/* Implement division using vrecpe/vrecps with -funsafe-math-optimizations.  */

(define_expand "div<mode>3"
  [(set (match_operand:VCVTF 0 "s_register_operand" "=w")
        (div:VCVTF (match_operand:VCVTF 1 "s_register_operand" "w")
                  (match_operand:VCVTF 2 "s_register_operand" "w")))]
  "TARGET_NEON && !optimize_size
   && flag_unsafe_math_optimizations && flag_reciprocal_math"
  {
    rtx rec = gen_reg_rtx (<MODE>mode);
    rtx vrecps_temp = gen_reg_rtx (<MODE>mode);

    /* Reciprocal estimate.  */
    emit_insn (gen_neon_vrecpe<mode> (rec, operands[2]));

    /* Perform 2 iterations of newton-raphson method.
       Two iterations seem to be sufficient, for single floating point
       since each iteration doubles number of bits in accuracy.
       vrecpe -> 8 bits.
       +2 iterations -> 32 bits, which is greater than 24 bit precision in fp value.  */
    for (int i = 0; i < 2; i++)
      {
        emit_insn (gen_neon_vrecps<mode> (vrecps_temp, rec, operands[2]));
        emit_insn (gen_mul<mode>3 (rec, rec, vrecps_temp));
      }

    /* We now have reciprocal in rec, perform operands[0] = operands[1] * rec.  */
    emit_insn (gen_mul<mode>3 (operands[0], operands[1], rec));
    DONE;
  }
)