Rapid searching and matching of data to a dynamic set of signatures facilitating parallel processing and hardware acceleration

1. A method, in a data processing system, for matching data to a dynamic set of signatures, the method comprising:

creating a state transition, result, and mask (STR&M) table based on a set of signatures, wherein the STR&M table comprises a state column, a plurality of condition columns, a result column, and a mask column, wherein each condition column corresponds to a set of input conditions that result from applying an input symbol map to an input character value, wherein for a given state each condition column corresponds to a set of input conditions and provides a next state transition, wherein the result column provides an identifier of a matched signature or an indicator of no match, and wherein the mask column provides a mask for updating a result, wherein a first row of the STR&M table corresponds to an initial state, a last row of the STR&M table corresponds to a persistent final NO_MATCH state, and other rows of the STR&M table correspond to input strings with continuations to a signature;

executing scanner code in each of a plurality of hardware devices in parallel to form a plurality of matching engines;

loading the STR&M table into each of the plurality of matching engines;

responsive to receiving a plurality of input records at the plurality of matching engines, extracting input strings from the plurality of input records;

submitting the plurality of input strings for scanning by the plurality of matching engines;

scanning, by the scanner code in each given matching engine, the plurality of input strings based on the STR&M table, comprising:

for a current state, responsive to at least a portion of a current input string matching a set of conditions corresponding to a given condition column, updating a signature set match result based on a result value in the result column and a mask value in the mask column without use of branching logic; and

responsive to reaching an end of the current input string or the NO_MATCH state, returning the signature set match result; and

receiving signature set match results from the plurality of matching engines.

2. The method of claim 1 , wherein creating the STR&M table comprises:

receiving a signature set specification;

parsing and analyzing the signature set specification;

generating a Finite State Machine (FSM) table based on a result of the parsing and analyzing of the signature set specification; and

converting the FSM table to the STR&M table.

3. The method of claim 2 , wherein creating the STR&M table further comprises translating the STR&M table to a binary format.

4. The method of claim 2 , wherein the signature set specification is ordered to ensure that at any character position in an input string there is at most one prioritized signature match.

5. The method of claim 1 , wherein the scanner code uses the mask and result column values to update the signature matching result without use of branching logic as follows:

result=((result & ˜stPtr[s][MCOL])+(stPtr[s][RCOL] & stPtr[s][MCOL])),

where result is the signature set matching result so far from a previous character position, stPtr[s] is a pointer to the current state, stPtr[s][MCOL] is a value of the mask column of the current state, and stPtr[s][RCOL] is a value of the result column of the current state.

6. The method of claim 1 , wherein the scanner code in each matching engine sets a next state based on a current state and the input symbol using the STR&M table, and advances input to a next input symbol until the end of the given current input string is reached or the NO_MATCH state is reached.

7. The method of claim 1 , wherein responsive to a given matching engine receiving a new STR&M table in binary form, the given matching engine loads the new STR&M table.

8. The method of claim 1 , wherein the plurality of hardware devices comprise a plurality of Single Instruction Multiple Data (SIMD), Graphics Processing Unit (GPU), or Field Programmable Gate Array (FPGA) hardware devices.

9. The method of claim 8 , wherein extracting the input strings from the plurality of input records comprises communicating through a computing device interface.

10. The method of claim 9 , wherein the computing device interface comprises an Open Computing Language (OpenCL) application programming interface.

11. The method of claim 8 , wherein the plurality of hardware devices comprise a Compute Unified Device Architecture (CUDA) parallel computing platform.