19867de9e7
Previously, any change in any function in an SCC would cause all analyses for all functions in the SCC to be invalidated. With this change, we now manually invalidate analyses for functions we modify, then let the pass manager know that all function analyses should be preserved since we've already handled function analysis invalidation. So far this only touches the inliner, argpromotion, function-attrs, and updateCGAndAnalysisManager(), since they are the most used. This is part of an effort to investigate running the function simplification pipeline less on functions we visit multiple times in the inliner pipeline. However, this causes major memory regressions especially on larger IR. To counteract this, turn on the option to eagerly invalidate function analyses. This invalidates analyses on functions immediately after they're processed in a module or scc to function adaptor for specific parts of the pipeline. Within an SCC, if a pass only modifies one function, other functions in the SCC do not have their analyses invalidated, so in later function passes in the SCC pass manager the analyses may still be cached. It is only after the function passes that the eager invalidation takes effect. For the default pipelines this makes sense because the inliner pipeline runs the function simplification pipeline after all other SCC passes (except CoroSplit which doesn't request any analyses). Overall this has mostly positive effects on compile time and positive effects on memory usage. https://llvm-compile-time-tracker.com/compare.php?from=7f627596977624730f9298a1b69883af1555765e&to=39e824e0d3ca8a517502f13032dfa67304841c90&stat=instructions https://llvm-compile-time-tracker.com/compare.php?from=7f627596977624730f9298a1b69883af1555765e&to=39e824e0d3ca8a517502f13032dfa67304841c90&stat=max-rss D113196 shows that we slightly regressed compile times in exchange for some memory improvements when turning on eager invalidation. D100917 shows that we slightly improved compile times in exchange for major memory regressions in some cases when invalidating less in SCC passes. Turning these on at the same time keeps the memory improvements while keeping compile times neutral/slightly positive. Reviewed By: asbirlea, nikic Differential Revision: https://reviews.llvm.org/D113304
247 lines
12 KiB
LLVM
247 lines
12 KiB
LLVM
; Validate ThinLTO postlink pipeline when we have Sample PGO
|
|
;
|
|
; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
|
|
; RUN: -pgo-kind=pgo-sample-use-pipeline -profile-file='%S/Inputs/new-pm-thinlto-samplepgo-defaults.prof' \
|
|
; RUN: -passes='thinlto<O1>' -S %s 2>&1 \
|
|
; RUN: | FileCheck %s --check-prefixes=CHECK-O,CHECK-O1,%llvmcheckext
|
|
; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
|
|
; RUN: -pgo-kind=pgo-sample-use-pipeline -profile-file='%S/Inputs/new-pm-thinlto-samplepgo-defaults.prof' \
|
|
; RUN: -passes='thinlto<O2>' -S %s 2>&1 \
|
|
; RUN: | FileCheck %s --check-prefixes=CHECK-O,CHECK-O2,CHECK-O23SZ,%llvmcheckext
|
|
; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager -passes-ep-pipeline-start='no-op-module' \
|
|
; RUN: -pgo-kind=pgo-sample-use-pipeline -profile-file='%S/Inputs/new-pm-thinlto-samplepgo-defaults.prof' \
|
|
; RUN: -passes='thinlto<O3>' -S %s 2>&1 \
|
|
; RUN: | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,%llvmcheckext
|
|
; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
|
|
; RUN: -pgo-kind=pgo-sample-use-pipeline -profile-file='%S/Inputs/new-pm-thinlto-samplepgo-defaults.prof' \
|
|
; RUN: -passes='thinlto<Os>' -S %s 2>&1 \
|
|
; RUN: | FileCheck %s --check-prefixes=CHECK-O,CHECK-Os,CHECK-O23SZ,%llvmcheckext
|
|
; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
|
|
; RUN: -pgo-kind=pgo-sample-use-pipeline -profile-file='%S/Inputs/new-pm-thinlto-samplepgo-defaults.prof' \
|
|
; RUN: -passes='thinlto<Oz>' -S %s 2>&1 \
|
|
; RUN: | FileCheck %s --check-prefixes=CHECK-O,CHECK-Oz,CHECK-O23SZ,%llvmcheckext
|
|
; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager -new-pm-debug-info-for-profiling \
|
|
; RUN: -pgo-kind=pgo-sample-use-pipeline -profile-file='%S/Inputs/new-pm-thinlto-samplepgo-defaults.prof' \
|
|
; RUN: -passes='thinlto<O2>' -S %s 2>&1 \
|
|
; RUN: | FileCheck %s --check-prefixes=CHECK-O,CHECK-O2,CHECK-O23SZ,%llvmcheckext
|
|
|
|
; Suppress FileCheck --allow-unused-prefixes=false diagnostics.
|
|
; CHECK-NOEXT: {{^}}
|
|
|
|
; CHECK-O: Running pass: Annotation2Metadata
|
|
; CHECK-O-NEXT: Running pass: ForceFunctionAttrsPass
|
|
; CHECK-EP-PIPELINE-START-NEXT: Running pass: NoOpModulePass
|
|
; CHECK-O-NEXT: Running pass: InferFunctionAttrsPass
|
|
; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
|
|
; CHECK-O-NEXT: Running analysis: TargetLibraryAnalysis
|
|
; CHECK-O-NEXT: Running pass: LowerExpectIntrinsicPass
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
|
|
; CHECK-O-NEXT: Running analysis: TargetIRAnalysis
|
|
; CHECK-O-NEXT: Running analysis: AssumptionAnalysis
|
|
; CHECK-O-NEXT: Running pass: SROAPass
|
|
; CHECK-O-NEXT: Running analysis: DominatorTreeAnalysis
|
|
; CHECK-O-NEXT: Running pass: EarlyCSEPass
|
|
; CHECK-O-NEXT: Running analysis: TargetLibraryAnalysis
|
|
; CHECK-O-NEXT: Running pass: CoroEarlyPass
|
|
; CHECK-O3-NEXT: Running pass: CallSiteSplittingPass
|
|
; 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: Running pass: SampleProfileLoaderPass
|
|
; CHECK-O-NEXT: Running analysis: ProfileSummaryAnalysis
|
|
; CHECK-O-NEXT: Running analysis: CallGraphAnalysis
|
|
; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
|
|
; CHECK-O-NEXT: Running pass: PGOIndirectCallPromotion
|
|
; CHECK-O-NEXT: Running pass: OpenMPOptPass
|
|
; CHECK-O-NEXT: Running pass: LowerTypeTestsPass
|
|
; CHECK-O-NEXT: Running pass: IPSCCPPass
|
|
; CHECK-O-NEXT: Running pass: CalledValuePropagationPass
|
|
; CHECK-O-NEXT: Running pass: GlobalOptPass
|
|
; CHECK-O-NEXT: Running pass: PromotePass
|
|
; CHECK-O-NEXT: Running pass: DeadArgumentEliminationPass
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; 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.
|
|
; CHECK-O-DAG: Running analysis: LoopAnalysis on foo
|
|
; CHECK-O-DAG: Running analysis: BranchProbabilityAnalysis on foo
|
|
; CHECK-O-NEXT: Running analysis: PostDominatorTreeAnalysis on foo
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass on foo
|
|
|
|
; CHECK-O-NEXT: Running pass: ModuleInlinerWrapperPass
|
|
; CHECK-O-NEXT: Running analysis: InlineAdvisorAnalysis
|
|
; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}GlobalsAA
|
|
; CHECK-O-NEXT: Running analysis: GlobalsAA
|
|
; CHECK-O-NEXT: Running pass: InvalidateAnalysisPass<{{.*}}AAManager
|
|
; CHECK-O-NEXT: Invalidating analysis: AAManager
|
|
; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
|
|
; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
|
|
; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis
|
|
; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
|
|
; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
|
|
; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass
|
|
; 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-O3-NEXT: Running pass: ArgumentPromotionPass
|
|
; CHECK-O2-NEXT: Running pass: OpenMPOptCGSCCPass
|
|
; CHECK-O3-NEXT: Running pass: OpenMPOptCGSCCPass
|
|
; CHECK-O-NEXT: Running pass: SROAPass
|
|
; CHECK-O-NEXT: Running pass: EarlyCSEPass
|
|
; CHECK-O-NEXT: Running analysis: MemorySSAAnalysis
|
|
; CHECK-O23SZ-NEXT: Running pass: SpeculativeExecutionPass
|
|
; CHECK-O23SZ-NEXT: Running pass: JumpThreadingPass
|
|
; CHECK-O23SZ-NEXT: Running analysis: LazyValueAnalysis
|
|
; CHECK-O23SZ-NEXT: Running pass: CorrelatedValuePropagationPass
|
|
; CHECK-O23SZ-NEXT: Invalidating analysis: LazyValueAnalysis
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
|
|
; CHECK-O3-NEXT: Running pass: AggressiveInstCombinePass
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; CHECK-O1-NEXT: Running pass: LibCallsShrinkWrapPass
|
|
; CHECK-O2-NEXT: Running pass: LibCallsShrinkWrapPass
|
|
; CHECK-O3-NEXT: Running pass: LibCallsShrinkWrapPass
|
|
; CHECK-O23SZ-NEXT: Running pass: TailCallElimPass
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
|
|
; CHECK-O-NEXT: Running pass: ReassociatePass
|
|
; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}OptimizationRemarkEmitterAnalysis
|
|
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
|
|
; CHECK-O-NEXT: Running pass: LCSSAPass
|
|
; CHECK-O-NEXT: Running analysis: ScalarEvolutionAnalysis
|
|
; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
|
|
; CHECK-O-NEXT: Running pass: LoopInstSimplifyPass
|
|
; CHECK-O-NEXT: Running pass: LoopSimplifyCFGPass
|
|
; CHECK-O-NEXT: Running pass: LICM
|
|
; CHECK-O-NEXT: Running pass: LoopRotatePass
|
|
; CHECK-O-NEXT: Running pass: LICM
|
|
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
|
|
; CHECK-O-NEXT: Running pass: LCSSAPass
|
|
; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
|
|
; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
|
|
; CHECK-O-NEXT: Running pass: LoopDeletionPass
|
|
; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
|
|
; CHECK-O-NEXT: Running pass: SROAPass on foo
|
|
; CHECK-Os-NEXT: Running pass: MergedLoadStoreMotionPass
|
|
; CHECK-Os-NEXT: Running pass: GVNPass
|
|
; CHECK-Os-NEXT: Running analysis: MemoryDependenceAnalysis
|
|
; CHECK-Os-NEXT: Running analysis: PhiValuesAnalysis
|
|
; CHECK-Oz-NEXT: Running pass: MergedLoadStoreMotionPass
|
|
; CHECK-Oz-NEXT: Running pass: GVNPass
|
|
; CHECK-Oz-NEXT: Running analysis: MemoryDependenceAnalysis
|
|
; CHECK-Oz-NEXT: Running analysis: PhiValuesAnalysis
|
|
; CHECK-O2-NEXT: Running pass: MergedLoadStoreMotionPass
|
|
; CHECK-O2-NEXT: Running pass: GVNPass
|
|
; CHECK-O2-NEXT: Running analysis: MemoryDependenceAnalysis
|
|
; CHECK-O2-NEXT: Running analysis: PhiValuesAnalysis
|
|
; CHECK-O3-NEXT: Running pass: MergedLoadStoreMotionPass
|
|
; CHECK-O3-NEXT: Running pass: GVNPass
|
|
; CHECK-O3-NEXT: Running analysis: MemoryDependenceAnalysis
|
|
; CHECK-O3-NEXT: Running analysis: PhiValuesAnalysis
|
|
; CHECK-O1-NEXT: Running pass: MemCpyOptPass
|
|
; CHECK-O-NEXT: Running pass: SCCPPass
|
|
; CHECK-O-NEXT: Running pass: BDCEPass
|
|
; CHECK-O-NEXT: Running analysis: DemandedBitsAnalysis
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; CHECK-O23SZ-NEXT: Running pass: JumpThreadingPass
|
|
; CHECK-O23SZ-NEXT: Running analysis: LazyValueAnalysis
|
|
; CHECK-O23SZ-NEXT: Running pass: CorrelatedValuePropagationPass
|
|
; CHECK-O23SZ-NEXT: Invalidating analysis: LazyValueAnalysis
|
|
; CHECK-O1-NEXT: Running pass: CoroElidePass
|
|
; CHECK-O-NEXT: Running pass: ADCEPass
|
|
; CHECK-O23SZ-NEXT: Running pass: MemCpyOptPass
|
|
; CHECK-O23SZ-NEXT: Running pass: DSEPass
|
|
; CHECK-O23SZ-NEXT: Running pass: LoopSimplifyPass
|
|
; CHECK-O23SZ-NEXT: Running pass: LCSSAPass
|
|
; CHECK-O23SZ-NEXT: Running pass: LICMPass
|
|
; CHECK-O23SZ-NEXT: Running pass: CoroElidePass
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; CHECK-O3-NEXT: Running pass: ControlHeightReductionPass on foo
|
|
; CHECK-O3-NEXT: Running analysis: RegionInfoAnalysis on foo
|
|
; CHECK-O3-NEXT: Running analysis: DominanceFrontierAnalysis on foo
|
|
; CHECK-O-NEXT: Running pass: CoroSplitPass
|
|
; CHECK-O-NEXT: Invalidating analysis: InlineAdvisorAnalysis
|
|
; CHECK-O-NEXT: Running pass: GlobalOptPass
|
|
; CHECK-O-NEXT: Running pass: GlobalDCEPass
|
|
; CHECK-O-NEXT: Running pass: EliminateAvailableExternallyPass
|
|
; CHECK-O-NEXT: Running pass: ReversePostOrderFunctionAttrsPass
|
|
; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}GlobalsAA
|
|
; CHECK-O-NEXT: Running pass: Float2IntPass
|
|
; CHECK-O-NEXT: Running pass: LowerConstantIntrinsicsPass
|
|
; CHECK-EXT: Running pass: {{.*}}::Bye
|
|
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
|
|
; CHECK-O-NEXT: Running pass: LCSSAPass
|
|
; CHECK-O-NEXT: Running pass: LoopRotatePass
|
|
; CHECK-O-NEXT: Running pass: LoopDeletionPass
|
|
; CHECK-O-NEXT: Running pass: LoopDistributePass
|
|
; CHECK-O-NEXT: Running pass: InjectTLIMappings
|
|
; CHECK-O-NEXT: Running pass: LoopVectorizePass
|
|
; CHECK-O-NEXT: Running pass: LoopLoadEliminationPass
|
|
; CHECK-O-NEXT: Running analysis: LoopAccessAnalysis
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
|
|
; CHECK-O2-NEXT: Running pass: SLPVectorizerPass
|
|
; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
|
|
; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
|
|
; CHECK-O-NEXT: Running pass: VectorCombinePass
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; CHECK-O-NEXT: Running pass: LoopUnrollPass
|
|
; CHECK-O-NEXT: Running pass: WarnMissedTransformationsPass
|
|
; CHECK-O-NEXT: Running pass: InstCombinePass
|
|
; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}OptimizationRemarkEmitterAnalysis
|
|
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
|
|
; CHECK-O-NEXT: Running pass: LCSSAPass
|
|
; CHECK-O-NEXT: Running pass: LICMPass
|
|
; CHECK-O-NEXT: Running pass: AlignmentFromAssumptionsPass
|
|
; CHECK-O-NEXT: Running pass: LoopSinkPass
|
|
; CHECK-O-NEXT: Running pass: InstSimplifyPass
|
|
; CHECK-O-NEXT: Running pass: DivRemPairsPass
|
|
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
|
|
; CHECK-O-NEXT: Running pass: CoroCleanupPass
|
|
; CHECK-O-NEXT: Running pass: CGProfilePass
|
|
; CHECK-O-NEXT: Running pass: GlobalDCEPass
|
|
; CHECK-O-NEXT: Running pass: ConstantMergePass
|
|
; CHECK-O-NEXT: Running pass: RelLookupTableConverterPass
|
|
; CHECK-O-NEXT: Running analysis: TargetIRAnalysis
|
|
; CHECK-O-NEXT: Running pass: AnnotationRemarksPass on foo
|
|
; CHECK-O-NEXT: Running pass: PrintModulePass
|
|
|
|
; Make sure we get the IR back out without changes when we print the module.
|
|
; CHECK-O-LABEL: define void @foo(i32 %n) local_unnamed_addr
|
|
; CHECK-O-NEXT: entry:
|
|
; CHECK-O-NEXT: br label %loop
|
|
; CHECK-O: loop:
|
|
; CHECK-O-NEXT: %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
|
|
; CHECK-O-NEXT: %iv.next = add i32 %iv, 1
|
|
; CHECK-O-NEXT: tail call void @bar()
|
|
; CHECK-O-NEXT: %cmp = icmp eq i32 %iv, %n
|
|
; CHECK-O-NEXT: br i1 %cmp, label %exit, label %loop
|
|
; CHECK-O: exit:
|
|
; CHECK-O-NEXT: ret void
|
|
; CHECK-O-NEXT: }
|
|
;
|
|
; Ignore a bunch of intervening metadata containing profile data.
|
|
;
|
|
|
|
declare void @bar() local_unnamed_addr
|
|
|
|
define void @foo(i32 %n) local_unnamed_addr {
|
|
entry:
|
|
br label %loop
|
|
loop:
|
|
%iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%iv.next = add i32 %iv, 1
|
|
tail call void @bar()
|
|
%cmp = icmp eq i32 %iv, %n
|
|
br i1 %cmp, label %exit, label %loop
|
|
exit:
|
|
ret void
|
|
}
|