Abstract: A method is provided for prioritizing the entries in a database, where each entry is composed of multiple dimensions. Prioritization is required when there are multiple matches in the database. The number of matches can be the same as the number of entries in the database. To prioritize such a huge number of entries in a minimum number of clock cycles, a distributed prioritizer is implemented by partitioning stored binary data into half nibbles comprising of two bits of data each. Each half nibble is encoded into an expanded format allotting priority value to the stored encoded half nibbles. The stored encoded half nibbles are compared across a word array to determine an exact match.

Abstract: A range check array structure for searching and comparing external data from an external search data key is disclosed. The structure has data storage means with at least one of an upper limit field, and a lower limit field, and one or more bit lines running therethrough for transmitting an input data word for comparison with the stored data word range. The input data word being compared with a respective stored data word to detect a match that is indicated along a match line by the check array structure. The check array structure further includes a range match detection means connected to the match line to determine the match or mismatch of the applied data stream with the stored data in each range check cell.

Abstract: A range check array structure for searching and comparing external data from an external search data key is disclosed. The structure has data storage means with at least one of an upper limit field, and a lower limit field, and one or more bit lines running therethrough for transmitting an input data word for comparison with the stored data word range. The input data word being compared with a respective stored data word to detect a match that is indicated along a match line by the check array structure. The check array structure further includes a range match detection means connected to the match line to determine the match or mismatch of the applied data stream with the stored data in each range check cell.

Abstract: A method is provided for prioritizing the entries in a database, where each entry is composed of multiple dimensions. Prioritization is required when there are multiple matches in the database. The number of matches can be the same as the number of entries in the database. To prioritize such a huge number of entries in a minimum number of clock cycles, a distributed prioritizer is implemented by partitioning stored binary data into half nibbles comprising of two bits of data each. Each half nibble is encoded into an expanded format allotting priority value to the stored encoded half nibbles. The stored encoded half nibbles are compared across a word array to determine an exact match.