[AMDGPU] Produce better memoperand for LDS DMA (llvm#75247)

1) It was marked as volatile. This is not needed and the only reason
   it was done is because it is both load and store and handled
   together with atomics. Global load to LDS was marked as volatile
   just because buffer load was done that way.
2) Preserve at least LDS (store) pointer which we always have with
   the intrinsics.
3) Use PoisonValue instead of nullptr for load memop as a Value.

Change-Id: I3f937cff3280a411653712357a144d5ce819fea6

Author: rampitec

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

@@ -1091,18 +1091,18 @@ 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;
       }
       }
@@ -1231,8 +1231,8 @@ 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: {
@@ -8710,7 +8710,9 @@ 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() &
@@ -8788,6 +8790,8 @@ 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() &