Implement ISD::VAARG lowering on PPC32.

llvm-svn: 134005
This commit is contained in:
Roman Divacky 2011-06-28 15:30:42 +00:00
parent 2a31eb49c7
commit 4394e68c24
2 changed files with 290 additions and 5 deletions

View File

@ -215,10 +215,11 @@ PPCTargetLowering::PPCTargetLowering(PPCTargetMachine &TM)
setOperationAction(ISD::VASTART , MVT::Other, Custom);
// VAARG is custom lowered with the 32-bit SVR4 ABI.
if ( TM.getSubtarget<PPCSubtarget>().isSVR4ABI()
&& !TM.getSubtarget<PPCSubtarget>().isPPC64())
if (TM.getSubtarget<PPCSubtarget>().isSVR4ABI()
&& !TM.getSubtarget<PPCSubtarget>().isPPC64()) {
setOperationAction(ISD::VAARG, MVT::Other, Custom);
else
setOperationAction(ISD::VAARG, MVT::i64, Custom);
} else
setOperationAction(ISD::VAARG, MVT::Other, Expand);
// Use the default implementation.
@ -1262,9 +1263,110 @@ SDValue PPCTargetLowering::LowerSETCC(SDValue Op, SelectionDAG &DAG) const {
SDValue PPCTargetLowering::LowerVAARG(SDValue Op, SelectionDAG &DAG,
const PPCSubtarget &Subtarget) const {
SDNode *Node = Op.getNode();
EVT VT = Node->getValueType(0);
EVT PtrVT = DAG.getTargetLoweringInfo().getPointerTy();
SDValue InChain = Node->getOperand(0);
SDValue VAListPtr = Node->getOperand(1);
const Value *SV = cast<SrcValueSDNode>(Node->getOperand(2))->getValue();
DebugLoc dl = Node->getDebugLoc();
llvm_unreachable("VAARG not yet implemented for the SVR4 ABI!");
return SDValue(); // Not reached
assert(!Subtarget.isPPC64() && "LowerVAARG is PPC32 only");
// gpr_index
SDValue GprIndex = DAG.getExtLoad(ISD::ZEXTLOAD, dl, MVT::i32, InChain,
VAListPtr, MachinePointerInfo(SV), MVT::i8,
false, false, 0);
InChain = GprIndex.getValue(1);
if (VT == MVT::i64) {
// Check if GprIndex is even
SDValue GprAnd = DAG.getNode(ISD::AND, dl, MVT::i32, GprIndex,
DAG.getConstant(1, MVT::i32));
SDValue CC64 = DAG.getSetCC(dl, MVT::i32, GprAnd,
DAG.getConstant(0, MVT::i32), ISD::SETNE);
SDValue GprIndexPlusOne = DAG.getNode(ISD::ADD, dl, MVT::i32, GprIndex,
DAG.getConstant(1, MVT::i32));
// Align GprIndex to be even if it isn't
GprIndex = DAG.getNode(ISD::SELECT, dl, MVT::i32, CC64, GprIndexPlusOne,
GprIndex);
}
// fpr index is 1 byte after gpr
SDValue FprPtr = DAG.getNode(ISD::ADD, dl, PtrVT, VAListPtr,
DAG.getConstant(1, MVT::i32));
// fpr
SDValue FprIndex = DAG.getExtLoad(ISD::ZEXTLOAD, dl, MVT::i32, InChain,
FprPtr, MachinePointerInfo(SV), MVT::i8,
false, false, 0);
InChain = FprIndex.getValue(1);
SDValue RegSaveAreaPtr = DAG.getNode(ISD::ADD, dl, PtrVT, VAListPtr,
DAG.getConstant(8, MVT::i32));
SDValue OverflowAreaPtr = DAG.getNode(ISD::ADD, dl, PtrVT, VAListPtr,
DAG.getConstant(4, MVT::i32));
// areas
SDValue OverflowArea = DAG.getLoad(MVT::i32, dl, InChain, OverflowAreaPtr,
MachinePointerInfo(), false, false, 0);
InChain = OverflowArea.getValue(1);
SDValue RegSaveArea = DAG.getLoad(MVT::i32, dl, InChain, RegSaveAreaPtr,
MachinePointerInfo(), false, false, 0);
InChain = RegSaveArea.getValue(1);
// select overflow_area if index > 8
SDValue CC = DAG.getSetCC(dl, MVT::i32, VT.isInteger() ? GprIndex : FprIndex,
DAG.getConstant(8, MVT::i32), ISD::SETLT);
SDValue Area = DAG.getNode(ISD::SELECT, dl, MVT::i32, CC, RegSaveArea,
OverflowArea);
// adjustment constant gpr_index * 4/8
SDValue RegConstant = DAG.getNode(ISD::MUL, dl, MVT::i32,
VT.isInteger() ? GprIndex : FprIndex,
DAG.getConstant(VT.isInteger() ? 4 : 8,
MVT::i32));
// OurReg = RegSaveArea + RegConstant
SDValue OurReg = DAG.getNode(ISD::ADD, dl, PtrVT, RegSaveArea,
RegConstant);
// Floating types are 32 bytes into RegSaveArea
if (VT.isFloatingPoint())
OurReg = DAG.getNode(ISD::ADD, dl, PtrVT, OurReg,
DAG.getConstant(32, MVT::i32));
// increase {f,g}pr_index by 1 (or 2 if VT is i64)
SDValue IndexPlus1 = DAG.getNode(ISD::ADD, dl, MVT::i32,
VT.isInteger() ? GprIndex : FprIndex,
DAG.getConstant(VT == MVT::i64 ? 2 : 1,
MVT::i32));
InChain = DAG.getTruncStore(InChain, dl, IndexPlus1,
VT.isInteger() ? VAListPtr : FprPtr,
MachinePointerInfo(SV),
MVT::i8, false, false, 0);
// determine if we should load from reg_save_area or overflow_area
SDValue Result = DAG.getNode(ISD::SELECT, dl, PtrVT, CC, OurReg, OverflowArea);
// increase overflow_area by 4/8 if gpr/fpr > 8
SDValue OverflowAreaPlusN = DAG.getNode(ISD::ADD, dl, PtrVT, OverflowArea,
DAG.getConstant(VT.isInteger() ? 4 : 8,
MVT::i32));
OverflowArea = DAG.getNode(ISD::SELECT, dl, MVT::i32, CC, OverflowArea,
OverflowAreaPlusN);
InChain = DAG.getTruncStore(InChain, dl, OverflowArea,
OverflowAreaPtr,
MachinePointerInfo(),
MVT::i32, false, false, 0);
return DAG.getLoad(VT, dl, InChain, Result, MachinePointerInfo(), false, false, 0);
}
SDValue PPCTargetLowering::LowerTRAMPOLINE(SDValue Op,
@ -4429,11 +4531,27 @@ SDValue PPCTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
void PPCTargetLowering::ReplaceNodeResults(SDNode *N,
SmallVectorImpl<SDValue>&Results,
SelectionDAG &DAG) const {
const TargetMachine &TM = getTargetMachine();
DebugLoc dl = N->getDebugLoc();
switch (N->getOpcode()) {
default:
assert(false && "Do not know how to custom type legalize this operation!");
return;
case ISD::VAARG: {
if (!TM.getSubtarget<PPCSubtarget>().isSVR4ABI()
|| TM.getSubtarget<PPCSubtarget>().isPPC64())
return;
EVT VT = N->getValueType(0);
if (VT == MVT::i64) {
SDValue NewNode = LowerVAARG(SDValue(N, 1), DAG, PPCSubTarget);
Results.push_back(NewNode);
Results.push_back(NewNode.getValue(1));
}
return;
}
case ISD::FP_ROUND_INREG: {
assert(N->getValueType(0) == MVT::ppcf128);
assert(N->getOperand(0).getValueType() == MVT::ppcf128);

View File

@ -0,0 +1,167 @@
; RUN: llc -O0 < %s | FileCheck %s
;ModuleID = 'test.c'
target datalayout = "E-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32"
target triple = "powerpc-unknown-freebsd9.0"
%struct.__va_list_tag = type { i8, i8, i16, i8*, i8* }
@var1 = common global i64 0, align 8
@var2 = common global double 0.0, align 8
@var3 = common global i32 0, align 4
define void @ppcvaargtest(%struct.__va_list_tag* %ap) nounwind {
entry:
%x = va_arg %struct.__va_list_tag* %ap, i64; Get from r5,r6
; CHECK: lbz 4, 0(3)
; CHECK-NEXT: lwz 5, 4(3)
; CHECK-NEXT: rlwinm 6, 4, 0, 31, 31
; CHECK-NEXT: cmplwi 0, 6, 0
; CHECK-NEXT: addi 6, 4, 1
; CHECK-NEXT: stw 3, -4(1)
; CHECK-NEXT: stw 6, -8(1)
; CHECK-NEXT: stw 4, -12(1)
; CHECK-NEXT: stw 5, -16(1)
; CHECK-NEXT: bne 0, .LBB0_2
; CHECK-NEXT: # BB#1: # %entry
; CHECK-NEXT: lwz 3, -12(1)
; CHECK-NEXT: stw 3, -8(1)
; CHECK-NEXT: .LBB0_2: # %entry
; CHECK-NEXT: lwz 3, -8(1)
; CHECK-NEXT: lwz 4, -4(1)
; CHECK-NEXT: lwz 5, 8(4)
; CHECK-NEXT: slwi 6, 3, 2
; CHECK-NEXT: addi 7, 3, 2
; CHECK-NEXT: cmpwi 0, 3, 8
; CHECK-NEXT: lwz 3, -16(1)
; CHECK-NEXT: addi 8, 3, 4
; CHECK-NEXT: add 5, 5, 6
; CHECK-NEXT: mfcr 0 # cr0
; CHECK-NEXT: stw 0, -20(1)
; CHECK-NEXT: stw 5, -24(1)
; CHECK-NEXT: stw 3, -28(1)
; CHECK-NEXT: stw 7, -32(1)
; CHECK-NEXT: stw 8, -36(1)
; CHECK-NEXT: blt 0, .LBB0_4
; CHECK-NEXT: # BB#3: # %entry
; CHECK-NEXT: lwz 3, -36(1)
; CHECK-NEXT: stw 3, -28(1)
; CHECK-NEXT: .LBB0_4: # %entry
; CHECK-NEXT: lwz 3, -28(1)
; CHECK-NEXT: lwz 4, -32(1)
; CHECK-NEXT: lwz 5, -4(1)
; CHECK-NEXT: stb 4, 0(5)
; CHECK-NEXT: lwz 4, -24(1)
; CHECK-NEXT: lwz 0, -20(1)
; CHECK-NEXT: mtcrf 128, 0
; CHECK-NEXT: stw 3, -40(1)
; CHECK-NEXT: stw 4, -44(1)
; CHECK-NEXT: blt 0, .LBB0_6
; CHECK-NEXT: # BB#5: # %entry
; CHECK-NEXT: lwz 3, -16(1)
; CHECK-NEXT: stw 3, -44(1)
; CHECK-NEXT: .LBB0_6: # %entry
; CHECK-NEXT: lwz 3, -44(1)
; CHECK-NEXT: lwz 4, -40(1)
; CHECK-NEXT: lwz 5, -4(1)
; CHECK-NEXT: stw 4, 4(5)
store i64 %x, i64* @var1, align 8
; CHECK-NEXT: lis 4, var1@ha
; CHECK-NEXT: lwz 6, 4(3)
; CHECK-NEXT: lwz 3, 0(3)
; CHECK-NEXT: la 7, var1@l(4)
; CHECK-NEXT: stw 3, var1@l(4)
; CHECK-NEXT: stw 6, 4(7)
%y = va_arg %struct.__va_list_tag* %ap, double; From f1
; CHECK-NEXT: lbz 3, 1(5)
; CHECK-NEXT: lwz 4, 4(5)
; CHECK-NEXT: lwz 6, 8(5)
; CHECK-NEXT: slwi 7, 3, 3
; CHECK-NEXT: add 6, 6, 7
; CHECK-NEXT: addi 7, 3, 1
; CHECK-NEXT: cmpwi 0, 3, 8
; CHECK-NEXT: addi 3, 4, 8
; CHECK-NEXT: addi 6, 6, 32
; CHECK-NEXT: mr 8, 4
; CHECK-NEXT: mfcr 0 # cr0
; CHECK-NEXT: stw 0, -48(1)
; CHECK-NEXT: stw 4, -52(1)
; CHECK-NEXT: stw 6, -56(1)
; CHECK-NEXT: stw 7, -60(1)
; CHECK-NEXT: stw 3, -64(1)
; CHECK-NEXT: stw 8, -68(1)
; CHECK-NEXT: blt 0, .LBB0_8
; CHECK-NEXT: # BB#7: # %entry
; CHECK-NEXT: lwz 3, -64(1)
; CHECK-NEXT: stw 3, -68(1)
; CHECK-NEXT: .LBB0_8: # %entry
; CHECK-NEXT: lwz 3, -68(1)
; CHECK-NEXT: lwz 4, -60(1)
; CHECK-NEXT: lwz 5, -4(1)
; CHECK-NEXT: stb 4, 1(5)
; CHECK-NEXT: lwz 4, -56(1)
; CHECK-NEXT: lwz 0, -48(1)
; CHECK-NEXT: mtcrf 128, 0
; CHECK-NEXT: stw 4, -72(1)
; CHECK-NEXT: stw 3, -76(1)
; CHECK-NEXT: blt 0, .LBB0_10
; CHECK-NEXT: # BB#9: # %entry
; CHECK-NEXT: lwz 3, -52(1)
; CHECK-NEXT: stw 3, -72(1)
; CHECK-NEXT: .LBB0_10: # %entry
; CHECK-NEXT: lwz 3, -72(1)
; CHECK-NEXT: lwz 4, -76(1)
; CHECK-NEXT: lwz 5, -4(1)
; CHECK-NEXT: stw 4, 4(5)
; CHECK-NEXT: lfd 0, 0(3)
store double %y, double* @var2, align 8
; CHECK-NEXT: lis 3, var2@ha
; CHECK-NEXT: stfd 0, var2@l(3)
%z = va_arg %struct.__va_list_tag* %ap, i32; From r7
; CHECK-NEXT: lbz 3, 0(5)
; CHECK-NEXT: lwz 4, 4(5)
; CHECK-NEXT: lwz 6, 8(5)
; CHECK-NEXT: slwi 7, 3, 2
; CHECK-NEXT: addi 8, 3, 1
; CHECK-NEXT: cmpwi 0, 3, 8
; CHECK-NEXT: addi 3, 4, 4
; CHECK-NEXT: add 6, 6, 7
; CHECK-NEXT: mr 7, 4
; CHECK-NEXT: stw 6, -80(1)
; CHECK-NEXT: stw 8, -84(1)
; CHECK-NEXT: stw 3, -88(1)
; CHECK-NEXT: stw 4, -92(1)
; CHECK-NEXT: stw 7, -96(1)
; CHECK-NEXT: mfcr 0 # cr0
; CHECK-NEXT: stw 0, -100(1)
; CHECK-NEXT: blt 0, .LBB0_12
; CHECK-NEXT: # BB#11: # %entry
; CHECK-NEXT: lwz 3, -88(1)
; CHECK-NEXT: stw 3, -96(1)
; CHECK-NEXT: .LBB0_12: # %entry
; CHECK-NEXT: lwz 3, -96(1)
; CHECK-NEXT: lwz 4, -84(1)
; CHECK-NEXT: lwz 5, -4(1)
; CHECK-NEXT: stb 4, 0(5)
; CHECK-NEXT: lwz 4, -80(1)
; CHECK-NEXT: lwz 0, -100(1)
; CHECK-NEXT: mtcrf 128, 0
; CHECK-NEXT: stw 4, -104(1)
; CHECK-NEXT: stw 3, -108(1)
; CHECK-NEXT: blt 0, .LBB0_14
; CHECK-NEXT: # BB#13: # %entry
; CHECK-NEXT: lwz 3, -92(1)
; CHECK-NEXT: stw 3, -104(1)
; CHECK-NEXT: .LBB0_14: # %entry
; CHECK-NEXT: lwz 3, -104(1)
; CHECK-NEXT: lwz 4, -108(1)
; CHECK-NEXT: lwz 5, -4(1)
; CHECK-NEXT: stw 4, 4(5)
; CHECK-NEXT: lwz 3, 0(3)
store i32 %z, i32* @var3, align 4
; CHECK-NEXT: lis 4, var3@ha
; CHECK-NEXT: stw 3, var3@l(4)
ret void
; CHECK-NEXT: stw 5, -112(1)
; CHECK-NEXT: blr
}