https://github.com/isanbard updated https://github.com/llvm/llvm-project/pull/235632
>From 1bc587dfe5def971b7b52f3818a4b76b2560e55f Mon Sep 17 00:00:00 2001 From: Bill Wendling <[email protected]> Date: Mon, 26 Oct 2026 00:18:20 -0700 Subject: [PATCH] [CodeGen] Fold an inline asm subregister operand at its slot offset A stack slot holds the whole register, and a folded operand referred to the start of the slot, so a subregister was folded only if it was at offset 0, and other subregisters got a reload into a register the asm may not have. Coalescing can turn an i686 "rm" byte operand into sub_8bit_hi of a GR32, which is at byte 1. Fold a subregister at its offset in the slot, from getStackSlotRange(), so getFrameIndexOperands() now takes an offset. Also add a third asm to qm_tied_high_byte, which clobbers every GPR, so that it reaches the folder. Without it, the value is reloaded into a register that's free at the second asm. Assisted-by: Claude Opus 5.5 --- llvm/include/llvm/CodeGen/MachineInstr.h | 4 +- llvm/include/llvm/CodeGen/TargetInstrInfo.h | 5 +- llvm/lib/CodeGen/MachineInstr.cpp | 39 ++++++----- llvm/lib/CodeGen/TargetInstrInfo.cpp | 65 +++++++++++-------- llvm/lib/Target/X86/X86InstrInfo.cpp | 3 +- llvm/lib/Target/X86/X86InstrInfo.h | 4 +- .../CodeGen/X86/greedy-inline-asm-fold.mir | 36 +++++----- 7 files changed, 84 insertions(+), 72 deletions(-) diff --git a/llvm/include/llvm/CodeGen/MachineInstr.h b/llvm/include/llvm/CodeGen/MachineInstr.h index dd689cf280f371..4185e8739d659b 100644 --- a/llvm/include/llvm/CodeGen/MachineInstr.h +++ b/llvm/include/llvm/CodeGen/MachineInstr.h @@ -1440,8 +1440,8 @@ class MachineInstr } /// Returns true if the register operand can be folded with a load or store /// into a frame index. Does so by checking the InlineAsm::Flag immediate - /// operand at OpId - 1, and that the register (or subregister) starts at the - /// beginning of the stack slot. + /// operand at OpId - 1, and that the register (or subregister) has a place + /// in the register's stack slot. LLVM_ABI bool mayFoldInlineAsmRegOp(unsigned OpId) const; /// Returns true if \p Reg can be folded to its stack slot in this inline diff --git a/llvm/include/llvm/CodeGen/TargetInstrInfo.h b/llvm/include/llvm/CodeGen/TargetInstrInfo.h index 97baf780275ee3..9bd88d716f4175 100644 --- a/llvm/include/llvm/CodeGen/TargetInstrInfo.h +++ b/llvm/include/llvm/CodeGen/TargetInstrInfo.h @@ -2418,13 +2418,14 @@ class LLVM_ABI TargetInstrInfo : public MCInstrInfo { // Get the call frame size just before MI. unsigned getCallFrameSizeAt(MachineInstr &MI) const; - /// Fills in the necessary MachineOperands to refer to a frame index. + /// Fills in the necessary MachineOperands to refer to a frame index, plus + /// \p Offset bytes. /// The best way to understand this is to print `asm(""::"m"(x));` after /// finalize-isel. Example: /// INLINEASM ... 262190 /* mem:m */, %stack.0.x.addr, 1, $noreg, 0, $noreg /// we would add placeholders for: ^ ^ ^ ^ virtual void getFrameIndexOperands(SmallVectorImpl<MachineOperand> &Ops, - int FI) const { + int FI, int64_t Offset) const { llvm_unreachable("unknown number of operands necessary"); } diff --git a/llvm/lib/CodeGen/MachineInstr.cpp b/llvm/lib/CodeGen/MachineInstr.cpp index 23f5170ea66d20..ed7d88c9935b25 100644 --- a/llvm/lib/CodeGen/MachineInstr.cpp +++ b/llvm/lib/CodeGen/MachineInstr.cpp @@ -2784,37 +2784,36 @@ bool MachineInstr::mayFoldInlineAsmRegOp(unsigned OpId) const { assert(OpId && "expected non-zero operand id"); assert(isInlineAsm() && "should only be used on inline asm"); - if (!getOperand(OpId).isReg()) - return false; - - if (isRegTiedToDefOperand(OpId)) + const MachineOperand &MO = getOperand(OpId); + const MachineOperand &MD = getOperand(OpId - 1); + if (!MO.isReg() || !MD.isImm()) return false; - const MachineOperand &MD = getOperand(OpId - 1); - if (!MD.isImm()) + InlineAsm::Flag F(MD.getImm()); + if (!F.isRegUseKind() && !F.isRegDefKind() && !F.isRegDefEarlyClobberKind()) return false; // A memory operand replaces exactly one register, so one register of a // multi-register operand (e.g. an i128 in two GR64s) can't be folded. - InlineAsm::Flag F(MD.getImm()); - if (F.getNumOperandRegisters() != 1) + if (!F.getRegMayBeFolded() || F.getNumOperandRegisters() != 1) return false; - // A memory operand refers to the start of the stack slot, which holds the - // whole register. A subregister is found there only if it's at bit offset 0 - // on a little-endian target; e.g. x86's sub_8bit_hi is at byte 1. (The use - // tied to a def, which is folded along with it, has the def's subregister.) - if (unsigned SubReg = getOperand(OpId).getSubReg()) { + // A use tied to a def is folded along with the def, not on its own. + if (isRegTiedToDefOperand(OpId)) + return false; + + // The stack slot holds the whole register, so a subregister is folded at + // its offset in the slot, if it has one. + if (unsigned SubReg = MO.getSubReg()) { const MachineFunction &MF = *getMF(); - if (!MF.getDataLayout().isLittleEndian() || - MF.getSubtarget().getRegisterInfo()->getSubRegIdxOffset(SubReg) != 0) - return false; + unsigned Size, Offset; + return MO.getReg().isVirtual() && + MF.getSubtarget().getInstrInfo()->getStackSlotRange( + MF.getRegInfo().getRegClass(MO.getReg()), SubReg, Size, Offset, + MF); } - if (F.isRegUseKind() || F.isRegDefKind() || F.isRegDefEarlyClobberKind()) - return F.getRegMayBeFolded(); - - return false; + return true; } bool MachineInstr::mayFoldInlineAsmReg(Register Reg) const { diff --git a/llvm/lib/CodeGen/TargetInstrInfo.cpp b/llvm/lib/CodeGen/TargetInstrInfo.cpp index 47bfa9cdc94610..5de5fac41b0005 100644 --- a/llvm/lib/CodeGen/TargetInstrInfo.cpp +++ b/llvm/lib/CodeGen/TargetInstrInfo.cpp @@ -650,16 +650,12 @@ static MachineInstr *foldPatchpoint(MachineFunction &MF, MachineInstr &MI, return NewMI; } -/// Rewrite each register operand of the inline asm \p MI that's set in \p Fold -/// (indexed by operand number) to refer to stack slot \p FI. -static void foldInlineAsmMemOperands(MachineInstr &MI, ArrayRef<bool> Fold, +/// Rewrite each register operand of the inline asm \p MI that has an entry in +/// \p Offsets (indexed by operand number) to refer to stack slot \p FI at +/// that byte offset. +static void foldInlineAsmMemOperands(MachineInstr &MI, + ArrayRef<std::optional<unsigned>> Offsets, int FI, const TargetInstrInfo &TII) { - SmallVector<MachineOperand, 5> MemOps; - TII.getFrameIndexOperands(MemOps, FI); - assert(!MemOps.empty() && "getFrameIndexOperands didn't create any operands"); - InlineAsm::Flag MemFlag(InlineAsm::Kind::Mem, MemOps.size()); - MemFlag.setMemConstraint(InlineAsm::ConstraintCode::m); - // A folded operand becomes the operands of a memory reference, moving every // later one, and MachineInstr can't move a tied operand. So untie everything // (untying a use also unties its def), re-add the operands from the first @@ -673,12 +669,12 @@ static void foldInlineAsmMemOperands(MachineInstr &MI, ArrayRef<bool> Fold, continue; MI.untieRegOperand(I); - if (!Fold[I]) + if (!Offsets[I]) Ties.emplace_back(DefIdx, I); } unsigned First = InlineAsm::MIOp_FirstOperand; - while (!Fold[First]) + while (!Offsets[First]) ++First; SmallVector<MachineOperand, 16> Tail(MI.operands_begin() + First, @@ -689,7 +685,8 @@ static void foldInlineAsmMemOperands(MachineInstr &MI, ArrayRef<bool> Fold, SmallVector<unsigned, 16> NewIdx; for (auto [I, MO] : enumerate(Tail)) { NewIdx.push_back(MI.getNumOperands()); - if (!Fold[First + I]) { + std::optional<unsigned> Offset = Offsets[First + I]; + if (!Offset) { MI.addOperand(MO); continue; } @@ -699,6 +696,12 @@ static void foldInlineAsmMemOperands(MachineInstr &MI, ArrayRef<bool> Fold, MachineOperand &FlagMO = MI.getOperand(MI.getNumOperands() - 1); assert(InlineAsm::Flag(FlagMO.getImm()).getNumOperandRegisters() == 1 && "cannot fold one register of a multi-register operand"); + SmallVector<MachineOperand, 5> MemOps; + TII.getFrameIndexOperands(MemOps, FI, *Offset); + assert(!MemOps.empty() && + "getFrameIndexOperands didn't create any operands"); + InlineAsm::Flag MemFlag(InlineAsm::Kind::Mem, MemOps.size()); + MemFlag.setMemConstraint(InlineAsm::ConstraintCode::m); FlagMO.setImm(MemFlag); for (const MachineOperand &MemOp : MemOps) MI.addOperand(MemOp); @@ -735,12 +738,14 @@ static MachineInstr *foldInlineAsmMemOperand(MachineInstr &MI, if (!MI.mayFoldInlineAsmReg(Reg)) return nullptr; - // Find the operands to fold. A use tied to another register's def keeps its - // register. The use tied to one of Reg's defs is folded along with the def, - // and reads the def's slot. That use need not hold Reg when the allocator - // lowers ties itself; the caller must then store the tied use's value into - // the slot before the asm. - SmallVector<bool, 16> Fold(MI.getNumOperands()); + // Find the operands to fold and where each refers to in the slot, which + // holds the whole register: a subregister is at its offset in it. A use + // tied to another register's def keeps its register. The use tied to one of + // Reg's defs is folded along with the def, and reads the def's slot. That + // use need not hold Reg when the allocator lowers ties itself; the caller + // must then store the tied use's value into the slot before the asm. + MachineFunction &MF = *MI.getMF(); + SmallVector<std::optional<unsigned>, 16> Offsets(MI.getNumOperands()); bool Reads = false; bool Writes = false; for (unsigned I = InlineAsm::MIOp_FirstOperand, E = MI.getNumOperands(); @@ -755,13 +760,21 @@ static MachineInstr *foldInlineAsmMemOperand(MachineInstr &MI, if (SlotMO.getReg() != Reg) continue; - Fold[I] = true; + unsigned Offset = 0; + if (unsigned SubReg = SlotMO.getSubReg()) { + unsigned Size; + [[maybe_unused]] bool InSlot = TII.getStackSlotRange( + MF.getRegInfo().getRegClass(Reg), SubReg, Size, Offset, MF); + assert(InSlot && "foldable subregister isn't in the stack slot"); + } + + Offsets[I] = Offset; Reads |= MO.readsReg(); Writes |= MO.isDef(); } MachineInstr &NewMI = TII.duplicate(*MI.getParent(), MI.getIterator(), MI); - foldInlineAsmMemOperands(NewMI, Fold, FI, TII); + foldInlineAsmMemOperands(NewMI, Offsets, FI, TII); // Update mayload/maystore metadata, and memoperands. MachineOperand &ExtraMO = NewMI.getOperand(InlineAsm::MIOp_ExtraInfo); @@ -774,12 +787,12 @@ static MachineInstr *foldInlineAsmMemOperand(MachineInstr &MI, ExtraMO.setImm(ExtraMO.getImm() | InlineAsm::Extra_MayStore); Flags |= MachineMemOperand::MOStore; } - MachineFunction *MF = NewMI.getMF(); - const MachineFrameInfo &MFI = MF->getFrameInfo(); - MachineMemOperand *MMO = MF->getMachineMemOperand( - MachinePointerInfo::getFixedStack(*MF, FI), Flags, MFI.getObjectSize(FI), - MFI.getObjectAlign(FI)); - NewMI.addMemOperand(*MF, MMO); + + const MachineFrameInfo &MFI = MF.getFrameInfo(); + MachineMemOperand *MMO = + MF.getMachineMemOperand(MachinePointerInfo::getFixedStack(MF, FI), Flags, + MFI.getObjectSize(FI), MFI.getObjectAlign(FI)); + NewMI.addMemOperand(MF, MMO); return &NewMI; } diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp index 251fb43e56000b..a38d1b36576205 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.cpp +++ b/llvm/lib/Target/X86/X86InstrInfo.cpp @@ -11031,10 +11031,11 @@ void X86InstrInfo::genAlternativeCodeSequence( // See also: X86DAGToDAGISel::SelectInlineAsmMemoryOperand(). void X86InstrInfo::getFrameIndexOperands(SmallVectorImpl<MachineOperand> &Ops, - int FI) const { + int FI, int64_t Offset) const { X86AddressMode M; M.BaseType = X86AddressMode::FrameIndexBase; M.Base.FrameIndex = FI; + M.Disp = Offset; M.getFullAddress(Ops); } diff --git a/llvm/lib/Target/X86/X86InstrInfo.h b/llvm/lib/Target/X86/X86InstrInfo.h index b8c1aa6b296905..cb2706ce47d59d 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.h +++ b/llvm/lib/Target/X86/X86InstrInfo.h @@ -703,8 +703,8 @@ class X86InstrInfo final : public X86GenInstrInfo { return false; } - void getFrameIndexOperands(SmallVectorImpl<MachineOperand> &Ops, - int FI) const override; + void getFrameIndexOperands(SmallVectorImpl<MachineOperand> &Ops, int FI, + int64_t Offset) const override; private: /// This is a helper for convertToThreeAddress for 8 and 16-bit instructions. diff --git a/llvm/test/CodeGen/X86/greedy-inline-asm-fold.mir b/llvm/test/CodeGen/X86/greedy-inline-asm-fold.mir index deec6136d87a53..311b969a71a3c9 100644 --- a/llvm/test/CodeGen/X86/greedy-inline-asm-fold.mir +++ b/llvm/test/CodeGen/X86/greedy-inline-asm-fold.mir @@ -224,13 +224,12 @@ body: | RET 0 ... --- -# A stack slot holds the whole register, so a subregister operand can be -# folded only if the subregister starts at the beginning of the slot. Each of -# these tests spills a value across an asm that clobbers every GPR, as above, -# and passes its low byte, its second byte, or both to a "Qm" operand of a -# second asm. +# A stack slot holds the whole register, so a subregister operand is folded +# at the subregister's offset in the slot. Each of these tests spills a value +# across an asm that clobbers every GPR, as above, and passes its low byte, +# its second byte, or both to a "Qm" operand of a second asm. # -# The low byte (sub_8bit) is at the start of the slot, so it's folded. +# The low byte (sub_8bit) is at offset 0. # # void qm_low_byte(unsigned long a) { # asm volatile("" : : : ALL_GPRS); @@ -254,8 +253,7 @@ body: | RET 0 ... --- -# The second byte (sub_8bit_hi) is at byte 1 of the slot, so it gets a reload -# instead of a fold to the start of the slot. +# The second byte (sub_8bit_hi) is at offset 1. # # void qm_high_byte(unsigned long a) { # asm volatile("" : : : ALL_GPRS); @@ -271,8 +269,7 @@ body: | ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: MOV64mr %stack.0, 1, $noreg, 0, $noreg, $rdi :: (store (s64) into %stack.0) ; CHECK-NEXT: INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 - ; CHECK-NEXT: [[MOV64rm:%[0-9]+]]:gr64_abcd = MOV64rm %stack.0, 1, $noreg, 0, $noreg :: (load (s64) from %stack.0) - ; CHECK-NEXT: INLINEASM &"", sideeffect attdialect, reguse:GR8_ABCD_H foldable, [[MOV64rm]].sub_8bit_hi + ; CHECK-NEXT: INLINEASM &"", sideeffect mayload attdialect, mem:m ops:5, %stack.0, 1, $noreg, 1, $noreg :: (load (s64) from %stack.0) ; CHECK-NEXT: RET 0 %0:gr64_abcd = COPY $rdi INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 @@ -280,8 +277,7 @@ body: | RET 0 ... --- -# Both bytes are subregisters of one value. Folding both operands would read -# byte 0 for each, so neither is folded. +# Both bytes are subregisters of one value, each folded at its own offset. # # void qm_both_bytes(unsigned long a) { # asm volatile("" : : : ALL_GPRS); @@ -298,8 +294,7 @@ body: | ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: MOV64mr %stack.0, 1, $noreg, 0, $noreg, $rdi :: (store (s64) into %stack.0) ; CHECK-NEXT: INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 - ; CHECK-NEXT: [[MOV64rm:%[0-9]+]]:gr64_abcd = MOV64rm %stack.0, 1, $noreg, 0, $noreg :: (load (s64) from %stack.0) - ; CHECK-NEXT: INLINEASM &"", sideeffect attdialect, reguse:GR8_ABCD_L foldable, [[MOV64rm]].sub_8bit, reguse:GR8_ABCD_H foldable, [[MOV64rm]].sub_8bit_hi + ; CHECK-NEXT: INLINEASM &"", sideeffect mayload attdialect, mem:m ops:5, %stack.0, 1, $noreg, 0, $noreg, mem:m ops:5, %stack.0, 1, $noreg, 1, $noreg :: (load (s64) from %stack.0) ; CHECK-NEXT: RET 0 %0:gr64_abcd = COPY $rdi INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 @@ -307,12 +302,14 @@ body: | RET 0 ... --- -# A def is folded along with the use tied to it, so neither is folded when the -# tied use is the second byte. +# A def is folded along with the use tied to it, both at the offset of the +# def's subregister. The third asm keeps the value in its slot after the +# second. # # unsigned long qm_tied_high_byte(unsigned long a) { # asm volatile("" : : : ALL_GPRS); # asm volatile("" : "+Qm"(((unsigned char *)&a)[1])); +# asm volatile("" : : : ALL_GPRS); # return a; # } name: qm_tied_high_byte @@ -325,13 +322,14 @@ body: | ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: MOV64mr %stack.0, 1, $noreg, 0, $noreg, $rdi :: (store (s64) into %stack.0) ; CHECK-NEXT: INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 - ; CHECK-NEXT: [[MOV64rm:%[0-9]+]]:gr64_abcd = MOV64rm %stack.0, 1, $noreg, 0, $noreg :: (load (s64) from %stack.0) - ; CHECK-NEXT: INLINEASM &"", sideeffect attdialect, regdef:GR8_ABCD_H foldable, def [[MOV64rm]].sub_8bit_hi, reguse tiedto:$0, [[MOV64rm]].sub_8bit_hi(tied-def 3) - ; CHECK-NEXT: $rax = COPY [[MOV64rm]] + ; CHECK-NEXT: INLINEASM &"", sideeffect mayload maystore attdialect, mem:m ops:5, %stack.0, 1, $noreg, 1, $noreg, mem:m ops:5, %stack.0, 1, $noreg, 1, $noreg :: (load store (s64) on %stack.0) + ; CHECK-NEXT: INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 + ; CHECK-NEXT: $rax = MOV64rm %stack.0, 1, $noreg, 0, $noreg :: (load (s64) from %stack.0) ; CHECK-NEXT: RET 0, $rax %0:gr64_abcd = COPY $rdi INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 INLINEASM &"", sideeffect attdialect, regdef:GR8_ABCD_H foldable, def %0.sub_8bit_hi, reguse tiedto:$0, %0.sub_8bit_hi(tied-def 3) + INLINEASM &"", sideeffect attdialect, clobber, implicit-def dead early-clobber $rax, clobber, implicit-def dead early-clobber $rbx, clobber, implicit-def dead early-clobber $rcx, clobber, implicit-def dead early-clobber $rdx, clobber, implicit-def dead early-clobber $rsi, clobber, implicit-def dead early-clobber $rdi, clobber, implicit-def dead early-clobber $rbp, clobber, implicit-def dead early-clobber $r8, clobber, implicit-def dead early-clobber $r9, clobber, implicit-def dead early-clobber $r10, clobber, implicit-def dead early-clobber $r11, clobber, implicit-def dead early-clobber $r12, clobber, implicit-def dead early-clobber $r13, clobber, implicit-def dead early-clobber $r14, clobber, implicit-def dead early-clobber $r15 $rax = COPY %0 RET 0, $rax ... _______________________________________________ llvm-branch-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
