From 21afc63ea7b8227ccb1b735255be55bf422136d6 Mon Sep 17 00:00:00 2001 From: Akira Hatanaka Date: Tue, 21 Jun 2011 00:40:49 +0000 Subject: [PATCH] Re-apply 132758 and 132768 which were speculatively reverted in 132777. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133494 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Target/Mips/MipsAsmPrinter.cpp | 16 ++++++ lib/Target/Mips/MipsISelDAGToDAG.cpp | 12 ++++ lib/Target/Mips/MipsISelLowering.cpp | 51 +++++++++-------- lib/Target/Mips/MipsISelLowering.h | 4 +- lib/Target/Mips/MipsInstrInfo.td | 16 ++++++ lib/Target/Mips/MipsMachineFunction.h | 18 +++++- lib/Target/Mips/MipsRegisterInfo.cpp | 10 ++-- test/CodeGen/Mips/alloca.ll | 81 +++++++++++++++++++++++++-- test/CodeGen/Mips/inlineasmmemop.ll | 23 ++++++++ 9 files changed, 191 insertions(+), 40 deletions(-) create mode 100644 test/CodeGen/Mips/inlineasmmemop.ll diff --git a/lib/Target/Mips/MipsAsmPrinter.cpp b/lib/Target/Mips/MipsAsmPrinter.cpp index 8caa7cd2f75..6f69ba388fd 100644 --- a/lib/Target/Mips/MipsAsmPrinter.cpp +++ b/lib/Target/Mips/MipsAsmPrinter.cpp @@ -56,6 +56,9 @@ namespace { bool PrintAsmOperand(const MachineInstr *MI, unsigned OpNo, unsigned AsmVariant, const char *ExtraCode, raw_ostream &O); + bool PrintAsmMemoryOperand(const MachineInstr *MI, unsigned OpNum, + unsigned AsmVariant, const char *ExtraCode, + raw_ostream &O); void printOperand(const MachineInstr *MI, int opNum, raw_ostream &O); void printUnsignedImm(const MachineInstr *MI, int opNum, raw_ostream &O); void printMemOperand(const MachineInstr *MI, int opNum, raw_ostream &O, @@ -304,6 +307,19 @@ bool MipsAsmPrinter::PrintAsmOperand(const MachineInstr *MI, unsigned OpNo, return false; } +bool MipsAsmPrinter::PrintAsmMemoryOperand(const MachineInstr *MI, + unsigned OpNum, unsigned AsmVariant, + const char *ExtraCode, + raw_ostream &O) { + if (ExtraCode && ExtraCode[0]) + return true; // Unknown modifier. + + const MachineOperand &MO = MI->getOperand(OpNum); + assert(MO.isReg() && "unexpected inline asm memory operand"); + O << "0($" << MipsAsmPrinter::getRegisterName(MO.getReg()) << ")"; + return false; +} + void MipsAsmPrinter::printOperand(const MachineInstr *MI, int opNum, raw_ostream &O) { const MachineOperand &MO = MI->getOperand(opNum); diff --git a/lib/Target/Mips/MipsISelDAGToDAG.cpp b/lib/Target/Mips/MipsISelDAGToDAG.cpp index d8a84ce5299..c35c8522443 100644 --- a/lib/Target/Mips/MipsISelDAGToDAG.cpp +++ b/lib/Target/Mips/MipsISelDAGToDAG.cpp @@ -94,6 +94,10 @@ private: inline SDValue getI32Imm(unsigned Imm) { return CurDAG->getTargetConstant(Imm, MVT::i32); } + + virtual bool SelectInlineAsmMemoryOperand(const SDValue &Op, + char ConstraintCode, + std::vector &OutOps); }; } @@ -462,6 +466,14 @@ SDNode* MipsDAGToDAGISel::Select(SDNode *Node) { return ResNode; } +bool MipsDAGToDAGISel:: +SelectInlineAsmMemoryOperand(const SDValue &Op, char ConstraintCode, + std::vector &OutOps) { + assert(ConstraintCode == 'm' && "unexpected asm memory constraint"); + OutOps.push_back(Op); + return false; +} + /// createMipsISelDag - This pass converts a legalized DAG into a /// MIPS-specific DAG, ready for instruction scheduling. FunctionPass *llvm::createMipsISelDag(MipsTargetMachine &TM) { diff --git a/lib/Target/Mips/MipsISelLowering.cpp b/lib/Target/Mips/MipsISelLowering.cpp index c42054e20b1..2155160d595 100644 --- a/lib/Target/Mips/MipsISelLowering.cpp +++ b/lib/Target/Mips/MipsISelLowering.cpp @@ -59,6 +59,7 @@ const char *MipsTargetLowering::getTargetNodeName(unsigned Opcode) const { case MipsISD::BuildPairF64: return "MipsISD::BuildPairF64"; case MipsISD::ExtractElementF64: return "MipsISD::ExtractElementF64"; case MipsISD::WrapperPIC: return "MipsISD::WrapperPIC"; + case MipsISD::DynAlloc: return "MipsISD::DynAlloc"; default: return NULL; } } @@ -1189,9 +1190,10 @@ MipsTargetLowering::EmitAtomicCmpSwapPartword(MachineInstr *MI, SDValue MipsTargetLowering:: LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const { - unsigned StackAlignment = - getTargetMachine().getFrameLowering()->getStackAlignment(); - assert(StackAlignment >= + MachineFunction &MF = DAG.getMachineFunction(); + MipsFunctionInfo *MipsFI = MF.getInfo(); + + assert(getTargetMachine().getFrameLowering()->getStackAlignment() >= cast(Op.getOperand(2).getNode())->getZExtValue() && "Cannot lower if the alignment of the allocated space is larger than \ that of the stack."); @@ -1211,24 +1213,14 @@ LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const // must be placed in the stack pointer register. Chain = DAG.getCopyToReg(StackPointer.getValue(1), dl, Mips::SP, Sub, SDValue()); - // Retrieve updated $sp. There is a glue input to prevent instructions that - // clobber $sp from being inserted between copytoreg and copyfromreg. - SDValue NewSP = DAG.getCopyFromReg(Chain, dl, Mips::SP, MVT::i32, - Chain.getValue(1)); - - // The stack space reserved by alloca is located right above the argument - // area. It is aligned on a boundary that is a multiple of StackAlignment. - MachineFunction &MF = DAG.getMachineFunction(); - MipsFunctionInfo *MipsFI = MF.getInfo(); - unsigned SPOffset = (MipsFI->getMaxCallFrameSize() + StackAlignment - 1) / - StackAlignment * StackAlignment; - SDValue AllocPtr = DAG.getNode(ISD::ADD, dl, MVT::i32, NewSP, - DAG.getConstant(SPOffset, MVT::i32)); // This node always has two return values: a new stack pointer // value and a chain - SDValue Ops[2] = { AllocPtr, NewSP.getValue(1) }; - return DAG.getMergeValues(Ops, 2, dl); + SDVTList VTLs = DAG.getVTList(MVT::i32, MVT::Other); + SDValue Ptr = DAG.getFrameIndex(MipsFI->getDynAllocFI(), getPointerTy()); + SDValue Ops[] = { Chain, Ptr, Chain.getValue(1) }; + + return DAG.getNode(MipsISD::DynAlloc, dl, VTLs, Ops, 3); } SDValue MipsTargetLowering:: @@ -1770,6 +1762,10 @@ MipsTargetLowering::LowerCall(SDValue Chain, SDValue Callee, if (IsPIC && !MipsFI->getGPFI()) MipsFI->setGPFI(MFI->CreateFixedObject(4, 0, true)); + // Get the frame index of the stack frame object that points to the location + // of dynamically allocated area on the stack. + int DynAllocFI = MipsFI->getDynAllocFI(); + // Update size of the maximum argument space. // For O32, a minimum of four words (16 bytes) of argument space is // allocated. @@ -1781,14 +1777,17 @@ MipsTargetLowering::LowerCall(SDValue Chain, SDValue Callee, if (MaxCallFrameSize < NextStackOffset) { MipsFI->setMaxCallFrameSize(NextStackOffset); - if (IsPIC) { - // $gp restore slot must be aligned. - unsigned StackAlignment = TFL->getStackAlignment(); - NextStackOffset = (NextStackOffset + StackAlignment - 1) / - StackAlignment * StackAlignment; - int GPFI = MipsFI->getGPFI(); - MFI->setObjectOffset(GPFI, NextStackOffset); - } + // Set the offsets relative to $sp of the $gp restore slot and dynamically + // allocated stack space. These offsets must be aligned to a boundary + // determined by the stack alignment of the ABI. + unsigned StackAlignment = TFL->getStackAlignment(); + NextStackOffset = (NextStackOffset + StackAlignment - 1) / + StackAlignment * StackAlignment; + + if (IsPIC) + MFI->setObjectOffset(MipsFI->getGPFI(), NextStackOffset); + + MFI->setObjectOffset(DynAllocFI, NextStackOffset); } // With EABI is it possible to have 16 args on registers. diff --git a/lib/Target/Mips/MipsISelLowering.h b/lib/Target/Mips/MipsISelLowering.h index fbcedfddf99..b7b85fd8f99 100644 --- a/lib/Target/Mips/MipsISelLowering.h +++ b/lib/Target/Mips/MipsISelLowering.h @@ -79,7 +79,9 @@ namespace llvm { BuildPairF64, ExtractElementF64, - WrapperPIC + WrapperPIC, + + DynAlloc }; } diff --git a/lib/Target/Mips/MipsInstrInfo.td b/lib/Target/Mips/MipsInstrInfo.td index 329a002667a..06513220b6f 100644 --- a/lib/Target/Mips/MipsInstrInfo.td +++ b/lib/Target/Mips/MipsInstrInfo.td @@ -39,6 +39,9 @@ def SDT_MipsDivRem : SDTypeProfile<0, 2, def SDT_MipsThreadPointer : SDTypeProfile<1, 0, [SDTCisPtrTy<0>]>; +def SDT_MipsDynAlloc : SDTypeProfile<1, 1, [SDTCisVT<0, i32>, + SDTCisVT<1, iPTR>]>; + // Call def MipsJmpLink : SDNode<"MipsISD::JmpLink",SDT_MipsJmpLink, [SDNPHasChain, SDNPOutGlue, SDNPOptInGlue, @@ -99,6 +102,10 @@ def MipsDivRemU : SDNode<"MipsISD::DivRemU", SDT_MipsDivRem, def MipsWrapperPIC : SDNode<"MipsISD::WrapperPIC", SDTIntUnaryOp>; +// Pointer to dynamically allocated stack area. +def MipsDynAlloc : SDNode<"MipsISD::DynAlloc", SDT_MipsDynAlloc, + [SDNPHasChain, SDNPInGlue]>; + //===----------------------------------------------------------------------===// // Mips Instruction Predicate Definitions. //===----------------------------------------------------------------------===// @@ -675,6 +682,12 @@ let addr=0 in // can be matched. It's similar to Sparc LEA_ADDRi def LEA_ADDiu : EffectiveAddress<"addiu\t$dst, ${addr:stackloc}">; +// DynAlloc node points to dynamically allocated stack space. +// $sp is added to the list of implicitly used registers to prevent dead code +// elimination from removing instructions that modify $sp. +let Uses = [SP] in +def DynAlloc : EffectiveAddress<"addiu\t$dst, ${addr:stackloc}">; + // MADD*/MSUB* def MADD : MArithR<0, "madd", MipsMAdd, 1>; def MADDU : MArithR<1, "maddu", MipsMAddu, 1>; @@ -852,6 +865,9 @@ def : Pat<(setge CPURegs:$lhs, immSExt16:$rhs), def : Pat<(setuge CPURegs:$lhs, immSExt16:$rhs), (XORi (SLTiu CPURegs:$lhs, immSExt16:$rhs), 1)>; +// select MipsDynAlloc +def : Pat<(MipsDynAlloc addr:$f), (DynAlloc addr:$f)>; + //===----------------------------------------------------------------------===// // Floating Point Support //===----------------------------------------------------------------------===// diff --git a/lib/Target/Mips/MipsMachineFunction.h b/lib/Target/Mips/MipsMachineFunction.h index df40e6c748a..dbb7a674422 100644 --- a/lib/Target/Mips/MipsMachineFunction.h +++ b/lib/Target/Mips/MipsMachineFunction.h @@ -27,6 +27,7 @@ namespace llvm { class MipsFunctionInfo : public MachineFunctionInfo { private: + MachineFunction& MF; /// SRetReturnReg - Some subtargets require that sret lowering includes /// returning the value of the returned struct in a register. This field /// holds the virtual register into which the sret argument is passed. @@ -47,6 +48,7 @@ private: // LowerCall except for the frame object for restoring $gp. std::pair InArgFIRange, OutArgFIRange; int GPFI; // Index of the frame object for restoring $gp + mutable int DynAllocFI; // Frame index of dynamically allocated stack area. unsigned MaxCallFrameSize; /// AtomicFrameIndex - To implement atomic.swap and atomic.cmp.swap @@ -55,10 +57,10 @@ private: int AtomicFrameIndex; public: MipsFunctionInfo(MachineFunction& MF) - : SRetReturnReg(0), GlobalBaseReg(0), + : MF(MF), SRetReturnReg(0), GlobalBaseReg(0), VarArgsFrameIndex(0), InArgFIRange(std::make_pair(-1, 0)), - OutArgFIRange(std::make_pair(-1, 0)), GPFI(0), MaxCallFrameSize(0), - AtomicFrameIndex(-1) + OutArgFIRange(std::make_pair(-1, 0)), GPFI(0), DynAllocFI(0), + MaxCallFrameSize(0), AtomicFrameIndex(-1) {} bool isInArgFI(int FI) const { @@ -81,6 +83,16 @@ public: bool needGPSaveRestore() const { return getGPFI(); } bool isGPFI(int FI) const { return GPFI && GPFI == FI; } + // The first call to this function creates a frame object for dynamically + // allocated stack area. + int getDynAllocFI() const { + if (!DynAllocFI) + DynAllocFI = MF.getFrameInfo()->CreateFixedObject(4, 0, true); + + return DynAllocFI; + } + bool isDynAllocFI(int FI) const { return DynAllocFI && DynAllocFI == FI; } + unsigned getSRetReturnReg() const { return SRetReturnReg; } void setSRetReturnReg(unsigned Reg) { SRetReturnReg = Reg; } diff --git a/lib/Target/Mips/MipsRegisterInfo.cpp b/lib/Target/Mips/MipsRegisterInfo.cpp index b0984afbebe..fa64f637c8e 100644 --- a/lib/Target/Mips/MipsRegisterInfo.cpp +++ b/lib/Target/Mips/MipsRegisterInfo.cpp @@ -179,12 +179,14 @@ eliminateFrameIndex(MachineBasicBlock::iterator II, int SPAdj, int Offset; // Calculate final offset. - // - There is no need to change the offset if the frame object is an outgoing - // argument or a $gp restore location, + // - There is no need to change the offset if the frame object is one of the + // following: an outgoing argument, pointer to a dynamically allocated + // stack space or a $gp restore location, // - If the frame object is any of the following, its offset must be adjusted // by adding the size of the stack: // incoming argument, callee-saved register location or local variable. - if (MipsFI->isOutArgFI(FrameIndex) || MipsFI->isGPFI(FrameIndex)) + if (MipsFI->isOutArgFI(FrameIndex) || MipsFI->isGPFI(FrameIndex) || + MipsFI->isDynAllocFI(FrameIndex)) Offset = spOffset; else Offset = spOffset + stackSize; @@ -213,7 +215,7 @@ eliminateFrameIndex(MachineBasicBlock::iterator II, int SPAdj, // 3. Locations for callee-saved registers. // Everything else is referenced relative to whatever register // getFrameRegister() returns. - if (MipsFI->isOutArgFI(FrameIndex) || + if (MipsFI->isOutArgFI(FrameIndex) || MipsFI->isDynAllocFI(FrameIndex) || (FrameIndex >= MinCSFI && FrameIndex <= MaxCSFI)) FrameReg = Mips::SP; else diff --git a/test/CodeGen/Mips/alloca.ll b/test/CodeGen/Mips/alloca.ll index 50eeecf991f..ff503ecce00 100644 --- a/test/CodeGen/Mips/alloca.ll +++ b/test/CodeGen/Mips/alloca.ll @@ -4,15 +4,15 @@ define i32 @twoalloca(i32 %size) nounwind { entry: ; CHECK: subu $[[T0:[0-9]+]], $sp, $[[SZ:[0-9]+]] ; CHECK: addu $sp, $zero, $[[T0]] -; CHECK: addu $[[SP1:[0-9]+]], $zero, $sp -; CHECK: subu $[[T1:[0-9]+]], $sp, $[[SZ]] -; CHECK: addu $sp, $zero, $[[T1]] -; CHECK: addu $[[SP2:[0-9]+]], $zero, $sp +; CHECK: addiu $[[T1:[0-9]+]], $sp, [[OFF:[0-9]+]] +; CHECK: subu $[[T2:[0-9]+]], $sp, $[[SZ]] +; CHECK: addu $sp, $zero, $[[T2]] +; CHECK: addiu $[[T3:[0-9]+]], $sp, [[OFF]] ; CHECK: lw $25, %call16(foo)($gp) -; CHECK: addiu $4, $[[SP1]], 24 +; CHECK: addu $4, $zero, $[[T1]] ; CHECK: jalr $25 ; CHECK: lw $25, %call16(foo)($gp) -; CHECK: addiu $4, $[[SP2]], 24 +; CHECK: addu $4, $zero, $[[T3]] ; CHECK: jalr $25 %tmp1 = alloca i8, i32 %size, align 4 %add.ptr = getelementptr inbounds i8* %tmp1, i32 5 @@ -29,3 +29,72 @@ declare void @foo2(double, double, i32) declare i32 @foo(i8*) +@.str = private unnamed_addr constant [22 x i8] c"%d %d %d %d %d %d %d\0A\00", align 1 + +define i32 @alloca2(i32 %size) nounwind { +entry: +; dynamic allocated stack area and $gp restore slot have the same offsets +; relative to $sp. +; +; CHECK: alloca2 +; CHECK: .cprestore [[OFF:[0-9]+]] +; CHECK: subu $[[T0:[0-9]+]], $sp, $[[SZ:[0-9]+]] +; CHECK: addu $sp, $zero, $[[T0]] +; CHECK: addiu $[[T1:[0-9]+]], $sp, [[OFF]] + + %tmp1 = alloca i8, i32 %size, align 4 + %0 = bitcast i8* %tmp1 to i32* + %cmp = icmp sgt i32 %size, 10 + br i1 %cmp, label %if.then, label %if.else + +if.then: ; preds = %entry +; CHECK: addiu $4, $[[T1]], 40 + + %add.ptr = getelementptr inbounds i8* %tmp1, i32 40 + %1 = bitcast i8* %add.ptr to i32* + call void @foo3(i32* %1) nounwind + %arrayidx15.pre = getelementptr inbounds i8* %tmp1, i32 12 + %.pre = bitcast i8* %arrayidx15.pre to i32* + br label %if.end + +if.else: ; preds = %entry +; CHECK: addiu $4, $[[T1]], 12 + + %add.ptr5 = getelementptr inbounds i8* %tmp1, i32 12 + %2 = bitcast i8* %add.ptr5 to i32* + call void @foo3(i32* %2) nounwind + br label %if.end + +if.end: ; preds = %if.else, %if.then +; CHECK: lw $5, 0($[[T1]]) +; CHECK: lw $25, %call16(printf) + + %.pre-phi = phi i32* [ %2, %if.else ], [ %.pre, %if.then ] + %tmp7 = load i32* %0, align 4, !tbaa !0 + %arrayidx9 = getelementptr inbounds i8* %tmp1, i32 4 + %3 = bitcast i8* %arrayidx9 to i32* + %tmp10 = load i32* %3, align 4, !tbaa !0 + %arrayidx12 = getelementptr inbounds i8* %tmp1, i32 8 + %4 = bitcast i8* %arrayidx12 to i32* + %tmp13 = load i32* %4, align 4, !tbaa !0 + %tmp16 = load i32* %.pre-phi, align 4, !tbaa !0 + %arrayidx18 = getelementptr inbounds i8* %tmp1, i32 16 + %5 = bitcast i8* %arrayidx18 to i32* + %tmp19 = load i32* %5, align 4, !tbaa !0 + %arrayidx21 = getelementptr inbounds i8* %tmp1, i32 20 + %6 = bitcast i8* %arrayidx21 to i32* + %tmp22 = load i32* %6, align 4, !tbaa !0 + %arrayidx24 = getelementptr inbounds i8* %tmp1, i32 24 + %7 = bitcast i8* %arrayidx24 to i32* + %tmp25 = load i32* %7, align 4, !tbaa !0 + %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([22 x i8]* @.str, i32 0, i32 0), i32 %tmp7, i32 %tmp10, i32 %tmp13, i32 %tmp16, i32 %tmp19, i32 %tmp22, i32 %tmp25) nounwind + ret i32 0 +} + +declare void @foo3(i32*) + +declare i32 @printf(i8* nocapture, ...) nounwind + +!0 = metadata !{metadata !"int", metadata !1} +!1 = metadata !{metadata !"omnipotent char", metadata !2} +!2 = metadata !{metadata !"Simple C/C++ TBAA", null} diff --git a/test/CodeGen/Mips/inlineasmmemop.ll b/test/CodeGen/Mips/inlineasmmemop.ll new file mode 100644 index 00000000000..c5658923dcc --- /dev/null +++ b/test/CodeGen/Mips/inlineasmmemop.ll @@ -0,0 +1,23 @@ +; RUN: llc -march=mipsel -mcpu=4ke < %s | FileCheck %s + +@g1 = external global i32 + +define i32 @f1(i32 %x) nounwind { +entry: +; CHECK: addiu $[[T0:[0-9]+]], $sp +; CHECK: #APP +; CHECK: sw $4, 0($[[T0]]) +; CHECK: #NO_APP +; CHECK: lw $[[T1:[0-9]+]], %got(g1)($gp) +; CHECK: #APP +; CHECK: lw $[[T3:[0-9]+]], 0($[[T0]]) +; CHECK: #NO_APP +; CHECK: sw $[[T3]], 0($[[T1]]) + + %l1 = alloca i32, align 4 + call void asm "sw $1, $0", "=*m,r"(i32* %l1, i32 %x) nounwind + %0 = call i32 asm "lw $0, $1", "=r,*m"(i32* %l1) nounwind + store i32 %0, i32* @g1, align 4 + ret i32 %0 +} +