[PPC] Custom lower ssubo for i64 (#118711)

This is a follow-up patch to improve the codegen for ssubo node for i64
in 64-bit mode by custom lowering.

Author: maryammo

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

@@ -200,8 +200,11 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
 
   // On P10, the default lowering generates better code using the
   // setbc instruction.
-  if (!Subtarget.hasP10Vector())
+  if (!Subtarget.hasP10Vector()) {
     setOperationAction(ISD::SSUBO, MVT::i32, Custom);
+    if (isPPC64)
+      setOperationAction(ISD::SSUBO, MVT::i64, Custom);
+  }
 
   // Match BITREVERSE to customized fast code sequence in the td file.
   setOperationAction(ISD::BITREVERSE, MVT::i32, Legal);
@@ -12051,16 +12054,19 @@ SDValue PPCTargetLowering::LowerSSUBO(SDValue Op, SelectionDAG &DAG) const {
   SDLoc dl(Op);
   SDValue LHS = Op.getOperand(0);
   SDValue RHS = Op.getOperand(1);
+  EVT VT = Op.getNode()->getValueType(0);
+
+  SDValue Sub = DAG.getNode(ISD::SUB, dl, VT, LHS, RHS);
 
-  SDValue Sub = DAG.getNode(ISD::SUB, dl, MVT::i32, LHS, RHS);
+  SDValue Xor1 = DAG.getNode(ISD::XOR, dl, VT, RHS, LHS);
+  SDValue Xor2 = DAG.getNode(ISD::XOR, dl, VT, Sub, LHS);
 
-  SDValue Xor1 = DAG.getNode(ISD::XOR, dl, MVT::i32, RHS, LHS);
-  SDValue Xor2 = DAG.getNode(ISD::XOR, dl, MVT::i32, Sub, LHS);
+  SDValue And = DAG.getNode(ISD::AND, dl, VT, Xor1, Xor2);
 
-  SDValue And = DAG.getNode(ISD::AND, dl, MVT::i32, Xor1, Xor2);
+  SDValue Overflow =
+      DAG.getNode(ISD::SRL, dl, VT, And,
+                  DAG.getConstant(VT.getSizeInBits() - 1, dl, MVT::i32));
 
-  SDValue Overflow = DAG.getNode(ISD::SRL, dl, MVT::i32, And,
-                                 DAG.getConstant(31, dl, MVT::i32));
   SDValue OverflowTrunc =
       DAG.getNode(ISD::TRUNCATE, dl, Op.getNode()->getValueType(1), Overflow);
 

llvm/test/CodeGen/PowerPC/saddo-ssubo.ll

@@ -144,12 +144,11 @@ entry:
 define i1 @test_ssubo_i64(i64 %a, i64 %b) nounwind {
 ; CHECK-LABEL: test_ssubo_i64:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    sub 5, 3, 4
-; CHECK-NEXT:    cmpdi 1, 4, 0
-; CHECK-NEXT:    cmpd 5, 3
-; CHECK-NEXT:    li 3, 1
-; CHECK-NEXT:    creqv 20, 5, 0
-; CHECK-NEXT:    isel 3, 0, 3, 20
+; CHECK-NEXT:    xor 5, 4, 3
+; CHECK-NEXT:    sub 4, 3, 4
+; CHECK-NEXT:    xor 3, 4, 3
+; CHECK-NEXT:    and 3, 5, 3
+; CHECK-NEXT:    rldicl 3, 3, 1, 63
 ; CHECK-NEXT:    blr
 entry:
   %res = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 %a, i64 %b) nounwind