US 8,069,102 B2Grant

Method and apparatus for processing financial information at hardware speeds using FPGA devices

Issue Date:2011-11-29

•34 Claims

•25 Drawing Sheets

Abstract

A method and apparatus use decision logic deployed on a reconfigurable logic device to process a stream of financial information at hardware speeds. The decision logic can be configured to perform data reduction operations on the financial information stream. Examples of such data reductions operations include data processing operations to compute a latest stock price, a minimum stock price, and a maximum stock price.

Metadata

Assignee

Washington University

Inventors

Ronald S. Indeck
Ron Kaplan Cytron
Mark Allen Franklin
Roger D. Chamberlain

Application Information

Application Number:US 11/561,615

Filing Date:2006-11-20

Priority Date:2002-05-21

Art Unit:3695

Classifications

IPC:

G06Q40/00

Patent Drawings (25 sheets)

Description

Cross Reference to Related Application

[0001] This application is a continuation of Ser. No. 10/153,151 filed May 21, 2002, now U.S. Pat. No. 7,139,743, the disclosure of which is incorporated herein by reference.

Background of the Invention

[0002] Indications are that the average database size and associated software support systems are growing at rates that are greater than the increase in processor performance (i.e., more than doubling roughly every 18 months). This is due to a number of factors including without limitation the desire to store more detailed information, to store information over longer periods of time, to merge databases from disparate organizations, and to deal with the large new databases which have arisen from emerging and important applications. For example, two emerging applications having large and rapidly growing databases are those connected with the genetics revolution and those associated with cataloging and accessing information on the Internet. In the case of the Internet, current industry estimates are that in excess of 1.5 million pages are added to the Internet each day. At the physical level this has been made possible by the remarkable growth in disk storage performance where magnetic storage density has been doubling every year or so for the past five years.

[0003] Search and retrieval functions are more easily performed on information when it is indexed. For example, with respect to financial information, it can be indexed by company name, stock symbol and price. Oftentimes, however, the information being searched is of a type that is either hard to categorize or index or which falls into multiple categories. As a result, the accuracy of a search for information is only as good as the accuracy and comprehensiveness of the index created therefor. In the case of the Internet, however, the information is not indexed. The bottleneck for indexing is the time taken to develop the reverse index needed to access web pages in reasonable time. For example, while there are search engines available, designing a search which will yield a manageable result is becoming increasingly difficult due to the large number of “hits” generated by less than a very detailed set of search instructions. For this reason, several “intelligent” search engines have been offered on the web, such as Google, which are intended to whittle down the search result using logic to eliminate presumed undesired “hits”.

[0004] With the next-generation Internet, ever-faster networks, and expansion of the Internet content, this bottleneck is becoming a critical concern. Further, it is becomingly exceedingly difficult to index information on a timely basis. In the case of the Internet, current industry estimates are that in excess of 1.5 million pages are added to the Internet each day. As a result, maintaining and updating a reverse index has become an enormous and continuous task and the bottleneck it causes is becoming a major impediment to the speed and accuracy of existing search and retrieval systems. Given the ever increasing amounts of information available, however, the ability to accurately and quickly search and retrieve desired information has become critical.

Description of Art

[0005] Associative memory devices for dealing with large databases are known in the prior art. Generally, these associative memory devices comprise peripheral memories for computers, computer networks, and the like, which operate asynchronously to the computer, network, etc. and provide increased efficiency for specialized searches. Additionally, it is also known in the prior art that these memory devices can include certain limited decision-making logic as an aid to a main CPU in accessing the peripheral memory. An example of such an associative memory device particularly adapted for use with a rotating memory such as a high speed disk or drum can be found in U.S. Pat. No. 3,906,455, the disclosure of which is incorporated herein by reference. This particular device provides a scheme for use with a rotating memory and teaches that two passes over a memory sector is necessary to presort and then sort the memory prior to performing any logical operations thereon. Thus, this device is taught as not being suitable for use with any linear or serial memory such as magnetic tape or the like.

[0006] Other examples of prior art devices may also be found in U.S. Pat. Nos. 3,729,712; 4,464,718; 5,050,075; 5,140,692; and 5,721,898; the disclosures of which are incorporated herein by reference.

[0007] As an example, in U.S. Pat. No. 4,464,718, Dixon performs fixed comparisons on a fixed number of bytes. They don't have the ability to scan and correlate arbitrarily over the data. They search serially along the tracks in a given disk cylinder but there is no provision for parallel searching across disks. Dixon's comparisons are limited by a fixed rigid number of standard logical operation types. Additionally, the circuitry presented supports only these single logical operations. There is no support for approximate or fuzzy matching.

[0008] While these prior art associative memory devices represent an attempt to speed the input and output of information to and from a peripheral memory, which in many cases is a mass storage memory device, all rely on the classic accessing of data stored in digital form by reading and interpreting the digital either address or content of the memory location. In other words, most such devices access data by its address but there are some devices that take advantage of the power of content addressing as is well known in the art. Nevertheless, in all of the prior art known to the inventors, the digital value of the address or data contained in the addressed location must be read and interpreted in its digital form in order to identify the data and then select it for processing. Not only does it take processing time to read and interpret the digital data represented by the address or content, this necessarily requires that the accessing circuit process the memory according to the structure of the data stored. In other words, if the data is stored in octets, then the accessing circuitry must access the data in octets and process it in an incremental manner. This “start and stop” processing serves to increase the input/output time required to access data. As is also well known in the art, this input/output time typically represents the bottleneck and effective limitation of processing power in any computer or computer network.

[0009] Furthermore, given the vast amount of information available to be searched, data reduction operations (i.e., the ability to summarize data in some aggregate form) has become critical. Oftentimes, the ability to quickly perform data reduction functions can provide a company with a significant competitive advantage.

[0010] Likewise, with the improvements in digital imaging technology, the ability to perform two dimensional matching such as on images has become necessary. For example, the ability to conduct matches on a particular image of an individual, such as his or her face or retina, or on a fingerprint, is becoming critical to law enforcement as it steps up its efforts on security in light of the Sep. 11, 2001 terrorist attacks. Image matching is also of importance to the military in the area of automatic target recognition.

[0011] Finally, existing searching devices cannot currently be quickly and easily reconfigured in response to changing application demands.

[0012] Accordingly, there is a need for an improved information search and retrieval system and method which overcomes these and other problems in the prior art.

[0013] In order to solve these and other problems in the prior art, the inventors herein have succeeded in designing and developing a method and apparatus for an associative memory using Field Programmable Gate Arrays (FPGA) in several embodiments described in the parent U.S. Pat. No. 7,139,743, which provide an elegantly simple solution to these prior art limitations as well as dramatically decreased access times for data stored in mass storage memories. As described below, the invention has several embodiments each of which has its own advantages.

[0014] U.S. Pat. No. 6,711,558, which is the parent of the '743 patent referenced above, discloses and claims the use of programmable logic and circuitry generally without being specific as to any choice between the various kinds of devices available for this part of the invention. In the '743 patent, the inventors disclose more specifically the use of FPGA's as part of the circuitry for various reasons as their best mode. There are several reasons for that. The first of these is speed. And, there are two different aspects of operation in which speed plays a part. The first of these is the speed of reconfiguration. It is known in the art that FPGA's may be quickly programmed in the field to optimize the search methodology using a template, the template having been prepared in advance and merely communicated to the FPGA's over a connecting bus. Should it then be desired to search using a different methodology, the FPGA's may then be quickly and conveniently re-programmed with another prepared template in a minimal number of clock cycles and the second search started immediately. Thus, with FPGA's as the re-configurable logic, shifting from one search to another is quite easy and quick, relative to other types of re-programmable logic devices.

[0015] A second aspect of speed is the amount of time required, once programmed, a search requires. As FPGA's are hardware devices, searching is done at hardware processing speeds which is orders of magnitude faster than at software processing speeds as would be experienced with a microprocessor, for example. Thus, FPGA's are desirable over other software implementations where speed is a consideration as it most often is.

[0016] In considering the use of templates, it is contemplated that at least several “generic” templates would be prepared in advance and would be available for use in performing text searching in either an absolute search, an approximate search, or a higher or advanced search mode incorporating a Boolean algebra logic capability, or a graphics search mode. These could then be stored in a CPU memory and be available either on command or loaded in automatically in response to a software queue indicating one of these searches.

[0017] Still another factor to consider is cost, and the recent price reductions in FPGA's have made them more feasible for implementation as a preferred embodiment for this application, especially as part of a hard disk drive accelerator as would be targeted for a pc market. It is fully expected that further cost reductions will add to the desirability of these for this implementation, as well as others as discussed in greater detail below.

[0018] Generally, various embodiments of the '743 patent describe a technique for data retrieval through approximate matching of a data key with a continuous reading of data as stored on a mass storage medium, using FPGA's to contain the template for the search and do the comparison, all in hardware and at essentially line speed. By utilizing FPGA's, the many advantages and features commonly known are made available. These include the ability to arrange the FPGA's in a “pipeline” orientation, in a “parallel” orientation, or even in an array incorporating a complex web overlay of interconnecting data paths allowing for complex searching algorithms. In its broadest, and perhaps most powerful, embodiment, the data key may be an analog signal and it is matched with an analog signal generated by a typical read/write device as it slews across the mass storage medium. In other words, the steps taught to be required in the prior art of not only reading the analog representation of digital data stored on the mass storage medium but also the conversion of that signal to its digital format prior to being compared are eliminated. Furthermore, there is no requirement that the data be “framed” or compared utilizing the structure or format in which the data has been organized and stored. For an analog signal, all that need be specified is the elapsed time of that signal which is used for comparison with a corresponding and continuously changing selected time portion of the “read” signal. Using any one of many standard correlation techniques as known in the prior art, the data “key” may then be approximately matched to the sliding “window” of data signal to determine a match. Significantly, the same amount of data may be scanned much more quickly and data matching the search request may be determined much more quickly as well. For example, the inventors have found that CPU based approximate searches of 200 megabytes of DNA sequences can take up to 10 seconds on a typical present day “high end” system, assuming the offline processing to index the database has already been completed. In that same 10 seconds, the inventors have found that a 10-gigabyte disk could be magnetically searched for approximate matches using the present invention. This represents a 50:1 improvement in performance. Furthermore, in a typical hard disk drive there are four surfaces and corresponding read/write heads, which may be all searched in parallel should each head be equipped with the present invention. As these searches can proceed in parallel, the total increase in speed or improvement represents a 200:1 advantage. Furthermore, additional hard disk drives may be accessed in parallel and scaled to further increase the advantage provided by the present invention.

[0019] By choosing an appropriate correlation or matching technique, and by setting an appropriate threshold, the search may be conducted to exactly match the desired signal, or more importantly and perhaps more powerfully, the threshold may be lowered to provide for approximate matching searches. This is generally considered a more powerful search mode in that databases may be scanned to find “hits” which may be valid even though the data may be only approximately that which is being sought. This allows searching to find data that has been corrupted, incorrectly entered data, data which only generally corresponds to a category, as well as other kinds of data searches that are highly desired in many applications. For example, a library of DNA sequences may be desired to be searched and hits found which represent an approximate match to a desired sequence of residues. This ensures that sequences which are close to the desired sequence are found and not discarded but for the difference in a forgivable number of residue mismatches. Given the ever-increasing volume and type of information desired to be searched, more complex searching techniques are needed. This is especially true in the area of molecular biology, “[O]ne of the most powerful methods for inferring the biological function of a gene (or the protein that it encodes) is by sequence similarity searching on protein and DNA sequence databases.” Garfield, “The Importance of (Sub)sequence Comparison in Molecular Biology,” pgs. 212-217, the disclosure of which is incorporated herein by reference. Current solutions for sequence matching are only available in software or non-reconfigurable hardware.

[0020] Still another application involves Internet searches provided by Internet search engines. In such a search, approximate matching allows for misspelled words, differently spelled words, and other variations to be accommodated without defeating a search or requiring a combinatorial number of specialized searches. This technique permits a search engine to provide a greater number of hits for any given search and ensure that a greater number of relevant web pages are found and cataloged in the search. Although, as mentioned above, this approximate matching casts a wider net which produces a greater number of “hits” which itself creates its own problems.

[0021] Still another possible application for the technology described in the '743 patent is for accessing databases which may be enormous in size or which may be stored as analog representations. For example, our society has seen the implementation of sound recording devices and their use in many forums including judicial proceedings. In recent history, tape recordings made in the President's oval office have risen in importance with respect to impeachment hearings. As can be appreciated, tape recordings made over the years of a presidency can accumulate into a huge database which might require a number of persons to actually listen to them in order to find instances where particular words are spoken that might be of interest. Utilizing the technology described in the '743 patent, an analog representation of that spoken word can be used as a key and sought to be matched while the database is scanned in a continuous manner and at rapid speed. Thus, the technology described in the '743 patent provides a powerful search tool for massive analog databases as well as massive digital databases.

[0022] While text-based searches are accommodated by the '743 patent as described above, storage media containing images, sound, and other representations have traditionally been more difficult to search than text. The '743 patent further describes embodiments that allow searching a large data base for the presence of such content or fragments thereof. For example, the key in this case could be a row or quadrant of pixels that represent the image being sought. Approximate matching of the key's signal can then allow identification of matches or near matches to the key. In still another image application, differences in pixels or groups of pixels can be searched and noted as results which can be important for satellite imaging where comparisons between images of the same geographic location are of interest as indicative of movement of equipment or troops.

[0023] The technology described in the '743 patent may be embodied in any of several configurations, as is noted more particularly below. However, one important embodiment is perhaps in the form of a disk drive accelerator which would be readily installed in any PC as an interface between the hard disk drive and the system bus. This disk drive accelerator could be provided with a set of standardized templates and would provide a “plug and play” solution for dramatically increasing the speed at which data could be accessed from the drive by the CPU. This would be an after market or retrofit device to be sold to the large installed base of PC's. It could also be provided as part of a new disk drive, packaged within the envelope of the drive case or enclosure for an external drive or provided as an additional plug in pc card as an adapter for an internal drive. Additional templates for various kinds of searches on various kinds of databases could be made available either with the purchase of the accelerator, such as by being encoded on a CD, or even over the Internet for download, as desired.

Brief Summary of the Invention

[0024] The present invention leverages the hardware acceleration and flexibility provided by reconfigurable logic devices to perform various operations on streaming data, particularly operations on streaming financial information such as data reduction operations (e.g., aggregate summarization operations). For example, in the financial industry, one might want to search financial information to identify a minimum, maximum, and latest price of a stock. The ability to perform data reduction searching such as this at high speeds cannot be under-estimated. One of the most valuable aspects of information is its timeliness. Companies that can quickly compute aggregate data reductions will clearly have a competitive advantage over those that cannot compute such aggregate data reductions as quickly.

[0025] Thus, in accordance with an exemplary aspect of the invention, the inventors disclose a method for processing financial information, the method comprising: (1) streaming financial information through a reconfigurable logic device, and (2) performing a data processing operation on the financial information with the reconfigurable logic device on a streaming basis as the financial information streams through the reconfigurable logic device.

[0026] In accordance with another exemplary aspect of the invention, the inventors disclose an apparatus for processing financial information, the apparatus comprising a reconfigurable logic device, wherein the reconfigurable logic device is configured to receive a stream of financial information and perform a data processing operation on the financial information on a streaming basis as the financial information streams through.

[0027] Moreover, in accordance with another exemplary aspect of the invention, the inventors disclose a method for processing financial information, the method comprising: (1) receiving a stream of financial information within a reconfigurable logic device, and (2) summarizing the received financial information in an aggregate form on a streaming basis using logic deployed on the reconfigurable logic device as the financial information streams through the reconfigurable logic device.

[0028] Furthermore, in accordance with another exemplary aspect of the invention, the inventors disclose a system comprising at least one reconfigurable logic device that is configured to (i) store a data key, (ii) receive a stream of target data, (iii) continuously match the target data against the data key to find matched data within target data, and (iv) summarize the matched data in an aggregate form, wherein the reconfigurable logic device is further configured to perform the continuous match operation and the summarization operation on a streaming basis as the target data streams through the reconfigurable logic device.

[0029] Further still, in accordance with yet another exemplary aspect of the invention, the inventors disclose a method comprising: (1) streaming target data into a reconfigurable logic device that has been loaded with a data key, (2) continuously matching the streaming target data against the data key to find matched data within the streaming target data, and (3) summarizing the matched data in an aggregate form, and wherein the matching step and the summarizing step are performed by the reconfigurable logic device on a streaming basis as the target data streams through the reconfigurable logic device.

[0030] While the principal advantages and features of the present invention have been briefly explained above, a more thorough understanding of the invention may be attained by referring to the drawings and description of the preferred embodiment which follow.

Brief Description of the Drawings

[0031] FIG. 1 is a block diagram illustrating an information search and retrieval system in accordance with one embodiment of the present invention;

[0032] FIG. 2 is a schematic of a conventional rigid disk drive system illustrating different insertion points for connection of the present invention;

[0033] FIG. 3 is a block diagram of one embodiment of the transformation of a search inquiry processed by the system of FIG. 1;

[0034] FIG. 4 is a block diagram of one embodiment of a hardware implementation of the present invention used to conduct an exact match search in a digital domain;

[0035] FIG. 5 is a block diagram of one embodiment of a hardware implementation of the present invention used to conduct an approximate match search in a digital domain;

[0036] FIG. 6 is a block diagram depicting the implementation of the present invention in a stand-alone configuration;

[0037] FIG. 7 is a block diagram depicting the present invention implemented as a shared remote mass storage device across a network;

[0038] FIG. 8 is a block diagram depicting the present invention as a network attached storage device (NASD);

[0039] FIG. 9 is a flowchart detailing the logical steps in the inventive method for searching and retrieving data from a magnetic storage medium;

[0040] FIG. 10 is a graphical representation of an analog signal as might be used as a data key;

[0041] FIG. 11 is a graphical representation of an analog signal representing the continuous reading of data from a magnetic storage medium in which the data key is present;

[0042] FIG. 12 is a graphical representation of the signal of FIG. 10 overlying and matched to the signal of FIG. 11;

[0043] FIG. 13 is a graphical representation of a correlation function calculated continuously as the target data in the magnetic storage medium is scanned and compared with the data key;

[0044] FIG. 14 is a graphical representation of a correlation function as the data key is continuously compared with a signal taken from reading a different set of target data from the magnetic storage medium but which also contains the data key;

[0045] FIG. 15 is one embodiment of a table generated by the present invention for use in performing sequence matching operations;

[0046] FIG. 16 is a block diagram of one embodiment of a systolic array architecture used by the present invention for computing the values of the table of FIG. 15;

[0047] FIGS. 17 and 18 are block diagrams of the systolic array architecture of FIG. 15 in operation during the combinational and latch part of the clock cycle, respectively, of the system of FIG. 1;

[0048] FIG. 19 is the table of FIG. 15 representing a particular sequence matching example;

[0049] FIG. 20 is a block diagram of the systolic array architecture of FIG. 16 for the example of FIG. 19;

[0050] FIGS. 20, 21 and 22 are block diagrams of the systolic array architecture of FIG. 20 in operation during the combinational and latch part of the clock cycle, respectively, of the system of FIG. 1;

[0051] FIG. 23 is a block diagram of one embodiment of a systolic array architecture used by the present invention in performing image matching operations;

[0052] FIG. 24 is a block diagram of another arrangement for the systolic array architecture in performing image matching operations;

[0053] FIG. 25 is a block diagram of one embodiment of an individual cell of the systolic array shown in FIG. 23;

[0054] FIG. 26 is a block diagram of another embodiment of an individual cell of the systolic array shown in FIG. 23;

[0055] FIG. 27 is a block diagram showing an example using the present invention for performing data reduction operations; and

[0056] FIG. 28 is a block diagram showing a more complex arrangement of FPGA's.

Detailed Description of the Preferred Embodiment

[0057] As shown in FIG. 1, the present invention is readily implemented in a stand-alone computer or computer system. In broad terms, the present invention is comprised of at least one re-configurable logic device 21 coupled to at least one magnetic mass storage medium 26, with that re-configurable logic device being an FPGA. As depicted in FIG. 1, the re-configurable logic device 21 may itself include a plurality of functional logic elements including a data shift register and possibly a microprocessor, or they could be on separate chips, or the individual logic elements could be configured in a pipeline or parallel orientation as shown in some of the other figures herein. In any event, re-configurable logic refers to any logic technology whose form and function can be significantly altered (i.e., reconfigured) in the field post-manufacture. Examples of re-configurable logic devices include without limitation programmable logic devices (PLDs). A PLD is an umbrella term for a variety of chips that are programmable. There are generally three physical structures for a PLD. The first is the permanent fuse type which blows apart lines or fuses them together by electrically melting an aluminum trace or insulator. This was the first type of PLD, known as a “programmable array logic” or PAL. The second type of PLD uses EEPROM or flash memory, and causes a transistor to open or close depending on the contents of its associated memory cell. The third type of PLD is RAM-based (which makes it dynamic and volatile), and its contents are loaded each time it starts up. An FPGA is an integrated circuit (IC) that contains an array of logic units that can be interconnected in an arbitrary manner. These logic units are referred to as CFB's or configurable logic blocks by one vendor (Xilinx). Both the specific function of each logic unit and the interconnections between logic units can be programmed in the field after manufacture of the IC. FPGAs are one of the most common PLD chips. FPGAs are available in all three structures. In the preferred embodiment of the present invention, re-configurable logic device 21 is constructed using Xilinx FPGA technology, and its configuration is developed using the Mentor synthesis tools and the Xilinx place-and-route tools, all of which are presently commercially available as known to those of skill in the art.

[0058] The re-configurable logic device 21 interfaces with the system or input/output bus 34 and, in one configuration, also interfaces with any disk caches 30 which may be present. It receives and processes search requests or inquires from the CPU 32 or network interface 36. Additionally, the device may aid in passing the results of the inquiries to either or both the disk cache 30 and/or the CPU 32 (by way of the bus 34).

[0059] The mass storage medium 26 provides the medium for storing large amounts of information which will hereafter be referred to as target data. The term “mass storage medium” should be understood as meaning any magnetic device used to store large amounts of data, and which is typically designated for use in a computer or computer network. Examples include without limitation hard disk drives or sub-units such as a single disk surface, and these systems may be rotating, linear, serial, parallel, or various combinations of each. For example, a rack of hard disk drive units could be connected in parallel and their parallel output provided at the transducer level to one or more re-configurable logic devices 21. Similarly, a bank of magnetic tape drives could be used, and their serial outputs each provided in parallel to one or more re-configurable logic devices 21. The data stored on the medium may be in analog or in digital form. For example, the data could be voice recordings. The present invention is thus scalable, permitting an increase in the amount of data stored by increasing the number of parallel mass storage media, while preserving the performance by increasing the number of parallel re-configurable logic devices or replicating the re-configurable logic device.

[0060] In the prior art as shown in the upper portion of FIG. 1, typically a disk controller 28 and/or a disk cache 30 may be used in the traditional sense for access by a CPU 32 over its system or input/output bus 34. The re-configurable logic device 21 accesses target data in the mass storage medium 26 via one or more data shift registers 24 and presents it for use at the system bus 34 without moving large blocks of memory from the mass storage medium 26 over the system bus 34 and into the working memory 33 of CPU 32 for sorting and accessing. In other words, as is explained in greater detail below, the CPU 32 may send a search request or inquiry to the re-configurable logic device 21 which then asynchronously accesses and sorts target data in the mass storage medium 26 and presents it for use either in a disk cache 30 as is known in the prior art or directly onto the system bus 34 without further processing being required by CPU 32 or use of its working memory 33. The CPU 32 is thus free to perform other tasks while the searching and matching activity is being performed by the present invention. Alternately, the control microprocessor may provide the search inquiry and template or programming instructions for the FPGA 21, and then perform the search and present the data on system bus 34 for access and use by CPU 32.

[0061] As has been explained above, the present invention may be used to perform a variety of different types of matching or data reduction operations on the target data. Each one of these operations will now be discussed in detail below. For all operations, however, it will be assumed that the target data is written onto the magnetic mass storage medium 26 with sufficient formatting information attached so that the logical structure of the target data can be extracted. Exact and approximate string matching will be described with reference to FIGS. 2-5. It can be appreciated, however, that the present invention is not limited to single string matches and is equally suitable for compound query matching (i.e., queries involving a plurality of text strings having a certain logical relationship therebetween or which use Boolean algebra logic). When performing an exact match with the re-configurable logic device 21 in the analog domain, shown as Point A in FIG. 2, where matching is done using analog comparators and correlation techniques, an exact match corresponds to setting a sufficiently high threshold value for matching the data key with analog target data on the mass storage medium 26. Approximate matching in the analog domain corresponds to setting appropriate (lesser) threshold values. The success of an approximate match may be determined by the correlation value set in the re-configurable logic device 21 or by using one of a number of matching-performance metrics stored therein such as the number of bits within a data key that are equal to the corresponding bits in the scanned target data.

[0062] More particularly, a conventional rigid disk drive may have a plurality of rotating disks with multiple transducers accessing each disk. Each of these transducers typically has its output feeding analog signal circuitry 18, such as amplifiers. This is represented at point A. As further shown in FIG. 2, typically the outputs of the analog circuitry are selectively provided to a single digital decoder 23 which then processes one such output. This is represented at point B. This digital output is typically then sent through error correction circuitry (ECC) 25 and at its output C is then passed on to the bus 34 or disk cache 30. For purposes of the present invention, it may be desirable to provide multiple parallel paths for target data by providing multiple digital decoders and ECC's. Exact matching in the digital domain could be performed at Point B or Point C, which corresponds to the pre- and post-error-corrected digital signal, respectively.

[0063] The results may be sent to a control microprocessor 22, which may or may not be configured as part of an FPGA, to execute logic associated with a compound or complex search inquiry. In the most general case, a compound search inquiry 40 will go through the transformation process illustrated in FIG. 3. In particular, the software system (not shown) that resides on the CPU 32 generates the search inquiry 40. This inquiry proceeds through a compiler 42, also located on the CPU 32, that is responsible for analyzing the search inquiry. There are three main results from this analysis: (1) determining the data key that will reside in the compare registers within the re-configurable logic device 21; (2) determining the combining logic that must be implemented in the control microprocessor 22; and (3) producing hardware description 44 in a standard hardware description language (HDL) format (or if possible retrieving one from a library) that will be used to generate synthesis commands 46 to the re-configurable logic device 21. Any commercially available HDL and associated compiler and synthesis tools may be used. The resulting logic functions may correspond to exact or inexact matches or wildcard operations and simple word level logic operations such as “and” and “or.” This synthesis information is sent to the control microprocessor 22 which acts to set up the re-configurable logic device 21, or FPGA. In the case of complex logic operations, a high-level language 48 such as C or C+ is used in conjunction with a compiler 50 to generate the appropriate synthesis commands to the microprocessor 22.

[0064] While the path shown in FIG. 3 is able to handle a wide range of potential search inquiries, it has the drawback that the latency introduced into the search process might be too long. If the time required for a search inquiry to flow through the transformations represented in FIG. 3 is of the same order as the time required to perform a search, the compilation process might become the performance bottleneck rather than the search itself. This issue can be addressed for a wide range of likely search inquiries by maintaining a set of precompiled hardware templates that handle the most common cases. These templates may be provided and maintained either in CPU 32 memory, made available through an off-line storage medium such as a CD, or even kept in the mass storage medium 26 itself. Still further, such templates may be communicated to CPU 32 such as over a network or the Internet.

[0065] One embodiment of such a hardware template 29 is illustrated in FIG. 4. In particular, the data shift register 27 contains target data streaming off the head (not shown) of one or more disks 19. A compare register stores the data key for which the user wishes to match. In the example shown, the data key is “Bagdad.” Fine-grained comparison logic device 31 performs element by element comparisons between the elements of the data shift register 27 and the compare register 35. The fine-grained comparison logic device 31 can be configured to be either case sensitive or case insensitive. Word-level comparison logic 37 is responsible for determining whether or not a match at the world-level occurs. In the case of a compound search inquiry, the word-level match signals are delivered to the control microprocessor 22 for evaluation thereof. A match to the compound search inquiry is then reported to the CPU 32 for further processing.

[0066] One embodiment of a hardware template for conducting approximate matching is illustrated in FIG. 5. In particular, the data shift register 27′ contains target data streaming off the head (not shown) of one or more disks 19′. A compare register 35′ stores the data key for which the user wishes to match. In the example shown, the data key is again “Bagdad.” Fine-grained comparison logic 31′ performs element by element comparisons between the elements of the data shift register 27′ and the compare register 21′. Again, the fine-grained comparison logic device 31′ can be configured to be either case sensitive or case insensitive. The template 29′ provides for alternate routing of elements in data shift register 27′ to individual cells of the fine-grained comparison logic device 21′. Specifically, each cell of the fine-grained comparison logic device 31′ can match more than one position in the data shift register 27′ such that the compare register 21′ can match both the commonly used spelling of “Baghdad” as well as the alternate “Bagdad” in shared hardware. Word-level comparison logic 37′ is responsible for determining whether or not a match at the word level occurs. In the case of a compound search inquiry, the word-level match signals are delivered to the control microprocessor 22 for evaluation thereof. A match to the compound search inquiry is then reported to the CPU 32 for further processing.

[0067] The actual configuration of the hardware template will of course vary with the search inquiry type. By providing a small amount of flexibility in the hardware templates (e.g., the target data stored in the compare registers, the routing of signals from the data shift registers and compare register elements to the cells of the fine-grained comparison logic device, and the width of the word-level comparison logic), such a template can support a wide range of word matches. As a result, this diminishes the frequency with which the full search inquiry transformation represented in FIG. 3 must take place, which in turn, increases the speed of the search.

[0068] It should be noted that the data entries identified in an “approximate” match search will include the “exact” hits that would result from an “exact” search. For clarity, when the word “match” is used, it should be understood that it includes a search or a data result found through either of an approximate search or an exact search. When the phrase “approximate match” or even just “approximate” is used, it should be understood that it could be either of the two searches described above as approximate searches, or for that matter any other kind of “fuzzy” search that has a big enough net to gather target data that are loosely related to the search inquiry or in particular, data key. Of course, an exact match is just that, and does not include any result other than an exact match of the search inquiry with a high degree of correlation.

[0069] Also shown in FIG. 1 is a network interface 36 interconnecting the present invention to a network 38 which may be a LAN, WAN, Internet, etc. and to which other computer systems 40 may be connected. With this arrangement, other computer systems 40 may conveniently also access the data stored on the mass storage medium 26 through the present invention 21. More specific examples are given below. Still further as shown in FIG. 1, the elements 20-24 may themselves be packaged together and form a disk drive accelerator that may be separately provided as a retrofit device for adapting existing pc's having their own disk drives with the advantages of the present invention. Alternately, the disk drive accelerator may also be offered as an option on a hard drive and packaged in the same enclosure for an external drive or provided as a separate pc board with connector interface for an internal drive. Still further alternatively, the disk drive accelerator may be offered as an option by pc suppliers as part of a pc ordered by a consumer, business or other end user. Still another embodiment could be that of being offered as part of a larger magnetic mass storage medium, or as an upgrade or retrofit kit for those applications or existing installations where the increased data handling capability could be used to good advantage.

[0070] As shown in FIGS. 6-8, the present invention may be implemented in a variety of computer and network configurations. As shown in FIG. 6, the present invention may be provided as part of a stand-alone computer system 41 comprising a CPU 43 connected to a system bus 45 which then accesses a mass storage medium 47 having the invention as disclosed herein.

[0071] As shown in FIG. 7, the mass storage medium 51 coupled with the present invention may be itself connected directly to a network 52 over which a plurality of independent computers or CPU's 54 may then access the mass storage medium 51. The mass storage medium 51 may itself be comprised of a bank of hard disk drives comprising a RAID, disk farm, or some other massively parallel memory device configuration to provide access and approximate matching capabilities to enormous amounts of data at significantly reduced access times.

[0072] As shown in FIG. 8, a mass storage medium 56 coupled with the present invention may be connected to a network 58 as a network attached storage device (NASD) such that over the network 58 a plurality of stand-alone computers 60 may have access thereto. With such a configuration, it is contemplated that each mass storage medium, represented for illustrative purposes only as a disk 57, would be accessible from any processor connected to the network. One such configuration would include assigning a unique IP address or other network address to each mass storage medium.

[0073] The configurations as exemplified by those shown in FIGS. 1 and 6-8 represent only examples of the various computer and network configurations with which the present invention would be compatible and highly useful. Others would be apparent to those having skill in the art and the present invention is not intended to be limited through the examples as shown herein which are meant to be instead illustrative of the versatility of the present invention.

[0074] As shown in FIG. 9, the method of the present invention for use in exact or approximate matching is described alternatively with respect to whether an analog or digital data domain is being searched. However, beginning at the start of the method, a CPU performs certain functions during which it may choose to access target data stored in a mass storage medium. Typically, the CPU runs a search inquiry application 62 which may be representative of a DNA search, an Internet search, an analog voice search, a fingerprint search, an image search, or some other such search during which an exact or approximate match to target data is desired. The search inquiry contains directives specifying various parameters which the disk control unit 28 and the re-configurable logic device 20 must have to properly obtain the data key from the mass storage medium 26. Examples of parameters include but are not limited to the following: the starting location for scanning the storage device; the final location after which (if there is not match) scanning is terminated; the data key to be used in the scanning; a specification of the approximate nature of the matching; and what information should be returned when a match occurs. The sort of information that can be returned includes the address of the information where the match was found, or a sector, record, portion of record or other data aggregate which contains the matched information. The data aggregate may also be dynamically specified in that the data returned on a match may be specified to be between bounding data specifiers with the matched data contained within the bounding field. As the example in FIG. 5 shows, looking for the word “bagdad” in a string of text might find the approximate match, due to misspelling, of the word “Baghdad”, and return a data field which is defined by the surrounding sentence. Another query parameter would indicate whether the returned information should be sent to the system or input/output bus 34, or the disk cache 30.

[0075] Referring back to FIG. 9, the search inquiry will typically result in the execution of one or more operating system utilities. As an example of a higher level utility command, for the UNIX operating system, this could be modified versions of glimpse, find, grep, apropos, etc. These functions cause the CPU to send commands 66 such as search, approximate search, etc., to the re-configurable logic device 21 with relevant portions of these commands also being sent to the disk controller 28 to, for example, initiate any mass storage medium positioning activity 69 that is later required for properly reading target data from the mass storage medium.

[0076] At this point, depending upon the particular methodology desired to be implemented in the particular embodiment of the invention, it would be necessary that an analog or digital data key is determined. This data key, which can be either exact or approximate for a text search, corresponds to the data being searched for. For an analog data key, it may either be pre-stored such as in the mass storage medium, developed using dedicated circuitry, or required to be generated. Should the analog data key be pre-stored, a send pre-stored data key step 68 would be performed by the microprocessor 22 (see FIG. 1) which would transmit the data key in digital and sampled format to the re-configurable logic device 20 as shown in step 70. Alternatively, should the analog data key not be pre-stored, it can be developed using one of a number of mechanisms, two of which are shown in FIG. 9. In one, the microprocessor 22 would write the data key on the magnetic mass storage medium as at step 72 and then next read the data key as at step 74 in order to generate an analog signal representation of the data key. In another, as at step 71, the digital version of the data key received from the CPU would be converted using appropriate digital to analog circuitry to an analog signal representation which would in turn be appropriately sampled. The data key would then next be stored as a digital sample thereof as in step 70. Should a digital data key be used, it is only necessary that the microprocessor 22 store the digital data key as at step 76 in the compare register of the re-configurable logic device. It should be understood that depending upon the particular structures desired to be included for each re-configurable logic device, the data key may reside in either or all of these components, it merely being preferable to ultimately get the appropriate digital format for the data key into the re-configurable logic device 21 for comparison and correlation.

[0077] Next, after the mass storage medium 26 reaches its starting location as at 79, the target data stored on the mass storage medium is continuously read as at step 78 to generate a continuous stream signal representative of the target data. Should an analog data key have been used, this analog data key may then be correlated with an analog read of the target data from the mass storage medium 26 as at step 80.

[0078] While the inventors contemplate that any of many prior art comparators and correlation circuitry could be used, for present purposes the inventors suggest that a digital sampling of the analog signal and data key could be quite useful for performing such comparison and calculating the correlation coefficient, as explained below. It is noted that this analog signal generated from reading the target data from mass storage medium 26 may be conveniently generated by devices in the prior art from the reading of either analog or digital data, it not being necessary that a digital data key be used to match digital target data as stored in mass storage medium 26. Alternatively, a correlation step 82 may be performed by matching the digital data key with a stream of digital target data as read from the mass storage medium 26. It should be noted that the data key may reflect the inclusion of approximate information or the re-configurable logic device 21 may be programmed to allow for same. Thus, correlating this with target data read from the mass storage medium enables approximate matching capabilities.

[0079] Referring back to FIG. 9, decision logic 84 next makes an intelligent decision as to whether a portion of the target data approximately matches or does not approximately match the data key. Should a match be found, then the target data is processed as at step 86 and the key data requested by the search inquiry is sent to a disk cache 30, directly onto system bus 34, or otherwise buffered or made available to a CPU 32, network interface 36, or otherwise as shown in FIGS. 1, and 6-8. A logical step 88 is preferably included for returning to the continuous reading of target data from the mass storage medium 26, indicating something like a “do” loop. However, it should be understood that this is a continuous process and that target data is processed from the mass storage medium 26 as a stream and not in individualized chunks, frames, bytes, or other predetermined portions of data. While this is not precluded, the present invention preferably allows a data key to be in essence “slid” over a continuously varying target data read signal such that there is no hesitation in reading target data from the mass storage medium 26. There is no requirement to synchronize reading to the start or end of any multi-bit data structure, or any other intermediate steps required to be performed as the target data is compared continuously “on the fly” as it is read from the mass storage medium 26. Eventually, the data access is completed as at step 90 and the process completed.

[0080] The inventors herein have preliminarily tested the present invention in the analog domain and have generated preliminary data demonstrate its operability and effectiveness. In particular, FIG. 10 is a graphical representation of a measured analog signal output from a read/write head as the read/write head reads a magnetic medium on which is stored a 10-bit digital data key. As shown therein, there are peaks in the analog signal which, as known in the art, represents the true analog signal generated by a read/write head as target data is read from a magnetic medium such as a hard disk. The scales shown in FIG. 10 are volts along the vertical axis and tenths of microseconds along the horizontal axis. As shown in FIG. 11, an analog signal is generated, again by a read/write head, as target data is read from a pseudo-random binary sequence stored in a test portion of a magnetic medium. The read signal does not provide an ideal square wave output when examined at this level.

[0081] FIG. 12 is a graphical representation, with the horizontal scale expanded, to more specifically illustrate the overlap between approximately two bits of the 8-bit data key and the corresponding two bits of target data found in the pseudo-random binary sequence encoded at a different location on the disk or magnetic medium.

[0082] FIG. 13 is a graphical representation of a correlation coefficient calculated continuously as the comparison is made between the data key and the continuous reading of target data from the hard disk. This correlation coefficient is calculated by sampling the analog signals at a high rate and using prior art signal processing correlation techniques. One such example may be found in Spatial Noise Phenomena of Longitudinal Magnetic Recording Media by Hoinville, Indeck and Muller, IEEE Transactions on Magnetics, Volume 28, no. 6, November 1992, the disclosure of which is incorporated herein by reference. A prior example of a reading, comparison, and coefficient calculation method and apparatus may be found in one or more of one of the co-inventor's prior patents, such as U.S. Pat. No. 5,740,244, the disclosure of which is incorporated herein by reference. The foregoing represent examples of devices and methods which may be used to implement the present invention, however, as mentioned elsewhere herein, other similar devices and methods may be likewise used and the purposes of the invention fulfilled.

[0083] As shown in FIG. 13, at approximately the point labeled 325, a distinct peak is noted at approximately 200 microseconds which approaches 1 Volt, indicating a very close match between the data key and the target data. FIG. 10 is also illustrative of the opportunity for approximate matching which is believed to be a powerful aspect of the present invention. Looking closely at FIG. 13, it is noted that there are other lesser peaks that appear in the correlation coefficient. Thus, if a threshold of 0.4 Volts were established as a decision point, then not only the peak occurring which approaches 1 would indicate a match or “hit” but also another five peaks would be indicative of a “hit”. In this manner, a desired coefficient value may be adjusted or predetermined as desired to suit particular search parameters. For example, when searching for a particular word in a large body of text, lower correlation values may indicate the word is present but misspelled.

[0084] FIG. 14 depicts the continuous calculation of a correlation coefficient between the same 8-bit data key but with a different target data set. Again, a single match is picked up at approximately 200 microseconds where the peak approaches 1 Volt. It is also noted that should a lower threshold be established additional hits would also be located in the target data.

[0085] As previously mentioned, the present invention is also capable of performing sequence matching searches. With reference to FIG. 15, a table 38 is generated by the re-configurable logic device 20 to conduct such a search. Specifically, p₁p₂p₃p₄represents the data key, p, or desired sequence to be searched. While the data key of FIG. 15 only shows four characters, this is for illustrative purposes only and it should be appreciated that a typical data key size for sequence searching is on the order of 500-1000, or even higher. The symbols t₁, t₂, t₃. . . t₉represent the target data, t, streaming off of the mass storage medium 26. Again, while only nine (9) characters of such data are shown, it should be appreciated that the typical size of the mass storage medium 26 and thus the target data streaming off of it can typically be in the range of several billion characters. The symbols d_i,jrepresent the edit distance at position i in the data key and position j in the target data. It is assumed that the data key is shorter relative to the target data, although it is not required to be so. There may be a set of known (constant) values for an additional row (d0,j) and column (di,0) not shown in FIG. 15.

[0086] The values for di,j are computed by the re-configurable logic device 20 using the fact that di,j is only a function of the following characters: (1) pi, (2) tj, (3) di−1,j−1, (4) di−1,j, and (5) di,j−1. This is illustrated in FIG. 15 with respect to the position d3,6 by showing its dependency on the values of d2,5 and d2,6 and d3,5 as well as p3 and t6. In one embodiment, the values for di,j are computed as follows:
di,j=max[di,j−1+A; di−1,j+A; di−1,j−1+Bi,j],
where A is a constant and Bi,j is a tabular function of pi and tj. The form of the function, however, can be quite arbitrary. In the biological literature, B is referred to as the scoring function. In the popular database searching program BLAST, scores are only a function of whether or not pi=tj. In other contexts, such as for amino acid sequences, the value of B is dependent upon the specific characters in p and t.

[0087] FIG. 16 shows one embodiment of a systolic array architecture used by the present invention to compute the values in the table 38 of FIG. 15. The characters of the data key are stored in the column of data registers 53, while the characters of the target data streaming off of the mass storage medium 26 are stored in the data shift registers 55. The values of di,j are stored in the systolic cells 59 which themselves are preferably FPGA's.

[0088] The operation of the array of FIG. 16 will now be illustrated using FIGS. 17 and 18. As shown in FIG. 17, in the first (i.e., combinational) part of the clock cycle of the system, the four underlined values are computed. For example, the new value d3,6 is shown to depend upon the same five values illustrated earlier in FIG. 15. As shown in FIG. 18, in the second (i.e., latch) part of the clock cycle, all the characters in di,j and tj are shifted one position to the right. A comparator 61 is positioned at each diagonal cell of the d array and determines when the threshold has been exceeded.

[0089] The sequence matching operation will now be described with reference to FIGS. 19-22 with respect to the following example:

- [0090] key=axbacs
- [0091] target data=pqraxabcstvq
- [0092] A=1
- [0093] B=2, if i=j
- [0094] B=−2 if i=j
  From these variables, the table of FIG. 19 is generated by the re-configurable logic device 20. Assuming a pre-determined threshold of “8”, the re-configurable logic device 20 will recognize a match at d6,9.

[0095] A portion of the synthesis arrays representing the values present in FIGS. 16-18 for this example are shown in FIGS. 20-22, respectively. A match is identified by the re-configurable logic device 20 when the value on any row exceeds a predetermined threshold. The threshold is set based on the desired degree of similarity desired between the data key and the target data stored in mass memory device 26. For example, in the case of an exact match search, the data key and target data must be identical. The match is then examined by the CPU 32 via a traceback operation with the table of FIG. 19. Specifically a “snapshot” of the table is sent to the CPU 32 at a predetermined time interval to assist in traceback operations once a match is identified. The interval is preferably not too often to overburden the CPU 32, but not so infrequent that it takes a lot of time and processing to recreate the table. To enable the CPU 32 to perform the traceback operation, it must be able to recreate the d array in the area surrounding the entry in the table that exceeded the threshold. To support this requirement, the systolic array can periodically output the values of a complete column of d (“a snapshot”) to the CPU 32. This will enable the CPU 32 to recreate any required portion of d greater than the index j of the snapshot.

[0096] Many matching applications operate on data representing a two dimensional entity, such as an image. FIG. 23 illustrates a systolic array 120 of re-configurable logic devices 20, preferably FPGA's, which enables matches on two dimensional data. The individual cells 122 each hold one pixel of the image for which the user is desiring to match (the image key) and one pixel of the image being searched (the target image). For images of sufficiently large size, it is likely they will not all fit into one re-configurable logic chip 124. In such cases, a candidate partitioning of cells to chips is shown with the dashed lines, placing a rectangular subarray of cells in each chip 124. The number of chip-to-chip connections can be minimized by using a subarray that is square (i.e., same number of cells in the vertical and horizontal dimension). Other more complicated arrangements are shown below.

[0097] Loading of the target image into the array 120 is explained using FIG. 24. Individual rows of each target image streaming off the mass magnetic medium 26, shown generally as point A, into the top row 130 of the array via the horizontal links 134 connecting each cell. With such a configuration, the top row 130 operates as a data shift register. When the entire row 130 is loaded, the row is shifted down to the next row 132 via the vertical links 136 shown in each column. Once the entire image is loaded into the array, a comparison operation is performed, which might require arbitrary communication between neighboring cells. This is supported by both the horizontal and vertical bi-directional links 126 and 128, respectively, shown in FIG. 23.

[0098] Although for simplicity purposes the individual bi-directional links 126 and 128 are shown simply in FIGS. 23 and 24, FIG. 28 shows the flexibility for implementing a much more complex set of bi-directional links. As shown in FIG. 28, data may be communicated from a mass storage medium 180 and be input to a first row of a plurality of cells 182, with each cell of the first row having a direct link to the corresponding cell 184 below it in a second row of cells with a simple link 186, and so on throughout the array 188 of cells. Overlying the array 188 of cells is a connector web 190 which provides direct connectivity between any two cells within the array without the need for transmission through any intervening cell. The output of the array 188 is represented by the sum of the exit links 192 at the bottom of the array 188. It should be understood that each cell in the array may be comprised of an FPGA, each one of which preferably has a re-configurable logic element corresponding to element 20 in FIG. 1, or any one of which may have a re-configurable logic element 20 as well as a data shift register 24, or any one of which may have the entirety of re-configurable logic device 21.

[0099] One embodiment for the individual cells of array 120 is illustrated in FIG. 25. The cell 140 includes a pixel register 142, LOADTi,j, which contains the pixels of the target image currently being loaded into the array. A register, 144 CMPTi,j, contains a copy of the pixel register 142 once the complete target image has been loaded. This configuration enables the last target image loaded to be compared in parallel with the next target image being loaded, essentially establishing a pipelined sequence of load, compare, load, compare, etc. A register 146, CMPPi,j, contains the pixels of the image key to be used for comparison purposes, and the compare logic 148 performs the matching operation between register 144 and register 146. The compare logic 148 may include the ability to communicate with the neighboring cells to the left, right, up, and down shown generally as 150, 152, 154, and 156, respectively, to allow for complex matching functions.

[0100] Another embodiment for the individual cells of array 120 of FIG. 23 is illustrated in FIG. 26. The cell 140 of FIG. 25 has been augmented to support simultaneous loading of the image key and the target image. In particular, the cell 160 includes the same components of the cell 140, but adds a new register 162, LOADPi,j, which is used to load the image key, and is operated in the same manner as register 142. With such a configuration, if one disk read head of the mass storage medium 26 is positioned above the image key, and a second disk read head is positioned above the target image, they can both flow off the disk in parallel and be concurrently loaded into the array 160.

[0101] The operation performed within the compare logic block can be any function that provides a judgment as to whether or not there are significant differences between the target image and the image key. An example includes cross-correlations across the entire image or sub-regions of the image as described in John C. Russ, The Image Processing Handbook, 3^rdedition, CRC Press 1999, which is incorporated herein by reference.

[0102] The present invention is also capable of performing data reduction searching. Such searching involves matching as previously described herein, but includes summarizing the matched data in some aggregate form. For example, in the financial industry, one might want to search financial information to identify a minimum, maximum, and latest price of a stock. A re-configurable logic device for computing such aggregate data reductions is illustrated as 100 in FIG. 27. Here, a data shift register 102 reads target data from a mass storage medium containing stock price information. In the example shown, three data reduction searches are shown, namely calculating the minimum price, the maximum price, and the latest price. As target data is fed into the data shift register 102, decision logic computes the desired data reduction operation. In particular, the stock price is fed to a minimum price comparator 110 and maximum price comparator 112 and stored therein. Each time a stock price is fed to comparator 110, it compares the last stored stock price to the stock price currently being fed to it and whichever is lower is stored in data register 104. Likewise, each time a stock price is fed to comparator 112, it compares the last stored stock price to the stock price currently being fed to it and whichever is higher is stored in data register 106. In order to compute the latest price, the stock price is fed into a data register 108 and the current time is fed into a comparator 114. Each time a time value is fed into comparator 114, it compares the last stored time with the current time and which ever is greater is stored in data register 116. Then, at the end of the desired time interval for which a calculation is being made, the latest price is determined.

[0103] While data reduction searching has been described with respect to the very simple financial example shown in FIG. 27, it can be appreciated that the present invention can perform data reduction searching for a variety of different applications of varying complexity requiring such functionality. The re-configurable logic device need simply be configured with the hardware and/or software to perform the necessary functions

[0104] The ability to perform data reduction searching at disk rotational speeds cannot be under-estimated. One of the most valuable aspects of information is its timeliness. People are growing to expect things at Internet speed. Companies that can quickly compute aggregate data reductions will clearly have a competitive advantage over those that cannot.

[0105] Various changes and modifications to the present invention would be apparent to those skilled in the art but yet which would not depart from the spirit of the invention. The preferred embodiment describes an implementation of the invention but this description is intended to be merely illustrative. Several alternatives have been also been above. For example, all of the operations exemplified by the analog processing have their equivalent counterparts in the digital domain. Thus, approximate matching and correlation types of processing can be done on the standard digital representation of the analog bit patterns. This can also be achieved in a continuous fashion using tailored digital logic, microprocessors and digital signal processors, or alternative combinations. It is therefore the inventors' intention that the present invention be limited solely by the scope of the claims appended hereto, and their legal equivalents.

Claims

What is claimed is:

1. A system for accelerated data reduction with respect to financial information, the system comprising:

at least one field programmable gate array (FPGA) having a hardware template deployed thereon for configuring the FPGA to perform a data reduction operation on streaming financial information, the hardware template deployed on the FPGA defining matching hardware logic and downstream summarization hardware logic that are resident on the FPGA;

wherein the matching hardware logic comprises a first data register configured to store a data key, and wherein the matching hardware logic is configured to (1) receive a stream of financial information, the financial information comprising a plurality of stock symbols and their associated stock prices, each stock price having an associated time, and (2) match the financial information against the data key to find matched data within the financial information, wherein the matched data comprises a plurality of stock prices and times for a stock;

wherein the summarization hardware logic comprises:

a data shift register, wherein the FPGA is further configured to stream the stock prices and times within the matched data through the data shift register;

a second data register configured to store a most recent minimum stock price for the stock of the matched data;

a third data register configured to store a most recent maximum stock price for the stock of the matched data;

a fourth data register configured to store a most recent latest stock price for the stock of the matched data;

a fifth data register configured to store a most recent time;

a first comparator;

a second comparator; and

a third comparator;

wherein the first comparator is configured to, as the stock prices and times stream through the data shift register, compare a current stock price in the data shift register with the stored most recent minimum stock price to determine which is lower; and

wherein the summarization hardware logic is further configured to update the stored most recent minimum stock price in the first data register with the current stock price in response to a determination by the first comparator that the current stock price is lower;

wherein the second comparator is configured to, as the stock prices and times stream through the data shift register, compare the current stock price in the data shift register with the stored most recent maximum stock price to determine which is higher;

wherein the summarization hardware logic is further configured to update the stored most recent maximum stock price in the second data register with the current stock price in response to a determination by the second comparator that the current stock price is higher;

wherein the third comparator is configured to, as the stock prices and times stream through the data shift register, compare the current time in the data shift register with the stored most recent time to determine which is later;

wherein the summarization hardware logic is further configured to update the stored most recent latest stock price in the third data register with the current stock price in the data shift register in response to a determination by the third comparator that the current time is later;

wherein the first, second, and third comparators are in a parallel orientation such that the first, second, and third comparators operate simultaneously with each other; and wherein the matching hardware logic and the summarization hardware logic are configured in a pipelined orientation such that the matching hardware logic and the summarization hardware logic operate simultaneously with each other, the summarization hardware logic being configured to operate on matched data previously found by the matching hardware logic while the matching hardware logic is configured to operate on new streaming financial information, the matching hardware logic and the summarization hardware logic thereby being configured to simultaneously operate together to generate a running computation of the minimum price, the maximum price, and the latest price for the stock prices within the matched data on a streaming basis as the financial information streams through the FPGA.

2. The system of claim 1 wherein the matching hardware logic is further configured to perform an exact match operation between the stream of financial information and the data key such that the matched data comprises exactly matched data.

3. The system of claim 1 wherein the matching hardware logic is further configured to perform the match operation on a frame-by-frame basis.

4. The system of claim 1 wherein the matching hardware logic is further configured to perform the match operation on a frameless basis.

5. The system of claim 1 wherein the matching hardware logic is further configured to perform an approximate match operation between the stream of financial information and the data key such that the matched data comprises approximately matched data.

6. The system of claim 1 further comprising a network interface, the network interface for receiving the hardware template from a remote source via a network.

7. The system of claim 1 wherein the matching hardware logic and the summarization hardware logic are configured to operate at hardware processing speeds.

8. The system of claim 1 further comprising:

at least one data storage device in communication with the FPGA, the at least one data storage device being configured to at least temporarily store the financial information; and

wherein the FPGA is further configured to read the financial information from the at least one data storage device to thereby receive the financial information stream.

9. The system of claim 8 wherein the at least one data storage device comprises a mass storage medium.

10. The system of claim 1 wherein the first data register comprises a plurality of cells configured to store elements of the data key, and wherein the matching hardware logic further comprises:

a second data shift register, the second data shift register having a plurality of cells configured to store elements of the streaming financial information, wherein each second data shift register cell has a corresponding first data register cell;

a fine-grained comparison logic device, the fine-grained comparison logic device being configured to perform an element-by-element comparison as between the financial information elements and data key elements stored within corresponding ones of the second data shift register cells and first data register cells; and

word-level comparison logic, the word-level comparison logic being configured to find the matched data based on the element-by-element comparison from the fine-grained comparison logic device; and

wherein the second data shift register is configured to continuously shift elements of the financial information from one second data shift register cell to the next.

11. The system of claim 10 wherein the fine-grained comparison logic device comprises a plurality of cells, each fine-grained comparison logic cell being in communication with a first data register cell and at least one second data shift register cell, and wherein the matching hardware logic is further configured to route financial information elements from at least one of the second data shift register cells to a plurality of different fine-grained comparison logic cells as the elements of the streaming financial information shift from one cell to the next within the second data shift register to thereby support approximate matching.

12. The system of claim 1 further comprising a memory for storing the hardware template, wherein the FPGA is configured to receive the hardware template from the memory for loading onto the FPGA to thereby configure the FPGA for performing the data reduction operation on streaming financial information.

13. The system of claim 12 further comprising:

a processor that is in communication with the FPGA, wherein the processor is configured to execute a software program, the software program being configured to transform an inquiry into the hardware template and communicate the hardware template to the memory for loading onto the FPGA.

14. The system of claim 13 further comprising:

a system bus, wherein the FPGA is in communication with the system bus; and

wherein the processor is in communication with the FPGA via the system bus; and

wherein the FPGA is further configured to provide the computed minimum, maximum and latest stock prices to the system bus for access by the processor.

15. The system of claim 13 further comprising:

a cache, wherein the FPGA is in communication with the cache; and

wherein the processor is in communication with the cache; and

wherein the FPGA is further configured to provide the computed minimum, maximum and latest stock prices to the cache for access by the processor.

16. The system of claim 13 wherein the hardware template is configured to support a plurality of different word matches for the matching hardware logic without requiring that a new hardware template be loaded onto the FPGA, and wherein the software program is further configured to determine a new data key and communicate the new data key to the FPGA for loading into the first data register to thereby modify the matching hardware logic to search for the new data key within the streaming financial information.

17. The system of claim 13 wherein the memory is configured to store a plurality of pre-compiled hardware templates, each pre-compiled hardware template defining a different data processing operation to be performed by the FPGA, wherein at least one of the pre-compiled hardware templates comprises the hardware template for performing the data reduction operation on streaming financial information; and

wherein the software program is further configured to, in response to the inquiry processing, select one of the stored pre-compiled hardware templates for communication from the memory to the FPGA to thereby transform the FPGA to perform the data processing operation defined by the selected pre-compiled hardware template.

18. A method for accelerated data reduction with respect to financial information, the method comprising:

receiving, by at least one field programmable gate array (FPGA), streaming financial information, the financial information comprising a plurality of stock symbols and their associated stock prices, each stock price having an associated time, the FPGA having a hardware template deployed thereon that configures the FPGA to perform a data reduction operation on streaming financial information, the hardware template deployed on the FPGA defining matching hardware logic and downstream summarization hardware logic that are resident on the FPGA;

storing a data key in a first data register, the first data register being a part of the matching hardware logic;

matching the financial information against the data key to find matched data within the financial information, wherein the matched data comprises a plurality of stock prices and times for a stock, the matching step being performed by the matching hardware logic;

streaming the stock prices and times within the matched data through a data shift register, the data shift register being a part of the summarization hardware logic;

storing a most recent minimum stock price for the stock of the matched data in a second data register;

storing a most recent maximum stock price for the stock of the matched data in a third data register;

storing a most recent latest stock price for the stock of the matched data in a fourth data register;

storing a most recent time in a fifth data register; and

as the stock prices and times stream through the data shift register, (i) comparing a current stock price in the data shift register with the stored most recent minimum stock price to determine which is lower using a first comparator, the first comparator being a part of the summarization hardware logic, (ii) updating the stored most recent minimum stock price with the current stock price if the minimum price comparing step results in a determination that the current stock price is lower, (iii) comparing the current stock price in the data shift register with the stored most recent maximum stock price to determine which is higher using a second comparator, the second comparator being a part of the summarization hardware logic, (iv) updating the stored most recent maximum stock price with the current stock price if the maximum price comparing step results in a determination that the current stock price is higher, (v) comparing a current time in the data shift register with the stored most recent time to determine which is later using a third comparator, the third comparator being a part of the summarization hardware logic, and (vi) updating the stored most recent latest stock price with the current stock price in the data shift register if the latest price comparing step results in a determination that the current time is later;

wherein the first, second, and third comparators are in a parallel orientation such that the minimum price comparing step, the maximum price comparing step, and the latest price comparing step operate simultaneously with respect to each other; and

wherein the matching hardware logic and the summarization hardware logic are configured in a pipelined orientation such that the matching step and the comparing steps are performed simultaneously with each other, the comparing steps operating on matched data previously found by the matching step while the matching step operates on new streaming financial information, the matching hardware logic and the summarization hardware logic thereby operating together simultaneously to generate a running computation of the minimum price, the maximum price, and the latest price for the stock prices within the matched data on a streaming basis as the financial information streams through the FPGA.

19. The method of claim 18 wherein the matching step comprises the matching hardware logic performing an exact match operation between the streaming financial information and the data key such that the matched data comprises exactly matched data.

20. The method of claim 18 wherein the matching step comprises the matching hardware logic performing the matching step on a frame-by-frame basis.

21. The method of claim 18 wherein the matching step comprises the matching hardware logic performing the matching step on a frameless basis.

22. The method of claim 18 wherein the matching step comprises the matching hardware logic performing an approximate match operation between the streaming financial information and the data key such that the matched data comprises approximately matched data.

23. The method of claim 18 further comprising:

a network interface receiving the hardware template from a remote source via a network; and

loading the received hardware template onto the FPGA to thereby configure the FPGA for performing the data reduction operation on streaming financial information.

24. The method of claim 18 wherein the FPGA performs the method steps at hardware processing speeds.

25. The method of claim 18 wherein the receiving step comprises:

the FPGA reading the financial information from a data storage device to thereby receive the stream of financial information.

26. The method of claim 25 wherein the data storage device comprises a mass storage medium.

27. The method of claim 18 further comprising:

loading the data key into the first data register, the first data register having a plurality of cells in which elements of the data key are stored;

the FPGA (i) loading the streaming financial information into a second data shift register, the second data shift register being a part of the matching hardware logic, the second data shift register having a plurality of cells in which elements of the streaming financial information are stored, wherein each second data shift register cell has a corresponding first data register cell, and (ii) streaming the financial information elements through the second data shift register cells;

wherein the matching step comprises the matching hardware logic (i) performing an element-by-element comparison as between the financial information elements and data key elements stored within corresponding ones of the second data shift register cells and the first data register cells using a fine-grained comparison logic device, the fine-grained comparison logic device being a part of the matching hardware logic, and (ii) responsive to the comparison by the fine-grained comparison logic device, finding the matched data using word-level comparison logic, the word-level comparison logic device being a part of the matching hardware logic; and

wherein the matching hardware logic performs the matching step continuously as the elements of the streaming financial information shift from one cell to the next within the second data shift register.

28. The method of claim 27 wherein the fine-grained comparison logic device comprises a plurality of cells, each fine-grained comparison logic cell being in communication with a first data register cell and at least one second data shift register cell, and wherein the matching step comprises the matching hardware logic routing financial information elements from at least one of the second data shift register cells to a plurality of different fine-grained comparison logic cells as the elements of the streaming financial information shift from one cell to the next within the second data shift register to thereby support approximate matching.

29. The method of claim 18 further comprising:

storing the hardware template in a memory;

the FPGA receiving the hardware template from the memory; and

loading the received hardware template onto the FPGA to thereby configure the FPGA for performing the data reduction operation on streaming financial information.

30. The method of claim 29 further comprising:

executing a software program on a processor that is in communication with the FPGA, wherein the executing step comprises the processor processing an inquiry to transform the inquiry into the hardware template;

communicating the hardware template to the memory; and

loading the communicated hardware template from the memory onto the FPGA.

31. The method of claim 30 further comprising:

the FPGA communicating the computed minimum, maximum and latest stock prices to a system bus; and

reading the communicated minimum, maximum and latest stock prices with a processor from the system bus.

32. The method of claim 30 further comprising:

the FPGA communicating the computed minimum, maximum and latest stock prices to a cache; and

reading the communicated minimum, maximum and latest stock prices with a processor from the cache.

33. The method of claim 30 wherein the hardware template is configured to support a plurality of different word matches for the matching step without requiring that a new hardware template be loaded onto the FPGA, wherein the executing step comprises the processor processing an inquiry to determine a new data key, the method further comprising:

communicating the new data key to the FPGA; and

loading the new data key into the first data register to thereby modify the matching step to search for the new data key within the streaming financial information.

34. The method of claim 30 further comprising:

storing a plurality of pre-compiled hardware templates in the memory, each pre-compiled hardware template defining a different data processing operation to be performed by the FPGA, wherein at least one of the pre-compiled hardware templates comprises the hardware template for performing the data reduction operation on the streaming financial information; and

wherein the executing step comprises the processor processing an inquiry to select one of the stored pre-compiled hardware templates for communication from the memory to the FPGA to thereby transform the FPGA to perform the data processing operation defined by the selected pre-compiled hardware template.

Patent Citations (332)

Patent	Date	Inventor	Cited By
US2046381(A)	1936-07-01	Hicks et al.	Applicant
US3082402(A)	1963-03-01	Scantlin	Applicant
US3296597(A)	1967-01-01	Scantlin et al.	Applicant
US3573747(A)	1971-04-01	Adams et al.	Applicant
US3581072(A)	1971-05-01	Nymeyer et al.	Applicant
US3601808(A)	1971-08-01	Vlack	Applicant
US3611314(A)	1971-10-01	Pritchard et al.	Applicant
US3729712(A)	1973-04-01	Glassman	Applicant
US3824375(A)	1974-07-01	Gross et al.	Applicant
US3848235(A)	1974-11-01	Lewis et al.	Applicant
US3906455(A)	1975-09-01	Houston et al.	Applicant
US4081607(A)	1978-03-01	Vitols et al.	Applicant
US4298898(A)	1981-11-01	Cardot	Applicant
US4314356(A)	1982-02-01	Scarbrough	Applicant
US4385393(A)	1983-05-01	Chaure et al.	Applicant
US4412287(A)	1983-10-01	Braddock, III	Applicant
US4464718(A)	1984-08-01	Dixon et al.	Applicant
US4550436(A)	1985-10-01	Freeman et al.	Applicant
US4674044(A)	1987-06-01	Kalmus et al.	Applicant
US4823306(A)	1989-04-01	Barbic et al.	Applicant
US4903201(A)	1990-02-01	Wagner	Applicant
US4941178(A)	1990-07-01	Chuang	Applicant
US5023910(A)	1991-06-01	Thomson	Applicant
US5038284(A)	1991-08-01	Kramer	Applicant
US5050075(A)	1991-09-01	Herman et al.	Applicant
US5063507(A)	1991-11-01	Lindsey et al.	Applicant
US5077665(A)	1991-12-01	Silverman et al.	Applicant
US5101353(A)	1992-03-01	Lupien et al.	Applicant
US5101424(A)	1992-03-01	Clayton et al.	Applicant
US5126936(A)	1992-06-01	Champion et al.	Applicant
US5140692(A)	1992-08-01	Morita	Applicant
US5161103(A)	1992-11-01	Kosaka et al.	Applicant
US5163131(A)	1992-11-01	Row et al.	Applicant
US5179626(A)	1993-01-01	Thomson	Applicant
US5226165(A)	1993-07-01	Martin	Applicant
US5243655(A)	1993-09-01	Wang	Applicant
US5249292(A)	1993-09-01	Chiappa	Applicant
US5255136(A)	1993-10-01	Machado et al.	Applicant
US5258908(A)	1993-11-01	Hartheimer et al.	Applicant
US5265065(A)	1993-11-01	Turtle	Applicant
US5267148(A)	1993-11-01	Kosaka et al.	Applicant
US5270922(A)	1993-12-01	Higgins	Applicant
US5297032(A)	1994-03-01	Trojan et al.	Applicant
US5313560(A)	1994-05-01	Maruoka et al.	Applicant
US5315634(A)	1994-05-01	Tanaka et al.	Applicant
US5319776(A)	1994-06-01	Hile et al.	Applicant
US5327521(A)	1994-07-01	Savic et al.	Applicant
US5339411(A)	1994-08-01	Heaton, Jr.	Applicant
US5347634(A)	1994-09-01	Herrell et al.	Applicant
US5371794(A)	1994-12-01	Diffie et al.	Applicant
US5375055(A)	1994-12-01	Togher et al.	Applicant
US5388259(A)	1995-02-01	Fleischman et al.	Applicant
US5396253(A)	1995-03-01	Chia	Applicant
US5404411(A)	1995-04-01	Banton et al.	Applicant
US5404488(A)	1995-04-01	Kerrigan et al.	Applicant
US5418951(A)	1995-05-01	Damashek	Applicant
US5421028(A)	1995-05-01	Swanson	Applicant
US5432822(A)	1995-07-01	Kaewell, Jr.	Applicant
US5461712(A)	1995-10-01	Chelstowski et al.	Applicant
US5463701(A)	1995-10-01	Kantner, Jr. et al.	Applicant
US5465353(A)	1995-11-01	Hull et al.	Applicant
US5481735(A)	1996-01-01	Mortensen et al.	Applicant
US5488725(A)	1996-01-01	Turtle et al.	Applicant
US5497317(A)	1996-03-01	Hawkins et al.	Applicant
US5497488(A)	1996-03-01	Akizawa et al.	Applicant
US5500793(A)	1996-03-01	Deming, Jr. et al.	Applicant
US5544352(A)	1996-08-01	Egger	Applicant
US5546578(A)	1996-08-01	Takada	Applicant
US5651125(A)	1997-07-01	Witt et al.	Applicant
US5687297(A)	1997-11-01	Coonan et al.	Applicant
US5701464(A)	1997-12-01	Aucsmith	Applicant
US5704060(A)	1997-12-01	Del Monte	Applicant
US5721898(A)	1998-02-01	Beardsley et al.	Applicant
US5740244(A)	1998-04-01	Indeck et al.	Applicant
US5740466(A)	1998-04-01	Geldman et al.	Applicant
US5774835(A)	1998-06-01	Ozawa	Applicant
US5774839(A)	1998-06-01	Shlomot	Applicant
US5781772(A)	1998-07-01	Wilkinson, III et al.	Applicant
US5781921(A)	1998-07-01	Nichols	Applicant
US5805832(A)	1998-09-01	Brown et al.	Applicant
US5809483(A)	1998-09-01	Broka et al.	Applicant
US5813000(A)	1998-09-01	Furlani	Applicant
US5819273(A)	1998-10-01	Vora et al.	Applicant
US5819290(A)	1998-10-01	Fujita	Applicant
US5826075(A)	1998-10-01	Bealkowski et al.	Applicant
US5845266(A)	1998-12-01	Lupien et al.	Applicant
US5857176(A)	1999-01-01	Ginsberg	Applicant
US5864738(A)	1999-01-01	Kessler et al.	Applicant
US5870730(A)	1999-02-01	Furuya et al.	Applicant
US5873071(A)	1999-02-01	Ferstenberg et al.	Applicant
US5884286(A)	1999-03-01	Daughtery, III	Applicant
US5905974(A)	1999-05-01	Fraser et al.	Applicant
US5913211(A)	1999-06-01	Nitta	Applicant
US5930753(A)	1999-07-01	Potamianos et al.	Applicant
US5943421(A)	1999-08-01	Grabon	Applicant
US5943429(A)	1999-08-01	Handel	Applicant
US5963923(A)	1999-10-01	Garber	Applicant
US5978801(A)	1999-11-01	Yuasa	Applicant
US5987432(A)	1999-11-01	Zusman et al.	Applicant
US5991881(A)	1999-11-01	Conklin et al.	Applicant
US5995963(A)	1999-11-01	Nanba et al.	Applicant
US6016483(A)	2000-01-01	Rickard	Applicant
US6023760(A)	2000-02-01	Karttunen	Applicant
US6028939(A)	2000-02-01	Yin	Applicant
US6044407(A)	2000-03-01	Jones et al.	Applicant
US6058391(A)	2000-05-01	Gardner	Applicant
US6061662(A)	2000-05-01	Makivic	Applicant
US6067569(A)	2000-05-01	Khaki et al.	Applicant
US6070172(A)	2000-05-01	Lowe	Applicant
US6073160(A)	2000-06-01	Grantham et al.	Applicant
US6105067(A)	2000-08-01	Batra	Applicant
US6134551(A)	2000-10-01	Aucsmith	Applicant
US6138176(A)	2000-10-01	McDonald et al.	Applicant
USRE36946(E)	2000-11-01	Diffie et al.	Applicant
US6147976(A)	2000-11-01	Shand et al.	Applicant
US6169969(B1)	2001-01-01	Cohen	Applicant
US6173270(B1)	2001-01-01	Cristofich et al.	Applicant
US6173276(B1)	2001-01-01	Kant et al.	Applicant
US6175874(B1)	2001-01-01	Imai et al.	Applicant
US6226676(B1)	2001-05-01	Crump et al.	Applicant
US6236980(B1)	2001-05-01	Reese	Applicant
US6263321(B1)	2001-07-01	Daughtery, III	Applicant
US6279113(B1)	2001-08-01	Vaidya	Applicant
US6304858(B1)	2001-10-01	Mosler et al.	Applicant
US6317728(B1)	2001-11-01	Kane	Applicant
US6317795(B1)	2001-11-01	Malkin et al.	Applicant
US6336150(B1)	2002-01-01	Ellis et al.	Applicant
US6339819(B1)	2002-01-01	Huppenthal et al.	Applicant
US6370645(B1)	2002-04-01	Lee	Applicant
US6377942(B1)	2002-04-01	Hinsley et al.	Applicant
US6381242(B1)	2002-04-01	Maher, III et al.	Applicant
US6389532(B1)	2002-05-01	Gupta et al.	Applicant
US6397259(B1)	2002-05-01	Lincke et al.	Applicant
US6397335(B1)	2002-05-01	Franczek et al.	Applicant
US6412000(B1)	2002-06-01	Riddle et al.	Applicant
US6415269(B1)	2002-07-01	Dinwoodie	Applicant
US6418419(B1)	2002-07-01	Nieboer et al.	Applicant
US6430272(B1)	2002-08-01	Maruyama et al.	Applicant
US6456632(B1)	2002-09-01	Baum et al.	Applicant
US6456982(B1)	2002-09-01	Pilipovic	Applicant
US6463474(B1)	2002-10-01	Fuh et al.	Applicant
US6499107(B1)	2002-12-01	Gleichauf et al.	Applicant
US6546375(B1)	2003-04-01	Pang et al.	Applicant
US6564263(B1)	2003-05-01	Bergman et al.	Applicant
US6578147(B1)	2003-06-01	Shanklin et al.	Applicant
US6594643(B1)	2003-07-01	Freeny, Jr.	Applicant
US6704816(B1)	2004-03-01	Burke	Applicant
US6711558(B1)	2004-03-01	Indeck et al.	Applicant
US6765918(B1)	2004-07-01	Dixon et al.	Applicant
US6766304(B2)	2004-07-01	Kemp, II et al.	Applicant
US6772132(B1)	2004-08-01	Kemp, II et al.	Applicant
US6772136(B2)	2004-08-01	Kant et al.	Applicant
US6772345(B1)	2004-08-01	Shetty	Applicant
US6778968(B1)	2004-08-01	Gulati	Applicant
US6785677(B1)	2004-08-01	Fritchman	Applicant
US6804667(B1)	2004-10-01	Martin	Applicant
US6807156(B1)	2004-10-01	Veres et al.	Applicant
US6839686(B1)	2005-01-01	Galant	Applicant
US6850906(B1)	2005-02-01	Chadha et al.	Applicant
US6870837(B2)	2005-03-01	Ho et al.	Applicant
US6877044(B2)	2005-04-01	Lo et al.	Applicant
US6886103(B1)	2005-04-01	Brustoloni et al.	Applicant
US6901461(B2)	2005-05-01	Bennett	Applicant
US6931408(B2)	2005-08-01	Adams et al.	Applicant
US6944168(B2)	2005-09-01	Paatela et al.	Applicant
US6978223(B2)	2005-12-01	Milliken	Applicant
US6980976(B2)	2005-12-01	Alpha et al.	Applicant
US6981054(B1)	2005-12-01	Krishna	Applicant
US7024384(B2)	2006-04-01	Daughtery, III	Applicant
US7046848(B1)	2006-05-01	Olcott	Applicant
US7065475(B1)	2006-06-01	Brundobler	Applicant
US7093023(B2)	2006-08-01	Lockwood et al.	Applicant
US7099838(B1)	2006-08-01	Gastineau et al.	Applicant
US7103569(B1)	2006-09-01	Groveman et al.	Applicant
US7127424(B2)	2006-10-01	Kemp, II et al.	Applicant
US7127510(B2)	2006-10-01	Yoda et al.	Applicant
US7139743(B2)	2006-11-01	Indeck et al.	Applicant
US7149715(B2)	2006-12-01	Browne et al.	Applicant
US7167980(B2)	2007-01-01	Chiu	Applicant
US7177833(B1)	2007-02-01	Marynowski et al.	Applicant
US7181437(B2)	2007-02-01	Indeck et al.	Applicant
US7181608(B2)	2007-02-01	Fallon et al.	Applicant
US7225188(B1)	2007-05-01	Gai et al.	Applicant
US7228289(B2)	2007-06-01	Brumfield et al.	Applicant
US7251629(B1)	2007-07-01	Marynowski et al.	Applicant
US7286564(B2)	2007-10-01	Roberts	Applicant
US7356498(B2)	2008-04-01	Kaminsky et al.	Applicant
US7362859(B1)	2008-04-01	Robertson et al.	Applicant
US7363277(B1)	2008-04-01	Dutta et al.	Applicant
US7406444(B2)	2008-07-01	Eng et al.	Applicant
US7565525(B2)	2009-07-01	Vorbach et al.	Examiner
US7840482(B2)	2010-11-01	Singla et al.	Applicant
US7917299(B2)	2011-03-01	Buhler et al.	Applicant
US7921046(B2)	2011-04-01	Parsons et al.	Applicant
US7945528(B2)	2011-05-01	Cytron et al.	Applicant
US7949650(B2)	2011-05-01	Indeck et al.	Applicant
US7953743(B2)	2011-05-01	Indeck et al.	Applicant
US7954114(B2)	2011-05-01	Chamberlain et al.	Applicant
US2001/0013048(A1)	2001-08-01	Imbert de Tremiolles et al.	Applicant
US2001/0014093(A1)	2001-08-01	Yoda et al.	Applicant
US2001/0033656(A1)	2001-10-01	Gligor et al.	Applicant
US2001/0052038(A1)	2001-12-01	Fallon et al.	Applicant
US2001/0056547(A1)	2001-12-01	Dixon	Applicant
US2002/0031125(A1)	2002-03-01	Sato	Applicant
US2002/0069370(A1)	2002-06-01	Mack	Applicant
US2002/0082967(A1)	2002-06-01	Kaminsky et al.	Applicant
US2002/0095512(A1)	2002-07-01	Rana et al.	Applicant
US2002/0105911(A1)	2002-08-01	Pruthi et al.	Applicant
US2002/0129140(A1)	2002-09-01	Peled et al.	Applicant
US2002/0138376(A1)	2002-09-01	Hinkle	Applicant
US2002/0162025(A1)	2002-10-01	Sutton et al.	Applicant
US2002/0166063(A1)	2002-11-01	Lachman et al.	Applicant
US2002/0181709(A1)	2002-12-01	Sorimachi et al.	Applicant
US2003/0009693(A1)	2003-01-01	Brock et al.	Applicant
US2003/0014662(A1)	2003-01-01	Gupta et al.	Applicant
US2003/0018630(A1)	2003-01-01	Indeck et al.	Applicant
US2003/0023876(A1)	2003-01-01	Bardsley et al.	Applicant
US2003/0033240(A1)	2003-02-01	Balson et al.	Applicant
US2003/0037037(A1)	2003-02-01	Adams et al.	Applicant
US2003/0039355(A1)	2003-02-01	McCanny et al.	Applicant
US2003/0043805(A1)	2003-03-01	Graham et al.	Applicant
US2003/0051043(A1)	2003-03-01	Wyschogrod et al.	Applicant
US2003/0055658(A1)	2003-03-01	RuDusky	Applicant
US2003/0055770(A1)	2003-03-01	RuDusky	Applicant
US2003/0055771(A1)	2003-03-01	RuDusky	Applicant
US2003/0055777(A1)	2003-03-01	Ginsberg	Applicant
US2003/0065607(A1)	2003-04-01	Satchwell	Examiner
US2003/0065943(A1)	2003-04-01	Geis et al.	Applicant
US2003/0074582(A1)	2003-04-01	Patel et al.	Applicant
US2003/0078865(A1)	2003-04-01	Lee	Applicant
US2003/0093347(A1)	2003-05-01	Gray	Applicant
US2003/0097481(A1)	2003-05-01	Richter	Applicant
US2003/0099254(A1)	2003-05-01	Richter	Applicant
US2003/0110229(A1)	2003-06-01	Kulig et al.	Applicant
US2003/0126065(A1)	2003-07-01	Eng et al.	Applicant
US2003/0163715(A1)	2003-08-01	Wong	Applicant
US2003/0177253(A1)	2003-09-01	Schuehler et al.	Applicant
US2003/0208430(A1)	2003-11-01	Gershon	Applicant
US2003/0221013(A1)	2003-11-01	Lockwood et al.	Applicant
US2004/0015633(A1)	2004-01-01	Smith	Applicant
US2004/0028047(A1)	2004-02-01	Hou et al.	Applicant
US2004/0034587(A1)	2004-02-01	Amberson et al.	Applicant
US2004/0049596(A1)	2004-03-01	Schuehler et al.	Applicant
US2004/0177340(A1)	2004-09-01	Hsu et al.	Applicant
US2004/0186804(A1)	2004-09-01	Chakraborty et al.	Applicant
US2004/0186814(A1)	2004-09-01	Chalermkraivuth et al.	Applicant
US2004/0199448(A1)	2004-10-01	Chalermkraivuth et al.	Applicant
US2004/0205149(A1)	2004-10-01	Dillon et al.	Applicant
US2005/0033672(A1)	2005-02-01	Lasry et al.	Applicant
US2005/0044344(A1)	2005-02-01	Stevens	Applicant
US2005/0086520(A1)	2005-04-01	Dharmapurikar et al.	Applicant
US2005/0091142(A1)	2005-04-01	Renton et al.	Applicant
US2005/0097027(A1)	2005-05-01	Kavanaugh	Applicant
US2005/0131790(A1)	2005-06-01	Benzschawel et al.	Applicant
US2005/0187844(A1)	2005-08-01	Chalermkraivuth et al.	Applicant
US2005/0187845(A1)	2005-08-01	Eklund et al.	Applicant
US2005/0187846(A1)	2005-08-01	Subbu et al.	Applicant
US2005/0187847(A1)	2005-08-01	Bonissone et al.	Applicant
US2005/0187848(A1)	2005-08-01	Bonissone et al.	Applicant
US2005/0187849(A1)	2005-08-01	Bollapragada et al.	Applicant
US2005/0195832(A1)	2005-09-01	Dharmapurikar et al.	Applicant
US2005/0197938(A1)	2005-09-01	Davie et al.	Applicant
US2005/0197939(A1)	2005-09-01	Davie et al.	Applicant
US2005/0197948(A1)	2005-09-01	Davie et al.	Applicant
US2005/0216384(A1)	2005-09-01	Partlow et al.	Applicant
US2005/0267836(A1)	2005-12-01	Crosthwaite et al.	Applicant
US2005/0283423(A1)	2005-12-01	Moser et al.	Applicant
US2006/0020536(A1)	2006-01-01	Renton et al.	Applicant
US2006/0031154(A1)	2006-02-01	Noviello et al.	Applicant
US2006/0031156(A1)	2006-02-01	Noviello et al.	Applicant
US2006/0053295(A1)	2006-03-01	Madhusudan et al.	Applicant
US2006/0059064(A1)	2006-03-01	Glinberg et al.	Applicant
US2006/0059065(A1)	2006-03-01	Glinberg et al.	Applicant
US2006/0059066(A1)	2006-03-01	Glinberg et al.	Applicant
US2006/0059067(A1)	2006-03-01	Glinberg et al.	Applicant
US2006/0059068(A1)	2006-03-01	Glinberg et al.	Applicant
US2006/0059069(A1)	2006-03-01	Glinberg et al.	Applicant
US2006/0059083(A1)	2006-03-01	Friesen et al.	Applicant
US2006/0143099(A1)	2006-06-01	Partlow et al.	Applicant
US2006/0259417(A1)	2006-11-01	Marynowski et al.	Applicant
US2006/0294059(A1)	2006-12-01	Chamberlain et al.	Applicant
US2007/0078837(A1)	2007-04-01	Indeck et al.	Applicant
US2007/0118500(A1)	2007-05-01	Indeck et al.	Applicant
US2007/0156574(A1)	2007-07-01	Marynowski et al.	Applicant
US2007/0174841(A1)	2007-07-01	Chamberlain et al.	Applicant
US2007/0277036(A1)	2007-11-01	Chamberlain et al.	Applicant
US2007/0294157(A1)	2007-12-01	Singla et al.	Applicant
US2008/0109413(A1)	2008-05-01	Indeck et al.	Applicant
US2008/0114760(A1)	2008-05-01	Indeck et al.	Applicant
US2008/0126320(A1)	2008-05-01	Indeck et al.	Applicant
US2008/0133453(A1)	2008-06-01	Indeck et al.	Applicant
US2008/0133519(A1)	2008-06-01	Indeck et al.	Applicant
US2009/0182683(A1)	2009-07-01	Taylor et al.	Applicant
US2009/0287628(A1)	2009-11-01	Indeck et al.	Applicant
US2011/0040701(A1)	2011-02-01	Singla et al.	Applicant
EP851358(A)	1998-07-01		Applicant
EP880088	1998-11-01		Applicant
EP887723	1998-12-01		Applicant
EP911738(A)	1999-04-01		Applicant
EP573991(A1)	2002-01-01		Applicant
JP2-136900(A)	1990-05-01		Applicant
JP3-014075(A)	1991-01-01		Applicant
JP9-145544(A)	1997-06-01		Applicant
JP9-269930	1997-10-01		Applicant
JP10-313341	1998-11-01		Applicant
JP11-306268(A)	1999-11-01		Applicant
JP11-316765(A)	1999-11-01		Applicant
JP2000357176	2000-12-01		Applicant
JP2001014239	2001-01-01		Applicant
JP2001217834	2001-08-01		Applicant
WO9010910	1990-09-01		Applicant
WO9737735	1997-10-01		Applicant
WO9905814	1999-02-01		Applicant
WO9955052	1999-10-01		Applicant
WO2000041136(A1)	2000-07-01		Applicant
WO1/22425(A)	2001-03-01		Applicant
WO139577	2001-06-01		Applicant
WO161913	2001-08-01		Applicant
WO180558	2001-10-01		Applicant
WO1/80082(A2)	2001-10-01		Applicant
WO2061525	2002-08-01		Applicant
WO2082271	2002-10-01		Applicant
WO2003100650	2003-04-01		Applicant
WO2003036845	2003-05-01		Applicant
WO3100662	2003-12-01		Applicant
WO2004017604	2004-02-01		Applicant
WO2005017708	2005-02-01		Applicant
WO2005017708(A2)	2005-02-01		Applicant
WO2005026925	2005-03-01		Applicant
WO2005048134(A)	2005-05-01		Applicant
WO2006023948	2006-03-01		Applicant
WO2010077829(A1)	2010-07-01		Applicant

Non-Patent Literature (172)

Anonymous, “Method for Allocating Computer Disk Space to a File of Know Size,” IBM Technical Disclosure Bulletin, vol. 27, No. IOB, Mar. 1, 1985, New York.Applicant
Arnold et al., “The Splash 2 Processor and Applications”, Proceedings 1993 IEEE International Conference on Computer Design: VLSI Iii Corrnputers and Processors (ICCD '93); Oct. 3, 1993; pp. 482-485; IEEE Computer Societr; Cambridge, MA USA.Applicant
Berk, “JLex: A lexical analyzer generator for JavaTM”, downloaded from http://www.cs.princeton.edu/˜appel/modernljava/Jlex/ in Jan. 2002.Applicant
Braun et al., “Layered Protocol Wrappers for Internet Packet Processing in Reconfigurable Hardware”, Proceedings of Hot Interconnects 9 (Hotl-9) Stanford, CA, Aug. 22-24, 2001, pp. 93-98.Applicant
Choi et al., “Design of a Flexible Open Platform for High Performance Active Networks”, Allerton Conference, Campaign, II, 1999.Applicant
Cloutier et al., “VIP: An FPGA—Based Processor for Image Processing and Neural Networks; Proceedings of Fifth International Conference on Microelectronics for Neural Networks”, Feb. 12, 1996; pp. 330-336; Los Alamitos, California.Applicant
Compton et al., “Configurable Computing: A Survey of Systems and Software”, Technical Report, Northwestern University, Dept. of BCE, 1999.Applicant
Ebeling et al., “RaPiD-Reconfigurable Pipelined Datapath”, University of Washington, Dept. of Computer Science and Engineering, Sep. 23, 1996; Seattle, WA.Applicant
Franklin et al., “Assisting Network Intrusion Detection with Reconfigurable Hardware”, Symposium on Field-Programmable Custom Computing Machines (FCCM 2002), Apr. 2002, Napa, California.Applicant
Gunther et al., “Assessing Document Relevance with Run-Time Reconfigurable Machines: FPGAs for custom computing machines”, 1996; Proceedings, IEEE Symposium on Napa Valley, CA, Apr. 17, 1996.Applicant
Hauck et al., “Software Technologies for Reconfigurable Systems”, Northwestern University, Dept. of BCE, Technical Report, 1996.Applicant
Hezel et al., “FPGA-based Template Matching using Distance Transforms”, Proceedings of the 10th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM '02); Apr. 22, 2002; pp. 89-97; IEEE Computer Society, USA.Applicant
Hollaar, Hardware Systems for Text information Retrieval; Procedings of the Sixth Annual International ACM Sigir Conference on Research and Development in Information Retrieval; Jun. 6-8, 1983; pp. 3-9; Baltimore, Maryland, USA.Applicant
Keutzer et al., “A Survey of Programmable Platforms-Network Proc”, University of California-Berkeley.Applicant
Kulig et al., “System and Method for Controlling Transmission of Data Packets Over an Information Network”, pending U.S. Patent Application.Applicant
Lin et al., “Real-Time Image Template Matching Based on Systolic Array Processor”, International Journal of Electronics; Dec. 1, 1992; pp. 1165-1176; vol. 73, No. 6; London, Great Britain.Applicant
Lockwood et al., Field Programmable Port Extender (FPX) for Distributed Routing and Queuing, ACM International Symposium on Field Programmable Gate Arrays (FPGA '2000), Monterey, CA, Feb. 2000, pp. 137-144.Applicant
Lockwood et al., FPGrep and FPSed: Regular Expression Search and Substitution for Packet Streaming in Fleid Programmable Hardware, unpublished.Applicant
Lockwood et al., Hello, World: A Simple Application for the Field Programmable Port Extender (FPX), Washington University, Department of Computer Science, Technical Report WUCS-00-12, Jul. 11, 2000.Applicant
Lockwood et al., “Parallel FPGA Programming over Backplane Chassis”, Washington University, Department of Computer Science, Technical Report WUCS-00-11, Jun. 12, 2000.Applicant
Lockwood et al., Reprogramable Network Packet Processing on the Field Programmable Port Extender (FPX), ACM International Symposium on Field Programmable Gal Arrays (FPGA '2001), Monterey, CA, Feb. 2001, pp. 87-93.Applicant
Lockwood, “An Open Platform for Development of Network Processing Modules in Reprogrammable Hardware”, IEG DesignCon 2001, Santa Clara, CA, Jan. 2001, Paper WB-19.Applicant
Lockwood, “Building Networks with Reprogrammable Hardware”, Field Programmable Port Extender: Jan. 2002 Gigabit Workshop Tutorial, Washington University, St. Louis, MO, Jan. 3-4, 2002.Applicant
Lockwood, “Evolvable Internet Hardware Platforms”, NASA/DoD Workshop on Evolvable Hardware (EHW'0I), Long Beach, CA, Jul. 12-14, 2001, pp. 271-279.Applicant
Lockwood, “Hardware Laboratory Configuration”, Field Programmable Port Extender: Jan. 2002 Gigabit Workshop Tutorial, Washington University, St. Louis, MO, Jan. 3-4, 2002.Applicant
Lockwood, “Introduction”, Field Programmable Port Extender: Jan. 2002 Gigabit Workshop Tutorial, Washington, University, St. Louis, MO, Jan. 3-4, 2002.Applicant
Lockwood, “Platform and Methodology for Teaching Design of Hardware Modules in Internet Routers and Firewalls”, IEEE Computer Society International Conference on Microelectronic Systems Education (MSE'2001), Las Vega, NV, Jun. 17-18, 2001, pp. 56-57.Applicant
Lockwood, “Protocol Processing on the FPX”, Field Programmable Port Extender: Jan. 2002 Gigabit Workshop Tutorial, Washington University, St. Louis, MO, Jan. 3-4, 2002.Applicant
Lockwood, “Simulation and Synthesis”, Field Programmable Port Extender: Jan. 2002 Gigabit Workshop Tutorial, Washington University, St. Louis, MO, Jan. 3-4, 2002.Applicant
Lockwood, “Simulation of the Hello World Application for the Field-Programmable Port Extender (FPX)”, Washington University, Applied Research Lab, Spring 2001 Gigabits Kits Workshop.Applicant
“Lucent Technologies Delivers Payload Plus Network Processors for Programmable, Multi-Protocol, OC-48c Processing”, Lucent Technologies Press Release, downloaded from http://www.lucent.comlpress/1000/0010320.meb.html on Mar. 21, 2002.Applicant
Mosanya et al., A FPGA-Based Hardware Implementation of Generalized Profile Search Using Online Arithmetic; ACM/Sigda International Symposium on Field Programmable Gate Arrays (FPGA'99); Feb. 21-23, 1999; pp. 101-111; Monterey, CA, USA.Applicant
Nunez et al., “The X-MatchLITE FPGA-Based Data Compressor”, Buromicro Conference 1999, Proceedings, Italy, Sep. 8-10, 1999, Los Alamitos, CA.Applicant
“Overview, Field Programmable Port Extender”, Jan. 2002 Gigabit Workshop Tutorial, Washington University, St. Louis, MO, Jan. 3-4 2002.Applicant
Partial International Search for PCT/US 03/15638; Feb. 3, 2004.Applicant
Patent Cooperation Treaty; International Search Report; May 6, 2004.Applicant
Patent Cooperation Treaty; International Search Report; Apr. 12, 2005.Applicant
Patent Cooperation Treaty; International Search Report; Jul. 10, 2003.Applicant
“Payload Plus Agere System Interface,” Agere Systems Product Brief, Jun. 2001, downloaded from Internet, Jan. 2002.Applicant
Pramanik et al., “A Hardware Patteren Matching Algorithm on a Dataflow”, Computer Journal; Jul. 1, 1985; pp. 264-269; vol. 28, No. 3; Oxford University Press, Surrey, Great Britain.Applicant
Pu et al., “The FPX KCPSM Module: An Embedded, Reconfigurable Active Processing Module for the Field Programmable Port Extender (FPX)”, Washington University, Department of Computer Science, Technical Report WUCS-01-14, Jul. 2001.Applicant
Ratha et al., “Convolution on Splash 2; Proceedings of IEEE Symposium on FPGAS for Custom Computing Machines”, Apr. 19, 1995; pp. 204-213; Los Alamitos, California.Applicant
Schmit, “Incremental Reconfiguration for Pipelined Applications”, Dept. of ECE, Carnegie Mellon University 1997, Pittsburgh, PA.Applicant
Shah, “Understanding Network Processors”, Version 1.0, University of California-Berkeley, Sep. 4, 2001.Applicant
Shirazi et al.; Quantitative Analysis of FPGA-based Database Searching, Journal of VLSI Signal Processing Systems For Signal, Image, and Video Technology; May 2001; pp. 85-96; vol. 28, No. 1/2; Kluwer Academic Publishers; Dordrecht, NL.Applicant
Sidhu et al., “Fast Regular Expression Matching using FPGAs”, IEEE Symposium on Field Programmable Custom Computing Machines (FCCM 2001), Apr. 2001.Applicant
Sidhu et al., “String Matching on Multicontext FPGAs using Self-Reconfiguration”, FPGA '99: Proceedings of the 1999 ACM/SIGDA 7th International Symposium on Field Programmable Gate Arrays, Feb. 1999, pp. 217-226.Applicant
Taylor et al., “Generalized RAD Module Interface Specification of the Field Programmable Port Extender (FPX) Version 2”, Washington University, Department of Computer Science, Technical Report, Jan. 8, 2000.Applicant
Taylor et al., “Modular Design Techniques for the FPX”, Field Programmable Port Extender, Jan. 2002 Gigabit Workshop Tutorial, Washington University, St. Louis, MO, Jan. 3-4, 2002.Applicant
“The Field-Programmable Port Extender (FPX)”, downloaded from http://www.ari.wustl.edu/arl/ in Mar. 2002.Applicant
Villasenor et al., Configurable Computer Solutions For Automatic Target Recognition; FPGAS for Custom Computing Machines, 1996,Proceedings, IEEE Symposium on Napa Valley, CA; Apr. 17-19, 1996; pp. 70-79; 1996 IEEE; Napa Valley, CA, Los Alamitos, CA, USA.Applicant
Yamaguchi et al., “High Speed Homology Search with FPGAs”, Proceedings Pacific Symposium on Biocomputing; Jan. 3-7, 2002; pp. 271-282; vol. 7; Online; Lihue, Hawaii, USA.Applicant
Baer, “Computer Systems Architecture”, 1990, pp. 262-265, Computer Science Press, Potomac, Maryland.Applicant
Baeza-Yates and Navarro, “New and Faster Filters for Multiple Approximate String Matching”, Random Structures and Algorithms (RSA), vol. 20, No. 1, Jan. 2002, pp. 23-49.Applicant
Hayes, “Computer Architecture and Organization”, Second Edition, 1988, pp. 448-459, McGraw-Hill, Inc.Applicant
Navarro, “A Guided Tour to Approximate String Matching”, ACM Computing Surveys, vol. 33, No. 1, Mar. 2001, pp. 31-88.Applicant
Ramakrishna et al., “A Performance Study of Hashing Functions for Hardware Applications”, Journal of Computing and Information, vol. 1, No. 1, May 1994, pp. 1621-1636.Applicant
Taylor and Turner, “Scalable Packet Classification using Distributed Crossproducting of Field Labels”, Proceedings of IEEE Infocom, vol. 20, No. 1, Mar. 2005, pp. 1-12.Applicant
Taylor, “Models, Algorithms, and Architectures for Scalable Packet Classification”, doctoral thesis, Department of Computer Science and Engineering, Washington University, St. Louis, MO, Aug. 2004.Applicant
“A Reconfigurable Computing Model for Biological Research Application of Smith-Waterman Analysis to Bacterial Genomes” A White Paper Prepared by Star Bridge Systems, Inc. [retrieved Dec. 12, 2006]. Retrieved from the Internet: <URL: http://www.starbridgesystems.com/resources/whitepapers/Smith%20 Waterman%20Whitepaper.pdf.Applicant
Altschul et al., “Basic Local Alignment Search Tool”, J. Mol. Biol., Oct. 5, 1990, 215, pp. 403-410.Applicant
Cavnar et al., “N-Gram-Based Text Categorization”, Proceedings of SDAIR-94, 3rd Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, pp. 161-175, 1994.Applicant
Chodowiec et al., “Fast Implementations of Secret-Key Block Ciphers Using Mixed Inter- and Outer-Round Pipelining”, Proceedings of International Symposium on FPGAs, pp. 94-102 (Feb. 2001).Applicant
Compton et al., “Reconfigurable Computing: A Survey of Systems and Software”, Technical Report, Northwestern University, Dept. of ECE, 1999, presented by Yi-Gang Tai.Applicant
Crosman, “Who Will Cure Your Data Latency?”, Storage & Servers, Jun. 20, 2007, URL: http://www.networkcomputing.com/article/printFullArticleSrc.jhtml?article ID=199905630.Applicant
Denoyer et al., “HMM-based Passage Models for Document Classification and Ranking”, Proceedings of ECIR-01, 23rd European Colloquim Information Retrieval Research, Darmstatd, DE, pp. 126-135, 2001.Applicant
Edgar, “Muscle: Multiple Sequence Alignment with High Accuracy and High Throughput”, Nucleic Acids Research, 2004, vol. 32, No. 5, pp. 1792-1797.Applicant
FIPS 197, “Advanced Encryption Standard”, National Institute of Standards and Technology (2001).Applicant
FIPS Pub. 46-3. Data Encryption Standard (DES). Revised version of 46-2. Reaffirmed Oct. 25, 1999.Applicant
Forgy, “RETE: A fast algorithm for the many pattern/many object pattern matching problem”, Artificial Intelligence, 19, pp. 17-37, 1982.Applicant
Harris, “Pete's Blog: Can FPGAs Overcome the FUD?”, Low-Latency.com, May 14, 2007, URL: http://www.a-teamgroup.com/article/pete-blog-can-fpgas-overcome-the-fud/.Applicant
Hirsch, “Tech Predictions for 2008”, Reconfigurable Computing, Jan. 16, 2008, URL: http://fpgacomputing.blogspot.com/2008—01—01—archive.html.Applicant
Hoinville, et al. “Spatial Noise Phenomena of Longitudinal Magnetic Recording Media”, IEEE Transactions on Magnetics, vol. 28, No. 6, Nov. 1992.Applicant
Hutchings et al., “Assisting Network Intrusion Detection with Reconfigurable Hardware”, FCCM 2002: 10th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, 2002.Applicant
International Search Report for PCT/US2004/016021 dated Aug. 18, 2005.Applicant
International Search Report for PCT/US2007/060835 dated Jul. 9, 2007.Applicant
International Search Report for PCT/US2008/065955 dated Aug. 22, 2008.Applicant
International Search Report for PCT/US2008/066929 dated Aug. 29, 2008.Applicant
Invitation to Pay Additional Fees and Annex to Form PCT/ISA/206 Communication Relating to the Results of the Partial International Search for International Application No. PCT/US2003/015638 dated Feb. 3, 2004.Applicant
Jeanmougin et al., “Multiple Sequence Alignment with Clustal X”, TIBS, 1998, vol. 23, pp. 403-405.Applicant
Jones et al., “A Probabilistic Model of Information Retrieval: Development and Status”, Information Processing and Management, Aug. 1998, 76 pages.Applicant
Jung et al., “Efficient VLSI for Lempel-Ziv Compression in Wireless Data Communication Networks”, IEEE Transactions on VLSI Systems, Sep. 1998, pp. 475-483, vol. 6, No. 3, Institute of Electrical and Electronics Engineers, Washington, DC, USA.Applicant
Pirsch et al., “VLSI Architectures for Video Compression—A Survey”, Proceedings of the IEEE, Feb. 1995, pp. 220-243, vol. 83, No. 2, Institute of Electrical and Electronics Engineers, Washington, DC, USA.Applicant
Ramakrishna et al., “Efficient Hardware Hashing Functions for High Performance Computers”, IEEE Transactions on Computers, Dec. 1997, vol. 46, No. 12.Applicant
Ranganathan et al., “High-Speed VLSI Designs for Lempe-Ziv Based Data Compression”, IEEE Transactions on Circuits and Systems-II: Analog and Digital Signal Processing, Feb. 1993, pp. 96-106, vol. 40, No. 2, Institute of Electrical and Electronics Engineers, Washington, DC, USA.Applicant
Ratha et al., “FPGA-based coprocessor for text string extraction”, IEEE, Sep. 11-13, 2000, pp. 217-221.Applicant
Roesch, “Snort—Lightweight Intrusion Detection for Networks”, Proceedings of LISA '99: 13th Systems Administration Conference; Nov. 7-12, 1999; pp. 229-238; USENIX Association, Seattle, WA USA.Applicant
Roy, “A bounded search algorithm for segmented channel routing for FPGA's and associated channel architecture issues”, IEEE, Nov. 11, 1993, pp. 1695-1705, vol. 12.Applicant
Schmerken, “With Hyperfeed Litigation Pending, Exegy Launches Low-Latency Ticker Plant”, in Wall Street & Technology Blog, Mar. 20, 2007, pp. 1-2.Applicant
Steinbach et al., “A Comparison of Document Clustering Techniques”, KDD Workshop on Text Mining, 2000.Applicant
Thompson et al., “The Clustal—X Windows Interface: Flexible Strategies for Multiple Sequence Alignment Aided by Quality Analysis Tools”, Nucleic Acids Research, 1997, vol. 25, No. 24, pp. 4876-4882.Applicant
Thomson Reuters, “Mellanox InfiniBand Accelerates the Exegy Ticker Plant at Major Exchanges”, Jul. 22, 2008, URL: http://www.reuters.com/article/pressRelease/idUS125385+22-Jul-2008+BW20080722.Applicant
Ziv et al., “A Universal Algorithm for Sequential Data Compression”, IEEE Trans. Inform. Theory, IT-23(3): 337-343 (1997).Applicant
Ziv et al., “Compression of Individual Sequence via Variable-Rate Coding”, IEEE Transactions on Information Theory, Sep. 1978, pp. 530-536, vol. IT-24, No. 5, Institute of Electrical and Electronics Engineers, Washington, DC, USA.Applicant
Guerdoux-Jamet et al., Systolic Filter for Fast DNA Similarity Search, IEEE, 1995, pp. 145-156.Applicant
Barone-Asesi, G and Whaley, R., “Efficient Analytic Approximation of American Option Values” Journal of Finance, vol. 42, No. 2 (Jun. 1987), 301-320.Applicant
Web-Pop (Professional Options Package) (www.pmpublishing.com).Applicant
Jason Cong et al., An Optimal Technology Mapping Algorithm for Delay Optimization in Lookup-Table Based FPGA Designs, IEEE, 1992, 48-53.Applicant
D.M. Gavrila et al., Multi-feature hierarchical template matching using distance transforms, IEEE, Aug, 16-20, 1998, vol. 1, 439-444.Applicant
“RFC793: Transmission Control Protocol, Darpa Internet Program, Protocol Specification”, Sep. 1981.Applicant
Anerousis et al., “Using the AT&T Labs PacketScope for Internet Measurement, Design, and Performance Analysis”, Network and Distributed Systems Research Laboratory, AT&T Labs-Research, Florham, Park, NJ, Oct. 1997.Applicant
Artan et al., “Multi-packet Signature Detection using Prefix Bloom Filters”, 2005, IEEE, pp. 1811-1816.Applicant
Baboescu et al., “Scalable Packet Classification”.Applicant
Bloom, “Space/Time Trade-offs in Hash Coding With Allowable Errors”, Communications of the ACM, Jul. 1970, pp. 422-426, vol. 13, No. 7, Computer Usage Company, Newton Upper Falls, Massachusetts, USA.Applicant
Chaney et al., “Design of a Gigabit ATM Switch”, Washington University, St. Louis.Applicant
Cuppu and Jacob, “Organizational Design Trade-Offs at the DRAM, Memory Bus and Memory Controller Level: Initial Results,” Technical Report UMB-SCA-1999-2, Univ. of Maryland Systems & Computer Architecture Group, Nov. 1999, pp. 1-10.Applicant
Dharmapurikar et al., “Deep Packet Inspection Using Parallel Bloom Filters,” Symposium on High Performance Interconnects (Hotl), Stanford, California, 2003, pp. 44-51.Applicant
Dharmapurikar et al., “Longest Prefix Matching Using Bloom Filters,” SIGCOMM, 2003, pp. 201-212.Applicant
Dharmapurikar et al., “Robust TCP Stream Reassembly in the Presence of Adversaries”, Proc. of the 14th Conference on USENIX Security Symposium—vol. 14, 16 pages, Baltimore, MD, 2005; http://www.icir.org/vern/papers/TcpReassembly/TCPReassembly.pdf.Applicant
Feldmann, “BLT: Bi-Layer Tracing of HTTP and TCP/IP”, AT&T Labs-Research, Florham Park, NJ, USA.Applicant
Gupta et al., “Packet Classification on Multiple Fields”, Computer Systems Laboratory, Stanford University, Stanford, CA.Applicant
Gurtov, “Effect of Delays on TCP Performance”, Cellular Systems Development, Sonera Corporation.Applicant
International Search Report for PCT/US2002/033286; Jan. 22, 2003.Applicant
International Search Report for PCT/US2005/030046; Sep. 25, 2006.Applicant
Jacobson et al., “RFC 1072: TCP Extensions for Long-Delay Paths”, Oct. 1988.Applicant
Jacobson et al., “tcpdump—dump traffic on a network”.Applicant
Johnson et al., “Pattern Matching in Reconfigurable Logic for Packet Classification”, College of Computing, Georgia Institute of Technology, Atlanta, GA.Applicant
Madhusudan, “Design of a System for Real-Time Worm Detection”, Hot Interconnects, pp. 77-83, Stanford, CA, Aug. 2004, found at http://www.hoti.org/hoti12/program/papers/2004/paper4.2.pdf.Applicant
Madhusudan, “Design of a System for Real-Time Worm Detection”, Master's Thesis, Washington Univ., Dept. of Computer Science and Engineering, St. Louis, MO, Aug. 2004.Applicant
Madhusudan, “Design of a System for Real-Time Worm Detection”, Power Point Presentation in Support of Master's Thesis, Washington Univ., Dept. of Computer Science and Engineering, St. Louis, MO, Aug. 2004.Applicant
Mao et al., “Cluster-based Online Monitoring System of Web Traffic”, Dept. of Computer Science and Technology, Tsinghua Univ., Bejing, 100084 P.R. China.Applicant
Moscola et al., “FPSed: A Streaming Content Search-And-Replace Module for an Internet Firewall”, Proc. of Hot Interconnects, 11th Symposium on High Performance Interconnects, pp. 122-129, Aug. 20, 2003.Applicant
Moscola, “FPGrep and FPSed: Packet Payload Processors for Managing the Flow of Digital Content on Local Area Networks and the Internet”, Master's Thesis, Sever Institute of Technology, Washington University, St. Louis, MO, Aug. 2003.Applicant
Necker et al., “TCP-Stream Reassembly and State Tracking in Hardware”, School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA.Applicant
Prakash et al., “OC-3072 Packet Classification Using BDDs and Pipelined SRAMs”, Department of Electrical and Computer Engineering, The University of Texas at Austin.Applicant
Roberts, “Internet Still Growing Dramatically Says Internet Founder”, Press Release, Caspian Networks, Inc.—Virtual Pressroom.Applicant
Schuehler et al., “Architecture for a Hardware Based, TCP/IP Content Scanning System”, IEEE Micro, 24(1):62-69, Jan.-Feb. 2004, USA.Applicant
Schuehler et al., “TCP-Splitter: A TCP/IP Flow Monitor in Reconfigurable Hardware”, Hot Interconnects 10 (Hotl-10), Stanford, CA, Aug. 21-23, 2002, pp. 127-131.Applicant
Shalunov et al., “Bulk TCP Use and Performance on Internet 2”.Applicant
Singh et al., “The EarlyBird System for Real-Time Detection on Unknown Worms”, Technical report CS2003-0761, Aug. 2003.Applicant
Taylor et al., “Dynamic Hardware Plugins (DHP): Exploiting Reconfigurable Hardware for High-Performance Programmable Routers”, Computer Networks, 38(3): 295-310 (16), Feb. 21, 2002, and online at http://www.cc.gatech.edu/classes/AY2007/cs8803hpc—fall/papers/phplugins.pdf.Applicant
Waldvogel et al., “Scalable High-Speed Prefix Matching”.Applicant
Weaver et al., “Very Fast Containment of Scanning Worms”, Proc. USENIX Security Symposium 2004, San Diego, CA, Aug. 2004, located at http://www.icsi.berkely.edu/˜nweaver/containment/containment.pdf.Applicant
Wooster et al., “HTTPDUMP Network HTTP Packet Snooper”, Apr. 25, 1996.Applicant
Yan et al., “Enhancing Collaborative Spam Detection with Bloom Filters”, 2006, IEEE, pp. 414-425.Applicant
Braun et al., “Protocol Wrappers for Layered Network Packet Processing in Reconfigurable Hardware”, IEEE Micro, Jan.-Feb. 2002, pp. 66-74.Applicant
Summons to Attend Oral Proceedings for European Patent Application No. 03729000.4 dated Mar. 17, 2010.Applicant
Fernandez, “Template Matching of Binary Targets in Grey-Scale Images: A Nonparametric Approach”, Pattern Recognition, 1997, pp. 1175-1182, vol. 30, No. 7.Applicant
International Preliminary Report on Patentability (Chapter I) for PCT/US2008/066929 dated Jan. 7, 2010.Applicant
Nwodoh et al., “A Processing System for Real-Time Holographic Video Computation”, Reconfigurable Technology: FPGAs for Computing and Application, Proceedings for the SPIE, Sep. 1999, Boston, pp. 129-140, vol. 3844.Applicant
English Translation of Office Action for JP Application 2004-508044 dated Feb. 9, 2010.Applicant
Office Action for U.S. Appl. No. 11/765,306 dated Mar. 29, 2010.Applicant
Written Submissions to EPO dated May 10, 2010 for European Patent Application No. 03729000.4.Applicant
Amanuma et al., “FPGA Architecture for High Speed Computation”, Proceedings of 60th Convention Architecture, Software Science, Engineering, Mar. 14, 2000, pp. 1-163-1-164, Information Processing Society, Japan.Applicant
Asami et al., “Improvement of DES Key Search on FPGA-Based Parallel Machine “RASH””, Proceedings of Information Processing Society, Aug. 15, 2000, pp. 50-57, vol. 41, No. SIG5 (HPS1), Japan.Applicant
Google Search Results Page for “field programmable gate array financial calculation stock market” over dates of Jan. 1, 1990-May 21, 2002, 1 page.Applicant
Gupta et al., “High-Speed Implementations of Rule-Based Systems,” ACM Transactions on Computer Systems, May 1989, pp. 119-146, vol. 7, Issue 2.Applicant
Gupta et al., “PMM: A Parallel Architecture for Production Systems,” Proceedings of the IEEE, Apr. 1992, pp. 693-696, vol. 2.Applicant
Office Action for AU Application 2009200148 dated Nov. 9, 2010.Applicant
Patterson, “High Performance DES Enctyption in Virtex(T™) FPGAs using JBits(™)”, IEEE Symposium on Field-Programmable Custom Computing Machines, 2000, pp. 113-121.Applicant
Sachin Tandon, “A Programmable Architecture for Real-Time Derivative Trading”, Master's Thesis, University of Edinburgh, 2003.Applicant
Seki et al., “High Speed Computation of Shogi With FPGA”, Proceedings of 58th Convention Architecture, Software Science, Engineering, Mar. 9, 1999, pp. 1-133-1-134.Applicant
Tau et al., “Transit Note #114: A First Generation DPGA Implementation”, Jan. 1995, 9 pages.Applicant
Yamaguchi et al., “An Approach for Homology Search with Reconfigurable Hardware”, Google, 2001, pp. 374-375.Applicant
Yoshitani et al., “Performance Evaluation of Parallel Volume Rendering Machine ReVolver/C40”, Study Report of Information Processing Society, Mar. 5, 1999, pp. 79-84, vol. 99, No. 21.Applicant
U.S. Appl. No. 61/421,545, filed Dec. 9, 2010 (Taylor et al.).Applicant
U.S. Appl. No. 13/076,906, filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/076,929, filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/076,951, filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/076,968, filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/076,982, filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/077,036, filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/077,224 filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/077,294, filed Mar. 31, 2011 (Parsons et al.).Applicant
U.S. Appl. No. 13/132,408, filed Jun. 2, 2011 (Taylor et al.).Applicant
U.S. Appl. No. 13/154,804, filed Jun. 7, 2011 (Taylor et al.).Applicant
U.S. Appl. No. 13/154,824, filed Jun. 7, 2011 (Taylor et al.).Applicant
Provisional Opinion of Examining Division for EP Patent Application No. 03729000.4 dated Jun. 2, 2010.Applicant
Decision of the Examining Division for EP Patent Application No. 03729000.4 dated Jul. 12, 2010.Applicant
Statement of Grounds of Appeal for EP Patent Application No. 03729000.4 dated Nov. 22, 2010.Applicant
Minutes of the Oral Proceedings for EP Patent Application No. 03729000.4 dated Jul. 12, 2010.Applicant
Notice of Allowance for U.S. Appl. No. 10/550,323 dated Aug. 5, 2011.Applicant

Abstract