Index: llvm/include/llvm/CodeGen/ReachingDefAnalysis.h =================================================================== --- llvm/include/llvm/CodeGen/ReachingDefAnalysis.h +++ llvm/include/llvm/CodeGen/ReachingDefAnalysis.h @@ -86,14 +86,30 @@ MachineFunctionProperties getRequiredProperties() const override { return MachineFunctionProperties().set( - MachineFunctionProperties::Property::NoVRegs); + MachineFunctionProperties::Property::NoVRegs).set( + MachineFunctionProperties::Property::TracksLiveness); } /// Provides the instruction id of the closest reaching def instruction of /// PhysReg that reaches MI, relative to the begining of MI's basic block. int getReachingDef(MachineInstr *MI, int PhysReg); - /// Provides the clearance - the number of instructions since the closest + /// Provides the instruction of the closest reaching def instruction of + /// PhysReg that reaches MI, relative to the begining of MI's basic block. + MachineInstr *getReachingMIDef(MachineInstr *MI, int PhysReg); + + /// Provides the MI, from the given block, corresponding to the Id or a + /// nullptr if the id does not refer to the block. + MachineInstr *getInstFromId(MachineBasicBlock *MBB, int InstId); + + /// Return whether A and B use the same def of PhysReg. + bool hasSameReachingDef(MachineInstr *A, MachineInstr *B, int PhysReg); + + /// Return whether the given register is used after MI, whether it's a local + /// use or a live out. + bool isRegUsedAfter(MachineInstr *MI, int PhysReg); + + // Provides the clearance - the number of instructions since the closest /// reaching def instuction of PhysReg that reaches MI. int getClearance(MachineInstr *MI, MCPhysReg PhysReg); Index: llvm/lib/CodeGen/ReachingDefAnalysis.cpp =================================================================== --- llvm/lib/CodeGen/ReachingDefAnalysis.cpp +++ llvm/lib/CodeGen/ReachingDefAnalysis.cpp @@ -6,6 +6,7 @@ // //===----------------------------------------------------------------------===// +#include "llvm/CodeGen/LivePhysRegs.h" #include "llvm/CodeGen/ReachingDefAnalysis.h" #include "llvm/CodeGen/TargetRegisterInfo.h" #include "llvm/CodeGen/TargetSubtargetInfo.h" @@ -189,7 +190,55 @@ return LatestDef; } +MachineInstr* ReachingDefAnalysis::getReachingMIDef(MachineInstr *MI, int PhysReg) { + return getInstFromId(MI->getParent(), getReachingDef(MI, PhysReg)); +} + +MachineInstr *ReachingDefAnalysis::getInstFromId(MachineBasicBlock *MBB, + int InstId) { + unsigned MBBNumber = MBB->getNumber(); + assert(MBBNumber < MBBReachingDefs.size() && + "Unexpected basic block number."); + assert(InstId < static_cast(MBB->size()) && + "Unexpected instruction id."); + + if (InstId < 0) + return nullptr; + + for (auto &MI : *MBB) { + if (InstIds.count(&MI) && InstIds[&MI] == InstId) + return &MI; + } + return nullptr; +} + int ReachingDefAnalysis::getClearance(MachineInstr *MI, MCPhysReg PhysReg) { assert(InstIds.count(MI) && "Unexpected machine instuction."); return InstIds[MI] - getReachingDef(MI, PhysReg); } + +bool ReachingDefAnalysis::hasSameReachingDef(MachineInstr *A, MachineInstr *B, + int PhysReg) { + MachineBasicBlock *ParentA = A->getParent(); + MachineBasicBlock *ParentB = B->getParent(); + if (ParentA != ParentB) + return false; + + return getReachingDef(A, PhysReg) == getReachingDef(B, PhysReg); +} + +bool ReachingDefAnalysis::isRegUsedAfter(MachineInstr *MI, int PhysReg) { + MachineBasicBlock *MBB = MI->getParent(); + LivePhysRegs LiveRegs(*TRI); + LiveRegs.addLiveOuts(*MBB); + if (LiveRegs.contains(PhysReg)) + return true; + + for (auto Last = MBB->rbegin(), End = MBB->rend(); Last != End; ++Last) { + LiveRegs.stepBackward(*Last); + if (LiveRegs.contains(PhysReg)) + return InstIds[&*Last] > InstIds[MI]; + } + return false; +} + Index: llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp =================================================================== --- llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp +++ llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp @@ -25,6 +25,8 @@ #include "llvm/CodeGen/MachineFunctionPass.h" #include "llvm/CodeGen/MachineLoopInfo.h" #include "llvm/CodeGen/MachineRegisterInfo.h" +#include "llvm/CodeGen/Passes.h" +#include "llvm/CodeGen/ReachingDefAnalysis.h" using namespace llvm; @@ -35,6 +37,7 @@ class ARMLowOverheadLoops : public MachineFunctionPass { MachineFunction *MF = nullptr; + ReachingDefAnalysis *RDA = nullptr; const ARMBaseInstrInfo *TII = nullptr; MachineRegisterInfo *MRI = nullptr; std::unique_ptr BBUtils = nullptr; @@ -47,6 +50,7 @@ void getAnalysisUsage(AnalysisUsage &AU) const override { AU.setPreservesCFG(); AU.addRequired(); + AU.addRequired(); MachineFunctionPass::getAnalysisUsage(AU); } @@ -54,7 +58,8 @@ MachineFunctionProperties getRequiredProperties() const override { return MachineFunctionProperties().set( - MachineFunctionProperties::Property::NoVRegs); + MachineFunctionProperties::Property::NoVRegs).set( + MachineFunctionProperties::Property::TracksLiveness); } StringRef getPassName() const override { @@ -95,7 +100,7 @@ LLVM_DEBUG(dbgs() << "ARM Loops on " << MF->getName() << " ------------- \n"); auto &MLI = getAnalysis(); - MF->getProperties().set(MachineFunctionProperties::Property::TracksLiveness); + RDA = &getAnalysis(); MRI = &MF->getRegInfo(); TII = static_cast(ST.getInstrInfo()); BBUtils = std::unique_ptr(new ARMBasicBlockUtils(*MF)); @@ -116,97 +121,40 @@ MI.getOpcode() == ARM::t2WhileLoopStart; } -template -static MachineInstr* SearchForDef(MachineInstr *Begin, T End, unsigned Reg) { - for(auto &MI : make_range(T(Begin), End)) { - for (auto &MO : MI.operands()) { - if (!MO.isReg() || !MO.isDef() || MO.getReg() != Reg) - continue; - return &MI; - } - } - return nullptr; -} - -static MachineInstr* SearchForUse(MachineInstr *Begin, - MachineBasicBlock::iterator End, - unsigned Reg) { - for(auto &MI : make_range(MachineBasicBlock::iterator(Begin), End)) { - for (auto &MO : MI.operands()) { - if (!MO.isReg() || !MO.isUse() || MO.getReg() != Reg) - continue; - return &MI; - } - } - return nullptr; -} - // Is it safe to define LR with DLS/WLS? // LR can defined if it is the operand to start, because it's the same value, // or if it's going to be equivalent to the operand to Start. MachineInstr *ARMLowOverheadLoops::IsSafeToDefineLR(MachineInstr *Start) { - auto IsMoveLR = [](MachineInstr *MI, unsigned Reg) { + // We can define LR because LR already contains the same value. + if (Start->getOperand(0).getReg() == ARM::LR) + return Start; + + unsigned CountReg = Start->getOperand(0).getReg(); + auto IsMoveLR = [&CountReg](MachineInstr *MI) { return MI->getOpcode() == ARM::tMOVr && MI->getOperand(0).getReg() == ARM::LR && - MI->getOperand(1).getReg() == Reg && + MI->getOperand(1).getReg() == CountReg && MI->getOperand(2).getImm() == ARMCC::AL; }; MachineBasicBlock *MBB = Start->getParent(); - unsigned CountReg = Start->getOperand(0).getReg(); - // Walk forward and backward in the block to find the closest instructions - // that define LR. Then also filter them out if they're not a mov lr. - MachineInstr *PredLRDef = SearchForDef(Start, MBB->rend(), ARM::LR); - if (PredLRDef && !IsMoveLR(PredLRDef, CountReg)) - PredLRDef = nullptr; - - MachineInstr *SuccLRDef = SearchForDef(Start, MBB->end(), ARM::LR); - if (SuccLRDef && !IsMoveLR(SuccLRDef, CountReg)) - SuccLRDef = nullptr; - - // We've either found one, two or none mov lr instructions... Now figure out - // if they are performing the equilvant mov that the Start instruction will. - // Do this by scanning forward and backward to see if there's a def of the - // register holding the count value. If we find a suitable def, return it as - // the insert point. Later, if InsertPt != Start, then we can remove the - // redundant instruction. - if (SuccLRDef) { - MachineBasicBlock::iterator End(SuccLRDef); - if (!SearchForDef(Start, End, CountReg)) { - return SuccLRDef; - } else - SuccLRDef = nullptr; - } - if (PredLRDef) { - MachineBasicBlock::reverse_iterator End(PredLRDef); - if (!SearchForDef(Start, End, CountReg)) { - return PredLRDef; - } else - PredLRDef = nullptr; - } - // We can define LR because LR already contains the same value. - if (Start->getOperand(0).getReg() == ARM::LR) - return Start; + // Find an insertion point: + // - Is there a (mov lr, Count) before Start? If so, and nothing else writes + // to Count before Start, we can insert at that mov. + // - Is there a (mov lr, Count) after Start? If so, and nothing else writes + // to Count after Start, we can insert at that mov. + if (auto *LRDef = RDA->getReachingMIDef(&MBB->back(), ARM::LR)) { + if (IsMoveLR(LRDef) && RDA->hasSameReachingDef(Start, LRDef, CountReg)) + return LRDef; + } // We've found no suitable LR def and Start doesn't use LR directly. Can we - // just define LR anyway? - const TargetRegisterInfo *TRI = MF->getSubtarget().getRegisterInfo(); - LivePhysRegs LiveRegs(*TRI); - LiveRegs.addLiveOuts(*MBB); - - // Not if we've haven't found a suitable mov and LR is live out. - if (LiveRegs.contains(ARM::LR)) - return nullptr; - - // If LR is not live out, we can insert the instruction if nothing else - // uses LR after it. - if (!SearchForUse(Start, MBB->end(), ARM::LR)) + // just define LR anyway? + if (!RDA->isRegUsedAfter(Start, ARM::LR)) return Start; - LLVM_DEBUG(dbgs() << "ARM Loops: Failed to find suitable insertion point for" - << " LR\n"); return nullptr; } @@ -378,19 +326,15 @@ } bool ARMLowOverheadLoops::RevertLoopDec(MachineInstr *MI, - bool AllowFlags) const { + bool SetFlags) const { LLVM_DEBUG(dbgs() << "ARM Loops: Reverting to sub: " << *MI); MachineBasicBlock *MBB = MI->getParent(); - // If nothing uses or defines CPSR between LoopDec and LoopEnd, use a t2SUBS. - bool SetFlags = false; - if (AllowFlags) { - if (auto *Def = SearchForDef(MI, MBB->end(), ARM::CPSR)) { - if (!SearchForUse(MI, MBB->end(), ARM::CPSR) && - Def->getOpcode() == ARM::t2LoopEnd) - SetFlags = true; - } - } + // If nothing defines CPSR between LoopDec and LoopEnd, use a t2SUBS. + if (SetFlags && + (RDA->isRegUsedAfter(MI, ARM::CPSR) || + !RDA->hasSameReachingDef(MI, &MBB->back(), ARM::CPSR))) + SetFlags = false; MachineInstrBuilder MIB = BuildMI(*MBB, MI, MI->getDebugLoc(), TII->get(ARM::t2SUBri)); Index: llvm/test/CodeGen/ARM/O3-pipeline.ll =================================================================== --- llvm/test/CodeGen/ARM/O3-pipeline.ll +++ llvm/test/CodeGen/ARM/O3-pipeline.ll @@ -154,6 +154,7 @@ ; CHECK-NEXT: ARM constant island placement and branch shortening pass ; CHECK-NEXT: MachineDominator Tree Construction ; CHECK-NEXT: Machine Natural Loop Construction +; CHECK-NEXT: ReachingDefAnalysis ; CHECK-NEXT: ARM Low Overhead Loops pass ; CHECK-NEXT: Contiguously Lay Out Funclets ; CHECK-NEXT: StackMap Liveness Analysis Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-def.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-def.mir @@ -0,0 +1,153 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -run-pass=arm-low-overhead-loops -verify-machineinstrs %s -o - | FileCheck %s +# Check that subs isn't used during the revert because there's a def after LoopDec. + +--- | + define i32 @do_copy(i32 %n, i32* nocapture %p, i32* nocapture readonly %q) { + entry: + %scevgep = getelementptr i32, i32* %q, i32 -1 + %scevgep3 = getelementptr i32, i32* %p, i32 -1 + call void @llvm.set.loop.iterations.i32(i32 %n) + %limit = lshr i32 %n, 1 + br label %while.body + + while.body: ; preds = %while.body, %entry + %lsr.iv4 = phi i32* [ %scevgep5, %while.body ], [ %scevgep3, %entry ] + %lsr.iv = phi i32* [ %scevgep1, %while.body ], [ %scevgep, %entry ] + %tmp = phi i32 [ %n, %entry ], [ %tmp2, %while.body ] + %scevgep7 = getelementptr i32, i32* %lsr.iv, i32 1 + %scevgep4 = getelementptr i32, i32* %lsr.iv4, i32 1 + %tmp1 = load i32, i32* %scevgep7, align 4 + %tmp2 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp, i32 1) + %half = lshr i32 %tmp1, 1 + %cmp = icmp ult i32 %tmp, %limit + %res = select i1 %cmp, i32 %tmp1, i32 %half + store i32 %res, i32* %scevgep4, align 4 + %scevgep1 = getelementptr i32, i32* %lsr.iv, i32 1 + %scevgep5 = getelementptr i32, i32* %lsr.iv4, i32 1 + %tmp3 = icmp ne i32 %tmp2, 0 + br i1 %tmp3, label %while.body, label %while.end + + while.end: ; preds = %while.body + ret i32 0 + } + + ; Function Attrs: noduplicate nounwind + declare void @llvm.set.loop.iterations.i32(i32) #0 + + ; Function Attrs: noduplicate nounwind + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #0 + + ; Function Attrs: nounwind + declare void @llvm.stackprotector(i8*, i8**) #1 + + attributes #0 = { noduplicate nounwind } + attributes #1 = { nounwind } + +... +--- +name: do_copy +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: do_copy + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $r0, $r1, $r2, $r7, $lr + ; CHECK: frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: $lr = tMOVr killed $r0, 14, $noreg + ; CHECK: renamable $r0, dead $cpsr = tSUBi3 killed renamable $r1, 4, 14, $noreg + ; CHECK: renamable $r1, dead $cpsr = tSUBi3 killed renamable $r2, 4, 14, $noreg + ; CHECK: renamable $r2 = t2LSRri renamable $lr, 1, 14, $noreg, $noreg + ; CHECK: bb.1.while.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2 + ; CHECK: renamable $r3, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14, $noreg :: (load 4 from %ir.scevgep7) + ; CHECK: tCMPhir renamable $lr, renamable $r2, 14, $noreg, implicit-def $cpsr + ; CHECK: $lr = t2SUBri killed renamable $lr, 1, 14, $noreg, $noreg + ; CHECK: t2IT 2, 8, implicit-def $itstate + ; CHECK: renamable $r3 = tLSRri $noreg, killed renamable $r3, 1, 2, killed $cpsr, implicit renamable $r3, implicit killed $itstate + ; CHECK: early-clobber renamable $r0 = t2STR_PRE killed renamable $r3, killed renamable $r0, 4, 14, $noreg :: (store 4 into %ir.scevgep4) + ; CHECK: t2CMPri renamable $lr, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: tBcc %bb.1, 4, killed $cpsr + ; CHECK: tB %bb.2, 14, $noreg + ; CHECK: bb.2.while.end: + ; CHECK: $r0, dead $cpsr = tMOVi8 0, 14, $noreg + ; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $r7, $lr + + frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + $lr = tMOVr killed $r0, 14, $noreg + renamable $r0, dead $cpsr = tSUBi3 killed renamable $r1, 4, 14, $noreg + renamable $r1, dead $cpsr = tSUBi3 killed renamable $r2, 4, 14, $noreg + renamable $r2 = t2LSRri renamable $lr, 1, 14, $noreg, $noreg + t2DoLoopStart renamable $lr + + bb.1.while.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $lr, $r0, $r1, $r2 + + renamable $r3, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14, $noreg :: (load 4 from %ir.scevgep7) + tCMPhir renamable $lr, renamable $r2, 14, $noreg, implicit-def $cpsr + renamable $lr = t2LoopDec killed renamable $lr, 1 + t2IT 2, 8, implicit-def $itstate + renamable $r3 = tLSRri $noreg, killed renamable $r3, 1, 2, killed $cpsr, implicit renamable $r3, implicit killed $itstate + early-clobber renamable $r0 = t2STR_PRE killed renamable $r3, killed renamable $r0, 4, 14, $noreg :: (store 4 into %ir.scevgep4) + t2CMPri renamable $lr, 0, 14, $noreg, implicit-def $cpsr + tBcc %bb.1, 4, killed $cpsr + tB %bb.2, 14, $noreg + + bb.2.while.end: + $r0, dead $cpsr = tMOVi8 0, 14, $noreg + tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + +... Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-use.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-use.mir @@ -0,0 +1,152 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -run-pass=arm-low-overhead-loops -verify-machineinstrs %s -o - | FileCheck %s +# Check that subs isn't used during the revert because there's a cpsr use after it. + +--- | + define i32 @do_copy(i32 %n, i32* nocapture %p, i32* nocapture readonly %q) { + entry: + %scevgep = getelementptr i32, i32* %q, i32 -1 + %scevgep3 = getelementptr i32, i32* %p, i32 -1 + call void @llvm.set.loop.iterations.i32(i32 %n) + %limit = lshr i32 %n, 1 + br label %while.body + + while.body: ; preds = %while.body, %entry + %lsr.iv4 = phi i32* [ %scevgep5, %while.body ], [ %scevgep3, %entry ] + %lsr.iv = phi i32* [ %scevgep1, %while.body ], [ %scevgep, %entry ] + %tmp = phi i32 [ %n, %entry ], [ %tmp2, %while.body ] + %scevgep7 = getelementptr i32, i32* %lsr.iv, i32 1 + %scevgep4 = getelementptr i32, i32* %lsr.iv4, i32 1 + %tmp1 = load i32, i32* %scevgep7, align 4 + %tmp2 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp, i32 1) + %half = lshr i32 %tmp1, 1 + %cmp = icmp ult i32 %tmp, %limit + %res = select i1 %cmp, i32 %tmp1, i32 %half + store i32 %res, i32* %scevgep4, align 4 + %scevgep1 = getelementptr i32, i32* %lsr.iv, i32 1 + %scevgep5 = getelementptr i32, i32* %lsr.iv4, i32 1 + %tmp3 = icmp ne i32 %tmp2, 0 + br i1 %tmp3, label %while.body, label %while.end + + while.end: ; preds = %while.body + ret i32 0 + } + + ; Function Attrs: noduplicate nounwind + declare void @llvm.set.loop.iterations.i32(i32) #0 + + ; Function Attrs: noduplicate nounwind + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #0 + + ; Function Attrs: nounwind + declare void @llvm.stackprotector(i8*, i8**) #1 + + attributes #0 = { noduplicate nounwind } + attributes #1 = { nounwind } + +... +--- +name: do_copy +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: do_copy + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $r0, $r1, $r2, $r7, $lr + ; CHECK: frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: renamable $r0, dead $cpsr = tSUBi3 killed renamable $r1, 4, 14, $noreg + ; CHECK: renamable $r1, dead $cpsr = tSUBi3 killed renamable $r2, 4, 14, $noreg + ; CHECK: renamable $r2 = t2LSRri renamable $r0, 1, 14, $noreg, $noreg + ; CHECK: $lr = tMOVr killed $r0, 14, $noreg + ; CHECK: bb.1.while.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2 + ; CHECK: renamable $r3, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14, $noreg :: (load 4 from %ir.scevgep7) + ; CHECK: tCMPhir renamable $lr, renamable $r2, 14, $noreg, implicit-def $cpsr + ; CHECK: $lr = t2SUBri killed renamable $lr, 1, 14, $noreg, $noreg + ; CHECK: t2IT 2, 8, implicit-def $itstate + ; CHECK: renamable $r3 = tLSRri $noreg, killed renamable $r3, 1, 2, killed $cpsr, implicit renamable $r3, implicit killed $itstate + ; CHECK: early-clobber renamable $r0 = t2STR_PRE killed renamable $r3, killed renamable $r0, 4, 14, $noreg :: (store 4 into %ir.scevgep4) + ; CHECK: t2CMPri $lr, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: tBcc %bb.1, 1, $cpsr + ; CHECK: tB %bb.2, 14, $noreg + ; CHECK: bb.2.while.end: + ; CHECK: $r0, dead $cpsr = tMOVi8 0, 14, $noreg + ; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $r7, $lr + + frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + renamable $r0, dead $cpsr = tSUBi3 killed renamable $r1, 4, 14, $noreg + renamable $r1, dead $cpsr = tSUBi3 killed renamable $r2, 4, 14, $noreg + t2DoLoopStart renamable $r0 + renamable $r2 = t2LSRri renamable $r0, 1, 14, $noreg, $noreg + $lr = tMOVr killed $r0, 14, $noreg + + bb.1.while.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $lr, $r0, $r1, $r2 + + renamable $r3, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14, $noreg :: (load 4 from %ir.scevgep7) + tCMPhir renamable $lr, renamable $r2, 14, $noreg, implicit-def $cpsr + renamable $lr = t2LoopDec killed renamable $lr, 1 + t2IT 2, 8, implicit-def $itstate + renamable $r3 = tLSRri $noreg, killed renamable $r3, 1, 2, killed $cpsr, implicit renamable $r3, implicit killed $itstate + early-clobber renamable $r0 = t2STR_PRE killed renamable $r3, killed renamable $r0, 4, 14, $noreg :: (store 4 into %ir.scevgep4) + t2LoopEnd killed renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.while.end: + $r0, dead $cpsr = tMOVi8 0, 14, $noreg + tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + +... Index: llvm/test/CodeGen/Thumb2/ifcvt-neon-deprecated.mir =================================================================== --- llvm/test/CodeGen/Thumb2/ifcvt-neon-deprecated.mir +++ llvm/test/CodeGen/Thumb2/ifcvt-neon-deprecated.mir @@ -1,54 +1,89 @@ -# RUN: llc -mtriple=thumbv7 -start-before=if-converter -o - %s | FileCheck %s +# RUN: llc -mtriple=thumbv7 -start-before=if-converter %s -o - | FileCheck %s + +--- | + ; ModuleID = 'vdup-test.ll' + source_filename = "vdup-test.ll" + target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64" + target triple = "thumbv7" + + define arm_aapcs_vfpcc <2 x i32> @NeonVdupMul(i32 %scalar, i32 %N, <2 x i32> %vector) { + entry: + %cmp = icmp ne i32 %N, 0 + %broadcast = insertelement <2 x i32> undef, i32 %scalar, i32 0 + %dup = shufflevector <2 x i32> %broadcast, <2 x i32> undef, <2 x i32> zeroinitializer + %mul = mul <2 x i32> %dup, %vector + br i1 %cmp, label %select.end, label %select.false + + select.false: ; preds = %entry + br label %select.end + + select.end: ; preds = %entry, %select.false + %res = phi <2 x i32> [ %mul, %entry ], [ %vector, %select.false ] + ret <2 x i32> %res + } + +... --- name: NeonVdupMul +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$d0', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 0 + offsetAdjustment: 0 + maxAlignment: 1 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: [] +callSites: [] +constants: [] +machineFunctionInfo: {} body: | - bb.0: - successors: %bb.2, %bb.1 + bb.0.entry: + successors: %bb.1(0x50000000), %bb.2(0x30000000) liveins: $d0, $r0, $r1 - - t2CMPri killed $r1, 0, 14, $noreg, implicit-def $cpsr + + t2CMPri killed renamable $r1, 0, 14, $noreg, implicit-def $cpsr t2Bcc %bb.2, 0, killed $cpsr - + bb.1: + successors: %bb.2(0x80000000) liveins: $d0, $r0 - - $d16 = VDUP32d killed $r0, 14, $noreg + + renamable $d16 = VDUP32d killed renamable $r0, 14, $noreg ; Verify that the neon instructions haven't been conditionalized: ; CHECK-LABEL: NeonVdupMul ; CHECK: vdup.32 ; CHECK: vmul.i32 - $d0 = VMULv2i32 killed $d16, killed $d0, 14, $noreg - - bb.2: + renamable $d0 = VMULv2i32 killed renamable $d16, killed renamable $d0, 14, $noreg + + bb.2.select.end: liveins: $d0 - - tBX_RET 14, $noreg, implicit $d0 - -... ---- -name: NeonVmovVfpLdr -body: | - bb.0.entry: - successors: %bb.1, %bb.2 - liveins: $r0, $r1 - - t2CMPri killed $r1, 0, 14, $noreg, implicit-def $cpsr - t2Bcc %bb.2, 1, killed $cpsr - - bb.1: - $d0 = VMOVv2i32 0, 14, $noreg - tBX_RET 14, $noreg, implicit $d0 - - bb.2: - liveins: $r0 - - $d0 = VLDRD killed $r0, 0, 14, $noreg - ; Verify that the neon instruction VMOVv2i32 hasn't been conditionalized, - ; but the VLDR instruction that is available both in the VFP and Advanced - ; SIMD extensions has. - ; CHECK-LABEL: NeonVmovVfpLdr - ; CHECK-DAG: vmov.i32 d0, #0x0 - ; CHECK-DAG: vldr{{ne|eq}} d0, [r0] + tBX_RET 14, $noreg, implicit $d0 ...