[VE] Change the way of lowering store

[kaz7]

Summary

Change lowering store iff the data operand is leagalized. In this way,
llvm can lower only operands first, then lower store instruction later.

[efocht]

Nice!

llvm/lib/Target/VE/VVPISelLowering.cpp

if (IsLoad) {
     SDValue NewLoadChainV = SDValue(NewLoadV.getNode(), 1);
 
     // Merge them back into one node.
     return CDAG.getMergeValues({DataV, NewLoadChainV});
   }
 
   // VVP_STORE
   assert(VVPOpc == VEISD::VVP_STORE);
+  if (getTypeAction(*CDAG.getDAG()->getContext(), Data.getValueType()) !=
+      TargetLowering::TypeLegal)
+    // Doesn't lower store instruction if an operand is not lowered yet.
+    // If it isn't, return SDValue().  In this way, LLVM will try to lower
+    // store instruction again after lowering all operands.
+    return SDValue();
   return CDAG.getNode(VEISD::VVP_STORE, Op.getNode()->getVTList(),
                       {Chain, Data, BasePtr, StrideV, Mask, AVL});
 }
 
 SDValue VETargetLowering::splitPackedLoadStore(SDValue Op,
                                                VECustomDAG &CDAG) const {
   auto VVPOC = *getVVPOpcode(Op.getOpcode());
   assert((VVPOC == VEISD::VVP_LOAD) || (VVPOC == VEISD::VVP_STORE));

llvm/test/CodeGen/VE/Vector/ticket-64420.ll

+; RUN: llc < %s -mtriple=ve -mattr=+vpu | FileCheck %s
 ; RUN: llc < %s -mtriple=ve -mattr=-vpu | FileCheck --check-prefix=SCALAR %s
 
 ; Check vector and scalar code generation for vector load instruction.
-; For the case of scalar, generates 2 stores of 8 bytes length.
+; For the case of vector, generates vst with 4 vector length.  For the
+; case of scalar, generates 2 stores of 8 bytes length.
 
 ; This is taken from a ticket below.
 ;   https://github.com/llvm/llvm-project/issues/64420
 
+; CHECK-LABEL: func:
+; CHECK:       # %bb.1:
+; CHECK-NEXT:    lea %s1, 256
+; CHECK-NEXT:    lvl %s1
+; CHECK-NEXT:    vbrd %v0, 0
+; CHECK-NEXT:    or %s1, 4, (0)1
+; CHECK-NEXT:    lvl %s1
+; CHECK-NEXT:    vstl %v0, 4, %s0
+; CHECK-NEXT:    b.l.t (, %s10)
+
 ; SCALAR-LABEL: func:
 ; SCALAR:       # %bb.1:
 ; SCALAR-NEXT:    st %s1, 8(, %s0)
 ; SCALAR-NEXT:    st %s1, (, %s0)
 ; SCALAR-NEXT:    b.l.t (, %s10)
 
 ; ModuleID = 'bugpoint-reduced-simplified.bc'
 source_filename = "test.c"