diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp --- a/llvm/lib/Transforms/IPO/SampleProfile.cpp +++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp @@ -183,6 +183,11 @@ cl::desc("Inline cold call sites in profile loader if it's beneficial " "for code size.")); +static cl::opt DisableSampleLoaderInlining( + "disable-sample-loader-inlining", cl::Hidden, cl::init(false), + cl::desc("If true, turn off inliner in sample profile loader. Used for " + "evaluation or debugging.")); + cl::opt ProfileInlineGrowthLimit( "sample-profile-inline-growth-limit", cl::Hidden, cl::init(12), cl::desc("The size growth ratio limit for proirity-based sample profile " @@ -1124,6 +1129,8 @@ /// \returns True if there is any inline happened. bool SampleProfileLoader::inlineHotFunctions( Function &F, DenseSet &InlinedGUIDs) { + if (DisableSampleLoaderInlining) + return false; // ProfAccForSymsInList is used in callsiteIsHot. The assertion makes sure // Profile symbol list is ignored when profile-sample-accurate is on. assert((!ProfAccForSymsInList || @@ -1400,7 +1407,8 @@ bool SampleProfileLoader::inlineHotFunctionsWithPriority( Function &F, DenseSet &InlinedGUIDs) { - + if (DisableSampleLoaderInlining) + return false; // ProfAccForSymsInList is used in callsiteIsHot. The assertion makes sure // Profile symbol list is ignored when profile-sample-accurate is on. assert((!ProfAccForSymsInList || diff --git a/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll b/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll --- a/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll +++ b/llvm/test/Transforms/SampleProfile/profile-context-tracker.ll @@ -17,12 +17,20 @@ ; _Z5funcAi:1 @ _Z8funcLeafi ; _Z5funcBi:1 @ _Z8funcLeafi +; Test the functions won't be inlined as a result of sampled profile if `disable-sample-loader-inlining` is true. +; +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -disable-sample-loader-inlining -S | FileCheck %s --check-prefix=INLINE-NONE +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -disable-sample-loader-inlining -S | FileCheck %s --check-prefix=INLINE-NONE +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -sample-profile-cold-inline-threshold=200 -profile-sample-accurate -disable-sample-loader-inlining -S | FileCheck %s --check-prefix=INLINE-NONE +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t -sample-profile-inline-size -sample-profile-cold-inline-threshold=200 -profile-sample-accurate -disable-sample-loader-inlining -S | FileCheck %s --check-prefix=INLINE-NONE + @factor = dso_local global i32 3, align 4, !dbg !0 define dso_local i32 @main() local_unnamed_addr #0 !dbg !18 { ; INLINE-ALL: @main{{.*}}!prof ![[MAIN_PROF:[0-9]+]] ; INLINE-HOT: @main{{.*}}!prof ![[MAIN_PROF:[0-9]+]] +; INLINE-NONE: @main{{.*}}!prof ![[MAIN_PROF:[0-9]+]] entry: br label %for.body, !dbg !25 @@ -36,10 +44,16 @@ ; _Z5funcBi is marked noinline ; INLINE-ALL: call i32 @_Z5funcBi ; INLINE-HOT: call i32 @_Z5funcBi +; +; _Z5funcBi isn't inlined since disable-sample-loader-inlining is true. +; INLINE-NONE: call i32 @_Z5funcBi %add = add nuw nsw i32 %x.011, 1, !dbg !31 %call1 = tail call i32 @_Z5funcAi(i32 %add), !dbg !28 ; INLINE-ALL-NOT: call i32 @_Z5funcAi ; INLINE-HOT: call i32 @_Z5funcAi +; +; _Z5funcAi is not inlined since `disable-sample-loader-inlining` is true. +; INLINE-NONE: call i32 @_Z5funcAi %add2 = add i32 %call, %r.010, !dbg !34 %add3 = add i32 %add2, %call1, !dbg !35 %dec = add nsw i32 %x.011, -1, !dbg !36 @@ -51,6 +65,7 @@ ; _Z5funcAi is inlined, so outline remainder should have zero counts ; INLINE-ALL: @_Z5funcAi{{.*}}!prof ![[FUNCA_PROF:[0-9]+]] ; INLINE-HOT: @_Z5funcAi{{.*}}!prof ![[FUNCA_PROF:[0-9]+]] +; INLINE-NONE: @_Z5funcAi{{.*}}!prof ![[FUNCA_PROF:[0-9]+]] entry: %add = add nsw i32 %x, 100000, !dbg !44 ; _Z8funcLeafi is already inlined on main->_Z5funcAi->_Z8funcLeafi, @@ -58,6 +73,9 @@ ; (merged and promoted) context profile ; INLINE-ALL: call i32 @_Z8funcLeafi ; INLINE-HOT-NOT: call i32 @_Z8funcLeafi +; +; `_Z8funcLeafi` isn't inlined if `disable-sample-loader-inlining` is true. +; INLINE-NONE: call i32 @_Z8funcLeafi %call = tail call i32 @_Z8funcLeafi(i32 %add), !dbg !45 ret i32 %call, !dbg !46 } @@ -67,6 +85,9 @@ ; inlined, so outline remainder should have empty profile ; INLINE-ALL: @_Z8funcLeafi{{.*}}!prof ![[LEAF_PROF:[0-9]+]] ; INLINE-HOT: @_Z8funcLeafi{{.*}}!prof ![[LEAF_PROF:[0-9]+]] +; +; _Z8funcLeafi won't be inlined if `disable-sample-loader-inlining` is true. +; INLINE-NONE: @_Z8funcLeafi{{.*}}!prof ![[LEAF_PROF:[0-9]+]] entry: %cmp = icmp sgt i32 %x, 0, !dbg !57 br i1 %cmp, label %while.body, label %while.cond2.preheader, !dbg !59 @@ -100,6 +121,8 @@ ; _Z5funcBi is marked noinline, so outline remainder has promoted context profile ; INLINE-ALL: @_Z5funcBi{{.*}}!prof ![[FUNCB_PROF:[0-9]+]] ; INLINE-HOT: @_Z5funcBi{{.*}}!prof ![[FUNCB_PROF:[0-9]+]] +; _Z5funcBi won't be inlined since `disable-sample-loader-inlining` is true. +; INLINE-NONE: @_Z5funcBi{{.*}}!prof ![[FUNCB_PROF:[0-9]+]] entry: %sub = add nsw i32 %x, -100000, !dbg !51 %call = tail call i32 @_Z8funcLeafi(i32 %sub), !dbg !52 @@ -107,6 +130,8 @@ ; should be inlined based on promoted context profile ; INLINE-ALL-NOT: call i32 @_Z8funcLeafi ; INLINE-HOT-NOT: call i32 @_Z8funcLeafi +; +; INLINE-NONE: call i32 @_Z8funcLeafi ret i32 %call, !dbg !53 } @@ -120,6 +145,11 @@ ; INLINE-HOT-DAG-SAME: [[LEAF_PROF]] = !{!"function_entry_count", i64 0} ; INLINE-HOT-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 13} +; INLINE-NONE: [[MAIN_PROF]] = !{!"function_entry_count", i64 1} +; INLINE-NONE: [[FUNCA_PROF]] = !{!"function_entry_count", i64 24} +; INLINE-NONE-DAG-SAME: [[LEAF_PROF]] = !{!"function_entry_count", i64 22} +; INLINE-NONE-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 32} + declare i32 @_Z3fibi(i32) attributes #0 = { nofree noinline norecurse nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" "use-sample-profile" }