[DAGCombiner] add fold (xor (smin(x, C), C)) -> select (x < C), xor(x, C), 0

Author: Yui5427

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -10086,6 +10086,48 @@ SDValue DAGCombiner::visitXOR(SDNode *N) {
   if (SDValue Combined = combineCarryDiamond(DAG, TLI, N0, N1, N))
     return Combined;
 
+  // fold (xor (smin(x, C), C)) -> select (x < C), xor(x, C), 0
+  // fold (xor (smin(C, x), C)) -> select (x < C), xor(x, C), 0
+  if (N0.getOpcode() == ISD::SMIN && N0.hasOneUse()) {
+    SDValue Op0 = N0.getOperand(0);
+    SDValue Op1 = N0.getOperand(1);
+
+    if (Op1 != N1) {
+      std::swap(Op0, Op1);
+    }
+
+    if (Op1 == N1) {
+      if (isa<ConstantSDNode>(N1)) {
+        EVT CCVT = getSetCCResultType(VT);
+        SDValue Cmp = DAG.getSetCC(SDLoc(N), CCVT, Op0, N1, ISD::SETLT);
+        SDValue XorXC = DAG.getNode(ISD::XOR, SDLoc(N), VT, Op0, N1);
+        SDValue Zero = DAG.getConstant(0, SDLoc(N), VT);
+        return DAG.getSelect(SDLoc(N), VT, Cmp, XorXC, Zero);
+      }
+    }
+  }
+
+  // fold (xor (smax(x, C), C)) -> select (x > C), xor(x, C), 0
+  // fold (xor (smax(C, x), C)) -> select (x > C), xor(x, C), 0
+  if (N0.getOpcode() == ISD::SMAX && N0.hasOneUse()) {
+    SDValue Op0 = N0.getOperand(0);
+    SDValue Op1 = N0.getOperand(1);
+
+    if (Op1 != N1) {
+      std::swap(Op0, Op1);
+    }
+
+    if (Op1 == N1) {
+      if (isa<ConstantSDNode>(N1)) {
+        EVT CCVT = getSetCCResultType(VT);
+        SDValue Cmp = DAG.getSetCC(SDLoc(N), CCVT, Op0, N1, ISD::SETGT);
+        SDValue XorXC = DAG.getNode(ISD::XOR, SDLoc(N), VT, Op0, N1);
+        SDValue Zero = DAG.getConstant(0, SDLoc(N), VT);
+        return DAG.getSelect(SDLoc(N), VT, Cmp, XorXC, Zero);
+      }
+    }
+  }
+
   return SDValue();
 }
 

llvm/test/CodeGen/AArch64/xor-smin-smax.ll

@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=aarch64-unknown-unknown | FileCheck %s
+
+; Test for DAGCombiner optimization: fold (xor (smin(x, C), C)) -> select (x < C), xor (x, C), 0
+
+define i64 @test_smin_neg_one(i64 %a) {
+; CHECK-LABEL: test_smin_neg_one:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    cmn x0, #1
+; CHECK-NEXT:    csinv x0, xzr, x0, ge
+; CHECK-NEXT:    ret
+  %1 = tail call i64 @llvm.smin.i64(i64 %a, i64 -1)
+  %retval.0 = xor i64 %1, -1
+  ret i64 %retval.0
+}
+
+define i64 @test_smin_zero(i64 %a) {
+; CHECK-LABEL: test_smin_zero:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    and x0, x0, x0, asr #63
+; CHECK-NEXT:    ret
+  %1 = tail call i64 @llvm.smin.i64(i64 %a, i64 0)
+  %retval.0 = xor i64 %1, 0
+  ret i64 %retval.0
+}
+
+define i64 @test_smin_constant(i64 %a) {
+; CHECK-LABEL: test_smin_constant:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    eor x8, x0, #0x8
+; CHECK-NEXT:    cmp x0, #8
+; CHECK-NEXT:    csel x0, x8, xzr, lt
+; CHECK-NEXT:    ret
+  %1 = tail call i64 @llvm.smin.i64(i64 %a, i64 8)
+  %retval.0 = xor i64 %1, 8
+  ret i64 %retval.0
+}
+
+; Test for DAGCombiner optimization: fold (xor (smax(x, C), C)) -> select (x > C), xor (x, C), 0
+
+define i64 @test_smax_neg_one(i64 %a) {
+; CHECK-LABEL: test_smax_neg_one:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mvn x8, x0
+; CHECK-NEXT:    bic x0, x8, x0, asr #63
+; CHECK-NEXT:    ret
+  %1 = tail call i64 @llvm.smax.i64(i64 %a, i64 -1)
+  %retval.0 = xor i64 %1, -1
+  ret i64 %retval.0
+}
+
+define i64 @test_smax_zero(i64 %a) {
+; CHECK-LABEL: test_smax_zero:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    bic x0, x0, x0, asr #63
+; CHECK-NEXT:    ret
+  %1 = tail call i64 @llvm.smax.i64(i64 %a, i64 0)
+  %retval.0 = xor i64 %1, 0
+  ret i64 %retval.0
+}
+
+define i64 @test_smax_constant(i64 %a) {
+; CHECK-LABEL: test_smax_constant:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    eor x8, x0, #0x8
+; CHECK-NEXT:    cmp x0, #8
+; CHECK-NEXT:    csel x0, x8, xzr, gt
+; CHECK-NEXT:    ret
+  %1 = tail call i64 @llvm.smax.i64(i64 %a, i64 8)
+  %retval.0 = xor i64 %1, 8
+  ret i64 %retval.0
+}
+
+declare i64 @llvm.smin.i64(i64, i64)
+declare i64 @llvm.smax.i64(i64, i64)