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 @@ -137,6 +137,19 @@ cl::desc("For symbols in profile symbol list, regard their profiles to " "be accurate. It may be overriden by profile-sample-accurate. ")); +static cl::opt ProfileSizeInline( + "sample-profile-inline-size", cl::Hidden, cl::init(false), + cl::desc("Inline cold call sites in profile loader if it's beneficial " + "for code size.")); + +static cl::opt ProfileReInlineAll( + "sample-profile-reinline-all", cl::Hidden, cl::init(false), + cl::desc("Re-inline all previously inlined calls from sample profile.")); + +static cl::opt SampleColdCallSiteThreshold( + "sample-profile-cold-inline-threshold", cl::Hidden, cl::init(45), + cl::desc("Threshold for inlining cold callsites")); + namespace { using BlockWeightMap = DenseMap; @@ -306,6 +319,8 @@ bool inlineCallInstruction(Instruction *I); bool inlineHotFunctions(Function &F, DenseSet &InlinedGUIDs); + // Inline cold/small functions in addition to hot ones + bool shouldInlineColdCallee(Instruction &CallInst); void printEdgeWeight(raw_ostream &OS, Edge E); void printBlockWeight(raw_ostream &OS, const BasicBlock *BB) const; void printBlockEquivalence(raw_ostream &OS, const BasicBlock *BB); @@ -885,6 +900,21 @@ return false; } +bool SampleProfileLoader::shouldInlineColdCallee(Instruction &CallInst) { + if (!ProfileSizeInline) + return false; + + Function *Callee = CallSite(&CallInst).getCalledFunction(); + if (Callee == nullptr) + return false; + + InlineCost Cost = + getInlineCost(cast(CallInst), getInlineParams(), + GetTTI(*Callee), GetAC, None, nullptr, nullptr); + + return Cost.getCost() <= SampleColdCallSiteThreshold; +} + /// Iteratively inline hot callsites of a function. /// /// Iteratively traverse all callsites of the function \p F, and find if @@ -917,20 +947,26 @@ SmallVector CIS; for (auto &BB : F) { bool Hot = false; - SmallVector Candidates; + SmallVector AllCandidates; + SmallVector ColdCandidates; for (auto &I : BB.getInstList()) { const FunctionSamples *FS = nullptr; if ((isa(I) || isa(I)) && !isa(I) && (FS = findCalleeFunctionSamples(I))) { - Candidates.push_back(&I); + AllCandidates.push_back(&I); if (FS->getEntrySamples() > 0) localNotInlinedCallSites.try_emplace(&I, FS); if (callsiteIsHot(FS, PSI)) Hot = true; + else if (shouldInlineColdCallee(I)) + ColdCandidates.push_back(&I); } } - if (Hot) { - CIS.insert(CIS.begin(), Candidates.begin(), Candidates.end()); + if (Hot || ProfileReInlineAll) { + CIS.insert(CIS.begin(), AllCandidates.begin(), AllCandidates.end()); + } + else { + CIS.insert(CIS.begin(), ColdCandidates.begin(), ColdCandidates.end()); } } for (auto I : CIS) { diff --git a/llvm/test/Transforms/SampleProfile/Inputs/inline-cold.prof b/llvm/test/Transforms/SampleProfile/Inputs/inline-cold.prof new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/SampleProfile/Inputs/inline-cold.prof @@ -0,0 +1,7 @@ +main:225715:0 + 2.1: 5553 + 3: 5391 + 3.1: _Z3sumii:0 + 0: 0 + 1: 0 + 2: 0 \ No newline at end of file diff --git a/llvm/test/Transforms/SampleProfile/inline-cold.ll b/llvm/test/Transforms/SampleProfile/inline-cold.ll new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/SampleProfile/inline-cold.ll @@ -0,0 +1,106 @@ +; Let sample profile loader replay inlining of small/cold functions + +; Make sure we don't inline the cold call sites by default +; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-cold.prof -S | FileCheck -check-prefix=NOTINLINE %s +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-cold.prof -S | FileCheck -check-prefix=NOTINLINE %s + +; Make sure we inline code call sites for size if requested +; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-cold.prof -sample-profile-inline-size -S | FileCheck -check-prefix=INLINE %s + +; Make sure we re-inline everything if requested +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-cold.prof -sample-profile-reinline-all -S | FileCheck -check-prefix=INLINE %s + +; Make sure the separate size threshold for sample profile loader inlining works +; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-cold.prof -sample-profile-inline-size -sample-profile-cold-inline-threshold=-500 -S | FileCheck -check-prefix=NOTINLINE %s + +@.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1 + +; Function Attrs: nounwind uwtable +define i32 @_Z3sumii(i32 %x, i32 %y) !dbg !4 { +entry: + %x.addr = alloca i32, align 4 + %y.addr = alloca i32, align 4 + store i32 %x, i32* %x.addr, align 4 + store i32 %y, i32* %y.addr, align 4 + %0 = load i32, i32* %x.addr, align 4, !dbg !11 + %1 = load i32, i32* %y.addr, align 4, !dbg !11 + %add = add nsw i32 %0, %1, !dbg !11 + ret i32 %add, !dbg !11 +} + +; Function Attrs: uwtable +define i32 @main() !dbg !7 { +entry: + %retval = alloca i32, align 4 + %s = alloca i32, align 4 + %i = alloca i32, align 4 + store i32 0, i32* %retval + store i32 0, i32* %i, align 4, !dbg !12 + br label %while.cond, !dbg !13 + +while.cond: ; preds = %if.end, %entry + %0 = load i32, i32* %i, align 4, !dbg !14 + %inc = add nsw i32 %0, 1, !dbg !14 + store i32 %inc, i32* %i, align 4, !dbg !14 + %cmp = icmp slt i32 %0, 400000000, !dbg !14 + br i1 %cmp, label %while.body, label %while.end, !dbg !14 + +while.body: ; preds = %while.cond + %1 = load i32, i32* %i, align 4, !dbg !16 + %cmp1 = icmp ne i32 %1, 100, !dbg !16 + br i1 %cmp1, label %if.then, label %if.else, !dbg !16 + + +if.then: ; preds = %while.body + %2 = load i32, i32* %i, align 4, !dbg !18 + %3 = load i32, i32* %s, align 4, !dbg !18 + %call = call i32 @_Z3sumii(i32 %2, i32 %3), !dbg !18 +; INLINE-NOT: call i32 @_Z3sumii +; NOTINLINE: call i32 @_Z3sumii + store i32 %call, i32* %s, align 4, !dbg !18 + br label %if.end, !dbg !18 + +if.else: ; preds = %while.body + store i32 30, i32* %s, align 4, !dbg !20 + br label %if.end + +if.end: ; preds = %if.else, %if.then + br label %while.cond, !dbg !22 + +while.end: ; preds = %while.cond + %4 = load i32, i32* %s, align 4, !dbg !24 + %call2 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 %4), !dbg !24 + ret i32 0, !dbg !25 +} + +declare i32 @printf(i8*, ...) #2 + +!llvm.dbg.cu = !{!0} +!llvm.module.flags = !{!8, !9} +!llvm.ident = !{!10} + +!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5 ", isOptimized: false, emissionKind: NoDebug, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2) +!1 = !DIFile(filename: "calls.cc", directory: ".") +!2 = !{} +!4 = distinct !DISubprogram(name: "sum", line: 3, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 3, file: !1, scope: !5, type: !6, retainedNodes: !2) +!5 = !DIFile(filename: "calls.cc", directory: ".") +!6 = !DISubroutineType(types: !2) +!7 = distinct !DISubprogram(name: "main", line: 7, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 7, file: !1, scope: !5, type: !6, retainedNodes: !2) +!8 = !{i32 2, !"Dwarf Version", i32 4} +!9 = !{i32 1, !"Debug Info Version", i32 3} +!10 = !{!"clang version 3.5 "} +!11 = !DILocation(line: 4, scope: !4) +!12 = !DILocation(line: 8, scope: !7) +!13 = !DILocation(line: 9, scope: !7) +!14 = !DILocation(line: 9, scope: !15) +!15 = !DILexicalBlockFile(discriminator: 2, file: !1, scope: !7) +!16 = !DILocation(line: 10, scope: !17) +!17 = distinct !DILexicalBlock(line: 10, column: 0, file: !1, scope: !7) +!18 = !DILocation(line: 10, scope: !19) +!19 = !DILexicalBlockFile(discriminator: 2, file: !1, scope: !17) +!20 = !DILocation(line: 10, scope: !21) +!21 = !DILexicalBlockFile(discriminator: 4, file: !1, scope: !17) +!22 = !DILocation(line: 10, scope: !23) +!23 = !DILexicalBlockFile(discriminator: 6, file: !1, scope: !17) +!24 = !DILocation(line: 11, scope: !7) +!25 = !DILocation(line: 12, scope: !7) \ No newline at end of file