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

[SystemZ] Generate XC loop for memset 0 of variable length. 

Benchmarking has shown that it is worthwhile to implement a variable length
memset of 0 with XC (exclusive or) like gcc does, instead of using a libcall.

This requires the use of the EXecute Relative Long (EXRL) instruction which
can now be done in a framework that can also be used with other target
instructions (not just XC).

Review: Ulrich Weigand

Differential Revision: https://reviews.llvm.org/D103865
This commit is contained in:
Jonas Paulsson 2021-06-04 19:32:03 -05:00
parent ddfb074a80
commit 37a92f3b03
7 changed files with 294 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
llvm/lib/Target/SystemZ/SystemZAsmPrinter.cpp
View File

@ -541,6 +541,30 @@ void SystemZAsmPrinter::emitInstruction(const MachineInstr *MI) {
LowerPATCHPOINT(*MI, Lower);
return;
case SystemZ::EXRL_Pseudo: {
unsigned TargetInsOpc = MI->getOperand(0).getImm();
Register LenMinus1Reg = MI->getOperand(1).getReg();
Register DestReg = MI->getOperand(2).getReg();
int64_t DestDisp = MI->getOperand(3).getImm();
Register SrcReg = MI->getOperand(4).getReg();
int64_t SrcDisp = MI->getOperand(5).getImm();
MCSymbol *DotSym = nullptr;
MCInst ET = MCInstBuilder(TargetInsOpc).addReg(DestReg)
.addImm(DestDisp).addImm(1).addReg(SrcReg).addImm(SrcDisp);
MCInstSTIPair ET_STI(ET, &MF->getSubtarget());
EXRLT2SymMap::iterator I = EXRLTargets2Sym.find(ET_STI);
if (I != EXRLTargets2Sym.end())
DotSym = I->second;
else
EXRLTargets2Sym[ET_STI] = DotSym = OutContext.createTempSymbol();
const MCSymbolRefExpr *Dot = MCSymbolRefExpr::create(DotSym, OutContext);
EmitToStreamer(
*OutStreamer,
MCInstBuilder(SystemZ::EXRL).addReg(LenMinus1Reg).addExpr(Dot));
return;
}
default:
Lower.lower(MI, LoweredMI);
break;
@ -698,6 +722,19 @@ void SystemZAsmPrinter::LowerPATCHPOINT(const MachineInstr &MI,
getSubtargetInfo());
}
void SystemZAsmPrinter::emitEXRLTargetInstructions() {
if (EXRLTargets2Sym.empty())
return;
// Switch to the .text section.
OutStreamer->SwitchSection(getObjFileLowering().getTextSection());
for (auto &I : EXRLTargets2Sym) {
OutStreamer->emitLabel(I.second);
const MCInstSTIPair &MCI_STI = I.first;
OutStreamer->emitInstruction(MCI_STI.first, *MCI_STI.second);
}
EXRLTargets2Sym.clear();
}
// Convert a SystemZ-specific constant pool modifier into the associated
// MCSymbolRefExpr variant kind.
static MCSymbolRefExpr::VariantKind
@ -746,6 +783,7 @@ bool SystemZAsmPrinter::PrintAsmMemoryOperand(const MachineInstr *MI,
}
void SystemZAsmPrinter::emitEndOfAsmFile(Module &M) {
emitEXRLTargetInstructions();
emitStackMaps(SM);
}

31
llvm/lib/Target/SystemZ/SystemZAsmPrinter.h
View File

@ -9,10 +9,11 @@
#ifndef LLVM_LIB_TARGET_SYSTEMZ_SYSTEMZASMPRINTER_H
#define LLVM_LIB_TARGET_SYSTEMZ_SYSTEMZASMPRINTER_H
#include "SystemZTargetMachine.h"
#include "SystemZMCInstLower.h"
#include "SystemZTargetMachine.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/StackMaps.h"
#include "llvm/MC/MCInstBuilder.h"
#include "llvm/Support/Compiler.h"
namespace llvm {
@ -26,6 +27,33 @@ class LLVM_LIBRARY_VISIBILITY SystemZAsmPrinter : public AsmPrinter {
private:
StackMaps SM;
typedef std::pair<MCInst, const MCSubtargetInfo *> MCInstSTIPair;
struct CmpMCInst {
bool operator()(const MCInstSTIPair &MCI_STI_A,
const MCInstSTIPair &MCI_STI_B) const {
if (MCI_STI_A.second != MCI_STI_B.second)
return uintptr_t(MCI_STI_A.second) < uintptr_t(MCI_STI_B.second);
const MCInst &A = MCI_STI_A.first;
const MCInst &B = MCI_STI_B.first;
assert(A.getNumOperands() == B.getNumOperands() &&
A.getNumOperands() == 5 && A.getOperand(2).getImm() == 1 &&
B.getOperand(2).getImm() == 1 && "Unexpected EXRL target MCInst");
if (A.getOpcode() != B.getOpcode())
return A.getOpcode() < B.getOpcode();
if (A.getOperand(0).getReg() != B.getOperand(0).getReg())
return A.getOperand(0).getReg() < B.getOperand(0).getReg();
if (A.getOperand(1).getImm() != B.getOperand(1).getImm())
return A.getOperand(1).getImm() < B.getOperand(1).getImm();
if (A.getOperand(3).getReg() != B.getOperand(3).getReg())
return A.getOperand(3).getReg() < B.getOperand(3).getReg();
if (A.getOperand(4).getImm() != B.getOperand(4).getImm())
return A.getOperand(4).getImm() < B.getOperand(4).getImm();
return false;
}
};
typedef std::map<MCInstSTIPair, MCSymbol *, CmpMCInst> EXRLT2SymMap;
EXRLT2SymMap EXRLTargets2Sym;
public:
SystemZAsmPrinter(TargetMachine &TM, std::unique_ptr<MCStreamer> Streamer)
: AsmPrinter(TM, std::move(Streamer)), SM(*this) {}
@ -49,6 +77,7 @@ private:
void LowerFENTRY_CALL(const MachineInstr &MI, SystemZMCInstLower &MCIL);
void LowerSTACKMAP(const MachineInstr &MI);
void LowerPATCHPOINT(const MachineInstr &MI, SystemZMCInstLower &Lower);
void emitEXRLTargetInstructions();
};
} // end namespace llvm

134
llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
View File

@ -7795,43 +7795,89 @@ MachineBasicBlock *SystemZTargetLowering::emitMemMemWrapper(
uint64_t DestDisp = MI.getOperand(1).getImm();
MachineOperand SrcBase = earlyUseOperand(MI.getOperand(2));
uint64_t SrcDisp = MI.getOperand(3).getImm();
uint64_t Length = MI.getOperand(4).getImm();
MachineOperand &LengthMO = MI.getOperand(4);
uint64_t ImmLength = LengthMO.isImm() ? LengthMO.getImm() : 0;
Register LenMinus1Reg =
LengthMO.isReg() ? LengthMO.getReg() : SystemZ::NoRegister;
// When generating more than one CLC, all but the last will need to
// branch to the end when a difference is found.
MachineBasicBlock *EndMBB = (Length > 256 && Opcode == SystemZ::CLC ?
SystemZ::splitBlockAfter(MI, MBB) : nullptr);
MachineBasicBlock *EndMBB = (ImmLength > 256 && Opcode == SystemZ::CLC
? SystemZ::splitBlockAfter(MI, MBB)
: nullptr);
// Check for the loop form, in which operand 5 is the trip count.
if (MI.getNumExplicitOperands() > 5) {
bool HaveSingleBase = DestBase.isIdenticalTo(SrcBase);
Register StartCountReg = MI.getOperand(5).getReg();
Register StartSrcReg = forceReg(MI, SrcBase, TII);
Register StartDestReg = (HaveSingleBase ? StartSrcReg :
forceReg(MI, DestBase, TII));
MachineBasicBlock *StartMBB = nullptr;
MachineBasicBlock *LoopMBB = nullptr;
MachineBasicBlock *NextMBB = nullptr;
MachineBasicBlock *DoneMBB = nullptr;
MachineBasicBlock *AllDoneMBB = nullptr;
bool HaveSingleBase = DestBase.isIdenticalTo(SrcBase);
Register StartSrcReg = forceReg(MI, SrcBase, TII);
Register StartDestReg =
(HaveSingleBase ? StartSrcReg : forceReg(MI, DestBase, TII));
const TargetRegisterClass *RC = &SystemZ::ADDR64BitRegClass;
Register ThisSrcReg = MRI.createVirtualRegister(RC);
Register ThisDestReg = (HaveSingleBase ? ThisSrcReg :
MRI.createVirtualRegister(RC));
Register ThisDestReg =
(HaveSingleBase ? ThisSrcReg : MRI.createVirtualRegister(RC));
Register NextSrcReg = MRI.createVirtualRegister(RC);
Register NextDestReg = (HaveSingleBase ? NextSrcReg :
MRI.createVirtualRegister(RC));
Register NextDestReg =
(HaveSingleBase ? NextSrcReg : MRI.createVirtualRegister(RC));
RC = &SystemZ::GR64BitRegClass;
Register ThisCountReg = MRI.createVirtualRegister(RC);
Register NextCountReg = MRI.createVirtualRegister(RC);
MachineBasicBlock *StartMBB = MBB;
MachineBasicBlock *DoneMBB = SystemZ::splitBlockBefore(MI, MBB);
MachineBasicBlock *LoopMBB = SystemZ::emitBlockAfter(StartMBB);
MachineBasicBlock *NextMBB =
(EndMBB ? SystemZ::emitBlockAfter(LoopMBB) : LoopMBB);
if (LengthMO.isReg()) {
AllDoneMBB = SystemZ::splitBlockBefore(MI, MBB);
StartMBB = SystemZ::emitBlockAfter(MBB);
LoopMBB = SystemZ::emitBlockAfter(StartMBB);
NextMBB = LoopMBB;
DoneMBB = SystemZ::emitBlockAfter(LoopMBB);
// StartMBB:
// # fall through to LoopMMB
MBB->addSuccessor(LoopMBB);
// MBB:
// # Jump to AllDoneMBB if LenMinus1Reg is -1, or fall thru to StartMBB.
BuildMI(MBB, DL, TII->get(SystemZ::CGHI))
.addReg(LenMinus1Reg).addImm(-1);
BuildMI(MBB, DL, TII->get(SystemZ::BRC))
.addImm(SystemZ::CCMASK_ICMP).addImm(SystemZ::CCMASK_CMP_EQ)
.addMBB(AllDoneMBB);
MBB->addSuccessor(AllDoneMBB);
MBB->addSuccessor(StartMBB);
// StartMBB:
// # Jump to DoneMBB if %StartCountReg is zero, or fall through to LoopMBB.
MBB = StartMBB;
BuildMI(MBB, DL, TII->get(SystemZ::CGHI))
.addReg(StartCountReg).addImm(0);
BuildMI(MBB, DL, TII->get(SystemZ::BRC))
.addImm(SystemZ::CCMASK_ICMP).addImm(SystemZ::CCMASK_CMP_EQ)
.addMBB(DoneMBB);
MBB->addSuccessor(DoneMBB);
MBB->addSuccessor(LoopMBB);
}
else {
StartMBB = MBB;
DoneMBB = SystemZ::splitBlockBefore(MI, MBB);
LoopMBB = SystemZ::emitBlockAfter(StartMBB);
NextMBB = (EndMBB ? SystemZ::emitBlockAfter(LoopMBB) : LoopMBB);
// StartMBB:
// # fall through to LoopMBB
MBB->addSuccessor(LoopMBB);
DestBase = MachineOperand::CreateReg(NextDestReg, false);
SrcBase = MachineOperand::CreateReg(NextSrcReg, false);
ImmLength &= 255;
if (EndMBB && !ImmLength)
// If the loop handled the whole CLC range, DoneMBB will be empty with
// CC live-through into EndMBB, so add it as live-in.
DoneMBB->addLiveIn(SystemZ::CC);
}
// LoopMBB:
// %ThisDestReg = phi [ %StartDestReg, StartMBB ],
@ -7846,7 +7892,6 @@ MachineBasicBlock *SystemZTargetLowering::emitMemMemWrapper(
//
// The prefetch is used only for MVC. The JLH is used only for CLC.
MBB = LoopMBB;
BuildMI(MBB, DL, TII->get(SystemZ::PHI), ThisDestReg)
.addReg(StartDestReg).addMBB(StartMBB)
.addReg(NextDestReg).addMBB(NextMBB);
@ -7882,7 +7927,6 @@ MachineBasicBlock *SystemZTargetLowering::emitMemMemWrapper(
//
// The AGHI, CGHI and JLH should be converted to BRCTG by later passes.
MBB = NextMBB;
BuildMI(MBB, DL, TII->get(SystemZ::LA), NextDestReg)
.addReg(ThisDestReg).addImm(256).addReg(0);
if (!HaveSingleBase)
@ -7898,18 +7942,39 @@ MachineBasicBlock *SystemZTargetLowering::emitMemMemWrapper(
MBB->addSuccessor(LoopMBB);
MBB->addSuccessor(DoneMBB);
DestBase = MachineOperand::CreateReg(NextDestReg, false);
SrcBase = MachineOperand::CreateReg(NextSrcReg, false);
Length &= 255;
if (EndMBB && !Length)
// If the loop handled the whole CLC range, DoneMBB will be empty with
// CC live-through into EndMBB, so add it as live-in.
DoneMBB->addLiveIn(SystemZ::CC);
MBB = DoneMBB;
if (LengthMO.isReg()) {
// DoneMBB:
// # Make PHIs for RemDestReg/RemSrcReg as the loop may or may not run.
// # Use EXecute Relative Long for the remainder of the bytes. The target
// instruction of the EXRL will have a length field of 1 since 0 is an
// illegal value. The number of bytes processed becomes (%LenMinus1Reg &
// 0xff) + 1.
// # Fall through to AllDoneMBB.
Register RemSrcReg = MRI.createVirtualRegister(&SystemZ::ADDR64BitRegClass);
Register RemDestReg = HaveSingleBase ? RemSrcReg
: MRI.createVirtualRegister(&SystemZ::ADDR64BitRegClass);
BuildMI(MBB, DL, TII->get(SystemZ::PHI), RemDestReg)
.addReg(StartDestReg).addMBB(StartMBB)
.addReg(NextDestReg).addMBB(LoopMBB);
if (!HaveSingleBase)
BuildMI(MBB, DL, TII->get(SystemZ::PHI), RemSrcReg)
.addReg(StartSrcReg).addMBB(StartMBB)
.addReg(NextSrcReg).addMBB(LoopMBB);
MRI.constrainRegClass(LenMinus1Reg, &SystemZ::ADDR64BitRegClass);
BuildMI(MBB, DL, TII->get(SystemZ::EXRL_Pseudo))
.addImm(Opcode)
.addReg(LenMinus1Reg)
.addReg(RemDestReg).addImm(DestDisp)
.addReg(RemSrcReg).addImm(SrcDisp);
MBB->addSuccessor(AllDoneMBB);
MBB = AllDoneMBB;
}
}
// Handle any remaining bytes with straight-line code.
while (Length > 0) {
uint64_t ThisLength = std::min(Length, uint64_t(256));
while (ImmLength > 0) {
uint64_t ThisLength = std::min(ImmLength, uint64_t(256));
// The previous iteration might have created out-of-range displacements.
// Apply them using LAY if so.
if (!isUInt<12>(DestDisp)) {
@ -7939,10 +8004,10 @@ MachineBasicBlock *SystemZTargetLowering::emitMemMemWrapper(
.setMemRefs(MI.memoperands());
DestDisp += ThisLength;
SrcDisp += ThisLength;
Length -= ThisLength;
ImmLength -= ThisLength;
// If there's another CLC to go, branch to the end if a difference
// was found.
if (EndMBB && Length > 0) {
if (EndMBB && ImmLength > 0) {
MachineBasicBlock *NextMBB = SystemZ::splitBlockBefore(MI, MBB);
BuildMI(MBB, DL, TII->get(SystemZ::BRC))
.addImm(SystemZ::CCMASK_ICMP).addImm(SystemZ::CCMASK_CMP_NE)
@ -8433,6 +8498,7 @@ MachineBasicBlock *SystemZTargetLowering::EmitInstrWithCustomInserter(
return emitMemMemWrapper(MI, MBB, SystemZ::OC);
case SystemZ::XCSequence:
case SystemZ::XCLoop:
case SystemZ::XCLoopVarLen:
return emitMemMemWrapper(MI, MBB, SystemZ::XC);
case SystemZ::CLCSequence:
case SystemZ::CLCLoop:

5
llvm/lib/Target/SystemZ/SystemZInstrFormats.td
View File

@ -5253,6 +5253,7 @@ multiclass CondUnaryRSYPseudoAndMemFold<string mnemonic,
// The Sequence form uses a straight-line sequence of instructions and
// the Loop form uses a loop of length-256 instructions followed by
// another instruction to handle the excess.
// The LoopVarLen form is for a loop with a non-constant length parameter.
multiclass MemorySS<string mnemonic, bits<8> opcode,
SDPatternOperator sequence, SDPatternOperator loop> {
def "" : SideEffectBinarySSa<mnemonic, opcode>;
@ -5265,6 +5266,10 @@ multiclass MemorySS<string mnemonic, bits<8> opcode,
imm64:$length, GR64:$count256),
[(loop bdaddr12only:$dest, bdaddr12only:$src,
imm64:$length, GR64:$count256)]>;
def LoopVarLen : Pseudo<(outs), (ins bdaddr12only:$dest, bdaddr12only:$src,
GR64:$length, GR64:$count256),
[(loop bdaddr12only:$dest, bdaddr12only:$src,
GR64:$length, GR64:$count256)]>;
}
}

8
llvm/lib/Target/SystemZ/SystemZInstrInfo.td
View File

@ -2165,8 +2165,12 @@ let Predicates = [FeatureDeflateConversion],
// Execute.
let hasSideEffects = 1 in {
def EX : SideEffectBinaryRX<"ex", 0x44, GR64>;
def EXRL : SideEffectBinaryRILPC<"exrl", 0xC60, GR64>;
def EX : SideEffectBinaryRX<"ex", 0x44, ADDR64>;
def EXRL : SideEffectBinaryRILPC<"exrl", 0xC60, ADDR64>;
let hasNoSchedulingInfo = 1 in
def EXRL_Pseudo : Pseudo<(outs), (ins i64imm:$TargetOpc, ADDR64:$lenMinus1,
bdaddr12only:$bdl1, bdaddr12only:$bd2),
[]>;
}
//===----------------------------------------------------------------------===//

16
llvm/lib/Target/SystemZ/SystemZSelectionDAGInfo.cpp
View File

@ -81,11 +81,12 @@ SDValue SystemZSelectionDAGInfo::EmitTargetCodeForMemset(
if (IsVolatile)
return SDValue();
auto *CByte = dyn_cast<ConstantSDNode>(Byte);
if (auto *CSize = dyn_cast<ConstantSDNode>(Size)) {
uint64_t Bytes = CSize->getZExtValue();
if (Bytes == 0)
return SDValue();
if (auto *CByte = dyn_cast<ConstantSDNode>(Byte)) {
if (CByte) {
// Handle cases that can be done using at most two of
// MVI, MVHI, MVHHI and MVGHI. The latter two can only be
// used if ByteVal is all zeros or all ones; in other casees,
@ -125,7 +126,6 @@ SDValue SystemZSelectionDAGInfo::EmitTargetCodeForMemset(
assert(Bytes >= 2 && "Should have dealt with 0- and 1-byte cases already");
// Handle the special case of a memset of 0, which can use XC.
auto *CByte = dyn_cast<ConstantSDNode>(Byte);
if (CByte && CByte->getZExtValue() == 0)
return emitMemMem(DAG, DL, SystemZISD::XC, SystemZISD::XC_LOOP,
Chain, Dst, Dst, Bytes);
@ -138,6 +138,18 @@ SDValue SystemZSelectionDAGInfo::EmitTargetCodeForMemset(
return emitMemMem(DAG, DL, SystemZISD::MVC, SystemZISD::MVC_LOOP,
Chain, DstPlus1, Dst, Bytes - 1);
}
// Variable length
if (CByte && CByte->getZExtValue() == 0) {
// Handle the special case of a variable length memset of 0 with XC.
SDValue LenMinus1 = DAG.getNode(ISD::ADD, DL, MVT::i64,
DAG.getZExtOrTrunc(Size, DL, MVT::i64),
DAG.getConstant(-1, DL, MVT::i64));
SDValue TripC = DAG.getNode(ISD::SRL, DL, MVT::i64, LenMinus1,
DAG.getConstant(8, DL, MVT::i64));
return DAG.getNode(SystemZISD::XC_LOOP, DL, MVT::Other, Chain, Dst, Dst,
LenMinus1, TripC);
}
return SDValue();
}

101
llvm/test/CodeGen/SystemZ/memset-05.ll Normal file
View File

@ -0,0 +1,101 @@
; Test memset 0 with variable length
;
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
define void @fun0(i8* %Addr, i64 %Len) {
; CHECK-LABEL: fun0:
; CHECK: # %bb.0:
; CHECK-NEXT: aghi %r3, -1
; CHECK-NEXT: cgibe %r3, -1, 0(%r14)
; CHECK-NEXT: .LBB0_1:
; CHECK-NEXT: srlg %r0, %r3, 8
; CHECK-NEXT: cgije %r0, 0, .LBB0_3
; CHECK-NEXT: .LBB0_2: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: xc 0(256,%r2), 0(%r2)
; CHECK-NEXT: la %r2, 256(%r2)
; CHECK-NEXT: brctg %r0, .LBB0_2
; CHECK-NEXT: .LBB0_3:
; CHECK-NEXT: exrl %r3, .Ltmp0
; CHECK-NEXT: br %r14
tail call void @llvm.memset.p0i8.i64(i8* %Addr, i8 0, i64 %Len, i1 false)
ret void
}
define void @fun1(i8* %Addr, i32 %Len) {
; CHECK-LABEL: fun1:
; CHECK: # %bb.0:
; CHECK-NEXT: llgfr %r1, %r3
; CHECK-NEXT: aghi %r1, -1
; CHECK-NEXT: cgibe %r1, -1, 0(%r14)
; CHECK-NEXT: .LBB1_1:
; CHECK-NEXT: srlg %r0, %r1, 8
; CHECK-NEXT: cgije %r0, 0, .LBB1_3
; CHECK-NEXT: .LBB1_2: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: xc 0(256,%r2), 0(%r2)
; CHECK-NEXT: la %r2, 256(%r2)
; CHECK-NEXT: brctg %r0, .LBB1_2
; CHECK-NEXT: .LBB1_3:
; CHECK-NEXT: exrl %r1, .Ltmp0
; CHECK-NEXT: br %r14
tail call void @llvm.memset.p0i8.i32(i8* %Addr, i8 0, i32 %Len, i1 false)
ret void
}
; Test that identical target instructions get reused.
define void @fun2(i8* %Addr, i32 %Len) {
; CHECK-LABEL: fun2:
; CHECK: # %bb.0:
; CHECK-NEXT: llgfr %r1, %r3
; CHECK-NEXT: aghi %r1, -1
; CHECK-NEXT: srlg %r0, %r1, 8
; CHECK-NEXT: cgije %r1, -1, .LBB2_5
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: lgr %r3, %r2
; CHECK-NEXT: cgije %r0, 0, .LBB2_4
; CHECK-NEXT: # %bb.2:
; CHECK-NEXT: lgr %r3, %r2
; CHECK-NEXT: lgr %r4, %r0
; CHECK-NEXT: .LBB2_3: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: xc 0(256,%r3), 0(%r3)
; CHECK-NEXT: la %r3, 256(%r3)
; CHECK-NEXT: brctg %r4, .LBB2_3
; CHECK-NEXT: .LBB2_4:
; CHECK-NEXT: exrl %r1, .Ltmp1
; CHECK-NEXT: .LBB2_5:
; CHECK-NEXT: cgije %r1, -1, .LBB2_10
; CHECK-NEXT: # %bb.6:
; CHECK-NEXT: lgr %r3, %r2
; CHECK-NEXT: cgije %r0, 0, .LBB2_9
; CHECK-NEXT: # %bb.7:
; CHECK-NEXT: lgr %r3, %r2
; CHECK-NEXT: lgr %r4, %r0
; CHECK-NEXT: .LBB2_8: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: xc 0(256,%r3), 0(%r3)
; CHECK-NEXT: la %r3, 256(%r3)
; CHECK-NEXT: brctg %r4, .LBB2_8
; CHECK-NEXT: .LBB2_9:
; CHECK-NEXT: exrl %r1, .Ltmp1
; CHECK-NEXT: .LBB2_10:
; CHECK-NEXT: cgibe %r1, -1, 0(%r14)
; CHECK-NEXT: .LBB2_11:
; CHECK-NEXT: cgije %r0, 0, .LBB2_13
; CHECK-NEXT: .LBB2_12: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: xc 0(256,%r2), 0(%r2)
; CHECK-NEXT: la %r2, 256(%r2)
; CHECK-NEXT: brctg %r0, .LBB2_12
; CHECK-NEXT: .LBB2_13:
; CHECK-NEXT: exrl %r1, .Ltmp0
; CHECK-NEXT: br %r14
tail call void @llvm.memset.p0i8.i32(i8* %Addr, i8 0, i32 %Len, i1 false)
tail call void @llvm.memset.p0i8.i32(i8* %Addr, i8 0, i32 %Len, i1 false)
tail call void @llvm.memset.p0i8.i32(i8* %Addr, i8 0, i32 %Len, i1 false)
ret void
}
; CHECK: .Ltmp0:
; CHECK-NEXT: xc 0(1,%r2), 0(%r2)
; CHECK-NEXT: .Ltmp1:
; CHECK-NEXT: xc 0(1,%r3), 0(%r3)
declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg)
declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i1 immarg)