Index: llvm/lib/Transforms/IPO/SampleProfile.cpp =================================================================== --- llvm/lib/Transforms/IPO/SampleProfile.cpp +++ llvm/lib/Transforms/IPO/SampleProfile.cpp @@ -148,14 +148,17 @@ "be accurate. It may be overriden by profile-sample-accurate. ")); static cl::opt ProfileMergeInlinee( - "sample-profile-merge-inlinee", cl::Hidden, cl::init(false), + "sample-profile-merge-inlinee", cl::Hidden, cl::init(true), cl::desc("Merge past inlinee's profile to outline version if sample " - "profile loader decided not to inline a call site.")); + "profile loader decided not to inline a call site. It will " + "only be enabled when top-down order of profile loading is " + "enabled. ")); static cl::opt ProfileTopDownLoad( - "sample-profile-top-down-load", cl::Hidden, cl::init(false), + "sample-profile-top-down-load", cl::Hidden, cl::init(true), cl::desc("Do profile annotation and inlining for functions in top-down " - "order of call graph during sample profile loading.")); + "order of call graph during sample profile loading. It only " + "works for new pass manager. ")); static cl::opt ProfileSizeInline( "sample-profile-inline-size", cl::Hidden, cl::init(false), @@ -1785,6 +1788,15 @@ FunctionOrderList.reserve(M.size()); if (!ProfileTopDownLoad || CG == nullptr) { + if (ProfileMergeInlinee) { + // Disable ProfileMergeInlinee if profile is not loaded in top down order, + // because the profile for a function may be used for the profile + // annotation of its outline copy before the profile merging of its + // non-inlined inline instances, and that is not the way how + // ProfileMergeInlinee is supposed to work. + ProfileMergeInlinee = false; + } + for (Function &F : M) if (!F.isDeclaration() && F.hasFnAttribute("use-sample-profile")) FunctionOrderList.push_back(&F); Index: llvm/test/Transforms/SampleProfile/inline-mergeprof.ll =================================================================== --- llvm/test/Transforms/SampleProfile/inline-mergeprof.ll +++ llvm/test/Transforms/SampleProfile/inline-mergeprof.ll @@ -1,10 +1,10 @@ ; Test we lose details of not inlined profile without '-sample-profile-merge-inlinee' -; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -S | FileCheck -check-prefix=SCALE %s -; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -S | FileCheck -check-prefix=SCALE %s +; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee=false -S | FileCheck -check-prefix=SCALE %s +; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee=true -S | FileCheck -check-prefix=SCALE %s +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee=false -S | FileCheck -check-prefix=SCALE %s ; Test we properly merge not inlined profile properly with '-sample-profile-merge-inlinee' -; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee -S | FileCheck -check-prefix=MERGE %s -; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee -S | FileCheck -check-prefix=MERGE %s +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee=true -S | FileCheck -check-prefix=MERGE %s @.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1 Index: llvm/test/Transforms/SampleProfile/inline-topdown.ll =================================================================== --- llvm/test/Transforms/SampleProfile/inline-topdown.ll +++ llvm/test/Transforms/SampleProfile/inline-topdown.ll @@ -1,10 +1,10 @@ ; Note that this needs new pass manager for now. Passing `-sample-profile-top-down-load` to legacy pass manager is a no-op. ; Test we aren't doing specialization for inlining with default source order -; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-topdown.prof -S | FileCheck -check-prefix=DEFAULT %s +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-topdown.prof -sample-profile-top-down-load=false -S | FileCheck -check-prefix=DEFAULT %s ; Test we specialize based on call path with context-sensitive profile while inlining with '-sample-profile-top-down-load' -; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-topdown.prof -sample-profile-merge-inlinee -sample-profile-top-down-load -S | FileCheck -check-prefix=TOPDOWN %s +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-topdown.prof -sample-profile-merge-inlinee -sample-profile-top-down-load=true -S | FileCheck -check-prefix=TOPDOWN %s @.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1