%.*]] to i8*
; CHECK-NEXT: [[CC6:%.*]] = bitcast float* [[CC:%.*]] to i8*
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[ITER_CHECK:%.*]], label [[FOR_END:%.*]]
; CHECK: iter.check:
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr float, float* [[AA]], i64 [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: [[SCEVGEP2:%.*]] = bitcast float* [[SCEVGEP]] to i8*
; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr float, float* [[BB]], i64 [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: [[SCEVGEP45:%.*]] = bitcast float* [[SCEVGEP4]] to i8*
; CHECK-NEXT: [[SCEVGEP7:%.*]] = getelementptr float, float* [[CC]], i64 [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: [[SCEVGEP78:%.*]] = bitcast float* [[SCEVGEP7]] to i8*
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult i8* [[AA1]], [[SCEVGEP45]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult i8* [[BB3]], [[SCEVGEP2]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: [[BOUND09:%.*]] = icmp ult i8* [[AA1]], [[SCEVGEP78]]
; CHECK-NEXT: [[BOUND110:%.*]] = icmp ult i8* [[CC6]], [[SCEVGEP2]]
; CHECK-NEXT: [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
; CHECK-NEXT: [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
; CHECK-NEXT: [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
; CHECK-NEXT: br i1 [[MEMCHECK_CONFLICT]], label [[VEC_EPILOG_SCALAR_PH]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
; CHECK: vector.main.loop.iter.check:
; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-NEXT: [[MIN_ITERS_CHECK12:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK12]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
@ -31,22 +50,22 @@ define dso_local void @f1(float* noalias %aa, float* noalias %bb, float* noalias
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds float, float* [[BB:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds float, float* [[BB]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = bitcast float* [[TMP2]] to <4 x float>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP3]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, float* [[CC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP3]], align 4, !alias.scope !0
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, float* [[CC]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP4]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = bitcast float* [[TMP5]] to <4 x float>*
; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x float>, <4 x float>* [[TMP6]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = fadd fast <4 x float> [[WIDE_LOAD]], [[WIDE_LOAD2]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, float* [[AA:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[WIDE_LOAD13:%.*]] = load <4 x float>, <4 x float>* [[TMP6]], align 4, !alias.scope !3
; CHECK-NEXT: [[TMP7:%.*]] = fadd fast <4 x float> [[WIDE_LOAD]], [[WIDE_LOAD13]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, float* [[AA]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds float, float* [[TMP8]], i32 0
; CHECK-NEXT: [[TMP10:%.*]] = bitcast float* [[TMP9]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP7]], <4 x float>* [[TMP10]], align 4
; CHECK-NEXT: store <4 x float> [[TMP7]], <4 x float>* [[TMP10]], align 4, !alias.scope !5, !noalias !7
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP8:!llvm.loop !.*]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END_LOOPEXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
@ -56,33 +75,33 @@ define dso_local void @f1(float* noalias %aa, float* noalias %bb, float* noalias
; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
; CHECK: vec.epilog.ph:
; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
; CHECK-NEXT: [[N_MOD_VF3:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: [[N_VEC4:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF3]]
; CHECK-NEXT: [[N_MOD_VF14:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: [[N_VEC15:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF14]]
; CHECK-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
; CHECK: vec.epilog.vector.body:
; CHECK-NEXT: [[INDEX5:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT6:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP12:%.*]] = add i64 [[INDEX5]], 0
; CHECK-NEXT: [[INDEX16:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT17:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP12:%.*]] = add i64 [[INDEX16]], 0
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds float, float* [[BB]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, float* [[TMP13]], i32 0
; CHECK-NEXT: [[TMP15:%.*]] = bitcast float* [[TMP14]] to <4 x float>*
; CHECK-NEXT: [[WIDE_LOAD8:%.*]] = load <4 x float>, <4 x float>* [[TMP15]], align 4
; CHECK-NEXT: [[WIDE_LOAD19:%.*]] = load <4 x float>, <4 x float>* [[TMP15]], align 4
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds float, float* [[CC]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, float* [[TMP16]], i32 0
; CHECK-NEXT: [[TMP18:%.*]] = bitcast float* [[TMP17]] to <4 x float>*
; CHECK-NEXT: [[WIDE_LOAD9:%.*]] = load <4 x float>, <4 x float>* [[TMP18]], align 4
; CHECK-NEXT: [[TMP19:%.*]] = fadd fast <4 x float> [[WIDE_LOAD8]], [[WIDE_LOAD9]]
; CHECK-NEXT: [[WIDE_LOAD20:%.*]] = load <4 x float>, <4 x float>* [[TMP18]], align 4
; CHECK-NEXT: [[TMP19:%.*]] = fadd fast <4 x float> [[WIDE_LOAD19]], [[WIDE_LOAD20]]
; CHECK-NEXT: [[TMP20:%.*]] = getelementptr inbounds float, float* [[AA]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds float, float* [[TMP20]], i32 0
; CHECK-NEXT: [[TMP22:%.*]] = bitcast float* [[TMP21]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP19]], <4 x float>* [[TMP22]], align 4
; CHECK-NEXT: [[INDEX_NEXT6]] = add i64 [[INDEX5]], 4
; CHECK-NEXT: [[TMP23:%.*]] = icmp eq i64 [[INDEX_NEXT6]], [[N_VEC4]]
; CHECK-NEXT: br i1 [[TMP23]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], [[LOOP2:!llvm.loop !.*]]
; CHECK-NEXT: [[INDEX_NEXT17]] = add i64 [[INDEX16]], 4
; CHECK-NEXT: [[TMP23:%.*]] = icmp eq i64 [[INDEX_NEXT17]], [[N_VEC15]]
; CHECK-NEXT: br i1 [[TMP23]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], [[LOOP10:!llvm.loop !.*]]
; CHECK: vec.epilog.middle.block:
; CHECK-NEXT: [[CMP_N7:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[N_VEC4]]
; CHECK-NEXT: br i1 [[CMP_N7]], label [[FOR_END_LOOPEXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK-NEXT: [[CMP_N18:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[N_VEC15]]
; CHECK-NEXT: br i1 [[CMP_N18]], label [[FOR_END_LOOPEXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK: vec.epilog.scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC4]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC15]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ], [ 0, [[ITER_CHECK]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
@ -95,7 +114,7 @@ define dso_local void @f1(float* noalias %aa, float* noalias %bb, float* noalias
; CHECK-NEXT: store float [[ADD]], float* [[ARRAYIDX4]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT_LOOPEXIT]], [[LOOP4:!llvm.loop !.*]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT_LOOPEXIT]], [[LOOP12:!llvm.loop !.*]]
; CHECK: for.end.loopexit.loopexit:
; CHECK-NEXT: br label [[FOR_END_LOOPEXIT]]
; CHECK: for.end.loopexit:
@ -158,6 +177,7 @@ for.end: ; preds = %for.end.loopexit, %
define dso_local signext i32 @f2(float* noalias %A, float* noalias %B, i32 signext %n) {
; CHECK-LABEL: @f2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A1:%.*]] = bitcast float* [[A:%.*]] to i8*
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[N:%.*]], 1
; CHECK-NEXT: br i1 [[CMP1]], label [[ITER_CHECK:%.*]], label [[FOR_END:%.*]]
; CHECK: iter.check:
@ -180,94 +200,110 @@ define dso_local signext i32 @f2(float* noalias %A, float* noalias %B, i32 signe
; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP7]], [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = or i1 [[TMP9]], [[MUL_OVERFLOW]]
; CHECK-NEXT: [[TMP11:%.*]] = or i1 false, [[TMP10]]
; CHECK-NEXT: br i1 [[TMP11]], label [[VEC_EPILOG_SCALAR_PH]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
; CHECK-NEXT: br i1 [[TMP11]], label [[VEC_EPILOG_SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr float, float* [[A]], i64 [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: [[SCEVGEP2:%.*]] = bitcast float* [[SCEVGEP]] to i8*
; CHECK-NEXT: [[TMP12:%.*]] = sext i32 [[TMP0]] to i64
; CHECK-NEXT: [[TMP13:%.*]] = add i64 [[TMP12]], 1
; CHECK-NEXT: [[TMP14:%.*]] = sub i64 [[TMP13]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: [[SCEVGEP3:%.*]] = getelementptr float, float* [[B:%.*]], i64 [[TMP14]]
; CHECK-NEXT: [[SCEVGEP34:%.*]] = bitcast float* [[SCEVGEP3]] to i8*
; CHECK-NEXT: [[TMP15:%.*]] = add nsw i64 [[TMP12]], 1
; CHECK-NEXT: [[SCEVGEP5:%.*]] = getelementptr float, float* [[B]], i64 [[TMP15]]
; CHECK-NEXT: [[SCEVGEP56:%.*]] = bitcast float* [[SCEVGEP5]] to i8*
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult i8* [[A1]], [[SCEVGEP56]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult i8* [[SCEVGEP34]], [[SCEVGEP2]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: [[MEMCHECK_CONFLICT:%.*]] = and i1 [[FOUND_CONFLICT]], true
; CHECK-NEXT: br i1 [[MEMCHECK_CONFLICT]], label [[VEC_EPILOG_SCALAR_PH]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
; CHECK: vector.main.loop.iter.check:
; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-NEXT: [[MIN_ITERS_CHECK7:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK7]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP12:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP16:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i64 [[INDEX]] to i32
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[TMP14:%.*]] = xor i32 [[TMP13]], -1
; CHECK-NEXT: [[TMP15:%.*]] = add i32 [[TMP14]], [[N]]
; CHECK-NEXT: [[TMP16:%.*]] = sext i32 [[TMP15]] to i64
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, float* [[TMP17]], i32 0
; CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds float, float* [[TMP18]], i32 -3
; CHECK-NEXT: [[TMP20:%.*]] = bitcast float* [[TMP19]] to <4 x float>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP20]], align 4
; CHECK-NEXT: [[REVERSE:%.*]] = shufflevector <4 x float> [[WIDE_LOAD]], <4 x float> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT: [[TMP21:%.*]] = fadd fast <4 x float> [[REVERSE]], <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds float, float* [[TMP22]], i32 0
; CHECK-NEXT: [[TMP17:%.*]] = add i32 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[TMP18:%.*]] = xor i32 [[TMP17]], -1
; CHECK-NEXT: [[TMP19:%.*]] = add i32 [[TMP18]], [[N]]
; CHECK-NEXT: [[TMP20:%.*]] = sext i32 [[TMP19]] to i64
; CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP20]]
; CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds float, float* [[TMP21]], i32 0
; CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds float, float* [[TMP22]], i32 -3
; CHECK-NEXT: [[TMP24:%.*]] = bitcast float* [[TMP23]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP21]], <4 x float>* [[TMP24]], align 4
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP24]], align 4, !alias.scope !13
; CHECK-NEXT: [[REVERSE:%.*]] = shufflevector <4 x float> [[WIDE_LOAD]], <4 x float> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT: [[TMP25:%.*]] = fadd fast <4 x float> [[REVERSE]], <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: [[TMP26:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP16]]
; CHECK-NEXT: [[TMP27:%.*]] = getelementptr inbounds float, float* [[TMP26]], i32 0
; CHECK-NEXT: [[TMP28:%.*]] = bitcast float* [[TMP27]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP25]], <4 x float>* [[TMP28]], align 4, !alias.scope !16, !noalias !13
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP25:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP25]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP5:!llvm.loop !.*]]
; CHECK-NEXT: [[TMP29:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP29]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP18:!llvm.loop !.*]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END_LOOPEXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
; CHECK: vec.epilog.iter.check:
; CHECK-NEXT: [[IND_END7:%.*]] = trunc i64 [[N_VEC]] to i32
; CHECK-NEXT: [[IND_END13:%.*]] = trunc i64 [[N_VEC]] to i32
; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_VEC]]
; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 4
; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
; CHECK: vec.epilog.ph:
; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: [[N_VEC3:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF2]]
; CHECK-NEXT: [[IND_END:%.*]] = trunc i64 [[N_VEC3]] to i32
; CHECK-NEXT: [[N_MOD_VF8:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 4
; CHECK-NEXT: [[N_VEC9:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF8]]
; CHECK-NEXT: [[IND_END:%.*]] = trunc i64 [[N_VEC9]] to i32
; CHECK-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
; CHECK: vec.epilog.vector.body:
; CHECK-NEXT: [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT5:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP26:%.*]] = add i64 [[INDEX4]], 0
; CHECK-NEXT: [[OFFSET_IDX9:%.*]] = trunc i64 [[INDEX4]] to i32
; CHECK-NEXT: [[TMP27:%.*]] = add i32 [[OFFSET_IDX9]], 0
; CHECK-NEXT: [[TMP28:%.*]] = xor i32 [[TMP27]], -1
; CHECK-NEXT: [[TMP29:%.*]] = add i32 [[TMP28]], [[N]]
; CHECK-NEXT: [[TMP30:%.*]] = sext i32 [[TMP29]] to i64
; CHECK-NEXT: [[TMP31:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP30]]
; CHECK-NEXT: [[TMP32:%.*]] = getelementptr inbounds float, float* [[TMP31]], i32 0
; CHECK-NEXT: [[TMP33:%.*]] = getelementptr inbounds float, float* [[TMP32]], i32 -3
; CHECK-NEXT: [[TMP34:%.*]] = bitcast float* [[TMP33]] to <4 x float>*
; CHECK-NEXT: [[WIDE_LOAD10:%.*]] = load <4 x float>, <4 x float>* [[TMP34]], align 4
; CHECK-NEXT: [[REVERSE11:%.*]] = shufflevector <4 x float> [[WIDE_LOAD10]], <4 x float> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT: [[TMP35:%.*]] = fadd fast <4 x float> [[REVERSE11]], <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: [[TMP36:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP26]]
; CHECK-NEXT: [[TMP37:%.*]] = getelementptr inbounds float, float* [[TMP36]], i32 0
; CHECK-NEXT: [[INDEX10:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT11:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP30:%.*]] = add i64 [[INDEX10]], 0
; CHECK-NEXT: [[OFFSET_IDX15:%.*]] = trunc i64 [[INDEX10]] to i32
; CHECK-NEXT: [[TMP31:%.*]] = add i32 [[OFFSET_IDX15]], 0
; CHECK-NEXT: [[TMP32:%.*]] = xor i32 [[TMP31]], -1
; CHECK-NEXT: [[TMP33:%.*]] = add i32 [[TMP32]], [[N]]
; CHECK-NEXT: [[TMP34:%.*]] = sext i32 [[TMP33]] to i64
; CHECK-NEXT: [[TMP35:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP34]]
; CHECK-NEXT: [[TMP36:%.*]] = getelementptr inbounds float, float* [[TMP35]], i32 0
; CHECK-NEXT: [[TMP37:%.*]] = getelementptr inbounds float, float* [[TMP36]], i32 -3
; CHECK-NEXT: [[TMP38:%.*]] = bitcast float* [[TMP37]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP35]], <4 x float>* [[TMP38]], align 4
; CHECK-NEXT: [[INDEX_NEXT5]] = add i64 [[INDEX4]], 4
; CHECK-NEXT: [[TMP39:%.*]] = icmp eq i64 [[INDEX_NEXT5]], [[N_VEC3]]
; CHECK-NEXT: br i1 [[TMP39]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], [[LOOP6:!llvm.loop !.*]]
; CHECK-NEXT: [[WIDE_LOAD16:%.*]] = load <4 x float>, <4 x float>* [[TMP38]], align 4
; CHECK-NEXT: [[REVERSE17:%.*]] = shufflevector <4 x float> [[WIDE_LOAD16]], <4 x float> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT: [[TMP39:%.*]] = fadd fast <4 x float> [[REVERSE17]], <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: [[TMP40:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP30]]
; CHECK-NEXT: [[TMP41:%.*]] = getelementptr inbounds float, float* [[TMP40]], i32 0
; CHECK-NEXT: [[TMP42:%.*]] = bitcast float* [[TMP41]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP39]], <4 x float>* [[TMP42]], align 4
; CHECK-NEXT: [[INDEX_NEXT11]] = add i64 [[INDEX10]], 4
; CHECK-NEXT: [[TMP43:%.*]] = icmp eq i64 [[INDEX_NEXT11]], [[N_VEC9]]
; CHECK-NEXT: br i1 [[TMP43]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], [[LOOP19:!llvm.loop !.*]]
; CHECK: vec.epilog.middle.block:
; CHECK-NEXT: [[CMP_N8:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[N_VEC3]]
; CHECK-NEXT: br i1 [[CMP_N8]], label [[FOR_END_LOOPEXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK-NEXT: [[CMP_N14:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[N_VEC9]]
; CHECK-NEXT: br i1 [[CMP_N14]], label [[FOR_END_LOOPEXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK: vec.epilog.scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[ITER_CHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL6:%.*]] = phi i32 [ [[IND_END]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END7]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[ITER_CHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC9]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ], [ 0, [[ITER_CHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL12:%.*]] = phi i32 [ [[IND_END]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END13]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ], [ 0, [[ITER_CHECK]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[I_014:%.*]] = phi i32 [ [[BC_RESUME_VAL6]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP40:%.*]] = xor i32 [[I_014]], -1
; CHECK-NEXT: [[SUB2:%.*]] = add i32 [[TMP40]], [[N]]
; CHECK-NEXT: [[I_014:%.*]] = phi i32 [ [[BC_RESUME_VAL12]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP44:%.*]] = xor i32 [[I_014]], -1
; CHECK-NEXT: [[SUB2:%.*]] = add i32 [[TMP44]], [[N]]
; CHECK-NEXT: [[IDXPROM:%.*]] = sext i32 [[SUB2]] to i64
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[IDXPROM]]
; CHECK-NEXT: [[TMP41:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CONV3:%.*]] = fadd fast float [[TMP41]], 1.000000e+00
; CHECK-NEXT: [[TMP45:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CONV3:%.*]] = fadd fast float [[TMP45]], 1.000000e+00
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store float [[CONV3]], float* [[ARRAYIDX5]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_014]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT_LOOPEXIT]], [[LOOP7:!llvm.loop !.*]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT_LOOPEXIT]], [[LOOP20:!llvm.loop !.*]]
; CHECK: for.end.loopexit.loopexit:
; CHECK-NEXT: br label [[FOR_END_LOOPEXIT]]
; CHECK: for.end.loopexit:
@ -356,7 +392,7 @@ define void @f3(i8* noalias %A, i64 %n) {
; CHECK-NEXT: store <4 x i8> <i8 1, i8 1, i8 1, i8 1>, <4 x i8>* [[TMP3]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP8:!llvm.loop !.*]]
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP21:!llvm.loop !.*]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END_LOOPEXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
@ -378,7 +414,7 @@ define void @f3(i8* noalias %A, i64 %n) {
; CHECK-NEXT: store <4 x i8> <i8 1, i8 1, i8 1, i8 1>, <4 x i8>* [[TMP8]], align 1
; CHECK-NEXT: [[INDEX_NEXT5]] = add i64 [[INDEX4]], 4
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT5]], [[N_VEC3]]
; CHECK-NEXT: br i1 [[TMP9]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], [[LOOP9:!llvm.loop !.*]]
; CHECK-NEXT: br i1 [[TMP9]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], [[LOOP22:!llvm.loop !.*]]
; CHECK: vec.epilog.middle.block:
; CHECK-NEXT: [[CMP_N6:%.*]] = icmp eq i64 [[N]], [[N_VEC3]]
; CHECK-NEXT: br i1 [[CMP_N6]], label [[FOR_END_LOOPEXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]]
@ -391,7 +427,7 @@ define void @f3(i8* noalias %A, i64 %n) {
; CHECK-NEXT: store i8 1, i8* [[ARRAYIDX]], align 1
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT_LOOPEXIT]], [[LOOP10:!llvm.loop !.*]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT_LOOPEXIT]], [[LOOP23:!llvm.loop !.*]]
; CHECK: for.end.loopexit.loopexit:
; CHECK-NEXT: br label [[FOR_END_LOOPEXIT]]
; CHECK: for.end.loopexit:

2
test/Transforms/LoopVersioningLICM/loopversioningLICM1.ll
View File

@ -1,5 +1,5 @@
; RUN: opt < %s -O1 -S -loop-versioning-licm -licm -debug-only=loop-versioning-licm -enable-new-pm=0 2>&1 | FileCheck %s
; RUN: opt < %s -S -passes='default<O1>,loop-versioning-licm,licm' -debug-only=loop-versioning-licm 2>&1 | FileCheck %s
; RUN: opt < %s -S -passes='default<O1>,loop-versioning-licm,licm' --aa-pipeline=default -debug-only=loop-versioning-licm 2>&1 | FileCheck %s
; REQUIRES: asserts
;
; Test to confirm loop is a candidate for LoopVersioningLICM.

2
test/Transforms/LoopVersioningLICM/loopversioningLICM2.ll
View File

@ -1,5 +1,5 @@
; RUN: opt < %s -O1 -S -loop-versioning-licm -licm -debug-only=loop-versioning-licm -disable-loop-unrolling -enable-new-pm=0 2>&1 | FileCheck %s
; RUN: opt < %s -S -passes='default<O1>,loop-versioning-licm,licm' -debug-only=loop-versioning-licm -disable-loop-unrolling 2>&1 | FileCheck %s
; RUN: opt < %s -S -passes='default<O1>,loop-versioning-licm,licm' --aa-pipeline=default -debug-only=loop-versioning-licm -disable-loop-unrolling 2>&1 | FileCheck %s
; REQUIRES: asserts
;
; Test to confirm loop is a good candidate for LoopVersioningLICM

2
test/Transforms/OpenMP/parallel_region_merging.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs
; RUN: opt -S -attributor -openmpopt -openmp-opt-enable-merging -enable-new-pm=0 < %s | FileCheck %s
; RUN: opt -S -aa-pipeline= -passes='attributor,cgscc(openmpopt)' -openmp-opt-enable-merging < %s | FileCheck %s
; RUN: opt -S -passes='attributor,cgscc(openmpopt)' -openmp-opt-enable-merging < %s | FileCheck %s
; #include <omp.h>
; void foo();
; void use(int);

2
test/Transforms/PhaseOrdering/ARM/arm_fill_q7.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S | FileCheck --check-prefix=OLDPM %s
; RUN: opt < %s -passes='default<O3>' -S | FileCheck --check-prefix=NEWPM %s
; RUN: opt < %s -passes='default<O3>' -aa-pipeline=default -S | FileCheck --check-prefix=NEWPM %s
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv6m-none-none-eabi"

2
test/Transforms/PhaseOrdering/X86/SROA-after-loop-unrolling.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -aa-pipeline=default -S | FileCheck %s
; This is based on the following most basic C++ code:
;

2
test/Transforms/PhaseOrdering/X86/addsub-inseltpoison.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -aa-pipeline=default -S | FileCheck %s
target triple = "x86_64--"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

2
test/Transforms/PhaseOrdering/X86/addsub.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -aa-pipeline=default -S | FileCheck %s
target triple = "x86_64--"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

2
test/Transforms/PhaseOrdering/X86/loop-idiom-vs-indvars.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -mcpu=core-avx2 < %s -O3 -S | FileCheck --check-prefix=ALL %s
; RUN: opt -mcpu=core-avx2 < %s -passes='default<O3>' -S | FileCheck --check-prefix=ALL %s
; RUN: opt -mcpu=core-avx2 < %s -passes='default<O3>' -aa-pipeline=default -S | FileCheck --check-prefix=ALL %s
; Not only should we be able to make the loop countable,
; %whatever.next recurrence should be rewritten, making loop dead.

2
test/Transforms/PhaseOrdering/X86/masked-memory-ops.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O2 -S | FileCheck %s
; RUN: opt < %s -passes='default<O2>' -S | FileCheck %s
; RUN: opt < %s -passes='default<O2>' -aa-pipeline=default -S | FileCheck %s
target triple = "x86_64--"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

2
test/Transforms/PhaseOrdering/X86/vdiv.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -aa-pipeline=default -S | FileCheck %s
; Test that IR is optimal after vectorization/unrolling/CSE/canonicalization.
; In particular, there should be no fdivs inside loops because that is expensive.

2
test/Transforms/PhaseOrdering/globalaa-retained.ll
View File

@ -1,5 +1,5 @@
; RUN: opt -O3 -S < %s -enable-new-pm=0 | FileCheck %s
; RUN: opt -passes='default<O3>' -S < %s | FileCheck %s
; RUN: opt -aa-pipeline=default -passes='default<O3>' -S < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64"

2
test/Transforms/PhaseOrdering/instcombine-sroa-inttoptr.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -S | FileCheck %s
; RUN: opt < %s -passes='default<O3>' -aa-pipeline=default -S | FileCheck %s
; This is based on the following most basic C++ code:
;

2
test/Transforms/PhaseOrdering/pr39282.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -O2 -S < %s -enable-new-pm=0 | FileCheck %s
; RUN: opt -passes='default<O2>' -S < %s | FileCheck %s
; RUN: opt -passes='default<O2>' -aa-pipeline=default -S < %s | FileCheck %s
define void @copy(i32* noalias %to, i32* noalias %from) {
; CHECK-LABEL: @copy(

2
test/Transforms/SimplifyCFG/X86/invalidate-dom.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -passes="default<O2>" -disable-output %s
; RUN: opt -aa-pipeline=default -passes="default<O2>" -disable-output %s
; REQUIRES: asserts
; PR42272

2
test/Transforms/ThinLTOBitcodeWriter/pr33536.ll
View File

@ -1,7 +1,7 @@
; Test for a bug specific to the new pass manager where we may build a domtree
; to make more precise AA queries for functions.
;
; RUN: opt -passes='no-op-module' -debug-pass-manager -thinlto-bc -thinlto-split-lto-unit -o %t %s
; RUN: opt -aa-pipeline=default -passes='no-op-module' -debug-pass-manager -thinlto-bc -thinlto-split-lto-unit -o %t %s
; RUN: llvm-modextract -b -n 0 -o - %t | llvm-dis | FileCheck --check-prefix=M0 %s
; RUN: llvm-modextract -b -n 1 -o - %t | llvm-dis | FileCheck --check-prefix=M1 %s

2
test/Transforms/ThinLTOBitcodeWriter/split-vfunc.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -thinlto-bc -thinlto-split-lto-unit -o %t %s
; RUN: opt -thinlto-bc -thinlto-split-lto-unit -o %t %s -aa-pipeline=default
; RUN: llvm-modextract -b -n 0 -o - %t | llvm-dis | FileCheck --check-prefix=M0 %s
; RUN: llvm-modextract -b -n 1 -o - %t | llvm-dis | FileCheck --check-prefix=M1 %s

6
tools/opt/NewPMDriver.cpp
View File

@ -67,7 +67,7 @@ static cl::opt<std::string>
AAPipeline("aa-pipeline",
cl::desc("A textual description of the alias analysis "
"pipeline for handling managed aliasing queries"),
cl::Hidden, cl::init("default"));
cl::Hidden);
/// {{@ These options accept textual pipeline descriptions which will be
/// inserted into default pipelines at the respective extension points
@ -348,7 +348,9 @@ bool llvm::runPassPipeline(StringRef Arg0, Module &M, TargetMachine *TM,
// Specially handle the alias analysis manager so that we can register
// a custom pipeline of AA passes with it.
AAManager AA;
if (Passes.empty()) {
if (!AAPipeline.empty()) {
assert(Passes.empty() &&
"--aa-pipeline and -foo-pass should not both be specified");
if (auto Err = PB.parseAAPipeline(AA, AAPipeline)) {
errs() << Arg0 << ": " << toString(std::move(Err)) << "\n";
return false;