ARM: use NOEN loads and stores if possible when handling struct byval.

This change is to be enabled in clang.

rdar://9877866

llvm-svn: 158684
This commit is contained in:
Manman Ren 2012-06-18 22:23:48 +00:00
parent 28cd12f265
commit 6e1fd46fdf
2 changed files with 56 additions and 8 deletions

View File

@ -6260,11 +6260,12 @@ EmitStructByval(MachineInstr *MI, MachineBasicBlock *BB) const {
bool isThumb2 = Subtarget->isThumb2();
MachineFunction *MF = BB->getParent();
MachineRegisterInfo &MRI = MF->getRegInfo();
unsigned ldrOpc, strOpc, UnitSize;
unsigned ldrOpc, strOpc, UnitSize = 0;
const TargetRegisterClass *TRC = isThumb2 ?
(const TargetRegisterClass*)&ARM::tGPRRegClass :
(const TargetRegisterClass*)&ARM::GPRRegClass;
const TargetRegisterClass *TRC_Vec = 0;
if (Align & 1) {
ldrOpc = isThumb2 ? ARM::t2LDRB_POST : ARM::LDRB_POST_IMM;
@ -6275,10 +6276,30 @@ EmitStructByval(MachineInstr *MI, MachineBasicBlock *BB) const {
strOpc = isThumb2 ? ARM::t2STRH_POST : ARM::STRH_POST;
UnitSize = 2;
} else {
ldrOpc = isThumb2 ? ARM::t2LDR_POST : ARM::LDR_POST_IMM;
strOpc = isThumb2 ? ARM::t2STR_POST : ARM::STR_POST_IMM;
UnitSize = 4;
// Check whether we can use NEON instructions.
if (!MF->getFunction()->hasFnAttr(Attribute::NoImplicitFloat) &&
Subtarget->hasNEON()) {
if ((Align % 16 == 0) && SizeVal >= 16) {
ldrOpc = ARM::VLD1q32wb_fixed;
strOpc = ARM::VST1q32wb_fixed;
UnitSize = 16;
TRC_Vec = (const TargetRegisterClass*)&ARM::DPairRegClass;
}
else if ((Align % 8 == 0) && SizeVal >= 8) {
ldrOpc = ARM::VLD1d32wb_fixed;
strOpc = ARM::VST1d32wb_fixed;
UnitSize = 8;
TRC_Vec = (const TargetRegisterClass*)&ARM::DPRRegClass;
}
}
// Can't use NEON instructions.
if (UnitSize == 0) {
ldrOpc = isThumb2 ? ARM::t2LDR_POST : ARM::LDR_POST_IMM;
strOpc = isThumb2 ? ARM::t2STR_POST : ARM::STR_POST_IMM;
UnitSize = 4;
}
}
unsigned BytesLeft = SizeVal % UnitSize;
unsigned LoopSize = SizeVal - BytesLeft;
@ -6289,10 +6310,17 @@ EmitStructByval(MachineInstr *MI, MachineBasicBlock *BB) const {
unsigned srcIn = src;
unsigned destIn = dest;
for (unsigned i = 0; i < LoopSize; i+=UnitSize) {
unsigned scratch = MRI.createVirtualRegister(TRC);
unsigned scratch = MRI.createVirtualRegister(UnitSize >= 8 ? TRC_Vec:TRC);
unsigned srcOut = MRI.createVirtualRegister(TRC);
unsigned destOut = MRI.createVirtualRegister(TRC);
if (isThumb2) {
if (UnitSize >= 8) {
AddDefaultPred(BuildMI(*BB, MI, dl,
TII->get(ldrOpc), scratch)
.addReg(srcOut, RegState::Define).addReg(srcIn).addImm(0));
AddDefaultPred(BuildMI(*BB, MI, dl, TII->get(strOpc), destOut)
.addReg(destIn).addImm(0).addReg(scratch));
} else if (isThumb2) {
AddDefaultPred(BuildMI(*BB, MI, dl,
TII->get(ldrOpc), scratch)
.addReg(srcOut, RegState::Define).addReg(srcIn).addImm(UnitSize));
@ -6434,8 +6462,14 @@ EmitStructByval(MachineInstr *MI, MachineBasicBlock *BB) const {
// [scratch, srcLoop] = LDR_POST(srcPhi, UnitSize)
// [destLoop] = STR_POST(scratch, destPhi, UnitSiz)
unsigned scratch = MRI.createVirtualRegister(TRC);
if (isThumb2) {
unsigned scratch = MRI.createVirtualRegister(UnitSize >= 8 ? TRC_Vec:TRC);
if (UnitSize >= 8) {
AddDefaultPred(BuildMI(BB, dl, TII->get(ldrOpc), scratch)
.addReg(srcLoop, RegState::Define).addReg(srcPhi).addImm(0));
AddDefaultPred(BuildMI(BB, dl, TII->get(strOpc), destLoop)
.addReg(destPhi).addImm(0).addReg(scratch));
} else if (isThumb2) {
AddDefaultPred(BuildMI(BB, dl, TII->get(ldrOpc), scratch)
.addReg(srcLoop, RegState::Define).addReg(srcPhi).addImm(UnitSize));

View File

@ -28,5 +28,19 @@ entry:
ret i32 0
}
; Generate a loop using NEON instructions
define i32 @h() nounwind ssp {
entry:
; CHECK: h:
; CHECK: vld1
; CHECK: sub
; CHECK: vst1
; CHECK: bne
%st = alloca %struct.LargeStruct, align 16
%call = call i32 @e3(%struct.LargeStruct* byval align 16 %st)
ret i32 0
}
declare i32 @e1(%struct.SmallStruct* nocapture byval %in) nounwind
declare i32 @e2(%struct.LargeStruct* nocapture byval %in) nounwind
declare i32 @e3(%struct.LargeStruct* nocapture byval align 16 %in) nounwind