[llvm] [AMDGPU] ISel for @llvm.amdgcn.cs.chain intrinsic (PR #68186)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Oct 4 00:42:29 PDT 2023
https://github.com/rovka created https://github.com/llvm/llvm-project/pull/68186
The @llvm.amdgcn.cs.chain intrinsic is essentially a call. The call parameters are bundled up into 2 intrinsic arguments, one for those that should go in the SGPRs (the 3rd intrinsic argument), and one for those that should go in the VGPRs (the 4th intrinsic argument). Both will often be some kind of aggregate.
Both instruction selection frameworks have some internal representation for intrinsics (G_INTRINSIC[_WITH_SIDE_EFFECTS] for GlobalISel, ISD::INTRINSIC_[VOID|WITH_CHAIN] for DAGISel), but we can't use those because aggregates are dissolved very early on during ISel and we'd lose the inreg information. Therefore, this patch shortcircuits both the IRTranslator and SelectionDAGBuilder to lower this intrinsic as a call from the very start. It tries to use the existing infrastructure as much as possible, by calling into the code for lowering tail calls.
This has already gone through a few rounds of review in Phab:
Differential Revision: https://reviews.llvm.org/D153761
>From 64872d88ac2af6b50cb4c2d49b6eadb757c705f7 Mon Sep 17 00:00:00 2001
From: Diana Picus <Diana-Magda.Picus at amd.com>
Date: Wed, 4 Oct 2023 09:24:45 +0200
Subject: [PATCH] [AMDGPU] ISel for @llvm.amdgcn.cs.chain intrinsic
The @llvm.amdgcn.cs.chain intrinsic is essentially a call. The call
parameters are bundled up into 2 intrinsic arguments, one for those that
should go in the SGPRs (the 3rd intrinsic argument), and one for those
that should go in the VGPRs (the 4th intrinsic argument). Both will
often be some kind of aggregate.
Both instruction selection frameworks have some internal representation
for intrinsics (G_INTRINSIC[_WITH_SIDE_EFFECTS] for GlobalISel,
ISD::INTRINSIC_[VOID|WITH_CHAIN] for DAGISel), but we can't use those
because aggregates are dissolved very early on during ISel and we'd lose
the inreg information. Therefore, this patch shortcircuits both the
IRTranslator and SelectionDAGBuilder to lower this intrinsic as a call
from the very start. It tries to use the existing infrastructure as much
as possible, by calling into the code for lowering tail calls.
This has already gone through a few rounds of review in Phab:
Differential Revision: https://reviews.llvm.org/D153761
---
llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp | 3 +
.../SelectionDAG/SelectionDAGBuilder.cpp | 54 ++
llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp | 94 ++-
llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h | 3 +
llvm/lib/Target/AMDGPU/SIISelLowering.cpp | 58 +-
llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp | 5 +
.../irtranslator-amdgcn-cs-chain.ll | 129 ++++
.../test/CodeGen/AMDGPU/amdgpu-cs-chain-cc.ll | 424 ++++++++++++
.../AMDGPU/amdgpu-cs-chain-preserve-cc.ll | 501 +++++++++++++-
.../isel-amdgcn-cs-chain-intrinsic-w32.ll | 637 +++++++++++++++++
.../isel-amdgcn-cs-chain-intrinsic-w64.ll | 645 ++++++++++++++++++
11 files changed, 2537 insertions(+), 16 deletions(-)
create mode 100644 llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-amdgcn-cs-chain.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w32.ll
create mode 100644 llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w64.ll
diff --git a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
index 764567ac7baada6..cdbfba63932231c 100644
--- a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
@@ -62,6 +62,7 @@
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/PatternMatch.h"
@@ -2388,6 +2389,8 @@ bool IRTranslator::translateKnownIntrinsic(const CallInst &CI, Intrinsic::ID ID,
Info.OrigRet = {Register(), Type::getVoidTy(CI.getContext()), 0};
return CLI->lowerCall(MIRBuilder, Info);
}
+ case Intrinsic::amdgcn_cs_chain:
+ return translateCallBase(CI, MIRBuilder);
case Intrinsic::fptrunc_round: {
uint32_t Flags = MachineInstr::copyFlagsFromInstruction(CI);
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index c5fd56795a5201a..cf026fa293f6496 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -76,6 +76,7 @@
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/IntrinsicsAArch64.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
#include "llvm/IR/IntrinsicsWebAssembly.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Metadata.h"
@@ -7418,6 +7419,59 @@ void SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I,
setValue(&I, Val);
return;
}
+ case Intrinsic::amdgcn_cs_chain: {
+ assert(I.arg_size() == 5 && "Additional args not supported yet");
+ assert(cast<ConstantInt>(I.getOperand(4))->isZero() &&
+ "Non-zero flags not supported yet");
+
+ // At this point we don't care if it's amdgpu_cs_chain or
+ // amdgpu_cs_chain_preserve.
+ CallingConv::ID CC = CallingConv::AMDGPU_CS_Chain;
+
+ Type *RetTy = I.getType();
+ assert(RetTy->isVoidTy() && "Should not return");
+
+ SDValue Callee = getValue(I.getOperand(0));
+
+ // We only have 2 actual args: one for the SGPRs and one for the VGPRs.
+ TargetLowering::ArgListTy Args;
+ Args.reserve(2);
+
+ for (unsigned Idx : {2, 3}) {
+ TargetLowering::ArgListEntry Arg;
+ Arg.Node = getValue(I.getOperand(Idx));
+ Arg.Ty = I.getOperand(Idx)->getType();
+ Arg.setAttributes(&I, Idx);
+ Args.push_back(Arg);
+ }
+
+ assert(Args[0].IsInReg && "SGPR args should be marked inreg");
+ assert(!Args[1].IsInReg && "VGPR args should not be marked inreg");
+
+ // We're also going to pass the EXEC mask as the last argument.
+ TargetLowering::ArgListEntry Arg;
+ Arg.Node = getValue(I.getOperand(1));
+ Arg.Ty = I.getOperand(1)->getType();
+ Arg.IsInReg = true;
+ Args.push_back(Arg);
+
+ TargetLowering::CallLoweringInfo CLI(DAG);
+ CLI.setDebugLoc(getCurSDLoc())
+ .setChain(getRoot())
+ .setCallee(CC, RetTy, Callee, std::move(Args))
+ .setNoReturn(true)
+ .setTailCall(true)
+ .setConvergent(I.isConvergent());
+ CLI.CB = &I;
+ std::pair<SDValue, SDValue> Result =
+ lowerInvokable(CLI, /*EHPadBB*/ nullptr);
+ (void)Result;
+ assert(!Result.first.getNode() && !Result.second.getNode() &&
+ "Should've lowered as tail call");
+
+ HasTailCall = true;
+ return;
+ }
case Intrinsic::ptrmask: {
SDValue Ptr = getValue(I.getOperand(0));
SDValue Const = getValue(I.getOperand(1));
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
index db0f56416051f01..02e1a5aa818bc8f 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
@@ -958,8 +958,10 @@ getAssignFnsForCC(CallingConv::ID CC, const SITargetLowering &TLI) {
static unsigned getCallOpcode(const MachineFunction &CallerF, bool IsIndirect,
bool IsTailCall, CallingConv::ID CC) {
- assert(!(IsIndirect && IsTailCall) && "Indirect calls can't be tail calls, "
- "because the address can be divergent");
+ // For calls to amdgpu_cs_chain functions, the address is known to be uniform.
+ assert((AMDGPU::isChainCC(CC) || !IsIndirect || !IsTailCall) &&
+ "Indirect calls can't be tail calls, "
+ "because the address can be divergent");
if (!IsTailCall)
return AMDGPU::G_SI_CALL;
@@ -1150,14 +1152,20 @@ bool AMDGPUCallLowering::isEligibleForTailCallOptimization(
void AMDGPUCallLowering::handleImplicitCallArguments(
MachineIRBuilder &MIRBuilder, MachineInstrBuilder &CallInst,
const GCNSubtarget &ST, const SIMachineFunctionInfo &FuncInfo,
+ CallingConv::ID CalleeCC,
ArrayRef<std::pair<MCRegister, Register>> ImplicitArgRegs) const {
if (!ST.enableFlatScratch()) {
// Insert copies for the SRD. In the HSA case, this should be an identity
// copy.
auto ScratchRSrcReg = MIRBuilder.buildCopy(LLT::fixed_vector(4, 32),
FuncInfo.getScratchRSrcReg());
- MIRBuilder.buildCopy(AMDGPU::SGPR0_SGPR1_SGPR2_SGPR3, ScratchRSrcReg);
- CallInst.addReg(AMDGPU::SGPR0_SGPR1_SGPR2_SGPR3, RegState::Implicit);
+
+ auto CalleeRSrcReg = AMDGPU::isChainCC(CalleeCC)
+ ? AMDGPU::SGPR48_SGPR49_SGPR50_SGPR51
+ : AMDGPU::SGPR0_SGPR1_SGPR2_SGPR3;
+
+ MIRBuilder.buildCopy(CalleeRSrcReg, ScratchRSrcReg);
+ CallInst.addReg(CalleeRSrcReg, RegState::Implicit);
}
for (std::pair<MCRegister, Register> ArgReg : ImplicitArgRegs) {
@@ -1253,7 +1261,8 @@ bool AMDGPUCallLowering::lowerTailCall(
// after the ordinary user argument registers.
SmallVector<std::pair<MCRegister, Register>, 12> ImplicitArgRegs;
- if (Info.CallConv != CallingConv::AMDGPU_Gfx) {
+ if (Info.CallConv != CallingConv::AMDGPU_Gfx &&
+ !AMDGPU::isChainCC(Info.CallConv)) {
// With a fixed ABI, allocate fixed registers before user arguments.
if (!passSpecialInputs(MIRBuilder, CCInfo, ImplicitArgRegs, Info))
return false;
@@ -1269,7 +1278,8 @@ bool AMDGPUCallLowering::lowerTailCall(
if (!handleAssignments(Handler, OutArgs, CCInfo, ArgLocs, MIRBuilder))
return false;
- handleImplicitCallArguments(MIRBuilder, MIB, ST, *FuncInfo, ImplicitArgRegs);
+ handleImplicitCallArguments(MIRBuilder, MIB, ST, *FuncInfo, CalleeCC,
+ ImplicitArgRegs);
// If we have -tailcallopt, we need to adjust the stack. We'll do the call
// sequence start and end here.
@@ -1283,6 +1293,23 @@ bool AMDGPUCallLowering::lowerTailCall(
MIRBuilder.buildInstr(AMDGPU::ADJCALLSTACKDOWN).addImm(NumBytes).addImm(0);
}
+ // If this is a chain call, we need to set EXEC right before the call.
+ if (AMDGPU::isChainCC(Info.CallConv)) {
+ ArgInfo ExecArg = Info.OrigArgs[1];
+ assert(ExecArg.Regs.size() == 1 && "Too many regs for EXEC");
+
+ if (!ExecArg.Ty->isIntegerTy(ST.getWavefrontSize()))
+ return false;
+
+ unsigned MovOpc = ST.isWave32() ? AMDGPU::S_MOV_B32 : AMDGPU::S_MOV_B64;
+ MCRegister Exec = TRI->getExec();
+ auto SetExec =
+ MIRBuilder.buildInstr(MovOpc).addDef(Exec).addReg(ExecArg.Regs[0]);
+ SetExec->getOperand(1).setReg(constrainOperandRegClass(
+ MF, *TRI, MRI, *ST.getInstrInfo(), *ST.getRegBankInfo(), *SetExec,
+ SetExec->getDesc(), SetExec->getOperand(1), 1));
+ }
+
// Now we can add the actual call instruction to the correct basic block.
MIRBuilder.insertInstr(MIB);
@@ -1303,8 +1330,60 @@ bool AMDGPUCallLowering::lowerTailCall(
return true;
}
+/// Lower a call to the @llvm.amdgcn.cs.chain intrinsic.
+bool AMDGPUCallLowering::lowerChainCall(MachineIRBuilder &MIRBuilder,
+ CallLoweringInfo &Info) const {
+ ArgInfo Callee = Info.OrigArgs[0];
+ ArgInfo SGPRArgs = Info.OrigArgs[2];
+ ArgInfo VGPRArgs = Info.OrigArgs[3];
+ ArgInfo Flags = Info.OrigArgs[4];
+
+ assert(cast<ConstantInt>(Flags.OrigValue)->isZero() &&
+ "Non-zero flags aren't supported yet.");
+ assert(Info.OrigArgs.size() == 5 && "Additional args aren't supported yet.");
+
+ MachineFunction &MF = MIRBuilder.getMF();
+ const Function &F = MF.getFunction();
+ const DataLayout &DL = F.getParent()->getDataLayout();
+
+ // The function to jump to is actually the first argument, so we'll change the
+ // Callee and other info to match that before using our existing helper.
+ const Value *CalleeV = Callee.OrigValue->stripPointerCasts();
+ if (const Function *F = dyn_cast<Function>(CalleeV)) {
+ Info.Callee = MachineOperand::CreateGA(F, 0);
+ Info.CallConv = F->getCallingConv();
+ } else {
+ assert(Callee.Regs.size() == 1 && "Too many regs for the callee");
+ Info.Callee = MachineOperand::CreateReg(Callee.Regs[0], false);
+ Info.CallConv = CallingConv::AMDGPU_CS_Chain; // amdgpu_cs_chain_preserve
+ // behaves the same here.
+ }
+
+ // The function that we're calling cannot be vararg (only the intrinsic is).
+ Info.IsVarArg = false;
+
+ assert(std::all_of(SGPRArgs.Flags.begin(), SGPRArgs.Flags.end(),
+ [](ISD::ArgFlagsTy F) { return F.isInReg(); }) &&
+ "SGPR arguments should be marked inreg");
+ assert(std::none_of(VGPRArgs.Flags.begin(), VGPRArgs.Flags.end(),
+ [](ISD::ArgFlagsTy F) { return F.isInReg(); }) &&
+ "VGPR arguments should not be marked inreg");
+
+ SmallVector<ArgInfo, 8> OutArgs;
+ splitToValueTypes(SGPRArgs, OutArgs, DL, Info.CallConv);
+ splitToValueTypes(VGPRArgs, OutArgs, DL, Info.CallConv);
+
+ Info.IsMustTailCall = true;
+ return lowerTailCall(MIRBuilder, Info, OutArgs);
+}
+
bool AMDGPUCallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
CallLoweringInfo &Info) const {
+ if (Function *F = Info.CB->getCalledFunction())
+ if (F->isIntrinsic())
+ return F->getIntrinsicID() == Intrinsic::amdgcn_cs_chain &&
+ lowerChainCall(MIRBuilder, Info);
+
if (Info.IsVarArg) {
LLVM_DEBUG(dbgs() << "Variadic functions not implemented\n");
return false;
@@ -1395,7 +1474,8 @@ bool AMDGPUCallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
- handleImplicitCallArguments(MIRBuilder, MIB, ST, *MFI, ImplicitArgRegs);
+ handleImplicitCallArguments(MIRBuilder, MIB, ST, *MFI, Info.CallConv,
+ ImplicitArgRegs);
// Get a count of how many bytes are to be pushed on the stack.
unsigned NumBytes = CCInfo.getStackSize();
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h
index 569c6d75204d417..a6e801f2a547b53 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h
@@ -75,10 +75,13 @@ class AMDGPUCallLowering final : public CallLowering {
void handleImplicitCallArguments(
MachineIRBuilder &MIRBuilder, MachineInstrBuilder &CallInst,
const GCNSubtarget &ST, const SIMachineFunctionInfo &MFI,
+ CallingConv::ID CalleeCC,
ArrayRef<std::pair<MCRegister, Register>> ImplicitArgRegs) const;
bool lowerTailCall(MachineIRBuilder &MIRBuilder, CallLoweringInfo &Info,
SmallVectorImpl<ArgInfo> &OutArgs) const;
+ bool lowerChainCall(MachineIRBuilder &MIRBuilder,
+ CallLoweringInfo &Info) const;
bool lowerCall(MachineIRBuilder &MIRBuilder,
CallLoweringInfo &Info) const override;
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index f170428b38c49a5..8eadec5e0797831 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -3259,6 +3259,9 @@ bool SITargetLowering::isEligibleForTailCallOptimization(
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins, SelectionDAG &DAG) const {
+ if (AMDGPU::isChainCC(CalleeCC))
+ return true;
+
if (!mayTailCallThisCC(CalleeCC))
return false;
@@ -3343,7 +3346,36 @@ bool SITargetLowering::mayBeEmittedAsTailCall(const CallInst *CI) const {
// The wave scratch offset register is used as the global base pointer.
SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
SmallVectorImpl<SDValue> &InVals) const {
+ CallingConv::ID CallConv = CLI.CallConv;
+ bool IsChainCallConv = AMDGPU::isChainCC(CallConv);
+
SelectionDAG &DAG = CLI.DAG;
+
+ TargetLowering::ArgListEntry RequestedExec;
+ if (IsChainCallConv) {
+ // The last argument should be the value that we need to put in EXEC.
+ // Pop it out of CLI.Outs and CLI.OutVals before we do any processing so we
+ // don't treat it like the rest of the arguments.
+ RequestedExec = CLI.Args.back();
+ assert(RequestedExec.Node && "No node for EXEC");
+
+ if (!RequestedExec.Ty->isIntegerTy(Subtarget->getWavefrontSize()))
+ return lowerUnhandledCall(CLI, InVals, "Invalid value for EXEC");
+
+ assert(CLI.Outs.back().OrigArgIndex == 2 && "Unexpected last arg");
+ CLI.Outs.pop_back();
+ CLI.OutVals.pop_back();
+
+ if (RequestedExec.Ty->isIntegerTy(64)) {
+ assert(CLI.Outs.back().OrigArgIndex == 2 && "Exec wasn't split up");
+ CLI.Outs.pop_back();
+ CLI.OutVals.pop_back();
+ }
+
+ assert(CLI.Outs.back().OrigArgIndex != 2 &&
+ "Haven't popped all the pieces of the EXEC mask");
+ }
+
const SDLoc &DL = CLI.DL;
SmallVector<ISD::OutputArg, 32> &Outs = CLI.Outs;
SmallVector<SDValue, 32> &OutVals = CLI.OutVals;
@@ -3351,7 +3383,6 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
SDValue Chain = CLI.Chain;
SDValue Callee = CLI.Callee;
bool &IsTailCall = CLI.IsTailCall;
- CallingConv::ID CallConv = CLI.CallConv;
bool IsVarArg = CLI.IsVarArg;
bool IsSibCall = false;
bool IsThisReturn = false;
@@ -3382,9 +3413,10 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
if (IsTailCall) {
IsTailCall = isEligibleForTailCallOptimization(
Callee, CallConv, IsVarArg, Outs, OutVals, Ins, DAG);
- if (!IsTailCall && CLI.CB && CLI.CB->isMustTailCall()) {
+ if (!IsTailCall &&
+ ((CLI.CB && CLI.CB->isMustTailCall()) || IsChainCallConv)) {
report_fatal_error("failed to perform tail call elimination on a call "
- "site marked musttail");
+ "site marked musttail or to llvm.amdgcn.cs.chain");
}
bool TailCallOpt = MF.getTarget().Options.GuaranteedTailCallOpt;
@@ -3407,7 +3439,7 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
CCState CCInfo(CallConv, IsVarArg, MF, ArgLocs, *DAG.getContext());
CCAssignFn *AssignFn = CCAssignFnForCall(CallConv, IsVarArg);
- if (CallConv != CallingConv::AMDGPU_Gfx) {
+ if (CallConv != CallingConv::AMDGPU_Gfx && !AMDGPU::isChainCC(CallConv)) {
// With a fixed ABI, allocate fixed registers before user arguments.
passSpecialInputs(CLI, CCInfo, *Info, RegsToPass, MemOpChains, Chain);
}
@@ -3433,16 +3465,20 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
// Adjust the stack pointer for the new arguments...
// These operations are automatically eliminated by the prolog/epilog pass
- if (!IsSibCall) {
+ if (!IsSibCall)
Chain = DAG.getCALLSEQ_START(Chain, 0, 0, DL);
+ if (!IsSibCall || IsChainCallConv) {
if (!Subtarget->enableFlatScratch()) {
SmallVector<SDValue, 4> CopyFromChains;
// In the HSA case, this should be an identity copy.
SDValue ScratchRSrcReg
= DAG.getCopyFromReg(Chain, DL, Info->getScratchRSrcReg(), MVT::v4i32);
- RegsToPass.emplace_back(AMDGPU::SGPR0_SGPR1_SGPR2_SGPR3, ScratchRSrcReg);
+ RegsToPass.emplace_back(IsChainCallConv
+ ? AMDGPU::SGPR48_SGPR49_SGPR50_SGPR51
+ : AMDGPU::SGPR0_SGPR1_SGPR2_SGPR3,
+ ScratchRSrcReg);
CopyFromChains.push_back(ScratchRSrcReg.getValue(1));
Chain = DAG.getTokenFactor(DL, CopyFromChains);
}
@@ -3568,6 +3604,15 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
InGlue = Chain.getValue(1);
}
+ auto *TRI = static_cast<const SIRegisterInfo *>(Subtarget->getRegisterInfo());
+
+ if (IsChainCallConv) {
+ // Set EXEC right before the call.
+ MCRegister ExecReg = TRI->getExec();
+ Chain = DAG.getCopyToReg(Chain, DL, ExecReg, RequestedExec.Node, InGlue);
+ InGlue = Chain.getValue(1);
+ }
+
std::vector<SDValue> Ops;
Ops.push_back(Chain);
Ops.push_back(Callee);
@@ -3596,7 +3641,6 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
// Add a register mask operand representing the call-preserved registers.
- auto *TRI = static_cast<const SIRegisterInfo*>(Subtarget->getRegisterInfo());
const uint32_t *Mask = TRI->getCallPreservedMask(MF, CallConv);
assert(Mask && "Missing call preserved mask for calling convention");
Ops.push_back(DAG.getRegisterMask(Mask));
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index e065b104db4eb33..f4dde175063c089 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -421,6 +421,11 @@ const uint32_t *SIRegisterInfo::getCallPreservedMask(const MachineFunction &MF,
case CallingConv::AMDGPU_Gfx:
return ST.hasGFX90AInsts() ? CSR_AMDGPU_SI_Gfx_GFX90AInsts_RegMask
: CSR_AMDGPU_SI_Gfx_RegMask;
+ case CallingConv::AMDGPU_CS_Chain:
+ case CallingConv::AMDGPU_CS_ChainPreserve:
+ // Calls to these functions never return, so we can pretend everything is
+ // preserved.
+ return AMDGPU_AllVGPRs_RegMask;
default:
return nullptr;
}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-amdgcn-cs-chain.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-amdgcn-cs-chain.ll
new file mode 100644
index 000000000000000..15ebda007520e72
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-amdgcn-cs-chain.ll
@@ -0,0 +1,129 @@
+; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
+; RUN: llc --global-isel=1 -march=amdgcn -mcpu=gfx1100 -stop-after=irtranslator -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=GFX11
+; RUN: llc --global-isel=1 -march=amdgcn -mcpu=gfx1030 -stop-after=irtranslator -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=GFX10
+
+declare amdgpu_cs_chain void @callee(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
+declare amdgpu_cs_chain_preserve void @callee_preserve(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
+declare void @llvm.amdgcn.cs.chain(ptr, i32, <3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 }, i32, ...) noreturn
+
+define amdgpu_cs_chain void @chain_call(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GFX11-LABEL: name: chain_call
+ ; GFX11: bb.1 (%ir-block.0):
+ ; GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; GFX11-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; GFX11-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; GFX11-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
+ ; GFX11-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
+ ; GFX11-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
+ ; GFX11-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
+ ; GFX11-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
+ ; GFX11-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee
+ ; GFX11-NEXT: [[C:%[0-9]+]]:sreg_32(s32) = G_CONSTANT i32 -1
+ ; GFX11-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; GFX11-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee
+ ; GFX11-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
+ ; GFX11-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; GFX11-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; GFX11-NEXT: $sgpr2 = COPY [[UV2]](s32)
+ ; GFX11-NEXT: $vgpr8 = COPY [[COPY3]](s32)
+ ; GFX11-NEXT: $vgpr9 = COPY [[COPY4]](p5)
+ ; GFX11-NEXT: $vgpr10 = COPY [[COPY5]](s32)
+ ; GFX11-NEXT: $vgpr11 = COPY [[COPY6]](s32)
+ ; GFX11-NEXT: $exec_lo = S_MOV_B32 [[C]](s32)
+ ; GFX11-NEXT: SI_TCRETURN [[GV1]](p0), @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GFX10-LABEL: name: chain_call
+ ; GFX10: bb.1 (%ir-block.0):
+ ; GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; GFX10-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
+ ; GFX10-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee
+ ; GFX10-NEXT: [[C:%[0-9]+]]:sreg_32(s32) = G_CONSTANT i32 -1
+ ; GFX10-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; GFX10-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee
+ ; GFX10-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
+ ; GFX10-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; GFX10-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; GFX10-NEXT: $sgpr2 = COPY [[UV2]](s32)
+ ; GFX10-NEXT: $vgpr8 = COPY [[COPY3]](s32)
+ ; GFX10-NEXT: $vgpr9 = COPY [[COPY4]](p5)
+ ; GFX10-NEXT: $vgpr10 = COPY [[COPY5]](s32)
+ ; GFX10-NEXT: $vgpr11 = COPY [[COPY6]](s32)
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]](<4 x s32>)
+ ; GFX10-NEXT: $exec_lo = S_MOV_B32 [[C]](s32)
+ ; GFX10-NEXT: SI_TCRETURN [[GV1]](p0), @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_preserve_call(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GFX11-LABEL: name: chain_preserve_call
+ ; GFX11: bb.1 (%ir-block.0):
+ ; GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; GFX11-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; GFX11-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; GFX11-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
+ ; GFX11-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
+ ; GFX11-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
+ ; GFX11-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
+ ; GFX11-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
+ ; GFX11-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee_preserve
+ ; GFX11-NEXT: [[C:%[0-9]+]]:sreg_32(s32) = G_CONSTANT i32 -1
+ ; GFX11-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; GFX11-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee_preserve
+ ; GFX11-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
+ ; GFX11-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; GFX11-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; GFX11-NEXT: $sgpr2 = COPY [[UV2]](s32)
+ ; GFX11-NEXT: $vgpr8 = COPY [[COPY3]](s32)
+ ; GFX11-NEXT: $vgpr9 = COPY [[COPY4]](p5)
+ ; GFX11-NEXT: $vgpr10 = COPY [[COPY5]](s32)
+ ; GFX11-NEXT: $vgpr11 = COPY [[COPY6]](s32)
+ ; GFX11-NEXT: $exec_lo = S_MOV_B32 [[C]](s32)
+ ; GFX11-NEXT: SI_TCRETURN [[GV1]](p0), @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GFX10-LABEL: name: chain_preserve_call
+ ; GFX10: bb.1 (%ir-block.0):
+ ; GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; GFX10-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
+ ; GFX10-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee_preserve
+ ; GFX10-NEXT: [[C:%[0-9]+]]:sreg_32(s32) = G_CONSTANT i32 -1
+ ; GFX10-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; GFX10-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee_preserve
+ ; GFX10-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
+ ; GFX10-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; GFX10-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; GFX10-NEXT: $sgpr2 = COPY [[UV2]](s32)
+ ; GFX10-NEXT: $vgpr8 = COPY [[COPY3]](s32)
+ ; GFX10-NEXT: $vgpr9 = COPY [[COPY4]](p5)
+ ; GFX10-NEXT: $vgpr10 = COPY [[COPY5]](s32)
+ ; GFX10-NEXT: $vgpr11 = COPY [[COPY6]](s32)
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]](<4 x s32>)
+ ; GFX10-NEXT: $exec_lo = S_MOV_B32 [[C]](s32)
+ ; GFX10-NEXT: SI_TCRETURN [[GV1]](p0), @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-cc.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-cc.ll
index 7beaf3103586375..6600107c82e8141 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-cc.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-cc.ll
@@ -31,6 +31,8 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_no_stack({ptr, i32, <4 x i32>} inre
ret void
}
+; FIXME: Setup s32.
+
define amdgpu_cs_chain void @amdgpu_cs_chain_simple_call(<4 x i32> inreg %sgpr, <4 x i32> %vgpr) {
; GISEL-GFX11-LABEL: amdgpu_cs_chain_simple_call:
; GISEL-GFX11: ; %bb.0:
@@ -374,3 +376,425 @@ define amdgpu_cs_chain void @amdgpu_cs_chain_spill(<24 x i32> inreg %sgprs, <24
call amdgpu_gfx void @use(<24 x i32> %sgprs, <24 x i32> %vgprs)
ret void
}
+
+define amdgpu_cs void @cs_to_chain(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: cs_to_chain:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: v_dual_mov_b32 v3, v0 :: v_dual_mov_b32 v10, v2
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_dual_mov_b32 v8, v3 :: v_dual_mov_b32 v9, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: cs_to_chain:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_mov_b32 s100, SCRATCH_RSRC_DWORD0
+; GISEL-GFX10-NEXT: s_mov_b32 s101, SCRATCH_RSRC_DWORD1
+; GISEL-GFX10-NEXT: s_mov_b32 s102, -1
+; GISEL-GFX10-NEXT: s_mov_b32 s103, 0x31c16000
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v3, v0
+; GISEL-GFX10-NEXT: s_add_u32 s100, s100, s3
+; GISEL-GFX10-NEXT: s_addc_u32 s101, s101, 0
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b64 s[48:49], s[100:101]
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v9, v1
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v10, v2
+; GISEL-GFX10-NEXT: s_mov_b64 s[50:51], s[102:103]
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: cs_to_chain:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_dual_mov_b32 v3, v0 :: v_dual_mov_b32 v10, v2
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_dual_mov_b32 v8, v3 :: v_dual_mov_b32 v9, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: cs_to_chain:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_mov_b32 s100, SCRATCH_RSRC_DWORD0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s101, SCRATCH_RSRC_DWORD1
+; DAGISEL-GFX10-NEXT: s_mov_b32 s102, -1
+; DAGISEL-GFX10-NEXT: s_mov_b32 s103, 0x31c16000
+; DAGISEL-GFX10-NEXT: s_add_u32 s100, s100, s3
+; DAGISEL-GFX10-NEXT: s_addc_u32 s101, s101, 0
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v3, v0
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b64 s[48:49], s[100:101]
+; DAGISEL-GFX10-NEXT: s_mov_b64 s[50:51], s[102:103]
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v9, v1
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v10, v2
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_to_chain(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_to_chain:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: chain_to_chain:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: chain_to_chain:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_to_chain:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_to_chain_use_all_v0_v7(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_to_chain_use_all_v0_v7:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v11, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v11
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: chain_to_chain_use_all_v0_v7:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v11, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v11
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: chain_to_chain_use_all_v0_v7:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v11, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v11
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_to_chain_use_all_v0_v7:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v11, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v11
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_to_chain_fewer_args(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_to_chain_fewer_args:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s2, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s2
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[2:3]
+; GISEL-GFX11-NEXT: s_add_u32 s2, s2, chain_callee_2 at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s3, s3, chain_callee_2 at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[2:3], s[2:3], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[2:3]
+;
+; GISEL-GFX10-LABEL: chain_to_chain_fewer_args:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s2, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s2
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[2:3]
+; GISEL-GFX10-NEXT: s_add_u32 s2, s2, chain_callee_2 at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s3, s3, chain_callee_2 at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[2:3], s[2:3], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[2:3]
+;
+; DAGISEL-GFX11-LABEL: chain_to_chain_fewer_args:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee_2 at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee_2 at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s2, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s2
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_to_chain_fewer_args:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee_2 at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee_2 at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s2, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s2
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ %s = shufflevector <3 x i32> %a, <3 x i32> zeroinitializer, <2 x i32> <i32 0, i32 1>
+ %v = shufflevector <3 x i32> %b, <3 x i32> zeroinitializer, <2 x i32> <i32 0, i32 1>
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <2 x i32>, <2 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v2i32(ptr @chain_callee_2, i32 -1, <2 x i32> inreg %s, <2 x i32> %v, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_to_chain_more_args(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_to_chain_more_args:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_mov_b32 s3, 0
+; GISEL-GFX11-NEXT: v_dual_mov_b32 v8, v1 :: v_dual_mov_b32 v11, 0
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee_2 at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee_2 at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: chain_to_chain_more_args:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: s_mov_b32 s3, 0
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v11, 0
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee_2 at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee_2 at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: chain_to_chain_more_args:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee_2 at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee_2 at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, 0
+; DAGISEL-GFX11-NEXT: v_dual_mov_b32 v8, v1 :: v_dual_mov_b32 v11, 0
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_to_chain_more_args:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee_2 at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee_2 at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, 0
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v11, 0
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ %s = shufflevector <3 x i32> %a, <3 x i32> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ %v = shufflevector <3 x i32> %b, <3 x i32> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <4 x i32>, <4 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v4i32(ptr @chain_callee_2, i32 -1, <4 x i32> inreg %s, <4 x i32> %v, i32 0)
+ unreachable
+}
+
+declare void @llvm.amdgcn.cs.chain.v2i32(ptr, i32, <2 x i32>, <2 x i32>, i32, ...)
+declare void @llvm.amdgcn.cs.chain.v3i32(ptr, i32, <3 x i32>, <3 x i32>, i32, ...)
+declare void @llvm.amdgcn.cs.chain.v4i32(ptr, i32, <4 x i32>, <4 x i32>, i32, ...)
+declare amdgpu_cs_chain void @chain_callee_2(<2 x i32> inreg, <2 x i32>)
+declare amdgpu_cs_chain void @chain_callee(<3 x i32> inreg, <3 x i32>)
+declare amdgpu_cs_chain void @chain_callee_4(<4 x i32> inreg, <4 x i32>)
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-preserve-cc.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-preserve-cc.ll
index daa3d39a3afebd8..7257a68005e427f 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-preserve-cc.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-preserve-cc.ll
@@ -4,8 +4,6 @@
; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX11 %s
; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1030 -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX10 %s
-declare amdgpu_gfx void @use(...)
-
; FIXME: The values of the counters are undefined on entry to amdgpu_cs_chain_preserve functions, so these waits are unnecessary.
define amdgpu_cs_chain_preserve void @amdgpu_cs_chain_preserve_no_stack({ptr, i32, <4 x i32>} inreg %a, {ptr, i32, <4 x i32>} %b) {
@@ -30,3 +28,502 @@ define amdgpu_cs_chain_preserve void @amdgpu_cs_chain_preserve_no_stack({ptr, i3
; DAGISEL-GFX10-NEXT: s_endpgm
ret void
}
+
+define amdgpu_cs void @cs_to_chain_preserve(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: cs_to_chain_preserve:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: v_dual_mov_b32 v3, v0 :: v_dual_mov_b32 v10, v2
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_dual_mov_b32 v8, v3 :: v_dual_mov_b32 v9, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: cs_to_chain_preserve:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_mov_b32 s100, SCRATCH_RSRC_DWORD0
+; GISEL-GFX10-NEXT: s_mov_b32 s101, SCRATCH_RSRC_DWORD1
+; GISEL-GFX10-NEXT: s_mov_b32 s102, -1
+; GISEL-GFX10-NEXT: s_mov_b32 s103, 0x31c16000
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v3, v0
+; GISEL-GFX10-NEXT: s_add_u32 s100, s100, s3
+; GISEL-GFX10-NEXT: s_addc_u32 s101, s101, 0
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b64 s[48:49], s[100:101]
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v9, v1
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v10, v2
+; GISEL-GFX10-NEXT: s_mov_b64 s[50:51], s[102:103]
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: cs_to_chain_preserve:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_dual_mov_b32 v3, v0 :: v_dual_mov_b32 v10, v2
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_dual_mov_b32 v8, v3 :: v_dual_mov_b32 v9, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: cs_to_chain_preserve:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_mov_b32 s100, SCRATCH_RSRC_DWORD0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s101, SCRATCH_RSRC_DWORD1
+; DAGISEL-GFX10-NEXT: s_mov_b32 s102, -1
+; DAGISEL-GFX10-NEXT: s_mov_b32 s103, 0x31c16000
+; DAGISEL-GFX10-NEXT: s_add_u32 s100, s100, s3
+; DAGISEL-GFX10-NEXT: s_addc_u32 s101, s101, 0
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v3, v0
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b64 s[48:49], s[100:101]
+; DAGISEL-GFX10-NEXT: s_mov_b64 s[50:51], s[102:103]
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v9, v1
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v10, v2
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_preserve_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_to_chain_preserve(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_to_chain_preserve:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: chain_to_chain_preserve:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: chain_to_chain_preserve:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_to_chain_preserve:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_preserve_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+; FIXME: Preserve things (i.e. v16)!
+; FIXME: Setup s32.
+
+define amdgpu_cs_chain_preserve void @chain_preserve_to_chain_preserve(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_preserve_to_chain_preserve:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: chain_preserve_to_chain_preserve:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: chain_preserve_to_chain_preserve:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_preserve_to_chain_preserve:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_preserve_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_preserve_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_preserve_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain_preserve void @chain_preserve_to_chain(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_preserve_to_chain:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: chain_preserve_to_chain:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: chain_preserve_to_chain:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_preserve_to_chain:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain_preserve void @chain_preserve_to_chain_use_all_v0_v7(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_preserve_to_chain_use_all_v0_v7:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v11, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v11
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; GISEL-GFX10-LABEL: chain_preserve_to_chain_use_all_v0_v7:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v11, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v11
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; GISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX11-LABEL: chain_preserve_to_chain_use_all_v0_v7:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v11, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v11
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_preserve_to_chain_use_all_v0_v7:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_callee at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_callee at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v11, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s3, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s3
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v11
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ call void asm "s_nop", "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <3 x i32>, <3 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v3i32(ptr @chain_callee, i32 -1, <3 x i32> inreg %a, <3 x i32> %b, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain_preserve void @chain_preserve_to_chain_preserve_fewer_args(<3 x i32> inreg %a, <3 x i32> %b) {
+; GISEL-GFX11-LABEL: chain_preserve_to_chain_preserve_fewer_args:
+; GISEL-GFX11: ; %bb.0:
+; GISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX11-NEXT: s_mov_b32 s2, s0
+; GISEL-GFX11-NEXT: ;;#ASMSTART
+; GISEL-GFX11-NEXT: s_nop
+; GISEL-GFX11-NEXT: ;;#ASMEND
+; GISEL-GFX11-NEXT: s_mov_b32 s0, s2
+; GISEL-GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX11-NEXT: s_getpc_b64 s[2:3]
+; GISEL-GFX11-NEXT: s_add_u32 s2, s2, chain_preserve_callee_2 at gotpcrel32@lo+4
+; GISEL-GFX11-NEXT: s_addc_u32 s3, s3, chain_preserve_callee_2 at gotpcrel32@hi+12
+; GISEL-GFX11-NEXT: s_load_b64 s[2:3], s[2:3], 0x0
+; GISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX11-NEXT: s_setpc_b64 s[2:3]
+;
+; GISEL-GFX10-LABEL: chain_preserve_to_chain_preserve_fewer_args:
+; GISEL-GFX10: ; %bb.0:
+; GISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; GISEL-GFX10-NEXT: s_mov_b32 s2, s0
+; GISEL-GFX10-NEXT: ;;#ASMSTART
+; GISEL-GFX10-NEXT: s_nop
+; GISEL-GFX10-NEXT: ;;#ASMEND
+; GISEL-GFX10-NEXT: s_mov_b32 s0, s2
+; GISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; GISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; GISEL-GFX10-NEXT: s_getpc_b64 s[2:3]
+; GISEL-GFX10-NEXT: s_add_u32 s2, s2, chain_preserve_callee_2 at gotpcrel32@lo+4
+; GISEL-GFX10-NEXT: s_addc_u32 s3, s3, chain_preserve_callee_2 at gotpcrel32@hi+12
+; GISEL-GFX10-NEXT: s_load_dwordx2 s[2:3], s[2:3], 0x0
+; GISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GISEL-GFX10-NEXT: s_setpc_b64 s[2:3]
+;
+; DAGISEL-GFX11-LABEL: chain_preserve_to_chain_preserve_fewer_args:
+; DAGISEL-GFX11: ; %bb.0:
+; DAGISEL-GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX11-NEXT: s_add_u32 s4, s4, chain_preserve_callee_2 at gotpcrel32@lo+4
+; DAGISEL-GFX11-NEXT: s_addc_u32 s5, s5, chain_preserve_callee_2 at gotpcrel32@hi+12
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX11-NEXT: s_load_b64 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX11-NEXT: s_mov_b32 s2, s0
+; DAGISEL-GFX11-NEXT: ;;#ASMSTART
+; DAGISEL-GFX11-NEXT: s_nop
+; DAGISEL-GFX11-NEXT: ;;#ASMEND
+; DAGISEL-GFX11-NEXT: s_mov_b32 s0, s2
+; DAGISEL-GFX11-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX11-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX11-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX11-NEXT: s_setpc_b64 s[4:5]
+;
+; DAGISEL-GFX10-LABEL: chain_preserve_to_chain_preserve_fewer_args:
+; DAGISEL-GFX10: ; %bb.0:
+; DAGISEL-GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_getpc_b64 s[4:5]
+; DAGISEL-GFX10-NEXT: s_add_u32 s4, s4, chain_preserve_callee_2 at gotpcrel32@lo+4
+; DAGISEL-GFX10-NEXT: s_addc_u32 s5, s5, chain_preserve_callee_2 at gotpcrel32@hi+12
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v1, v8
+; DAGISEL-GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; DAGISEL-GFX10-NEXT: s_mov_b32 s2, s0
+; DAGISEL-GFX10-NEXT: ;;#ASMSTART
+; DAGISEL-GFX10-NEXT: s_nop
+; DAGISEL-GFX10-NEXT: ;;#ASMEND
+; DAGISEL-GFX10-NEXT: s_mov_b32 s0, s2
+; DAGISEL-GFX10-NEXT: v_mov_b32_e32 v8, v1
+; DAGISEL-GFX10-NEXT: s_mov_b32 exec_lo, -1
+; DAGISEL-GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; DAGISEL-GFX10-NEXT: s_setpc_b64 s[4:5]
+ %s = shufflevector <3 x i32> %a, <3 x i32> zeroinitializer, <2 x i32> <i32 0, i32 1>
+ %v = shufflevector <3 x i32> %b, <3 x i32> zeroinitializer, <2 x i32> <i32 0, i32 1>
+ call void asm "s_nop", "~{v0},~{v8},~{v16},~{s0}"()
+ call void(ptr, i32, <2 x i32>, <2 x i32>, i32, ...) @llvm.amdgcn.cs.chain.v2i32(ptr @chain_preserve_callee_2, i32 -1, <2 x i32> inreg %s, <2 x i32> %v, i32 0)
+ unreachable
+}
+
+; Note that amdgpu_cs_chain_preserve functions are not allowed to call
+; llvm.amdgcn.cs.chain with more vgpr args than they received as parameters.
+
+declare void @llvm.amdgcn.cs.chain.v3i32(ptr, i32, <3 x i32>, <3 x i32>, i32, ...)
+declare amdgpu_cs_chain_preserve void @chain_preserve_callee(<3 x i32> inreg, <3 x i32>)
+declare amdgpu_cs_chain void @chain_callee(<3 x i32> inreg, <3 x i32>)
+
+declare void @llvm.amdgcn.cs.chain.v2i32(ptr, i32, <2 x i32>, <2 x i32>, i32, ...)
+declare amdgpu_cs_chain_preserve void @chain_preserve_callee_2(<2 x i32> inreg, <2 x i32>)
diff --git a/llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w32.ll b/llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w32.ll
new file mode 100644
index 000000000000000..00e6e121a279cc5
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w32.ll
@@ -0,0 +1,637 @@
+; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
+; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=GISEL-GFX11 %s
+; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1030 -mattr=+wavefrontsize32,-wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=GISEL-GFX10 %s
+; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX11 %s
+; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1030 -mattr=+wavefrontsize32,-wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX10 %s
+
+declare amdgpu_cs_chain void @callee(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
+declare amdgpu_cs_chain_preserve void @callee_preserve(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
+declare void @llvm.amdgcn.cs.chain(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) noreturn
+
+define amdgpu_cs_chain void @chain_to_chain(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: chain_to_chain
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX11-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: chain_to_chain
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX10-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: chain_to_chain
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: chain_to_chain
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs void @cs_to_chain(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: cs_to_chain
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX11-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: cs_to_chain
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX10-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: cs_to_chain
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: cs_to_chain
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_to_chain_preserve(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: chain_to_chain_preserve
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX11-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: chain_to_chain_preserve
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX10-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: chain_to_chain_preserve
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: chain_to_chain_preserve
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs void @cs_to_chain_preserve(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: cs_to_chain_preserve
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX11-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: cs_to_chain_preserve
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX10-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: cs_to_chain_preserve
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: cs_to_chain_preserve
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @indirect(ptr inreg %callee, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: indirect
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY7]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY8]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX11-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: indirect
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY8]]
+ ; GISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; GISEL-GFX10-NEXT: $exec_lo = S_MOV_B32 [[S_MOV_B32_]]
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: indirect
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: indirect
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
+ ; DAGISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec_lo = COPY [[S_MOV_B32_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr %callee, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @non_imm_exec(i32 inreg %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: non_imm_exec
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY7]]
+ ; GISEL-GFX11-NEXT: $exec_lo = S_MOV_B32 [[COPY]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: non_imm_exec
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY8]]
+ ; GISEL-GFX10-NEXT: $exec_lo = S_MOV_B32 [[COPY]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: non_imm_exec
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec_lo = COPY [[COPY7]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: non_imm_exec
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY8]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec_lo = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i32 %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
diff --git a/llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w64.ll b/llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w64.ll
new file mode 100644
index 000000000000000..be3269d812a62ef
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/isel-amdgcn-cs-chain-intrinsic-w64.ll
@@ -0,0 +1,645 @@
+; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
+; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=GISEL-GFX11 %s
+; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1030 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=GISEL-GFX10 %s
+; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX11 %s
+; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1030 -mattr=-wavefrontsize32,+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX10 %s
+
+declare amdgpu_cs_chain void @callee(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
+declare amdgpu_cs_chain_preserve void @callee_preserve(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
+declare void @llvm.amdgcn.cs.chain(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) noreturn
+
+define amdgpu_cs_chain void @chain_to_chain(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: chain_to_chain
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX11-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: chain_to_chain
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX10-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: chain_to_chain
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: chain_to_chain
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs void @cs_to_chain(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: cs_to_chain
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX11-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: cs_to_chain
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX10-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: cs_to_chain
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: cs_to_chain
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @chain_to_chain_preserve(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: chain_to_chain_preserve
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX11-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: chain_to_chain_preserve
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX10-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: chain_to_chain_preserve
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: chain_to_chain_preserve
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs void @cs_to_chain_preserve(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: cs_to_chain_preserve
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX11-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: cs_to_chain_preserve
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX10-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: cs_to_chain_preserve
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: cs_to_chain_preserve
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee_preserve + 4, target-flags(amdgpu-gotprel32-hi) @callee_preserve + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee_preserve, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @indirect(ptr inreg %callee, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: indirect
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY7]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY8]]
+ ; GISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX11-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: indirect
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY8]]
+ ; GISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
+ ; GISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; GISEL-GFX10-NEXT: $exec = S_MOV_B64 [[S_MOV_B64_]]
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: indirect
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
+ ; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: indirect
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
+ ; DAGISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec = COPY [[S_MOV_B64_]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[REG_SEQUENCE]], 0, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr %callee, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
+
+define amdgpu_cs_chain void @non_imm_exec(i64 inreg %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
+ ; GISEL-GFX11-LABEL: name: non_imm_exec
+ ; GISEL-GFX11: bb.1 (%ir-block.0):
+ ; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX11-NEXT: {{ $}}
+ ; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY2]]
+ ; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY3]]
+ ; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY5]]
+ ; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY6]]
+ ; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY7]]
+ ; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY8]]
+ ; GISEL-GFX11-NEXT: $exec = S_MOV_B64 [[REG_SEQUENCE]]
+ ; GISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX11-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; GISEL-GFX10-LABEL: name: non_imm_exec
+ ; GISEL-GFX10: bb.1 (%ir-block.0):
+ ; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; GISEL-GFX10-NEXT: {{ $}}
+ ; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
+ ; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
+ ; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
+ ; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
+ ; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY2]]
+ ; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY3]]
+ ; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY5]]
+ ; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY6]]
+ ; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY7]]
+ ; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY8]]
+ ; GISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
+ ; GISEL-GFX10-NEXT: $exec = S_MOV_B64 [[REG_SEQUENCE]]
+ ; GISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc
+ ; GISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; GISEL-GFX10-NEXT: SI_TCRETURN [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
+ ;
+ ; DAGISEL-GFX11-LABEL: name: non_imm_exec
+ ; DAGISEL-GFX11: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX11-NEXT: {{ $}}
+ ; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
+ ; DAGISEL-GFX11-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX11-NEXT: $exec = COPY [[REG_SEQUENCE]]
+ ; DAGISEL-GFX11-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ ;
+ ; DAGISEL-GFX10-LABEL: name: non_imm_exec
+ ; DAGISEL-GFX10: bb.0 (%ir-block.0):
+ ; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
+ ; DAGISEL-GFX10-NEXT: {{ $}}
+ ; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
+ ; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
+ ; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
+ ; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
+ ; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; DAGISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
+ ; DAGISEL-GFX10-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def dead $scc
+ ; DAGISEL-GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:ccr_sgpr_64 = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
+ ; DAGISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
+ ; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
+ ; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
+ ; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
+ ; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
+ ; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
+ ; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
+ ; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
+ ; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
+ ; DAGISEL-GFX10-NEXT: $exec = COPY [[REG_SEQUENCE]]
+ ; DAGISEL-GFX10-NEXT: SI_TCRETURN killed [[S_LOAD_DWORDX2_IMM]], @callee, 0, amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
+ call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i64 %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
+ unreachable
+}
More information about the llvm-commits
mailing list