bool IsIntrinOpcode;
isFMA3(Opc, &IsIntrinOpcode);
- unsigned GroupsNum;
+ size_t GroupsNum;
const unsigned (*OpcodeGroups)[3];
if (IsIntrinOpcode) {
- GroupsNum = sizeof(IntrinOpcodeGroups) / sizeof(IntrinOpcodeGroups[0]);
+ GroupsNum = array_lengthof(IntrinOpcodeGroups);
OpcodeGroups = IntrinOpcodeGroups;
} else {
- GroupsNum = sizeof(RegularOpcodeGroups) / sizeof(RegularOpcodeGroups[0]);
+ GroupsNum = array_lengthof(RegularOpcodeGroups);
OpcodeGroups = RegularOpcodeGroups;
}
const unsigned *FoundOpcodesGroup = nullptr;
- unsigned FormIndex;
+ size_t FormIndex;
// Look for the input opcode in the corresponding opcodes table.
- unsigned GroupIndex = 0;
- for (; GroupIndex < GroupsNum && !FoundOpcodesGroup; GroupIndex++) {
- for (FormIndex = 0; FormIndex < FormsNum; FormIndex++) {
+ for (size_t GroupIndex = 0; GroupIndex < GroupsNum && !FoundOpcodesGroup;
+ ++GroupIndex) {
+ for (FormIndex = 0; FormIndex < FormsNum; ++FormIndex) {
if (OpcodeGroups[GroupIndex][FormIndex] == Opc) {
FoundOpcodesGroup = OpcodeGroups[GroupIndex];
break;
int Reg = FromEFLAGS ? DestReg : SrcReg;
bool is32 = X86::GR32RegClass.contains(Reg);
bool is64 = X86::GR64RegClass.contains(Reg);
+
if ((FromEFLAGS || ToEFLAGS) && (is32 || is64)) {
+ int Mov = is64 ? X86::MOV64rr : X86::MOV32rr;
+ int Push = is64 ? X86::PUSH64r : X86::PUSH32r;
+ int PushF = is64 ? X86::PUSHF64 : X86::PUSHF32;
+ int Pop = is64 ? X86::POP64r : X86::POP32r;
+ int PopF = is64 ? X86::POPF64 : X86::POPF32;
+ int AX = is64 ? X86::RAX : X86::EAX;
+
+ if (!Subtarget.hasLAHFSAHF()) {
+ assert(is64 && "Not having LAHF/SAHF only happens on 64-bit.");
+ // Moving EFLAGS to / from another register requires a push and a pop.
+ // Notice that we have to adjust the stack if we don't want to clobber the
+ // first frame index. See X86FrameLowering.cpp - clobbersTheStack.
+ if (FromEFLAGS) {
+ BuildMI(MBB, MI, DL, get(PushF));
+ BuildMI(MBB, MI, DL, get(Pop), DestReg);
+ }
+ if (ToEFLAGS) {
+ BuildMI(MBB, MI, DL, get(Push))
+ .addReg(SrcReg, getKillRegState(KillSrc));
+ BuildMI(MBB, MI, DL, get(PopF));
+ }
+ return;
+ }
+
// The flags need to be saved, but saving EFLAGS with PUSHF/POPF is
// inefficient. Instead:
// - Save the overflow flag OF into AL using SETO, and restore it using a
// Notice that we have to adjust the stack if we don't want to clobber the
// first frame index. See X86FrameLowering.cpp - clobbersTheStack.
- int Mov = is64 ? X86::MOV64rr : X86::MOV32rr;
- int Push = is64 ? X86::PUSH64r : X86::PUSH32r;
- int Pop = is64 ? X86::POP64r : X86::POP32r;
- int AX = is64 ? X86::RAX : X86::EAX;
- bool AXDead = (Reg == AX) ||
- (MachineBasicBlock::LQR_Dead ==
- MBB.computeRegisterLiveness(&getRegisterInfo(), AX, MI));
+ bool AXDead = (Reg == AX);
+ // FIXME: The above could figure out that AX is dead in more cases with:
+ // || (MachineBasicBlock::LQR_Dead ==
+ // MBB.computeRegisterLiveness(&getRegisterInfo(), AX, MI));
+ //
+ // Unfortunately this is slightly broken, see PR24535 and the likely
+ // related PR25033 PR24991 PR24992 PR25201. These issues seem to
+ // showcase sub-register / super-register confusion: a previous kill
+ // of AH but no kill of AL leads computeRegisterLiveness to
+ // erroneously conclude that AX is dead.
+ //
+ // Once fixed, also update cmpxchg-clobber-flags.ll and
+ // peephole-na-phys-copy-folding.ll.
if (!AXDead)
BuildMI(MBB, MI, DL, get(Push)).addReg(AX, getKillRegState(true));
case X86::DIVSSrr_Int: case X86::VDIVSSrr_Int:
case X86::MULSSrr_Int: case X86::VMULSSrr_Int:
case X86::SUBSSrr_Int: case X86::VSUBSSrr_Int:
+ case X86::VFMADDSSr132r_Int: case X86::VFNMADDSSr132r_Int:
+ case X86::VFMADDSSr213r_Int: case X86::VFNMADDSSr213r_Int:
+ case X86::VFMADDSSr231r_Int: case X86::VFNMADDSSr231r_Int:
+ case X86::VFMSUBSSr132r_Int: case X86::VFNMSUBSSr132r_Int:
+ case X86::VFMSUBSSr213r_Int: case X86::VFNMSUBSSr213r_Int:
+ case X86::VFMSUBSSr231r_Int: case X86::VFNMSUBSSr231r_Int:
return false;
default:
return true;
case X86::DIVSDrr_Int: case X86::VDIVSDrr_Int:
case X86::MULSDrr_Int: case X86::VMULSDrr_Int:
case X86::SUBSDrr_Int: case X86::VSUBSDrr_Int:
+ case X86::VFMADDSDr132r_Int: case X86::VFNMADDSDr132r_Int:
+ case X86::VFMADDSDr213r_Int: case X86::VFNMADDSDr213r_Int:
+ case X86::VFMADDSDr231r_Int: case X86::VFNMADDSDr231r_Int:
+ case X86::VFMSUBSDr132r_Int: case X86::VFNMSUBSDr132r_Int:
+ case X86::VFMSUBSDr213r_Int: case X86::VFNMSUBSDr213r_Int:
+ case X86::VFMSUBSDr231r_Int: case X86::VFNMSUBSDr231r_Int:
return false;
default:
return true;
// domains, but they require a bit more work than just switching opcodes.
static const uint16_t *lookup(unsigned opcode, unsigned domain) {
- for (unsigned i = 0, e = array_lengthof(ReplaceableInstrs); i != e; ++i)
- if (ReplaceableInstrs[i][domain-1] == opcode)
- return ReplaceableInstrs[i];
+ for (const uint16_t (&Row)[3] : ReplaceableInstrs)
+ if (Row[domain-1] == opcode)
+ return Row;
return nullptr;
}
static const uint16_t *lookupAVX2(unsigned opcode, unsigned domain) {
- for (unsigned i = 0, e = array_lengthof(ReplaceableInstrsAVX2); i != e; ++i)
- if (ReplaceableInstrsAVX2[i][domain-1] == opcode)
- return ReplaceableInstrsAVX2[i];
+ for (const uint16_t (&Row)[3] : ReplaceableInstrsAVX2)
+ if (Row[domain-1] == opcode)
+ return Row;
return nullptr;
}