The actual fix

Author: svs-quic

llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp

@@ -689,10 +689,16 @@ bool RISCVDAGToDAGISel::trySignedBitfieldInsertInMask(SDNode *Node) {
   if (!isShiftedMask_32(C1) || isInt<12>(C1))
     return false;
 
+  // INSBI will clobber the input register in N0. Bail out if we need a copy to
+  // preserve this value.
+  SDValue N0 = Node->getOperand(0);
+  if (!N0.hasOneUse())
+    return false;
+
   // If C1 is a shifted mask (but can't be formed as an ORI),
   // use a bitfield insert of -1.
   // Transform (or x, C1)
-  //        -> (qc.insbi x, width, shift)
+  //        -> (qc.insbi x, -1, width, shift)
   const unsigned Leading = llvm::countl_zero((uint32_t)C1);
   const unsigned Trailing = llvm::countr_zero((uint32_t)C1);
   const unsigned Width = 32 - Leading - Trailing;
@@ -705,7 +711,7 @@ bool RISCVDAGToDAGISel::trySignedBitfieldInsertInMask(SDNode *Node) {
   SDLoc DL(Node);
   MVT VT = Node->getSimpleValueType(0);
 
-  SDValue Ops[] = {CurDAG->getSignedTargetConstant(-1, DL, VT),
+  SDValue Ops[] = {N0, CurDAG->getSignedTargetConstant(-1, DL, VT),
                    CurDAG->getTargetConstant(Width, DL, VT),
                    CurDAG->getTargetConstant(Trailing, DL, VT)};
   SDNode *BitIns = CurDAG->getMachineNode(RISCV::QC_INSBI, DL, VT, Ops);

llvm/lib/Target/RISCV/RISCVInstrInfoXqci.td

@@ -845,10 +845,11 @@ let Predicates = [HasVendorXqcibi, IsRV32] in {
 let Predicates = [HasVendorXqcibm, IsRV32] in {
 let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in {
   def QC_INSBRI : QCIRVInstRI<0b1, simm11, "qc.insbri">;
-  def QC_INSBI : RVInstIBase<0b001, OPC_CUSTOM_0, (outs GPRNoX0:$rd),
-                             (ins simm5:$imm5, uimm5_plus1:$width,
+  def QC_INSBI : RVInstIBase<0b001, OPC_CUSTOM_0, (outs GPRNoX0:$rd_wb),
+                             (ins GPRNoX0:$rd, simm5:$imm5, uimm5_plus1:$width,
                              uimm5:$shamt), "qc.insbi",
                              "$rd, $imm5, $width, $shamt"> {
+    let Constraints = "$rd = $rd_wb";
     bits<5> imm5;
     bits<5> shamt;
     bits<5> width;

llvm/test/CodeGen/RISCV/xqcibm-cto-clo-brev.ll

@@ -105,6 +105,7 @@ define i16 @test_cttz_i16(i16 %a) nounwind {
 ;
 ; RV32ZBBXQCIBM-LABEL: test_cttz_i16:
 ; RV32ZBBXQCIBM:       # %bb.0:
+; RV32ZBBXQCIBM-NEXT:    not a0, a0
 ; RV32ZBBXQCIBM-NEXT:    qc.insbi a0, -1, 1, 16
 ; RV32ZBBXQCIBM-NEXT:    ctz a0, a0
 ; RV32ZBBXQCIBM-NEXT:    ret

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

@@ -57,11 +57,13 @@ define i32 @test_insbi_mask_mv(i32 %a, i32 %b) nounwind {
 ;
 ; RV32IXQCIBM-LABEL: test_insbi_mask_mv:
 ; RV32IXQCIBM:       # %bb.0:
+; RV32IXQCIBM-NEXT:    mv a0, a1
 ; RV32IXQCIBM-NEXT:    qc.insbi a0, -1, 16, 0
 ; RV32IXQCIBM-NEXT:    ret
 ;
 ; RV32IXQCIBMZBS-LABEL: test_insbi_mask_mv:
 ; RV32IXQCIBMZBS:       # %bb.0:
+; RV32IXQCIBMZBS-NEXT:    mv a0, a1
 ; RV32IXQCIBMZBS-NEXT:    qc.insbi a0, -1, 16, 0
 ; RV32IXQCIBMZBS-NEXT:    ret
   %or = or i32 %b, 65535
@@ -99,14 +101,16 @@ define i32 @test_insbi_shifted_mask_multiple_uses(i32 %a) nounwind {
 ;
 ; RV32IXQCIBM-LABEL: test_insbi_shifted_mask_multiple_uses:
 ; RV32IXQCIBM:       # %bb.0:
-; RV32IXQCIBM-NEXT:    qc.insbi a1, -1, 4, 12
+; RV32IXQCIBM-NEXT:    lui a1, 15
+; RV32IXQCIBM-NEXT:    or a1, a1, a0
 ; RV32IXQCIBM-NEXT:    addi a0, a0, 10
 ; RV32IXQCIBM-NEXT:    xor a0, a0, a1
 ; RV32IXQCIBM-NEXT:    ret
 ;
 ; RV32IXQCIBMZBS-LABEL: test_insbi_shifted_mask_multiple_uses:
 ; RV32IXQCIBMZBS:       # %bb.0:
-; RV32IXQCIBMZBS-NEXT:    qc.insbi a1, -1, 4, 12
+; RV32IXQCIBMZBS-NEXT:    lui a1, 15
+; RV32IXQCIBMZBS-NEXT:    or a1, a1, a0
 ; RV32IXQCIBMZBS-NEXT:    addi a0, a0, 10
 ; RV32IXQCIBMZBS-NEXT:    xor a0, a0, a1
 ; RV32IXQCIBMZBS-NEXT:    ret