Skip to content

[AMDGPU] Produce better memoperand for LDS DMA #75247

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 18, 2023
Merged

[AMDGPU] Produce better memoperand for LDS DMA #75247

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
14863af
[AMDGPU] Produce better memoperand for LDS DMA
rampitec Dec 12, 2023
e058b4f
Merge branch 'main' into lds-dma-memop
rampitec Dec 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 10 additions & 6 deletions llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1134,18 +1134,18 @@ bool SITargetLowering::getTgtMemIntrinsic(IntrinsicInfo &Info,
MachineMemOperand::MOStore |
MachineMemOperand::MODereferenceable;

// XXX - Should this be volatile without known ordering?
Info.flags |= MachineMemOperand::MOVolatile;

switch (IntrID) {
default:
// XXX - Should this be volatile without known ordering?
Info.flags |= MachineMemOperand::MOVolatile;
break;
case Intrinsic::amdgcn_raw_buffer_load_lds:
case Intrinsic::amdgcn_raw_ptr_buffer_load_lds:
case Intrinsic::amdgcn_struct_buffer_load_lds:
case Intrinsic::amdgcn_struct_ptr_buffer_load_lds: {
unsigned Width = cast<ConstantInt>(CI.getArgOperand(2))->getZExtValue();
Info.memVT = EVT::getIntegerVT(CI.getContext(), Width * 8);
Info.ptrVal = CI.getArgOperand(1);
return true;
}
}
Expand Down Expand Up @@ -1274,8 +1274,8 @@ bool SITargetLowering::getTgtMemIntrinsic(IntrinsicInfo &Info,
Info.opc = ISD::INTRINSIC_VOID;
unsigned Width = cast<ConstantInt>(CI.getArgOperand(2))->getZExtValue();
Info.memVT = EVT::getIntegerVT(CI.getContext(), Width * 8);
Info.flags |= MachineMemOperand::MOLoad | MachineMemOperand::MOStore |
MachineMemOperand::MOVolatile;
Info.ptrVal = CI.getArgOperand(1);
Info.flags |= MachineMemOperand::MOLoad | MachineMemOperand::MOStore;
return true;
}
case Intrinsic::amdgcn_ds_bvh_stack_rtn: {
Expand Down Expand Up @@ -9142,7 +9142,9 @@ SDValue SITargetLowering::LowerINTRINSIC_VOID(SDValue Op,
MachinePointerInfo LoadPtrI = LoadMMO->getPointerInfo();

MachinePointerInfo StorePtrI = LoadPtrI;
StorePtrI.V = nullptr;
LoadPtrI.V = PoisonValue::get(
PointerType::get(*DAG.getContext(), AMDGPUAS::GLOBAL_ADDRESS));
LoadPtrI.AddrSpace = AMDGPUAS::GLOBAL_ADDRESS;
StorePtrI.AddrSpace = AMDGPUAS::LOCAL_ADDRESS;

auto F = LoadMMO->getFlags() &
Expand Down Expand Up @@ -9220,6 +9222,8 @@ SDValue SITargetLowering::LowerINTRINSIC_VOID(SDValue Op,
MachinePointerInfo LoadPtrI = LoadMMO->getPointerInfo();
LoadPtrI.Offset = Op->getConstantOperandVal(5);
MachinePointerInfo StorePtrI = LoadPtrI;
LoadPtrI.V = PoisonValue::get(
PointerType::get(*DAG.getContext(), AMDGPUAS::GLOBAL_ADDRESS));
LoadPtrI.AddrSpace = AMDGPUAS::GLOBAL_ADDRESS;
StorePtrI.AddrSpace = AMDGPUAS::LOCAL_ADDRESS;
auto F = LoadMMO->getFlags() &
Expand Down