[PowerPC] Add custom lowering for ssubo

This patch is to improve the codegen for ssubo node for i32 in 64-bit mode
by custom lowering.

Author: maryammo

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

@@ -198,6 +198,10 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
     }
   }
 
+  if (!Subtarget.hasP10Vector() && isPPC64) {
+    setOperationAction(ISD::SSUBO, MVT::i32, Custom);
+  }
+
   // Match BITREVERSE to customized fast code sequence in the td file.
   setOperationAction(ISD::BITREVERSE, MVT::i32, Legal);
   setOperationAction(ISD::BITREVERSE, MVT::i64, Legal);
@@ -11967,6 +11971,36 @@ SDValue PPCTargetLowering::LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const {
   llvm_unreachable("ERROR:Should return for all cases within swtich.");
 }
 
+SDValue PPCTargetLowering::LowerSSUBO(SDValue Op, SelectionDAG &DAG) const {
+
+  SDLoc dl(Op);
+
+  SDValue LHS64 = DAG.getNode(ISD::ANY_EXTEND, dl, MVT::i64, Op.getOperand(0));
+  SDValue RHS64 = DAG.getNode(ISD::ANY_EXTEND, dl, MVT::i64, Op.getOperand(1));
+
+  SDValue Sub = DAG.getNode(ISD::SUB, dl, MVT::i64, LHS64, RHS64);
+
+  SDValue Extsw = DAG.getNode(ISD::SIGN_EXTEND_INREG, dl, MVT::i64, Sub,
+                              DAG.getValueType(MVT::i32));
+
+  SDValue Xor = DAG.getNode(ISD::XOR, dl, MVT::i64, Extsw, Sub);
+
+  SDValue Addic = DAG.getNode(ISD::ADDC, dl, DAG.getVTList(MVT::i64, MVT::Glue),
+                              Xor, DAG.getConstant(-1, dl, MVT::i64));
+
+  SDValue Overflow =
+      DAG.getNode(ISD::SUBE, dl, DAG.getVTList(MVT::i64, MVT::Glue), Xor, Addic,
+                  Addic.getValue(1));
+
+  SDValue OverflowTrunc =
+      DAG.getNode(ISD::TRUNCATE, dl, Op.getNode()->getValueType(1), Overflow);
+  SDValue SubTrunc =
+      (Sub->getValueType(0) != Op.getNode()->getValueType(0))
+          ? DAG.getNode(ISD::TRUNCATE, dl, Op.getNode()->getValueType(0), Sub)
+          : Sub;
+  return DAG.getMergeValues({SubTrunc, OverflowTrunc}, dl);
+}
+
 /// LowerOperation - Provide custom lowering hooks for some operations.
 ///
 SDValue PPCTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
@@ -11988,6 +12022,8 @@ SDValue PPCTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::SETCC:              return LowerSETCC(Op, DAG);
   case ISD::INIT_TRAMPOLINE:    return LowerINIT_TRAMPOLINE(Op, DAG);
   case ISD::ADJUST_TRAMPOLINE:  return LowerADJUST_TRAMPOLINE(Op, DAG);
+  case ISD::SSUBO:
+    return LowerSSUBO(Op, DAG);
 
   case ISD::INLINEASM:
   case ISD::INLINEASM_BR:       return LowerINLINEASM(Op, DAG);

llvm/lib/Target/PowerPC/PPCISelLowering.h

@@ -1278,6 +1278,7 @@ namespace llvm {
     SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
+    SDValue LowerSSUBO(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerINIT_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerADJUST_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerINLINEASM(SDValue Op, SelectionDAG &DAG) const;

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

@@ -129,12 +129,11 @@ entry:
 define i1 @test_ssubo_i32(i32 %a, i32 %b) nounwind {
 ; CHECK-LABEL: test_ssubo_i32:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    sub 5, 3, 4
-; CHECK-NEXT:    cmpwi 1, 4, 0
-; CHECK-NEXT:    cmpw 5, 3
-; CHECK-NEXT:    li 3, 1
-; CHECK-NEXT:    creqv 20, 5, 0
-; CHECK-NEXT:    isel 3, 0, 3, 20
+; CHECK-NEXT:    sub 3, 3, 4
+; CHECK-NEXT:    extsw 4, 3
+; CHECK-NEXT:    xor 3, 4, 3
+; CHECK-NEXT:    addic 4, 3, -1
+; CHECK-NEXT:    subfe 3, 4, 3
 ; CHECK-NEXT:    blr
 entry:
   %res = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 %a, i32 %b) nounwind