forked from OSchip/llvm-project
PPC: Support dynamic allocas with large alignment
Support for dynamic stack alignments in the PPC backend has been unfinished, in part because it depends on dynamic stack realignment (which I only just recently implemented fully). Now we can also support dynamic allocas with higher than the default target stack alignment (16 bytes). In order to round-up the requested size to the maximum requested alignment, we need an additional register to hold the rounded-up size. We're already using one scavenged register to hold the previous stack-pointer value (which needs to be stored with the signal-safe stdux update), and so when we have dynamic allocas and a large alignment, we allocate two emergency spill slots for the scavenger. llvm-svn: 186562
This commit is contained in:
parent
213c4cb18c
commit
1860763c76
|
@ -1237,8 +1237,12 @@ PPCFrameLowering::addScavengingSpillSlot(MachineFunction &MF,
|
|||
RC->getAlignment(),
|
||||
false));
|
||||
|
||||
// Might we have over-aligned allocas?
|
||||
bool HasAlVars = MFI->hasVarSizedObjects() &&
|
||||
MFI->getMaxAlignment() > getStackAlignment();
|
||||
|
||||
// These kinds of spills might need two registers.
|
||||
if (spillsCR(MF) || spillsVRSAVE(MF))
|
||||
if (spillsCR(MF) || spillsVRSAVE(MF) || HasAlVars)
|
||||
RS->addScavengingFrameIndex(MFI->CreateStackObject(RC->getSize(),
|
||||
RC->getAlignment(),
|
||||
false));
|
||||
|
|
|
@ -269,8 +269,8 @@ void PPCRegisterInfo::lowerDynamicAlloc(MachineBasicBlock::iterator II) const {
|
|||
// Get stack alignments.
|
||||
unsigned TargetAlign = MF.getTarget().getFrameLowering()->getStackAlignment();
|
||||
unsigned MaxAlign = MFI->getMaxAlignment();
|
||||
if (MaxAlign > TargetAlign)
|
||||
report_fatal_error("Dynamic alloca with large aligns not supported");
|
||||
assert((maxCallFrameSize & (MaxAlign-1)) == 0 &&
|
||||
"Maximum call-frame size not sufficiently aligned");
|
||||
|
||||
// Determine the previous frame's address. If FrameSize can't be
|
||||
// represented as 16 bits or we need special alignment, then we load the
|
||||
|
@ -296,39 +296,61 @@ void PPCRegisterInfo::lowerDynamicAlloc(MachineBasicBlock::iterator II) const {
|
|||
.addReg(PPC::R1);
|
||||
}
|
||||
|
||||
bool KillNegSizeReg = MI.getOperand(1).isKill();
|
||||
unsigned NegSizeReg = MI.getOperand(1).getReg();
|
||||
|
||||
// Grow the stack and update the stack pointer link, then determine the
|
||||
// address of new allocated space.
|
||||
if (LP64) {
|
||||
if (MaxAlign > TargetAlign) {
|
||||
unsigned UnalNegSizeReg = NegSizeReg;
|
||||
NegSizeReg = MF.getRegInfo().createVirtualRegister(G8RC);
|
||||
|
||||
// Unfortunately, there is no andi, only andi., and we can't insert that
|
||||
// here because we might clobber cr0 while it is live.
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::LI8), NegSizeReg)
|
||||
.addImm(~(MaxAlign-1));
|
||||
|
||||
unsigned NegSizeReg1 = NegSizeReg;
|
||||
NegSizeReg = MF.getRegInfo().createVirtualRegister(G8RC);
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::AND8), NegSizeReg)
|
||||
.addReg(UnalNegSizeReg, getKillRegState(KillNegSizeReg))
|
||||
.addReg(NegSizeReg1, RegState::Kill);
|
||||
KillNegSizeReg = true;
|
||||
}
|
||||
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::STDUX), PPC::X1)
|
||||
.addReg(Reg, RegState::Kill)
|
||||
.addReg(PPC::X1)
|
||||
.addReg(MI.getOperand(1).getReg());
|
||||
if (!MI.getOperand(1).isKill())
|
||||
.addReg(NegSizeReg, getKillRegState(KillNegSizeReg));
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::ADDI8), MI.getOperand(0).getReg())
|
||||
.addReg(PPC::X1)
|
||||
.addImm(maxCallFrameSize);
|
||||
else
|
||||
// Implicitly kill the register.
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::ADDI8), MI.getOperand(0).getReg())
|
||||
.addReg(PPC::X1)
|
||||
.addImm(maxCallFrameSize)
|
||||
.addReg(MI.getOperand(1).getReg(), RegState::ImplicitKill);
|
||||
} else {
|
||||
if (MaxAlign > TargetAlign) {
|
||||
unsigned UnalNegSizeReg = NegSizeReg;
|
||||
NegSizeReg = MF.getRegInfo().createVirtualRegister(GPRC);
|
||||
|
||||
// Unfortunately, there is no andi, only andi., and we can't insert that
|
||||
// here because we might clobber cr0 while it is live.
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::LI), NegSizeReg)
|
||||
.addImm(~(MaxAlign-1));
|
||||
|
||||
unsigned NegSizeReg1 = NegSizeReg;
|
||||
NegSizeReg = MF.getRegInfo().createVirtualRegister(GPRC);
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::AND), NegSizeReg)
|
||||
.addReg(UnalNegSizeReg, getKillRegState(KillNegSizeReg))
|
||||
.addReg(NegSizeReg1, RegState::Kill);
|
||||
KillNegSizeReg = true;
|
||||
}
|
||||
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::STWUX), PPC::R1)
|
||||
.addReg(Reg, RegState::Kill)
|
||||
.addReg(PPC::R1)
|
||||
.addReg(MI.getOperand(1).getReg());
|
||||
|
||||
if (!MI.getOperand(1).isKill())
|
||||
.addReg(NegSizeReg, getKillRegState(KillNegSizeReg));
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::ADDI), MI.getOperand(0).getReg())
|
||||
.addReg(PPC::R1)
|
||||
.addImm(maxCallFrameSize);
|
||||
else
|
||||
// Implicitly kill the register.
|
||||
BuildMI(MBB, II, dl, TII.get(PPC::ADDI), MI.getOperand(0).getReg())
|
||||
.addReg(PPC::R1)
|
||||
.addImm(maxCallFrameSize)
|
||||
.addReg(MI.getOperand(1).getReg(), RegState::ImplicitKill);
|
||||
}
|
||||
|
||||
// Discard the DYNALLOC instruction.
|
||||
|
|
|
@ -0,0 +1,39 @@
|
|||
; RUN: llc -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 < %s | FileCheck %s
|
||||
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
|
||||
target triple = "powerpc64-unknown-linux-gnu"
|
||||
|
||||
%struct.s = type { i32, i32 }
|
||||
|
||||
declare void @bar(i32*, i32*) #0
|
||||
|
||||
define void @goo(%struct.s* byval nocapture readonly %a, i32 signext %n) #0 {
|
||||
entry:
|
||||
%0 = zext i32 %n to i64
|
||||
%vla = alloca i32, i64 %0, align 128
|
||||
%vla1 = alloca i32, i64 %0, align 128
|
||||
%a2 = getelementptr inbounds %struct.s* %a, i64 0, i32 0
|
||||
%1 = load i32* %a2, align 4, !tbaa !0
|
||||
store i32 %1, i32* %vla1, align 128, !tbaa !0
|
||||
%b = getelementptr inbounds %struct.s* %a, i64 0, i32 1
|
||||
%2 = load i32* %b, align 4, !tbaa !0
|
||||
%arrayidx3 = getelementptr inbounds i32* %vla1, i64 1
|
||||
store i32 %2, i32* %arrayidx3, align 4, !tbaa !0
|
||||
call void @bar(i32* %vla1, i32* %vla) #0
|
||||
ret void
|
||||
|
||||
; CHECK-LABEL: @goo
|
||||
|
||||
; CHECK-DAG: li [[REG1:[0-9]+]], -128
|
||||
; CHECK-DAG: neg [[REG2:[0-9]+]],
|
||||
; CHECK: and [[REG1]], [[REG2]], [[REG1]]
|
||||
; CHECK: stdux {{[0-9]+}}, 1, [[REG1]]
|
||||
|
||||
; CHECK: blr
|
||||
|
||||
}
|
||||
|
||||
attributes #0 = { nounwind }
|
||||
|
||||
!0 = metadata !{metadata !"int", metadata !1}
|
||||
!1 = metadata !{metadata !"omnipotent char", metadata !2}
|
||||
!2 = metadata !{metadata !"Simple C/C++ TBAA"}
|
Loading…
Reference in New Issue