Index: llvm/lib/CodeGen/MachineOutliner.cpp =================================================================== --- llvm/lib/CodeGen/MachineOutliner.cpp +++ llvm/lib/CodeGen/MachineOutliner.cpp @@ -96,6 +96,13 @@ cl::desc("Enable the machine outliner on linkonceodr functions"), cl::init(false)); +// Set the number of times to repeatedly apply outlining. +// Defaults to 1, but more repetitions can save additional size. +static cl::opt + NumRepeat("machine-outline-runs", cl::Hidden, + cl::desc("The number of times to apply machine outlining"), + cl::init(1)); + namespace { /// Represents an undefined index in the suffix tree. @@ -841,6 +848,9 @@ /// linkonceodr linkage. bool OutlineFromLinkOnceODRs = false; + /// The current repeat number of machine outlining. + unsigned OutlineRepeatedNum = 0; + /// Set to true if the outliner should run on all functions in the module /// considered safe for outlining. /// Set to true by default for compatibility with llc's -run-pass option. @@ -899,9 +909,12 @@ InstructionMapper &Mapper, unsigned Name); - /// Calls 'doOutline()'. + /// Calls runOnceOnModule NumRepeat times bool runOnModule(Module &M) override; + /// Calls 'doOutline()'. + bool runOnceOnModule(Module &M, unsigned Iter); + /// Construct a suffix tree on the instructions in \p M and outline repeated /// strings from that tree. bool doOutline(Module &M, unsigned &OutlinedFunctionNum); @@ -1098,7 +1111,13 @@ // Create the function name. This should be unique. // FIXME: We should have a better naming scheme. This should be stable, // regardless of changes to the outliner's cost model/traversal order. - std::string FunctionName = ("OUTLINED_FUNCTION_" + Twine(Name)).str(); + std::string FunctionName; + if (OutlineRepeatedNum > 0) + FunctionName = ("OUTLINED_FUNCTION_" + Twine(OutlineRepeatedNum + 1) + "_" + + Twine(Name)) + .str(); + else + FunctionName = ("OUTLINED_FUNCTION_" + Twine(Name)).str(); // Create the function using an IR-level function. LLVMContext &C = M.getContext(); @@ -1415,12 +1434,14 @@ } } -bool MachineOutliner::runOnModule(Module &M) { +bool MachineOutliner::runOnceOnModule(Module &M, unsigned Iter) { // Check if there's anything in the module. If it's empty, then there's // nothing to outline. if (M.empty()) return false; + OutlineRepeatedNum = Iter; + // Number to append to the current outlined function. unsigned OutlinedFunctionNum = 0; @@ -1484,3 +1505,24 @@ return OutlinedSomething; } + +// Apply machine outlining for NumRepeat times. +bool MachineOutliner::runOnModule(Module &M) { + if (NumRepeat < 1) + report_fatal_error("Expect NumRepeat for machine outlining " + "is equal or greater than 1!\n"); + + bool Changed = false; + unsigned I; + for (I = 0; I < NumRepeat; I++) { + if (!runOnceOnModule(M, I)) { + LLVM_DEBUG(dbgs() << "Stopped outlining at iteration " << I + << " because no changes were found.\n";); + return Changed; + } + Changed = true; + } + LLVM_DEBUG(dbgs() << "Stopped outlining because iteration " << I + << " >= " << NumRepeat << "\n";); + return Changed; +} Index: llvm/test/CodeGen/AArch64/machine-outliner-iterative.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/AArch64/machine-outliner-iterative.mir @@ -0,0 +1,152 @@ +# RUN: llc -mtriple=aarch64--- -run-pass=machine-outliner -machine-outline-runs=2 -verify-machineinstrs %s -o - | FileCheck %s --check-prefix TWO-RUNS +# RUN: llc -mtriple=aarch64--- -run-pass=machine-outliner -machine-outline-runs=4 -verify-machineinstrs %s -o - | FileCheck %s --check-prefix FOUR-RUNS + +# Example of Repeated Instruction Sequence - Iterative Machine Outlining +# +#; define void @"$s12"(...) { define i64 @"$s5” (...) { define void @"$s13"(...) { +# ... ... ... +# %8 = load i1, i1* %7 %8 = load i1, i1* %7 +# %9 = load i4, i4*, %6 %9 = load i4, i4*, %6 %9 = load i4, i4*, %6 +# store i4 %9, i4* %5 store i4 %9, i4* %5 store i4 %9, i4* %5 +# ... ... ... +# } } } +# +# After machine outliner (1st time) +# +# define void @"$s12"(...) { define i64 @"$s5” (...) { define void @"$s13"(...) { +# ... ... ... +# %8 = load i1, i1* %7 %8 = load i1, i1* %7 +# call void @outlined_function_1_1 call void @outlined_function_1_1 call void @outlined_function_1_1 +# ... ... ... +# } } } +# +# After machine outliner (2nd time) +# +# define void @"$s12"(...) { define i64 @"$s5” (...) { define void @"$s13"(...) { +# ... ... ... +# call void @outlined_function_2_1 call void @outlined_function_1_1 call void @outlined_function_2_1 +# ... ... ... +# } } } +# +# Check whether machine outliner can further find the outlining opportunity after machine +# outlining has performed. +# +--- | + target triple = "aarch64-apple-darwin" + + declare void @foo() local_unnamed_addr + + declare void @widget() local_unnamed_addr + + ; Function Attrs: minsize noredzone optsize + define void @baz.14() #0 { + ret void + } + + ; Function Attrs: minsize noredzone optsize + define void @baz.15() #0 { + ret void + } + + ; Function Attrs: minsize noredzone optsize + define void @baz.16() #0 { + ret void + } + + attributes #0 = { minsize noredzone optsize } +... +--- +name: baz.14 +tracksRegLiveness: true +stack: + - { id: 0, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8, + stack-id: default, callee-saved-register: '$x19', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +body: | + bb.0: + liveins: $x0, $x19, $lr + + early-clobber $sp = frame-setup STPXpre killed $lr, killed $x19, $sp, -2 :: (store 8 into %stack.1), (store 8 into %stack.0) + frame-setup CFI_INSTRUCTION def_cfa_offset 16 + frame-setup CFI_INSTRUCTION offset $w19, -8 + frame-setup CFI_INSTRUCTION offset $w30, -16 + renamable $x19 = COPY $x0 + renamable $x0 = nuw ADDXri $x0, 48, 0 + $x1 = ADDXri $sp, 0, 0 + dead $w2 = MOVi32imm 33, implicit-def $x2 + $x3 = COPY $xzr + BL @foo, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit killed $x1, implicit killed $x2, implicit killed $x3, implicit-def $sp + $x0 = COPY killed renamable $x19 + BL @widget, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp + early-clobber $sp, $lr, $x19 = frame-destroy LDPXpost $sp, 2 :: (load 8 from %stack.1), (load 8 from %stack.0) + RET_ReallyLR + +... +--- +name: baz.15 +stack: + - { id: 0, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8, + stack-id: default, callee-saved-register: '$x19', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +body: | + bb.0: + early-clobber $sp = frame-setup STPXpre killed $lr, killed $x19, $sp, -2 :: (store 8 into %stack.1), (store 8 into %stack.0) + frame-setup CFI_INSTRUCTION def_cfa_offset 16 + frame-setup CFI_INSTRUCTION offset $w19, -8 + frame-setup CFI_INSTRUCTION offset $w30, -16 + renamable $x19 = COPY $x0 + renamable $x0 = nuw ADDXri killed renamable $x1, 16, 0 + $x1 = ADDXri $sp, 0, 0 + dead $w2 = MOVi32imm 33, implicit-def $x2 + $x3 = COPY $xzr + BL @foo, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit $x1, implicit killed $x2, implicit killed $x3, implicit-def $sp + $x0 = COPY killed renamable $x19 + BL @widget, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp + early-clobber $sp, $lr, $x19 = frame-destroy LDPXpost $sp, 2 :: (load 8 from %stack.1), (load 8 from %stack.0) + RET_ReallyLR + +... +--- +name: baz.16 +tracksRegLiveness: true +stack: + - { id: 0, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8, + stack-id: default, callee-saved-register: '$x19', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +body: | + bb.0: + liveins: $x0, $x19, $lr + + early-clobber $sp = frame-setup STPXpre killed $lr, killed $x19, $sp, -2 :: (store 8 into %stack.1), (store 8 into %stack.0) + frame-setup CFI_INSTRUCTION def_cfa_offset 16 + frame-setup CFI_INSTRUCTION offset $w19, -8 + frame-setup CFI_INSTRUCTION offset $w30, -16 + renamable $x19 = COPY $x0 + renamable $x0 = nuw ADDXri $x0, 48, 0 + $x1 = ADDXri $sp, 0, 0 + dead $w2 = MOVi32imm 33, implicit-def $x2 + $x3 = COPY $xzr + BL @foo, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit killed $x1, implicit killed $x2, implicit killed $x3, implicit-def $sp + $x0 = COPY killed renamable $x19 + BL @widget, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp + early-clobber $sp, $lr, $x19 = frame-destroy LDPXpost $sp, 2 :: (load 8 from %stack.1), (load 8 from %stack.0) + RET_ReallyLR + +... + +# TWO-RUNS: name: OUTLINED_FUNCTION_2_0 +# TWO-RUNS-DAG: bb.0: +# TWO-RUNS-DAG: renamable $x19 = COPY $x0 +# TWO-RUNS-NEXT: renamable $x0 = nuw ADDXri $x0, 48, 0 +# TWO-RUNS-NEXT: TCRETURNdi @OUTLINED_FUNCTION_0, 0, implicit $sp +# FOUR-RUNS-NOT: [[OUTLINED:OUTLINED_FUNCTION_3_[0-9]+]] +# FOUR-RUNS-NOT: [[OUTLINED:OUTLINED_FUNCTION_4_[0-9]+]]