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

AMDGPU/GlobalISel: Cleanup call lowering sequence 

Now that handleAssignments is handling all of the argument splitting,
we don't have to move the insert point around.
This commit is contained in:
Matt Arsenault 2021-03-03 16:57:24 -05:00
parent bc4a5bdce4
commit 3231d2b581
1 changed files with 12 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
View File

@ -944,6 +944,10 @@ bool AMDGPUCallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
for (auto &OrigArg : Info.OrigArgs)
splitToValueTypes(OrigArg, OutArgs, DL, Info.CallConv);
SmallVector<ArgInfo, 8> InArgs;
if (Info.CanLowerReturn && !Info.OrigRet.Ty->isVoidTy())
splitToValueTypes(Info.OrigRet, InArgs, DL, Info.CallConv);
// If we can lower as a tail call, do that instead.
bool CanTailCallOpt = false;
@ -1031,27 +1035,9 @@ bool AMDGPUCallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
1));
}
auto OrigInsertPt = MIRBuilder.getInsertPt();
// Now we can add the actual call instruction to the correct position.
MIRBuilder.insertInstr(MIB);
// Insert this now to give us an anchor point for managing the insert point.
MachineInstrBuilder CallSeqEnd =
MIRBuilder.buildInstr(AMDGPU::ADJCALLSTACKDOWN);
SmallVector<ArgInfo, 8> InArgs;
if (!Info.CanLowerReturn) {
insertSRetLoads(MIRBuilder, Info.OrigRet.Ty, Info.OrigRet.Regs,
Info.DemoteRegister, Info.DemoteStackIndex);
} else if (!Info.OrigRet.Ty->isVoidTy()) {
splitToValueTypes(Info.OrigRet, InArgs, DL, Info.CallConv);
}
// Make sure the raw argument copies are inserted before the marshalling to
// the original types.
MIRBuilder.setInsertPt(MIRBuilder.getMBB(), CallSeqEnd);
// Finally we can copy the returned value back into its virtual-register. In
// symmetry with the arguments, the physical register must be an
// implicit-define of the call instruction.
@ -1065,10 +1051,15 @@ bool AMDGPUCallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
}
uint64_t CalleePopBytes = NumBytes;
CallSeqEnd.addImm(0)
MIRBuilder.buildInstr(AMDGPU::ADJCALLSTACKDOWN)
.addImm(0)
.addImm(CalleePopBytes);
// Restore the insert point to after the call sequence.
MIRBuilder.setInsertPt(MIRBuilder.getMBB(), OrigInsertPt);
if (!Info.CanLowerReturn) {
insertSRetLoads(MIRBuilder, Info.OrigRet.Ty, Info.OrigRet.Regs,
Info.DemoteRegister, Info.DemoteStackIndex);
}
return true;
}