[RISCV] Fold (sext_inreg (setcc), i1) -> (sub 0, (setcc).

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -16639,33 +16639,38 @@ static SDValue performSETCCCombine(SDNode *N, SelectionDAG &DAG,
 }
 
 static SDValue
-performSIGN_EXTEND_INREGCombine(SDNode *N, SelectionDAG &DAG,
+performSIGN_EXTEND_INREGCombine(SDNode *N, TargetLowering::DAGCombinerInfo &DCI,
                                 const RISCVSubtarget &Subtarget) {
+  SelectionDAG &DAG = DCI.DAG;
   SDValue Src = N->getOperand(0);
   EVT VT = N->getValueType(0);
   EVT SrcVT = cast<VTSDNode>(N->getOperand(1))->getVT();
   unsigned Opc = Src.getOpcode();
+  SDLoc DL(N);
 
   // Fold (sext_inreg (fmv_x_anyexth X), i16) -> (fmv_x_signexth X)
   // Don't do this with Zhinx. We need to explicitly sign extend the GPR.
   if (Opc == RISCVISD::FMV_X_ANYEXTH && SrcVT.bitsGE(MVT::i16) &&
       Subtarget.hasStdExtZfhmin())
-    return DAG.getNode(RISCVISD::FMV_X_SIGNEXTH, SDLoc(N), VT,
-                       Src.getOperand(0));
+    return DAG.getNode(RISCVISD::FMV_X_SIGNEXTH, DL, VT, Src.getOperand(0));
 
   // Fold (sext_inreg (shl X, Y), i32) -> (sllw X, Y) iff Y u< 32
   if (Opc == ISD::SHL && Subtarget.is64Bit() && SrcVT == MVT::i32 &&
       VT == MVT::i64 && !isa<ConstantSDNode>(Src.getOperand(1)) &&
       DAG.computeKnownBits(Src.getOperand(1)).countMaxActiveBits() <= 5)
-    return DAG.getNode(RISCVISD::SLLW, SDLoc(N), VT, Src.getOperand(0),
+    return DAG.getNode(RISCVISD::SLLW, DL, VT, Src.getOperand(0),
                        Src.getOperand(1));
 
+  // Fold (sext_inreg (setcc), i1) -> (sub 0, (setcc)
+  if (Opc == ISD::SETCC && DCI.isAfterLegalizeDAG())
+    return DAG.getNode(ISD::SUB, DL, VT, DAG.getConstant(0, DL, VT), Src);
+
   // Fold (sext_inreg (xor (setcc), -1), i1) -> (add (setcc), -1)
   if (Opc == ISD::XOR && SrcVT == MVT::i1 &&
       isAllOnesConstant(Src.getOperand(1)) &&
-      Src.getOperand(0).getOpcode() == ISD::SETCC)
-    return DAG.getNode(ISD::ADD, SDLoc(N), VT, Src.getOperand(0),
-                       DAG.getAllOnesConstant(SDLoc(N), VT));
+      Src.getOperand(0).getOpcode() == ISD::SETCC && DCI.isAfterLegalizeDAG())
+    return DAG.getNode(ISD::ADD, DL, VT, Src.getOperand(0),
+                       DAG.getAllOnesConstant(DL, VT));
 
   return SDValue();
 }
@@ -20088,7 +20093,7 @@ SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
   case ISD::SETCC:
     return performSETCCCombine(N, DAG, Subtarget);
   case ISD::SIGN_EXTEND_INREG:
-    return performSIGN_EXTEND_INREGCombine(N, DAG, Subtarget);
+    return performSIGN_EXTEND_INREGCombine(N, DCI, Subtarget);
   case ISD::ZERO_EXTEND:
     // Fold (zero_extend (fp_to_uint X)) to prevent forming fcvt+zexti32 during
     // type legalization. This is safe because fp_to_uint produces poison if

llvm/test/CodeGen/RISCV/rv32xandesperf.ll

@@ -377,6 +377,32 @@ define zeroext i8 @sexti1_i32_setcc(i32 signext %a) {
   ret i8 %sext
 }
 
+; Make sure we don't use seqz+nds.bfos instead of snez+addi
+define i32 @sexti1_i32_setcc_2(i32 %a, i32 %b) {
+; CHECK-LABEL: sexti1_i32_setcc_2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xor a0, a0, a1
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    addi a0, a0, -1
+; CHECK-NEXT:    ret
+  %icmp = icmp eq i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
+; Make sure we don't use nds.bfos instead of neg.
+define i32 @sexti1_i32_setcc_3(i32 %a, i32 %b) {
+; CHECK-LABEL: sexti1_i32_setcc_3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    slt a1, a0, a1
+; CHECK-NEXT:    li a0, 0
+; CHECK-NEXT:    sub a0, a0, a1
+; CHECK-NEXT:    ret
+  %icmp = icmp slt i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
 define i32 @sexti8_i32(i32 %a) {
 ; CHECK-LABEL: sexti8_i32:
 ; CHECK:       # %bb.0:

llvm/test/CodeGen/RISCV/rv32xtheadbb.ll

@@ -334,6 +334,44 @@ define zeroext i8 @sexti1_i32_setcc(i32 signext %a) {
   ret i8 %sext
 }
 
+; Make sure we don't use seqz+th.ext instead of snez+addi
+define i32 @sexti1_i32_setcc_2(i32 %a, i32 %b) {
+; RV32I-LABEL: sexti1_i32_setcc_2:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    xor a0, a0, a1
+; RV32I-NEXT:    snez a0, a0
+; RV32I-NEXT:    addi a0, a0, -1
+; RV32I-NEXT:    ret
+;
+; RV32XTHEADBB-LABEL: sexti1_i32_setcc_2:
+; RV32XTHEADBB:       # %bb.0:
+; RV32XTHEADBB-NEXT:    xor a0, a0, a1
+; RV32XTHEADBB-NEXT:    snez a0, a0
+; RV32XTHEADBB-NEXT:    addi a0, a0, -1
+; RV32XTHEADBB-NEXT:    ret
+  %icmp = icmp eq i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
+; Make sure we don't use th.ext instead of neg.
+define i32 @sexti1_i32_setcc_3(i32 %a, i32 %b) {
+; RV32I-LABEL: sexti1_i32_setcc_3:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    slt a0, a0, a1
+; RV32I-NEXT:    neg a0, a0
+; RV32I-NEXT:    ret
+;
+; RV32XTHEADBB-LABEL: sexti1_i32_setcc_3:
+; RV32XTHEADBB:       # %bb.0:
+; RV32XTHEADBB-NEXT:    slt a0, a0, a1
+; RV32XTHEADBB-NEXT:    neg a0, a0
+; RV32XTHEADBB-NEXT:    ret
+  %icmp = icmp slt i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
 define i32 @sextb_i32(i32 %a) nounwind {
 ; RV32I-LABEL: sextb_i32:
 ; RV32I:       # %bb.0:

llvm/test/CodeGen/RISCV/rv64xandesperf.ll

@@ -290,6 +290,31 @@ define zeroext i8 @sexti1_i32_setcc(i32 signext %a) {
   ret i8 %sext
 }
 
+; Make sure we don't use seqz+nds.bfos instead of snez+addi
+define signext i32 @sexti1_i32_setcc_2(i32 signext %a, i32 signext %b) {
+; CHECK-LABEL: sexti1_i32_setcc_2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xor a0, a0, a1
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    addi a0, a0, -1
+; CHECK-NEXT:    ret
+  %icmp = icmp eq i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
+; Make sure we don't use nds.bfos instead of neg.
+define signext i32 @sexti1_i32_setcc_3(i32 signext %a, i32 signext %b) {
+; CHECK-LABEL: sexti1_i32_setcc_3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    slt a0, a0, a1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %icmp = icmp slt i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
 define signext i32 @sexti8_i32(i32 signext %a) {
 ; CHECK-LABEL: sexti8_i32:
 ; CHECK:       # %bb.0:
@@ -360,6 +385,31 @@ define zeroext i8 @sexti1_i64_setcc(i64 %a) {
   ret i8 %sext
 }
 
+; Make sure we don't use seqz+nds.bfos instead of snez+addi
+define i64 @sexti1_i64_setcc_2(i64 %a, i64 %b) {
+; CHECK-LABEL: sexti1_i64_setcc_2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xor a0, a0, a1
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    addi a0, a0, -1
+; CHECK-NEXT:    ret
+  %icmp = icmp eq i64 %a, %b
+  %sext = sext i1 %icmp to i64
+  ret i64 %sext
+}
+
+; Make sure we don't use nds.bfos instead of neg.
+define i64 @sexti1_i64_setcc_3(i64 %a, i64 %b) {
+; CHECK-LABEL: sexti1_i64_setcc_3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    slt a0, a0, a1
+; CHECK-NEXT:    neg a0, a0
+; CHECK-NEXT:    ret
+  %icmp = icmp slt i64 %a, %b
+  %sext = sext i1 %icmp to i64
+  ret i64 %sext
+}
+
 define i64 @sexti8_i64(i64 %a) {
 ; CHECK-LABEL: sexti8_i64:
 ; CHECK:       # %bb.0:

llvm/test/CodeGen/RISCV/rv64xtheadbb.ll

@@ -655,6 +655,44 @@ define zeroext i8 @sexti1_i32_setcc(i32 signext %a) {
   ret i8 %sext
 }
 
+; Make sure we don't use seqz+th.ext instead of snez+addi
+define signext i32 @sexti1_i32_setcc_2(i32 signext %a, i32 signext %b) {
+; RV64I-LABEL: sexti1_i32_setcc_2:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    xor a0, a0, a1
+; RV64I-NEXT:    snez a0, a0
+; RV64I-NEXT:    addi a0, a0, -1
+; RV64I-NEXT:    ret
+;
+; RV64XTHEADBB-LABEL: sexti1_i32_setcc_2:
+; RV64XTHEADBB:       # %bb.0:
+; RV64XTHEADBB-NEXT:    xor a0, a0, a1
+; RV64XTHEADBB-NEXT:    snez a0, a0
+; RV64XTHEADBB-NEXT:    addi a0, a0, -1
+; RV64XTHEADBB-NEXT:    ret
+  %icmp = icmp eq i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
+; Make sure we don't use th.ext instead of neg.
+define signext i32 @sexti1_i32_setcc_3(i32 signext %a, i32 signext %b) {
+; RV64I-LABEL: sexti1_i32_setcc_3:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    slt a0, a0, a1
+; RV64I-NEXT:    neg a0, a0
+; RV64I-NEXT:    ret
+;
+; RV64XTHEADBB-LABEL: sexti1_i32_setcc_3:
+; RV64XTHEADBB:       # %bb.0:
+; RV64XTHEADBB-NEXT:    slt a0, a0, a1
+; RV64XTHEADBB-NEXT:    neg a0, a0
+; RV64XTHEADBB-NEXT:    ret
+  %icmp = icmp slt i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
 define i64 @sexti1_i64(i64 %a) nounwind {
 ; RV64I-LABEL: sexti1_i64:
 ; RV64I:       # %bb.0:
@@ -706,6 +744,44 @@ define zeroext i8 @sexti1_i64_setcc(i64 %a) {
   ret i8 %sext
 }
 
+; Make sure we don't use seqz+th.ext instead of snez+addi
+define i64 @sexti1_i64_setcc_2(i64 %a, i64 %b) {
+; RV64I-LABEL: sexti1_i64_setcc_2:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    xor a0, a0, a1
+; RV64I-NEXT:    snez a0, a0
+; RV64I-NEXT:    addi a0, a0, -1
+; RV64I-NEXT:    ret
+;
+; RV64XTHEADBB-LABEL: sexti1_i64_setcc_2:
+; RV64XTHEADBB:       # %bb.0:
+; RV64XTHEADBB-NEXT:    xor a0, a0, a1
+; RV64XTHEADBB-NEXT:    snez a0, a0
+; RV64XTHEADBB-NEXT:    addi a0, a0, -1
+; RV64XTHEADBB-NEXT:    ret
+  %icmp = icmp eq i64 %a, %b
+  %sext = sext i1 %icmp to i64
+  ret i64 %sext
+}
+
+; Make sure we don't use th.ext instead of neg.
+define i64 @sexti1_i64_setcc_3(i64 %a, i64 %b) {
+; RV64I-LABEL: sexti1_i64_setcc_3:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    slt a0, a0, a1
+; RV64I-NEXT:    neg a0, a0
+; RV64I-NEXT:    ret
+;
+; RV64XTHEADBB-LABEL: sexti1_i64_setcc_3:
+; RV64XTHEADBB:       # %bb.0:
+; RV64XTHEADBB-NEXT:    slt a0, a0, a1
+; RV64XTHEADBB-NEXT:    neg a0, a0
+; RV64XTHEADBB-NEXT:    ret
+  %icmp = icmp slt i64 %a, %b
+  %sext = sext i1 %icmp to i64
+  ret i64 %sext
+}
+
 define signext i32 @sextb_i32(i32 signext %a) nounwind {
 ; RV64I-LABEL: sextb_i32:
 ; RV64I:       # %bb.0:

llvm/test/CodeGen/RISCV/xqcibm-extract.ll

@@ -74,6 +74,56 @@ define zeroext i8 @sexti1_i32_setcc(i32 signext %a) {
   ret i8 %sext
 }
 
+; Make sure we don't use seqz+qc.ext instead of snez+addi
+define i32 @sexti1_i32_setcc_2(i32 %a, i32 %b) {
+; RV32I-LABEL: sexti1_i32_setcc_2:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    xor a0, a0, a1
+; RV32I-NEXT:    snez a0, a0
+; RV32I-NEXT:    addi a0, a0, -1
+; RV32I-NEXT:    ret
+;
+; RV32XQCIBM-LABEL: sexti1_i32_setcc_2:
+; RV32XQCIBM:       # %bb.0:
+; RV32XQCIBM-NEXT:    xor a0, a0, a1
+; RV32XQCIBM-NEXT:    snez a0, a0
+; RV32XQCIBM-NEXT:    addi a0, a0, -1
+; RV32XQCIBM-NEXT:    ret
+;
+; RV32XQCIBMZBB-LABEL: sexti1_i32_setcc_2:
+; RV32XQCIBMZBB:       # %bb.0:
+; RV32XQCIBMZBB-NEXT:    xor a0, a0, a1
+; RV32XQCIBMZBB-NEXT:    snez a0, a0
+; RV32XQCIBMZBB-NEXT:    addi a0, a0, -1
+; RV32XQCIBMZBB-NEXT:    ret
+  %icmp = icmp eq i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
+
+; Make sure we don't use qc.ext instead of neg.
+define i32 @sexti1_i32_setcc_3(i32 %a, i32 %b) {
+; RV32I-LABEL: sexti1_i32_setcc_3:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    slt a0, a0, a1
+; RV32I-NEXT:    neg a0, a0
+; RV32I-NEXT:    ret
+;
+; RV32XQCIBM-LABEL: sexti1_i32_setcc_3:
+; RV32XQCIBM:       # %bb.0:
+; RV32XQCIBM-NEXT:    slt a0, a0, a1
+; RV32XQCIBM-NEXT:    neg a0, a0
+; RV32XQCIBM-NEXT:    ret
+;
+; RV32XQCIBMZBB-LABEL: sexti1_i32_setcc_3:
+; RV32XQCIBMZBB:       # %bb.0:
+; RV32XQCIBMZBB-NEXT:    slt a0, a0, a1
+; RV32XQCIBMZBB-NEXT:    neg a0, a0
+; RV32XQCIBMZBB-NEXT:    ret
+  %icmp = icmp slt i32 %a, %b
+  %sext = sext i1 %icmp to i32
+  ret i32 %sext
+}
 
 define i32 @sexti8_i32(i8 %a) nounwind {
 ; RV32I-LABEL: sexti8_i32: