maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert r368987, it caused PR43016. 

llvm-svn: 369080
This commit is contained in:
Nico Weber 2019-08-16 02:21:21 +00:00
parent effc28c139
commit ee96499a42
32 changed files with 291 additions and 347 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
llvm/lib/Target/AArch64/AArch64CallingConvention.td
View File

@ -317,12 +317,6 @@ def CC_AArch64_GHC : CallingConv<[
CCIfType<[i64], CCAssignToReg<[X19, X20, X21, X22, X23, X24, X25, X26, X27, X28]>>
]>;
// The order of the callee-saves in this file is important, because the
// FrameLowering code will use this order to determine the layout the
// callee-save area in the stack frame. As can be observed below, Darwin
// requires the frame-record (LR, FP) to be at the top the callee-save area,
// whereas for other platforms they are at the bottom.
// FIXME: LR is only callee-saved in the sense that *we* preserve it and are
// presumably a callee to someone. External functions may not do so, but this
// is currently safe since BL has LR as an implicit-def and what happens after a
@ -331,13 +325,7 @@ def CC_AArch64_GHC : CallingConv<[
// It would be better to model its preservation semantics properly (create a
// vreg on entry, use it in RET & tail call generation; make that vreg def if we
// end up saving LR as part of a call frame). Watch this space...
def CSR_AArch64_AAPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24,
X25, X26, X27, X28, LR, FP,
D8, D9, D10, D11,
D12, D13, D14, D15)>;
// Darwin puts the frame-record at the top of the callee-save area.
def CSR_Darwin_AArch64_AAPCS : CalleeSavedRegs<(add LR, FP, X19, X20, X21, X22,
def CSR_AArch64_AAPCS : CalleeSavedRegs<(add LR, FP, X19, X20, X21, X22,
X23, X24, X25, X26, X27, X28,
D8, D9, D10, D11,
D12, D13, D14, D15)>;
@ -345,21 +333,21 @@ def CSR_Darwin_AArch64_AAPCS : CalleeSavedRegs<(add LR, FP, X19, X20, X21, X22,
// Win64 has unwinding codes for an (FP,LR) pair, save_fplr and save_fplr_x.
// We put FP before LR, so that frame lowering logic generates (FP,LR) pairs,
// and not (LR,FP) pairs.
def CSR_Win_AArch64_AAPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24,
X25, X26, X27, X28, FP, LR,
def CSR_Win_AArch64_AAPCS : CalleeSavedRegs<(add FP, LR, X19, X20, X21, X22,
X23, X24, X25, X26, X27, X28,
D8, D9, D10, D11,
D12, D13, D14, D15)>;
// AArch64 PCS for vector functions (VPCS)
// must (additionally) preserve full Q8-Q23 registers
def CSR_AArch64_AAVPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24,
X25, X26, X27, X28, LR, FP,
def CSR_AArch64_AAVPCS : CalleeSavedRegs<(add LR, FP, X19, X20, X21, X22,
X23, X24, X25, X26, X27, X28,
(sequence "Q%u", 8, 23))>;
// Functions taking SVE arguments or returning an SVE type
// must (additionally) preserve full Z8-Z23 and predicate registers P4-P15
def CSR_AArch64_SVE_AAPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24,
X25, X26, X27, X28, LR, FP,
def CSR_AArch64_SVE_AAPCS : CalleeSavedRegs<(add LR, FP, X19, X20, X21, X22,
X23, X24, X25, X26, X27, X28,
(sequence "Z%u", 8, 23),
(sequence "P%u", 4, 15))>;
@ -374,7 +362,7 @@ def CSR_AArch64_SVE_AAPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24,
def CSR_AArch64_AAPCS_ThisReturn : CalleeSavedRegs<(add CSR_AArch64_AAPCS, X0)>;
def CSR_AArch64_AAPCS_SwiftError
: CalleeSavedRegs<(sub CSR_Darwin_AArch64_AAPCS, X21)>;
: CalleeSavedRegs<(sub CSR_AArch64_AAPCS, X21)>;
// The function used by Darwin to obtain the address of a thread-local variable
// guarantees more than a normal AAPCS function. x16 and x17 are used on the
@ -390,7 +378,7 @@ def CSR_AArch64_TLS_Darwin
// fast path calls a function that follows CSR_AArch64_TLS_Darwin,
// CSR_AArch64_CXX_TLS_Darwin should be a subset of CSR_AArch64_TLS_Darwin.
def CSR_AArch64_CXX_TLS_Darwin
: CalleeSavedRegs<(add CSR_Darwin_AArch64_AAPCS,
: CalleeSavedRegs<(add CSR_AArch64_AAPCS,
(sub (sequence "X%u", 1, 28), X15, X16, X17, X18),
(sequence "D%u", 0, 31))>;

79
llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
View File

@ -44,15 +44,11 @@
// | |
// |-----------------------------------|
// | |
// | callee-saved gpr registers | <--.
// | | | On Darwin platforms these
// |- - - - - - - - - - - - - - - - - -| | callee saves are swapped,
// | | | (frame record first)
// | prev_fp, prev_lr | <--'
// | prev_fp, prev_lr |
// | (a.k.a. "frame record") |
// |-----------------------------------| <- fp(=x29)
// | |
// | callee-saved fp/simd/SVE regs |
// | other callee-saved registers |
// | |
// |-----------------------------------|
// |.empty.space.to.make.part.below....|
@ -84,20 +80,6 @@
// * A frame pointer is definitely needed when there are local variables with
// more-than-default alignment requirements.
//
// For Darwin platforms the frame-record (fp, lr) is stored at the top of the
// callee-saved area, since the unwind encoding does not allow for encoding
// this dynamically and existing tools depend on this layout. For other
// platforms, the frame-record is stored at the bottom of the (gpr) callee-saved
// area to allow SVE stack objects (allocated directly below the callee-saves,
// if available) to be accessed directly from the framepointer.
// The SVE spill/fill instructions have VL-scaled addressing modes such
// as:
// ldr z8, [fp, #-7 mul vl]
// For SVE the size of the vector length (VL) is not known at compile-time, so
// '#-7 mul vl' is an offset that can only be evaluated at runtime. With this
// layout, we don't need to add an unscaled offset to the framepointer before
// accessing the SVE object in the frame.
//
// In some cases when a base pointer is not strictly needed, it is generated
// anyway when offsets from the frame pointer to access local variables become
// so large that the offset can't be encoded in the immediate fields of loads
@ -811,10 +793,6 @@ static bool needsWinCFI(const MachineFunction &MF) {
F.needsUnwindTableEntry();
}
static bool isTargetDarwin(const MachineFunction &MF) {
return MF.getSubtarget<AArch64Subtarget>().isTargetDarwin();
}
void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
MachineBasicBlock::iterator MBBI = MBB.begin();
@ -974,9 +952,9 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
}
if (HasFP) {
// Only set up FP if we actually need to.
int FPOffset = isTargetDarwin(MF) ? (AFI->getCalleeSavedStackSize() - 16) : 0;
// Only set up FP if we actually need to. Frame pointer is fp =
// sp - fixedobject - 16.
int FPOffset = AFI->getCalleeSavedStackSize() - 16;
if (CombineSPBump)
FPOffset += AFI->getLocalStackSize();
@ -1158,9 +1136,7 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
if (needsFrameMoves) {
const DataLayout &TD = MF.getDataLayout();
const int StackGrowth = isTargetDarwin(MF)
? (2 * -TD.getPointerSize(0))
: -AFI->getCalleeSavedStackSize();
const int StackGrowth = -TD.getPointerSize(0);
Register FramePtr = RegInfo->getFrameRegister(MF);
// An example of the prologue:
//
@ -1232,7 +1208,7 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
// Define the current CFA rule to use the provided FP.
unsigned Reg = RegInfo->getDwarfRegNum(FramePtr, true);
unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createDefCfa(
nullptr, Reg, StackGrowth - FixedObject));
nullptr, Reg, 2 * StackGrowth - FixedObject));
BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
@ -1486,13 +1462,11 @@ void AArch64FrameLowering::emitEpilogue(MachineFunction &MF,
// FIXME: Rather than doing the math here, we should instead just use
// non-post-indexed loads for the restores if we aren't actually going to
// be able to save any instructions.
if (!IsFunclet && (MFI.hasVarSizedObjects() || AFI->isStackRealigned())) {
int64_t OffsetToFrameRecord =
isTargetDarwin(MF) ? (-(int64_t)AFI->getCalleeSavedStackSize() + 16) : 0;
if (!IsFunclet && (MFI.hasVarSizedObjects() || AFI->isStackRealigned()))
emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::FP,
{OffsetToFrameRecord, MVT::i8},
{-(int64_t)AFI->getCalleeSavedStackSize() + 16, MVT::i8},
TII, MachineInstr::FrameDestroy, false, NeedsWinCFI);
} else if (NumBytes)
else if (NumBytes)
emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::SP,
{NumBytes, MVT::i8}, TII, MachineInstr::FrameDestroy, false,
NeedsWinCFI);
@ -1552,8 +1526,7 @@ static StackOffset getFPOffset(const MachineFunction &MF, int ObjectOffset) {
bool IsWin64 =
Subtarget.isCallingConvWin64(MF.getFunction().getCallingConv());
unsigned FixedObject = IsWin64 ? alignTo(AFI->getVarArgsGPRSize(), 16) : 0;
unsigned FPAdjust = isTargetDarwin(MF) ? 16 : AFI->getCalleeSavedStackSize();
return {ObjectOffset + FixedObject + FPAdjust, MVT::i8};
return {ObjectOffset + FixedObject + 16, MVT::i8};
}
static StackOffset getStackOffset(const MachineFunction &MF, int ObjectOffset) {
@ -1716,23 +1689,6 @@ static bool invalidateWindowsRegisterPairing(unsigned Reg1, unsigned Reg2,
return true;
}
/// Returns true if Reg1 and Reg2 cannot be paired using a ldp/stp instruction.
/// WindowsCFI requires that only consecutive registers can be paired.
/// LR and FP need to be allocated together when the frame needs to save
/// the frame-record. This means any other register pairing with LR is invalid.
static bool invalidateRegisterPairing(unsigned Reg1, unsigned Reg2,
bool NeedsWinCFI, bool NeedsFrameRecord) {
if (NeedsWinCFI)
return invalidateWindowsRegisterPairing(Reg1, Reg2, true);
// If we need to store the frame record, don't pair any register
// with LR other than FP.
if (NeedsFrameRecord)
return Reg2 == AArch64::LR;
return false;
}
namespace {
struct RegPairInfo {
@ -1752,7 +1708,7 @@ struct RegPairInfo {
static void computeCalleeSaveRegisterPairs(
MachineFunction &MF, const std::vector<CalleeSavedInfo> &CSI,
const TargetRegisterInfo *TRI, SmallVectorImpl<RegPairInfo> &RegPairs,
bool &NeedShadowCallStackProlog, bool NeedsFrameRecord) {
bool &NeedShadowCallStackProlog) {
if (CSI.empty())
return;
@ -1794,8 +1750,7 @@ static void computeCalleeSaveRegisterPairs(
switch (RPI.Type) {
case RegPairInfo::GPR:
if (AArch64::GPR64RegClass.contains(NextReg) &&
!invalidateRegisterPairing(RPI.Reg1, NextReg, NeedsWinCFI,
NeedsFrameRecord))
!invalidateWindowsRegisterPairing(RPI.Reg1, NextReg, NeedsWinCFI))
RPI.Reg2 = NextReg;
break;
case RegPairInfo::FPR64:
@ -1829,10 +1784,6 @@ static void computeCalleeSaveRegisterPairs(
(CSI[i].getFrameIdx() + 1 == CSI[i + 1].getFrameIdx())) &&
"Out of order callee saved regs!");
assert((!RPI.isPaired() || RPI.Reg2 != AArch64::FP ||
RPI.Reg1 == AArch64::LR) &&
"FrameRecord must be allocated together with LR");
// MachO's compact unwind format relies on all registers being stored in
// adjacent register pairs.
assert((!produceCompactUnwindFrame(MF) ||
@ -1881,7 +1832,7 @@ bool AArch64FrameLowering::spillCalleeSavedRegisters(
bool NeedShadowCallStackProlog = false;
computeCalleeSaveRegisterPairs(MF, CSI, TRI, RegPairs,
NeedShadowCallStackProlog, hasFP(MF));
NeedShadowCallStackProlog);
const MachineRegisterInfo &MRI = MF.getRegInfo();
if (NeedShadowCallStackProlog) {
@ -2011,7 +1962,7 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
bool NeedShadowCallStackProlog = false;
computeCalleeSaveRegisterPairs(MF, CSI, TRI, RegPairs,
NeedShadowCallStackProlog, hasFP(MF));
NeedShadowCallStackProlog);
auto EmitMI = [&](const RegPairInfo &RPI) {
unsigned Reg1 = RPI.Reg1;

5
llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp
View File

@ -64,9 +64,8 @@ AArch64RegisterInfo::getCalleeSavedRegs(const MachineFunction *MF) const {
return CSR_AArch64_AAPCS_SwiftError_SaveList;
if (MF->getFunction().getCallingConv() == CallingConv::PreserveMost)
return CSR_AArch64_RT_MostRegs_SaveList;
if (MF->getSubtarget<AArch64Subtarget>().isTargetDarwin())
return CSR_Darwin_AArch64_AAPCS_SaveList;
return CSR_AArch64_AAPCS_SaveList;
else
return CSR_AArch64_AAPCS_SaveList;
}
const MCPhysReg *AArch64RegisterInfo::getCalleeSavedRegsViaCopy(

124
llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
View File

@ -99,18 +99,18 @@ entry:
; CHECK: .cfi_startproc
; Check that used callee-saved registers are saved
; CHECK: sub sp, sp, #32
; CHECK: stp x30, x19, [sp, #16]
; CHECK: stp x19, x30, [sp, #16]
; Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa_offset 32
; CHECK: .cfi_offset w19, -8
; CHECK: .cfi_offset w30, -16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w19, -16
; Check correct access to arguments passed on the stack, through stack pointer
; CHECK: ldr d[[DARG:[0-9]+]], [sp, #56]
; CHECK: ldr w[[IARG:[0-9]+]], [sp, #40]
; Check correct access to local variable on the stack, through stack pointer
; CHECK: ldr w[[ILOC:[0-9]+]], [sp, #12]
; Check epilogue:
; CHECK: ldp x30, x19, [sp, #16]
; CHECK: ldp x19, x30, [sp, #16]
; CHECK: ret
; CHECK: .cfi_endproc
@ -180,28 +180,28 @@ entry:
; CHECK-LABEL: novla_dynamicrealign_call
; CHECK: .cfi_startproc
; Check that used callee-saved registers are saved
; CHECK: stp x29, x30, [sp, #-32]!
; CHECK: str x19, [sp, #-32]!
; Check that the frame pointer is created:
; CHECK: str x19, [sp, #16]
; CHECK: mov x29, sp
; CHECK: stp x29, x30, [sp, #16]
; CHECK: add x29, sp, #16
; Check the dynamic realignment of the stack pointer to a 128-byte boundary
; CHECK: sub x9, sp, #96
; CHECK: and sp, x9, #0xffffffffffffff80
; Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa w29, 32
; CHECK: .cfi_offset w19, -16
; CHECK: .cfi_offset w30, -24
; CHECK: .cfi_offset w29, -32
; CHECK: .cfi_def_cfa w29, 16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w29, -16
; CHECK: .cfi_offset w19, -32
; Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #56]
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #40]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #40]
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #24]
; Check correct access to local variable on the stack, through re-aligned stack pointer
; CHECK: ldr w[[ILOC:[0-9]+]], [sp]
; Check epilogue:
; Check that stack pointer get restored from frame pointer.
; CHECK: mov sp, x29
; CHECK: ldr x19, [sp, #16]
; CHECK: ldp x29, x30, [sp], #32
; CHECK: sub sp, x29, #16 // =16
; CHECK: ldp x29, x30, [sp, #16]
; CHECK: ldr x19, [sp], #32
; CHECK: ret
; CHECK: .cfi_endproc
@ -284,22 +284,22 @@ entry:
; CHECK-LABEL: vla_nodynamicrealign_call
; CHECK: .cfi_startproc
; Check that used callee-saved registers are saved
; CHECK: stp x29, x30, [sp, #-32]!
; CHECK: stp x20, x19, [sp, #-32]!
; Check that the frame pointer is created:
; CHECK: stp x20, x19, [sp, #16]
; CHECK: mov x29, sp
; CHECK: stp x29, x30, [sp, #16]
; CHECK: add x29, sp, #16
; Check that space is reserved on the stack for the local variable,
; rounded up to a multiple of 16 to keep the stack pointer 16-byte aligned.
; CHECK: sub sp, sp, #16
; Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa w29, 32
; CHECK: .cfi_offset w19, -8
; CHECK: .cfi_offset w20, -16
; CHECK: .cfi_offset w30, -24
; CHECK: .cfi_offset w29, -32
; CHECK: .cfi_def_cfa w29, 16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w29, -16
; CHECK: .cfi_offset w19, -24
; CHECK: .cfi_offset w20, -32
; Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #40]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #56]
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #40]
; Check correct reservation of 16-byte aligned VLA (size in w0) on stack
; CHECK: mov w9, w0
; CHECK: mov x10, sp
@ -309,14 +309,14 @@ entry:
; CHECK: sub x[[VLASPTMP:[0-9]+]], x10, x9
; CHECK: mov sp, x[[VLASPTMP]]
; Check correct access to local variable, through frame pointer
; CHECK: ldur w[[ILOC:[0-9]+]], [x29, #-4]
; CHECK: ldur w[[ILOC:[0-9]+]], [x29, #-20]
; Check correct accessing of the VLA variable through the base pointer
; CHECK: ldr w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
; Check epilogue:
; Check that stack pointer get restored from frame pointer.
; CHECK: mov sp, x29
; CHECK: ldp x20, x19, [sp, #16]
; CHECK: ldp x29, x30, [sp], #32
; CHECK: sub sp, x29, #16 // =16
; CHECK: ldp x29, x30, [sp, #16]
; CHECK: ldp x20, x19, [sp], #32
; CHECK: ret
; CHECK: .cfi_endproc
@ -385,11 +385,11 @@ entry:
; CHECK-LABEL: vla_dynamicrealign_call
; CHECK: .cfi_startproc
; Check that used callee-saved registers are saved
; CHECK: stp x29, x30, [sp, #-48]!
; CHECK: str x21, [sp, #16]
; CHECK: stp x20, x19, [sp, #32]
; CHECK: str x21, [sp, #-48]!
; CHECK: stp x20, x19, [sp, #16]
; Check that the frame pointer is created:
; CHECK: mov x29, sp
; CHECK: stp x29, x30, [sp, #32]
; CHECK: add x29, sp, #32
; Check that the stack pointer gets re-aligned to 128
; bytes & the base pointer (x19) gets initialized to
; this 128-byte aligned area for local variables &
@ -398,15 +398,15 @@ entry:
; CHECK: and sp, x9, #0xffffffffffffff80
; CHECK: mov x19, sp
; Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa w29, 48
; CHECK: .cfi_offset w19, -8
; CHECK: .cfi_offset w20, -16
; CHECK: .cfi_offset w21, -32
; CHECK: .cfi_offset w30, -40
; CHECK: .cfi_offset w29, -48
; CHECK: .cfi_def_cfa w29, 16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w29, -16
; CHECK: .cfi_offset w19, -24
; CHECK: .cfi_offset w20, -32
; CHECK: .cfi_offset w21, -48
; Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #56]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #72]
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #40]
; Check correct reservation of 16-byte aligned VLA (size in w0) on stack
; and set-up of base pointer (x19).
; CHECK: mov w9, w0
@ -421,10 +421,10 @@ entry:
; CHECK: ldr w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
; Check epilogue:
; Check that stack pointer get restored from frame pointer.
; CHECK: mov sp, x29
; CHECK: ldp x20, x19, [sp, #32]
; CHECK: ldr x21, [sp, #16]
; CHECK: ldp x29, x30, [sp], #48
; CHECK: sub sp, x29, #32
; CHECK: ldp x29, x30, [sp, #32]
; CHECK: ldp x20, x19, [sp, #16]
; CHECK: ldr x21, [sp], #48
; CHECK: ret
; CHECK: .cfi_endproc
@ -493,10 +493,10 @@ entry:
; CHECK-LABEL: vla_dynamicrealign_nocall
; Check that used callee-saved registers are saved
; CHECK: stp x29, x30, [sp, #-32]!
; CHECK: str x19, [sp, #16]
; CHECK: str x19, [sp, #-32]!
; Check that the frame pointer is created:
; CHECK: mov x29, sp
; CHECK: stp x29, x30, [sp, #16]
; CHECK: add x29, sp, #16
; Check that the stack pointer gets re-aligned to 128
; bytes & the base pointer (x19) gets initialized to
; this 128-byte aligned area for local variables &
@ -505,8 +505,8 @@ entry:
; CHECK: and sp, x9, #0xffffffffffffff80
; CHECK: mov x19, sp
; Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #40]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #56]
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #40]
; Check correct reservation of 16-byte aligned VLA (size in w0) on stack
; and set-up of base pointer (x19).
; CHECK: mov w9, w0
@ -521,9 +521,9 @@ entry:
; CHECK: ldr w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
; Check epilogue:
; Check that stack pointer get restored from frame pointer.
; CHECK: mov sp, x29
; CHECK: ldr x19, [sp, #16]
; CHECK: ldp x29, x30, [sp], #32
; CHECK: sub sp, x29, #16
; CHECK: ldp x29, x30, [sp, #16]
; CHECK: ldr x19, [sp], #32
; CHECK: ret
; CHECK-MACHO-LABEL: _vla_dynamicrealign_nocall:
@ -579,10 +579,10 @@ entry:
; CHECK-LABEL: vla_dynamicrealign_nocall_large_align
; Check that used callee-saved registers are saved
; CHECK: stp x29, x30, [sp, #-32]!
; CHECK: str x19, [sp, #16]
; CHECK: stp x28, x19, [sp, #-32]!
; Check that the frame pointer is created:
; CHECK: mov x29, sp
; CHECK: stp x29, x30, [sp, #16]
; CHECK: add x29, sp, #16
; Check that the stack pointer gets re-aligned to 128
; bytes & the base pointer (x19) gets initialized to
; this 128-byte aligned area for local variables &
@ -591,8 +591,8 @@ entry:
; CHECK: and sp, x9, #0xffffffffffff8000
; CHECK: mov x19, sp
; Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #40]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #56]
; CHECK: ldr w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr d[[DARG:[0-9]+]], [x29, #40]
; Check correct reservation of 16-byte aligned VLA (size in w0) on stack
; and set-up of base pointer (x19).
; CHECK: mov w9, w0
@ -607,9 +607,9 @@ entry:
; CHECK: ldr w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
; Check epilogue:
; Check that stack pointer get restored from frame pointer.
; CHECK: mov sp, x29
; CHECK: ldr x19, [sp, #16]
; CHECK: ldp x29, x30, [sp], #32
; CHECK: sub sp, x29, #16
; CHECK: ldp x29, x30, [sp, #16]
; CHECK: ldp x28, x19, [sp], #32
; CHECK: ret
; CHECK-MACHO-LABEL: _vla_dynamicrealign_nocall_large_align:

24
llvm/test/CodeGen/AArch64/aarch64-vector-pcs.mir
View File

@ -176,12 +176,12 @@ body: |
; CHECK-NEXT: frame-setup STPQi killed $q13, killed $q12, $sp, 11
; CHECK-NEXT: frame-setup STPQi killed $q11, killed $q10, $sp, 13
; CHECK-NEXT: frame-setup STPQi killed $q9, killed $q8, $sp, 15
; CHECK-NEXT: frame-setup STPXi killed $fp, killed $lr, $sp, 34 :: (store 8 into %stack.{{[0-9]+}}), (store 8 into %stack.{{[0-9]+}})
; CHECK-NEXT: frame-setup STPXi killed $x28, killed $x27, $sp, 36
; CHECK-NEXT: frame-setup STPXi killed $x26, killed $x25, $sp, 38
; CHECK-NEXT: frame-setup STPXi killed $x24, killed $x23, $sp, 40
; CHECK-NEXT: frame-setup STPXi killed $x22, killed $x21, $sp, 42
; CHECK-NEXT: frame-setup STPXi killed $x20, killed $x19, $sp, 44
; CHECK-NEXT: frame-setup STPXi killed $x28, killed $x27, $sp, 34 :: (store 8 into %stack.{{[0-9]+}}), (store 8 into %stack.{{[0-9]+}})
; CHECK-NEXT: frame-setup STPXi killed $x26, killed $x25, $sp, 36
; CHECK-NEXT: frame-setup STPXi killed $x24, killed $x23, $sp, 38
; CHECK-NEXT: frame-setup STPXi killed $x22, killed $x21, $sp, 40
; CHECK-NEXT: frame-setup STPXi killed $x20, killed $x19, $sp, 42
; CHECK-NEXT: frame-setup STPXi killed $fp, killed $lr, $sp, 44
...
---
@ -242,12 +242,12 @@ body: |
; CHECK-NEXT: frame-setup STPQi killed $q13, killed $q12, $sp, 10
; CHECK-NEXT: frame-setup STPQi killed $q11, killed $q10, $sp, 12
; CHECK-NEXT: frame-setup STPQi killed $q9, killed $q8, $sp, 14
; CHECK-NEXT: frame-setup STPXi killed $fp, killed $lr, $sp, 32 :: (store 8 into %stack.{{[0-9]+}}), (store 8 into %stack.{{[0-9]+}})
; CHECK-NEXT: frame-setup STPXi killed $x28, killed $x27, $sp, 34
; CHECK-NEXT: frame-setup STPXi killed $x26, killed $x25, $sp, 36
; CHECK-NEXT: frame-setup STPXi killed $x24, killed $x23, $sp, 38
; CHECK-NEXT: frame-setup STPXi killed $x22, killed $x21, $sp, 40
; CHECK-NEXT: frame-setup STPXi killed $x20, killed $x19, $sp, 42
; CHECK-NEXT: frame-setup STPXi killed $x28, killed $x27, $sp, 32 :: (store 8 into %stack.{{[0-9]+}}), (store 8 into %stack.{{[0-9]+}})
; CHECK-NEXT: frame-setup STPXi killed $x26, killed $x25, $sp, 34
; CHECK-NEXT: frame-setup STPXi killed $x24, killed $x23, $sp, 36
; CHECK-NEXT: frame-setup STPXi killed $x22, killed $x21, $sp, 38
; CHECK-NEXT: frame-setup STPXi killed $x20, killed $x19, $sp, 40
; CHECK-NEXT: frame-setup STPXi killed $fp, killed $lr, $sp, 42
; CHECK-NEXT: $sp = frame-setup SUBXri $sp, 176, 0
...

72
llvm/test/CodeGen/AArch64/addsub-constant-folding.ll
View File

@ -19,15 +19,15 @@ define i32 @add_const_add_const(i32 %arg) {
define i32 @add_const_add_const_extrause(i32 %arg) {
; CHECK-LABEL: add_const_add_const_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: add w0, w0, #8 // =8
; CHECK-NEXT: bl use
; CHECK-NEXT: add w0, w19, #10 // =10
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = add i32 %arg, 8
call void @use(i32 %t0)
@ -96,15 +96,15 @@ define i32 @add_const_sub_const(i32 %arg) {
define i32 @add_const_sub_const_extrause(i32 %arg) {
; CHECK-LABEL: add_const_sub_const_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: add w0, w0, #8 // =8
; CHECK-NEXT: bl use
; CHECK-NEXT: add w0, w19, #6 // =6
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = add i32 %arg, 8
call void @use(i32 %t0)
@ -174,16 +174,16 @@ define i32 @add_const_const_sub(i32 %arg) {
define i32 @add_const_const_sub_extrause(i32 %arg) {
; CHECK-LABEL: add_const_const_sub_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: add w0, w0, #8 // =8
; CHECK-NEXT: bl use
; CHECK-NEXT: mov w8, #-6
; CHECK-NEXT: sub w0, w8, w19
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = add i32 %arg, 8
call void @use(i32 %t0)
@ -252,15 +252,15 @@ define i32 @sub_const_add_const(i32 %arg) {
define i32 @sub_const_add_const_extrause(i32 %arg) {
; CHECK-LABEL: sub_const_add_const_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: sub w0, w0, #8 // =8
; CHECK-NEXT: bl use
; CHECK-NEXT: sub w0, w19, #6 // =6
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = sub i32 %arg, 8
call void @use(i32 %t0)
@ -329,15 +329,15 @@ define i32 @sub_const_sub_const(i32 %arg) {
define i32 @sub_const_sub_const_extrause(i32 %arg) {
; CHECK-LABEL: sub_const_sub_const_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: sub w0, w0, #8 // =8
; CHECK-NEXT: bl use
; CHECK-NEXT: sub w0, w19, #10 // =10
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = sub i32 %arg, 8
call void @use(i32 %t0)
@ -407,16 +407,16 @@ define i32 @sub_const_const_sub(i32 %arg) {
define i32 @sub_const_const_sub_extrause(i32 %arg) {
; CHECK-LABEL: sub_const_const_sub_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: sub w0, w0, #8 // =8
; CHECK-NEXT: bl use
; CHECK-NEXT: mov w8, #10
; CHECK-NEXT: sub w0, w8, w19
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = sub i32 %arg, 8
call void @use(i32 %t0)
@ -486,17 +486,17 @@ define i32 @const_sub_add_const(i32 %arg) {
define i32 @const_sub_add_const_extrause(i32 %arg) {
; CHECK-LABEL: const_sub_add_const_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w8, #8
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: sub w0, w8, w0
; CHECK-NEXT: bl use
; CHECK-NEXT: mov w8, #10
; CHECK-NEXT: sub w0, w8, w19
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = sub i32 8, %arg
call void @use(i32 %t0)
@ -566,17 +566,17 @@ define i32 @const_sub_sub_const(i32 %arg) {
define i32 @const_sub_sub_const_extrause(i32 %arg) {
; CHECK-LABEL: const_sub_sub_const_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w8, #8
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: sub w0, w8, w0
; CHECK-NEXT: bl use
; CHECK-NEXT: mov w8, #6
; CHECK-NEXT: sub w0, w8, w19
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = sub i32 8, %arg
call void @use(i32 %t0)
@ -645,17 +645,17 @@ define i32 @const_sub_const_sub(i32 %arg) {
define i32 @const_sub_const_sub_extrause(i32 %arg) {
; CHECK-LABEL: const_sub_const_sub_extrause:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w19, -16
; CHECK-NEXT: mov w8, #8
; CHECK-NEXT: sub w19, w8, w0
; CHECK-NEXT: mov w0, w19
; CHECK-NEXT: bl use
; CHECK-NEXT: mov w8, #2
; CHECK-NEXT: sub w0, w8, w19
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%t0 = sub i32 8, %arg
call void @use(i32 %t0)

13
llvm/test/CodeGen/AArch64/alloca.ll
View File

@ -117,9 +117,9 @@ define void @test_alloca_large_frame(i64 %n) {
; CHECK-MACHO-LABEL: test_alloca_large_frame:
; CHECK: stp x29, x30, [sp, #-32]!
; CHECK: stp x28, x19, [sp, #16]
; CHECK: mov x29, sp
; CHECK: stp x28, x19, [sp, #-32]!
; CHECK: stp x29, x30, [sp, #16]
; CHECK: add x29, sp, #16
; CHECK: sub sp, sp, #1953, lsl #12
; CHECK: sub sp, sp, #512
@ -136,9 +136,9 @@ define void @test_alloca_large_frame(i64 %n) {
ret void
; CHECK: mov sp, x29
; CHECK: ldp x28, x19, [sp, #16]
; CHECK: ldp x29, x30, [sp], #32
; CHECK: sub sp, x29, #16
; CHECK: ldp x29, x30, [sp, #16]
; CHECK: ldp x28, x19, [sp], #32
; CHECK-MACHO: sub sp, x29, #16
; CHECK-MACHO: ldp x29, x30, [sp, #16]
@ -152,7 +152,6 @@ define void @test_scoped_alloca(i64 %n) {
; CHECK-LABEL: test_scoped_alloca:
%sp = call i8* @llvm.stacksave()
; CHECK: mov x29, sp
; CHECK: mov [[SAVED_SP:x[0-9]+]], sp
; CHECK: mov [[OLDSP:x[0-9]+]], sp

4
llvm/test/CodeGen/AArch64/arm64-alloca-frame-pointer-offset.ll
View File

@ -1,8 +1,8 @@
; RUN: llc -mtriple=arm64-eabi -mcpu=cyclone < %s | FileCheck %s
; CHECK: foo
; CHECK-DAG: str w[[REG0:[0-9]+]], [x29, #24]
; CHECK-DAG: str w[[REG0]], [x29, #28]
; CHECK-DAG: stur w[[REG0:[0-9]+]], [x29, #-24]
; CHECK-DAG: stur w[[REG0]], [x29, #-20]
define i32 @foo(i32 %a) nounwind {
%retval = alloca i32, align 4
%a.addr = alloca i32, align 4

12
llvm/test/CodeGen/AArch64/cgp-usubo.ll
View File

@ -151,10 +151,10 @@ end:
define i1 @usubo_ult_cmp_dominates_i64(i64 %x, i64 %y, i64* %p, i1 %cond) nounwind {
; CHECK-LABEL: usubo_ult_cmp_dominates_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str x30, [sp, #-48]! // 8-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT: str x22, [sp, #-48]! // 8-byte Folded Spill
; CHECK-NEXT: stp x21, x20, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w20, w3
; CHECK-NEXT: stp x22, x21, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT: tbz w3, #0, .LBB8_3
; CHECK-NEXT: // %bb.1: // %t
; CHECK-NEXT: cmp x0, x1
@ -172,9 +172,9 @@ define i1 @usubo_ult_cmp_dominates_i64(i64 %x, i64 %y, i64* %p, i1 %cond) nounwi
; CHECK-NEXT: .LBB8_3: // %f
; CHECK-NEXT: and w0, w20, #0x1
; CHECK-NEXT: .LBB8_4: // %f
; CHECK-NEXT: ldp x20, x19, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT: ldp x22, x21, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #48 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT: ldp x21, x20, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x22, [sp], #48 // 8-byte Folded Reload
; CHECK-NEXT: ret
entry:
br i1 %cond, label %t, label %f

1
llvm/test/CodeGen/AArch64/fast-isel-sp-adjust.ll
View File

@ -13,7 +13,6 @@
; CHECK-ERRORS: LLVM ERROR: FastISel missed call
; CHECK-LABEL: foo:
; CHECK: sub
; CHECK-DAG: mov x[[SP:[0-9]+]], sp
; CHECK-DAG: mov [[TMP:w[0-9]+]], #4104
; CHECK: mov w[[OFFSET:[0-9]+]], [[TMP]]

2
llvm/test/CodeGen/AArch64/irg_sp_tagp.ll
View File

@ -35,7 +35,7 @@ entry:
define void @realign() {
entry:
; CHECK-LABEL: realign:
; CHECK: mov x29, sp
; CHECK: add x29, sp, #16
; CHECK: and sp, x{{[0-9]*}}, #0xffffffffffffffc0
; CHECK: irg [[R:x[0-9]+]], sp{{$}}
; CHECK: addg x0, [[R]], #0, #1

2
llvm/test/CodeGen/AArch64/regress-w29-reserved-with-fp.ll
View File

@ -5,7 +5,7 @@ declare void @bar()
define void @test_w29_reserved() {
; CHECK-LABEL: test_w29_reserved:
; CHECK: mov x29, sp
; CHECK: add x29, sp, #{{[0-9]+}}
%val1 = load volatile i32, i32* @var
%val2 = load volatile i32, i32* @var

6
llvm/test/CodeGen/AArch64/reverse-csr-restore-seq.mir
View File

@ -97,10 +97,10 @@ body: |
B %bb.1
bb.1:
; CHECK: $x21, $x20 = frame-destroy LDPXi $sp, 2
; BEFORELDSTOPT-NEXT: $lr = frame-destroy LDRXui $sp, 0
; CHECK: $x20, $lr = frame-destroy LDPXi $sp, 2
; BEFORELDSTOPT-NEXT: $x21 = frame-destroy LDRXui $sp, 0
; BEFORELDSTOPT-NEXT: $sp = frame-destroy ADDXri $sp, 32, 0
; AFTERLDSTOPT-NEXT: early-clobber $sp, $lr = frame-destroy LDRXpost $sp, 32
; AFTERLDSTOPT-NEXT: early-clobber $sp, $x21 = frame-destroy LDRXpost $sp, 32
RET_ReallyLR
...

8
llvm/test/CodeGen/AArch64/seh-finally.ll
View File

@ -86,7 +86,7 @@ entry:
define void @stack_realign() #0 personality i8* bitcast (i32 (...)* @__C_specific_handler to i8*) {
entry:
; CHECK-LABEL: stack_realign
; CHECK: mov x29, sp
; CHECK: add x29, sp, #16
; CHECK: sub x9, sp, #64
; CHECK: and sp, x9, #0xffffffffffffffe0
; CHECK: mov x19, sp
@ -205,15 +205,15 @@ entry:
define void @vla_and_realign(i32 %n) #0 personality i8* bitcast (i32 (...)* @__C_specific_handler to i8*) {
entry:
; CHECK-LABEL: vla_and_realign
; CHECK: mov x29, sp
; CHECK: add x29, sp, #16
; CHECK: sub x9, sp, #64
; CHECK: and sp, x9, #0xffffffffffffffe0
; CHECK: mov x19, sp
; CHECK: mov x1, #-2
; CHECK: stur x1, [x19]
; CHECK: .set .Lvla_and_realign$frame_escape_0, 32
; CHECK: str w0, [x29, #28]
; CHECK: ldr w8, [x29, #28]
; CHECK: stur w0, [x29, #-4]
; CHECK: ldur w8, [x29, #-4]
; CHECK: mov x9, sp
; CHECK: str x9, [x19, #24]
; CHECK: str x8, [x19, #16]

2
llvm/test/CodeGen/AArch64/shadow-call-stack.ll
View File

@ -41,7 +41,7 @@ define i32 @f4() shadowcallstack {
%res12 = add i32 %res1, %res2
%res34 = add i32 %res3, %res4
%res1234 = add i32 %res12, %res34
; CHECK: ldp x30,{{.*}}, [sp
; CHECK: ldp {{.*}}x30, [sp
; CHECK: ldr x30, [x18, #-8]!
; CHECK: ret
ret i32 %res1234

2
llvm/test/CodeGen/AArch64/sink-copy-for-shrink-wrap.ll
View File

@ -4,7 +4,7 @@
; CHECK-NOT: stp
; CHECK-NOT: mov w{{[0-9]+}}, w0
; CHECK-LABEL: %bb.1:
; CHECK: stp {{.*}}x19
; CHECK: stp x19
; CHECK: mov w{{[0-9]+}}, w0
define i32 @shrinkwrapme(i32 %paramAcrossCall, i32 %paramNotAcrossCall) {

4
llvm/test/CodeGen/AArch64/spill-stack-realignment.mir
View File

@ -13,7 +13,7 @@ frameInfo:
# CHECK: id: 0, name: '', type: default, offset: -64, size: 4, alignment: 64
# CHECK-NEXT: stack-id: default
# CHECK-NEXT: local-offset: -64
# CHECK: id: 1, name: '', type: default, offset: -4, size: 4, alignment: 4
# CHECK: id: 1, name: '', type: default, offset: -20, size: 4, alignment: 4
# CHECK-NEXT: stack-id: default
# CHECK-NEXT: local-offset: -68
stack:
@ -23,7 +23,7 @@ stack:
# CHECK: body:
# CHECK: $sp = ANDXri killed ${{x[0-9]+}}, 7865
# CHECK: STRSui $s0, $sp, 0
# CHECK: STRSui $s0, $fp, 7
# CHECK: STURSi $s0, $fp, -4
body: |
bb.0.entry:
liveins: $s0

4
llvm/test/CodeGen/AArch64/sponentry.ll
View File

@ -38,8 +38,8 @@ define dso_local void @foo([24 x i64]*) {
; CHECK: foo:
; CHECK: sub sp, sp, #448
; CHECK: add x29, sp, #416
; CHECK: add x1, x29, #32
; CHECK: add x29, sp, #432
; CHECK: add x1, x29, #16
; CHECK: bl _setjmpex
; NOFP: sub sp, sp, #432

2
llvm/test/CodeGen/AArch64/stack-guard-reassign.ll
View File

@ -5,4 +5,4 @@
; CHECK-LABEL: fn:
; CHECK: adrp x8, __stack_chk_guard
; CHECK-NEXT: ldr x8, [x8, :lo12:__stack_chk_guard]
; CHECK-NEXT: stur x8, [x29, #-8]
; CHECK-NEXT: stur x8, [x29, #-24]

2
llvm/test/CodeGen/AArch64/stack-guard-vaarg.ll
View File

@ -9,7 +9,7 @@
; CHECK: ldr [[GUARD:x[0-9]+]]{{.*}}:lo12:__stack_chk_guard]
; Make sure the canary is placed relative to the frame pointer, not
; the stack pointer.
; CHECK: stur [[GUARD]], [x29, #-8]
; CHECK: stur [[GUARD]], [x29, #-24]
define void @test(i8* %i, ...) #0 {
entry:
%buf = alloca [10 x i8], align 1

16
llvm/test/CodeGen/AArch64/unfold-masked-merge-scalar-constmask-innerouter.ll
View File

@ -202,16 +202,16 @@ declare void @use32(i32) nounwind
define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_A_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w8, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: and w20, w8, #0xffff00
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 16776960
@ -223,15 +223,15 @@ define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
define i32 @in_multiuse_B_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_B_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w0, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: and w20, w0, #0xffff00
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 16776960

16
llvm/test/CodeGen/AArch64/unfold-masked-merge-scalar-constmask-interleavedbits.ll
View File

@ -208,16 +208,16 @@ declare void @use32(i32) nounwind
define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_A_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w8, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: and w20, w8, #0x55555555
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 1431655765
@ -229,15 +229,15 @@ define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
define i32 @in_multiuse_B_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_B_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w0, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: and w20, w0, #0x55555555
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 1431655765

16
llvm/test/CodeGen/AArch64/unfold-masked-merge-scalar-constmask-interleavedbytehalves.ll
View File

@ -204,16 +204,16 @@ declare void @use32(i32) nounwind
define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_A_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w8, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: and w20, w8, #0xf0f0f0f
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 252645135
@ -225,15 +225,15 @@ define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
define i32 @in_multiuse_B_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_B_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w0, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: and w20, w0, #0xf0f0f0f
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 252645135

16
llvm/test/CodeGen/AArch64/unfold-masked-merge-scalar-constmask-lowhigh.ll
View File

@ -197,16 +197,16 @@ declare void @use32(i32) nounwind
define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_A_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w8, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: and w20, w8, #0xffff
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 65535
@ -218,15 +218,15 @@ define i32 @in_multiuse_A_constmask(i32 %x, i32 %y, i32 %z) nounwind {
define i32 @in_multiuse_B_constmask(i32 %x, i32 %y, i32 %z) nounwind {
; CHECK-LABEL: in_multiuse_B_constmask:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w0, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: and w20, w0, #0xffff
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, 65535

16
llvm/test/CodeGen/AArch64/unfold-masked-merge-scalar-variablemask.ll
View File

@ -552,16 +552,16 @@ declare void @use32(i32) nounwind
define i32 @in_multiuse_A(i32 %x, i32 %y, i32 %z, i32 %mask) nounwind {
; CHECK-LABEL: in_multiuse_A:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w8, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: and w20, w8, w3
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, %mask
@ -572,15 +572,15 @@ define i32 @in_multiuse_A(i32 %x, i32 %y, i32 %z, i32 %mask) nounwind {
define i32 @in_multiuse_B(i32 %x, i32 %y, i32 %z, i32 %mask) nounwind {
; CHECK-LABEL: in_multiuse_B:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: str x20, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: eor w0, w0, w1
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp x19, x30, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: and w20, w0, w3
; CHECK-NEXT: bl use32
; CHECK-NEXT: eor w0, w20, w19
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ldp x19, x30, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x20, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
%n0 = xor i32 %x, %y
%n1 = and i32 %n0, %mask

6
llvm/test/CodeGen/AArch64/unreachable-emergency-spill-slot.mir
View File

@ -14,11 +14,11 @@ stack:
body: |
bb.0:
STRXui undef $x8, %stack.0, 0
; CHECK: STRXui undef $x8, $fp, 0
; CHECK: STURXi undef $x8, $fp, -24
B %bb.1
bb.1:
liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6, $x7, $x8, $x9, $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $x18, $x19, $x20, $x21, $x22, $x23, $x24, $x25, $x26, $x27, $x28
RET_ReallyLR implicit $x19, implicit $x20, implicit $x21, implicit $x22, implicit $x23, implicit $x24, implicit $x25, implicit $x26, implicit $x27, implicit $x28
liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6, $x7, $x8, $x9, $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $x18, $x19, $x20, $x21, $x22, $x23, $x24, $x25, $x26, $x27, $x28, $fp, $lr
RET_ReallyLR implicit $x21, implicit $x22, implicit $x23, implicit $x24, implicit $x25, implicit $x26, implicit $x27, implicit $x28
...
---
name: fpDoesNotFit

70
llvm/test/CodeGen/AArch64/win64_vararg.ll
View File

@ -103,21 +103,21 @@ declare i32 @__stdio_common_vsprintf(i64, i8*, i64, i8*, i8*, i8*) local_unnamed
declare i64* @__local_stdio_printf_options() local_unnamed_addr #4
; CHECK-LABEL: fp
; CHECK: stp x29, x30, [sp, #-96]
; CHECK: str x21, [sp, #16]
; CHECK: stp x19, x20, [sp, #32]
; CHECK: mov x29, sp
; CHECK: add x8, x29, #56
; CHECK: str x21, [sp, #-96]!
; CHECK: stp x19, x20, [sp, #16]
; CHECK: stp x29, x30, [sp, #32]
; CHECK: add x29, sp, #32
; CHECK: add x8, x29, #24
; CHECK: mov x19, x2
; CHECK: mov x20, x1
; CHECK: mov x21, x0
; CHECK: stp x3, x4, [x29, #56]
; CHECK: stp x5, x6, [x29, #72]
; CHECK: str x7, [x29, #88]
; CHECK: str x8, [x29, #24]
; CHECK: stp x3, x4, [x29, #24]
; CHECK: stp x5, x6, [x29, #40]
; CHECK: str x7, [x29, #56]
; CHECK: str x8, [sp, #8]
; CHECK: bl __local_stdio_printf_options
; CHECK: ldr x8, [x0]
; CHECK: add x5, x29, #56
; CHECK: add x5, x29, #24
; CHECK: mov x1, x21
; CHECK: mov x2, x20
; CHECK: orr x0, x8, #0x2
@ -126,9 +126,9 @@ declare i64* @__local_stdio_printf_options() local_unnamed_addr #4
; CHECK: bl __stdio_common_vsprintf
; CHECK: cmp w0, #0
; CHECK: csinv w0, w0, wzr, ge
; CHECK: ldp x19, x20, [sp, #32]
; CHECK: ldr x21, [sp, #16]
; CHECK: ldp x29, x30, [sp], #96
; CHECK: ldp x29, x30, [sp, #32]
; CHECK: ldp x19, x20, [sp, #16]
; CHECK: ldr x21, [sp], #96
; CHECK: ret
define i32 @fp(i8*, i64, i8*, ...) local_unnamed_addr #6 {
%4 = alloca i8*, align 8
@ -150,26 +150,26 @@ define i32 @fp(i8*, i64, i8*, ...) local_unnamed_addr #6 {
attributes #6 = { "no-frame-pointer-elim"="true" }
; CHECK-LABEL: vla
; CHECK: stp x29, x30, [sp, #-112]!
; CHECK: str x23, [sp, #16]
; CHECK: stp x21, x22, [sp, #32]
; CHECK: stp x19, x20, [sp, #48]
; CHECK: mov x29, sp
; CHECK: add x8, x29, #64
; CHECK: str x8, [x29, #24]
; CHECK: str x23, [sp, #-112]!
; CHECK: stp x21, x22, [sp, #16]
; CHECK: stp x19, x20, [sp, #32]
; CHECK: stp x29, x30, [sp, #48]
; CHECK: add x29, sp, #48
; CHECK: add x8, x29, #16
; CHECK: stur x8, [x29, #-40]
; CHECK: mov w8, w0
; CHECK: add x8, x8, #15
; CHECK: lsr x15, x8, #4
; CHECK: mov x19, x1
; CHECK: mov [[REG2:x[0-9]+]], sp
; CHECK: stp x2, x3, [x29, #64]
; CHECK: stp x4, x5, [x29, #80]
; CHECK: stp x6, x7, [x29, #96]
; CHECK: stp x2, x3, [x29, #16]
; CHECK: stp x4, x5, [x29, #32]
; CHECK: stp x6, x7, [x29, #48]
; CHECK: bl __chkstk
; CHECK: mov x8, sp
; CHECK: sub [[REG:x[0-9]+]], x8, x15, lsl #4
; CHECK: mov sp, [[REG]]
; CHECK: ldr [[REG3:x[0-9]+]], [x29, #24]
; CHECK: ldur [[REG3:x[0-9]+]], [x29, #-40]
; CHECK: sxtw [[REG4:x[0-9]+]], w0
; CHECK: bl __local_stdio_printf_options
; CHECK: ldr x8, [x0]
@ -181,11 +181,11 @@ attributes #6 = { "no-frame-pointer-elim"="true" }
; CHECK: mov x5, [[REG3]]
; CHECK: bl __stdio_common_vsprintf
; CHECK: mov sp, [[REG2]]
; CHECK: mov sp, x29
; CHECK: ldp x19, x20, [sp, #48]
; CHECK: ldp x21, x22, [sp, #32]
; CHECK: ldr x23, [sp, #16]
; CHECK: ldp x29, x30, [sp], #112
; CHECK: sub sp, x29, #48
; CHECK: ldp x29, x30, [sp, #48]
; CHECK: ldp x19, x20, [sp, #32]
; CHECK: ldp x21, x22, [sp, #16]
; CHECK: ldr x23, [sp], #112
; CHECK: ret
define void @vla(i32, i8*, ...) local_unnamed_addr {
%3 = alloca i8*, align 8
@ -212,9 +212,9 @@ declare void @llvm.stackrestore(i8*)
; CHECK-LABEL: snprintf
; CHECK-DAG: sub sp, sp, #96
; CHECK-DAG: str x30, [sp, #16]
; CHECK-DAG: str x21, [sp, #24]
; CHECK-DAG: stp x19, x20, [sp, #32]
; CHECK-DAG: str x21, [sp, #16]
; CHECK-DAG: stp x19, x20, [sp, #24]
; CHECK-DAG: str x30, [sp, #40]
; CHECK-DAG: add x8, sp, #56
; CHECK-DAG: mov x19, x2
; CHECK-DAG: mov x20, x1
@ -232,9 +232,9 @@ declare void @llvm.stackrestore(i8*)
; CHECK-DAG: mov x3, x19
; CHECK-DAG: mov x4, xzr
; CHECK-DAG: bl __stdio_common_vsprintf
; CHECK-DAG: ldr x30, [sp, #16]
; CHECK-DAG: ldr x21, [sp, #24]
; CHECK-DAG: ldp x19, x20, [sp, #32]
; CHECK-DAG: ldr x30, [sp, #40]
; CHECK-DAG: ldp x19, x20, [sp, #24]
; CHECK-DAG: ldr x21, [sp, #16]
; CHECK-DAG: cmp w0, #0
; CHECK-DAG: csinv w0, w0, wzr, ge
; CHECK-DAG: add sp, sp, #96

20
llvm/test/CodeGen/AArch64/wineh-frame5.mir
View File

@ -3,10 +3,12 @@
# Check multiple epilogues, save_reg, save_reg_x.
# CHECK-LABEL: bb.0.entry:
# CHECK: early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -4
# CHECK-NEXT: frame-setup SEH_SaveFPLR_X -32
# CHECK-NEXT: frame-setup STRXui killed $x19, $sp, 2
# CHECK-NEXT: frame-setup SEH_SaveReg 19, 16
# CHECK: early-clobber $sp = frame-setup STRXpre killed $x28, $sp, -32
# CHECK-NEXT: frame-setup SEH_SaveReg_X 28, -32
# CHECK-NEXT: frame-setup STRXui killed $x19, $sp, 1
# CHECK-NEXT: frame-setup SEH_SaveReg 19, 8
# CHECK-NEXT: frame-setup STRXui killed $lr, $sp, 2
# CHECK-NEXT: frame-setup SEH_SaveReg 30, 16
# CHECK-NEXT: $sp = frame-setup SUBXri $sp, 496, 0
# CHECK-NEXT: frame-setup SEH_StackAlloc 496
# CHECK-NEXT: frame-setup SEH_PrologEnd
@ -15,10 +17,12 @@
# CHECK: frame-destroy SEH_EpilogStart
# CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 496, 0
# CHECK-NEXT: frame-destroy SEH_StackAlloc 496
# CHECK-NEXT: $x19 = frame-destroy LDRXui $sp, 2
# CHECK-NEXT: frame-destroy SEH_SaveReg 19, 16
# CHECK-NEXT: early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 4
# CHECK-NEXT: frame-destroy SEH_SaveFPLR_X -32
# CHECK-NEXT: $lr = frame-destroy LDRXui $sp, 2
# CHECK-NEXT: frame-destroy SEH_SaveReg 30, 16
# CHECK-NEXT: $x19 = frame-destroy LDRXui $sp, 1
# CHECK-NEXT: frame-destroy SEH_SaveReg 19, 8
# CHECK-NEXT: early-clobber $sp, $x28 = frame-destroy LDRXpost $sp, 32
# CHECK-NEXT: frame-destroy SEH_SaveReg_X 28, -32
# CHECK-NEXT: frame-destroy SEH_EpilogEnd
# CHECK-NEXT: TCRETURNdi @"?func2@@YAHXZ", 0, csr_aarch64_aapcs, implicit $sp

12
llvm/test/CodeGen/AArch64/wineh-frame7.mir
View File

@ -3,8 +3,10 @@
# Test that stack probe results in Nop unwind codes in the prologue. Test
# save_fplr, save_reg_x and stack_alloc with multiple updates.
# CHECK: early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2
# CHECK-NEXT: frame-setup SEH_SaveFPLR_X -16
# CHECK: early-clobber $sp = frame-setup STRXpre killed $x28, $sp, -32
# CHECK-NEXT: frame-setup SEH_SaveReg_X 28, -32
# CHECK-NEXT: frame-setup STPXi killed $fp, killed $lr, $sp, 2
# CHECK-NEXT: frame-setup SEH_SaveFPLR 16
# CHECK-NEXT: $x15 = frame-setup MOVZXi 56009, 0
# CHECK-NEXT: frame-setup SEH_Nop
# CHECK-NEXT: $x15 = frame-setup MOVKXi $x15, 2, 16
@ -19,8 +21,10 @@
# CHECK-NEXT: frame-destroy SEH_StackAlloc 2990080
# CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 3216, 0
# CHECK-NEXT: frame-destroy SEH_StackAlloc 3216
# CHECK-NEXT: early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2
# CHECK-NEXT: frame-destroy SEH_SaveFPLR_X -16
# CHECK-NEXT: $fp, $lr = frame-destroy LDPXi $sp, 2
# CHECK-NEXT: frame-destroy SEH_SaveFPLR 16
# CHECK-NEXT: early-clobber $sp, $x28 = frame-destroy LDRXpost $sp, 32
# CHECK-NEXT: frame-destroy SEH_SaveReg_X 28, -32
# CHECK-NEXT: frame-destroy SEH_EpilogEnd
# CHECK-NEXT: RET_ReallyLR implicit killed $w0
--- |

12
llvm/test/CodeGen/AArch64/wineh-try-catch-realign.ll
View File

@ -9,17 +9,17 @@
; it shouldn't access the parent's frame via sp, and the prologue and
; epilogue should be symmetrical.
; CHECK-LABEL: "?catch$2@?0??a@@YAXXZ@4HA":
; CHECK: stp x29, x30, [sp, #-32]!
; CHECK-NEXT: str x28, [sp, #16]
; CHECK-NEXT: str x19, [sp, #24]
; CHECK: str x28, [sp, #-32]!
; CHECK-NEXT: str x19, [sp, #8]
; CHECK-NEXT: stp x29, x30, [sp, #16]
; CHECK-NEXT: add x0, x19, #64
; CHECK-NEXT: mov w1, wzr
; CHECK-NEXT: bl "?bb@@YAXPEAHH@Z"
; CHECK-NEXT: adrp x0, .LBB0_1
; CHECK-NEXT: add x0, x0, .LBB0_1
; CHECK-NEXT: ldr x19, [sp, #24]
; CHECK-NEXT: ldr x28, [sp, #16]
; CHECK-NEXT: ldp x29, x30, [sp], #32
; CHECK-NEXT: ldp x29, x30, [sp, #16]
; CHECK-NEXT: ldr x19, [sp, #8]
; CHECK-NEXT: ldr x28, [sp], #32
; CHECK-NEXT: ret

36
llvm/test/CodeGen/AArch64/wineh-try-catch.ll
View File

@ -15,11 +15,11 @@
; on-entry sp - 672. We check this offset in the table later on.
; CHECK-LABEL: "?func@@YAHXZ":
; CHECK: stp x29, x30, [sp, #-48]!
; CHECK: str x28, [sp, #16]
; CHECK: str x21, [sp, #24]
; CHECK: stp x19, x20, [sp, #32]
; CHECK: mov x29, sp
; CHECK: str x28, [sp, #-48]!
; CHECK: str x21, [sp, #8]
; CHECK: stp x19, x20, [sp, #16]
; CHECK: stp x29, x30, [sp, #32]
; CHECK: add x29, sp, #32
; CHECK: sub sp, sp, #624
; CHECK: mov x19, sp
; CHECK: mov x0, #-2
@ -47,10 +47,10 @@
; CHECK-LABEL: "?catch$2@?0??func@@YAHXZ@4HA":
; Check that the stack space is allocated only for the callee saved registers.
; CHECK: stp x29, x30, [sp, #-48]!
; CHECK: str x28, [sp, #16]
; CHECK: str x21, [sp, #24]
; CHECK: stp x19, x20, [sp, #32]
; CHECK: str x28, [sp, #-48]!
; CHECK: str x21, [sp, #8]
; CHECK: stp x19, x20, [sp, #16]
; CHECK: stp x29, x30, [sp, #32]
; CHECK: add x20, x19, #12
; Check that there are no further stack updates.
@ -87,18 +87,18 @@
; UNWIND: Prologue [
; UNWIND-NEXT: ; nop
; UNWIND-NEXT: ; sub sp, #624
; UNWIND-NEXT: ; mov fp, sp
; UNWIND-NEXT: ; stp x19, x20, [sp, #32]
; UNWIND-NEXT: ; str x21, [sp, #24]
; UNWIND-NEXT: ; str x28, [sp, #16]
; UNWIND-NEXT: ; stp x29, x30, [sp, #-48]!
; UNWIND-NEXT: ; add fp, sp, #32
; UNWIND-NEXT: ; stp x29, x30, [sp, #32]
; UNWIND-NEXT: ; stp x19, x20, [sp, #16]
; UNWIND-NEXT: ; str x21, [sp, #8]
; UNWIND-NEXT: ; str x28, [sp, #48]!
; UNWIND-NEXT: ; end
; UNWIND: Function: ?catch$2@?0??func@@YAHXZ@4HA
; UNWIND: Prologue [
; UNWIND-NEXT: ; stp x19, x20, [sp, #32]
; UNWIND-NEXT: ; str x21, [sp, #24]
; UNWIND-NEXT: ; str x28, [sp, #16]
; UNWIND-NEXT: ; stp x29, x30, [sp, #-48]!
; UNWIND-NEXT: ; stp x29, x30, [sp, #32]
; UNWIND-NEXT: ; stp x19, x20, [sp, #16]
; UNWIND-NEXT: ; str x21, [sp, #8]
; UNWIND-NEXT: ; str x28, [sp, #48]!
; UNWIND-NEXT: ; end
target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"

4
llvm/test/CodeGen/AArch64/wineh_shrinkwrap.mir
View File

@ -9,14 +9,14 @@
# The same test gets shrink wrapped on Linux ARM64.
# WIN64-LABEL: bb.0.entry:
# WIN64: early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -4
# WIN64: early-clobber $sp = frame-setup STRXpre killed $x28, $sp, -32
# WIN64-LABEL: bb.1:
# WIN64-LABEL: bb.2.if.then:
# LINUX-LABEL: bb.0.entry:
# LINUX-LABEL: bb.1:
# LINUX-LABEL: bb.2.if.then:
# LINUX: early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -32
# LINUX: early-clobber $sp = frame-setup STRXpre killed $x28, $sp, -32
--- |
; ModuleID = 'shrink.cpp'
target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"