[RISCV] Optimize (and (icmp x, 0, neq), (icmp y, 0, neq)) utilizing zicond extension

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -16117,6 +16117,45 @@ static SDValue reverseZExtICmpCombine(SDNode *N, SelectionDAG &DAG,
   return DAG.getNode(ISD::ZERO_EXTEND, DL, VT, Res);
 }
 
+// (and (i1) f, (setcc c, 0, ne)) -> (czero.nez f, c)
+// (and (i1) f, (setcc c, 0, eq)) -> (czero.eqz f, c)
+// (and (setcc c, 0, ne), (i1) g) -> (czero.nez g, c)
+// (and (setcc c, 0, eq), (i1) g) -> (czero.eqz g, c)
+static SDValue combineANDOfSETCCToCZERO(SDNode *N,
+                                        SelectionDAG &DAG,
+                                        const RISCVSubtarget &Subtarget) {
+  if (!Subtarget.hasCZEROLike())
+    return SDValue();
+
+  SDValue N0 = N->getOperand(0);
+  SDValue N1 = N->getOperand(1);
+
+  auto IsEqualCompZero = [](SDValue &V) -> bool {
+    if (V.getOpcode() == ISD::SETCC && isNullConstant(V.getOperand(1))) {
+      ISD::CondCode CC = cast<CondCodeSDNode>(V.getOperand(2))->get();
+      if (ISD::isIntEqualitySetCC(CC))
+        return true;
+    }
+    return false;
+  };
+
+  if (!IsEqualCompZero(N0))
+    std::swap(N0, N1);
+  if (!IsEqualCompZero(N0))
+    return SDValue();
+
+  KnownBits Known = DAG.computeKnownBits(N1);
+  if (Known.getMaxValue().sgt(1))
+    return SDValue();
+
+  unsigned CzeroOpcode = (cast<CondCodeSDNode>(N0.getOperand(2))->get() == ISD::SETNE) ?
+    RISCVISD::CZERO_EQZ : RISCVISD::CZERO_NEZ;
+
+  EVT VT = N->getValueType(0);
+  SDLoc DL(N);
+  return DAG.getNode(CzeroOpcode, DL, VT, N1, N0.getOperand(0));
+}
+
 static SDValue reduceANDOfAtomicLoad(SDNode *N,
                                      TargetLowering::DAGCombinerInfo &DCI) {
   SelectionDAG &DAG = DCI.DAG;
@@ -16180,7 +16219,9 @@ static SDValue performANDCombine(SDNode *N,
 
   if (SDValue V = reverseZExtICmpCombine(N, DAG, Subtarget))
     return V;
-
+  if (DCI.isAfterLegalizeDAG())
+    if (SDValue V = combineANDOfSETCCToCZERO(N, DAG, Subtarget))
+      return V;
   if (SDValue V = combineBinOpToReduce(N, DAG, Subtarget))
     return V;
   if (SDValue V = combineBinOpOfExtractToReduceTree(N, DAG, Subtarget))

llvm/test/CodeGen/RISCV/zicond-opts.ll

@@ -7,17 +7,15 @@ define i32 @icmp_and(i64 %x, i64 %y) {
 ; RV32ZICOND-LABEL: icmp_and:
 ; RV32ZICOND:       # %bb.0:
 ; RV32ZICOND-NEXT:    or a2, a2, a3
+; RV32ZICOND-NEXT:    snez a2, a2
 ; RV32ZICOND-NEXT:    or a0, a0, a1
-; RV32ZICOND-NEXT:    snez a1, a2
-; RV32ZICOND-NEXT:    snez a0, a0
-; RV32ZICOND-NEXT:    and a0, a0, a1
+; RV32ZICOND-NEXT:    czero.eqz a0, a2, a0
 ; RV32ZICOND-NEXT:    ret
 ;
 ; RV64ZICOND-LABEL: icmp_and:
 ; RV64ZICOND:       # %bb.0:
 ; RV64ZICOND-NEXT:    snez a1, a1
-; RV64ZICOND-NEXT:    snez a0, a0
-; RV64ZICOND-NEXT:    and a0, a0, a1
+; RV64ZICOND-NEXT:    czero.eqz a0, a1, a0
 ; RV64ZICOND-NEXT:    ret
   %3 = icmp ne i64 %y, 0
   %4 = icmp ne i64 %x, 0
@@ -26,27 +24,50 @@ define i32 @icmp_and(i64 %x, i64 %y) {
   ret i32 %6
 }
 
+; (and (icmp x. 0, ne), (icmp y, 0, ne)) -> (czero.eqz (icmp x, 0, ne), y)
+define i32 @icmp_and_select(i64 %x, i64 %y, i32 %z) {
+; RV32ZICOND-LABEL: icmp_and_select:
+; RV32ZICOND:       # %bb.0:
+; RV32ZICOND-NEXT:    sgtz a5, a3
+; RV32ZICOND-NEXT:    snez a2, a2
+; RV32ZICOND-NEXT:    czero.eqz a5, a5, a3
+; RV32ZICOND-NEXT:    czero.nez a2, a2, a3
+; RV32ZICOND-NEXT:    or a2, a2, a5
+; RV32ZICOND-NEXT:    or a0, a0, a1
+; RV32ZICOND-NEXT:    czero.eqz a0, a2, a0
+; RV32ZICOND-NEXT:    czero.eqz a0, a4, a0
+; RV32ZICOND-NEXT:    ret
+;
+; RV64ZICOND-LABEL: icmp_and_select:
+; RV64ZICOND:       # %bb.0:
+; RV64ZICOND-NEXT:    sgtz a1, a1
+; RV64ZICOND-NEXT:    czero.eqz a0, a1, a0
+; RV64ZICOND-NEXT:    czero.eqz a0, a2, a0
+; RV64ZICOND-NEXT:    ret
+  %3 = icmp sgt i64 %y, 0
+  %4 = icmp ne i64 %x, 0
+  %5 = and i1 %4, %3
+  %6 = select i1 %5, i32 %z, i32 0
+  ret i32 %6
+}
+
 ; (and (and (icmp x, 0, ne), (icmp y, 0, ne)), (icmp z, 0, ne)) -> (czero.eqz (czero.eqz (icmp x, 0, ne), y), z)
 define i32 @icmp_and_and(i64 %x, i64 %y, i64 %z) {
 ; RV32ZICOND-LABEL: icmp_and_and:
 ; RV32ZICOND:       # %bb.0:
 ; RV32ZICOND-NEXT:    or a2, a2, a3
 ; RV32ZICOND-NEXT:    or a0, a0, a1
-; RV32ZICOND-NEXT:    or a4, a4, a5
-; RV32ZICOND-NEXT:    snez a1, a2
 ; RV32ZICOND-NEXT:    snez a0, a0
-; RV32ZICOND-NEXT:    and a0, a1, a0
-; RV32ZICOND-NEXT:    snez a1, a4
-; RV32ZICOND-NEXT:    and a0, a1, a0
+; RV32ZICOND-NEXT:    czero.eqz a0, a0, a2
+; RV32ZICOND-NEXT:    or a4, a4, a5
+; RV32ZICOND-NEXT:    czero.eqz a0, a0, a4
 ; RV32ZICOND-NEXT:    ret
 ;
 ; RV64ZICOND-LABEL: icmp_and_and:
 ; RV64ZICOND:       # %bb.0:
-; RV64ZICOND-NEXT:    snez a1, a1
 ; RV64ZICOND-NEXT:    snez a0, a0
-; RV64ZICOND-NEXT:    and a0, a1, a0
-; RV64ZICOND-NEXT:    snez a1, a2
-; RV64ZICOND-NEXT:    and a0, a1, a0
+; RV64ZICOND-NEXT:    czero.eqz a0, a0, a1
+; RV64ZICOND-NEXT:    czero.eqz a0, a0, a2
 ; RV64ZICOND-NEXT:    ret
   %4 = icmp ne i64 %y, 0
   %5 = icmp ne i64 %x, 0