Index: lib/Target/AArch64/AArch64ISelDAGToDAG.cpp =================================================================== --- lib/Target/AArch64/AArch64ISelDAGToDAG.cpp +++ lib/Target/AArch64/AArch64ISelDAGToDAG.cpp @@ -1974,7 +1974,8 @@ // f = Opc Opd0, Opd1, LSB, MSB ; where Opc is a BFM, LSB = imm, and MSB = imm2 static bool isBitfieldInsertOpFromOr(SDNode *N, unsigned &Opc, SDValue &Dst, SDValue &Src, unsigned &ImmR, - unsigned &ImmS, SelectionDAG *CurDAG) { + unsigned &ImmS, const APInt &UsefulBits, + SelectionDAG *CurDAG) { assert(N->getOpcode() == ISD::OR && "Expect a OR operation"); // Set Opc @@ -1988,8 +1989,6 @@ // Because of simplify-demanded-bits in DAGCombine, involved masks may not // have the expected shape. Try to undo that. - APInt UsefulBits; - getUsefulBits(SDValue(N, 0), UsefulBits); unsigned NumberOfIgnoredLowBits = UsefulBits.countTrailingZeros(); unsigned NumberOfIgnoredHighBits = UsefulBits.countLeadingZeros(); @@ -2083,11 +2082,18 @@ unsigned Opc; unsigned LSB, MSB; SDValue Opd0, Opd1; + EVT VT = N->getValueType(0); + APInt NUsefulBits; + getUsefulBits(SDValue(N, 0), NUsefulBits); + + // If all bits are not useful, just return UNDEF. + if (!NUsefulBits) + return CurDAG->SelectNodeTo(N, TargetOpcode::IMPLICIT_DEF, VT); - if (!isBitfieldInsertOpFromOr(N, Opc, Opd0, Opd1, LSB, MSB, CurDAG)) + if (!isBitfieldInsertOpFromOr(N, Opc, Opd0, Opd1, LSB, MSB, NUsefulBits, + CurDAG)) return nullptr; - EVT VT = N->getValueType(0); SDLoc dl(N); SDValue Ops[] = { Opd0, Opd1, Index: test/CodeGen/AArch64/bitfield-insert.ll =================================================================== --- test/CodeGen/AArch64/bitfield-insert.ll +++ test/CodeGen/AArch64/bitfield-insert.ll @@ -215,3 +215,25 @@ ret void } + +; Tests when all the bits from one operand are not useful +define i32 @test_nouseful_bits(i8 %a, i32 %b) { +; CHECK-LABEL: test_nouseful_bits: +; CHECK: bfi +; CHECK: bfi +; CHECK: bfi +; CHECK-NOT: bfi +; CHECK-NOT: or +; CHECK: lsl + %conv = zext i8 %a to i32 ; 0 0 0 A + %shl = shl i32 %b, 8 ; B2 B1 B0 0 + %or = or i32 %conv, %shl ; B2 B1 B0 A + %shl.1 = shl i32 %or, 8 ; B1 B0 A 0 + %or.1 = or i32 %conv, %shl.1 ; B1 B0 A A + %shl.2 = shl i32 %or.1, 8 ; B0 A A 0 + %or.2 = or i32 %conv, %shl.2 ; B0 A A A + %shl.3 = shl i32 %or.2, 8 ; A A A 0 + %or.3 = or i32 %conv, %shl.3 ; A A A A + %shl.4 = shl i32 %or.3, 8 ; A A A 0 + ret i32 %shl.4 +}