Abstract: Apparatus and process identifies a maximum or minimum value among a plurality of binary values on a plurality of a-bit wide wires in an integrated circuit module. An N-bit vector K is calculated based on n most significant bits of all a-bit binary signals, where N=2n. M N-bit vectors K—0, . . . ,K_(M?1) are calculated based on the n most significant and the m least significant bits of all a-bit binary signals, where M is at least 2m?1. A table is constructed from vectors K—0, . . . ,K(M?1) to create table vectors. A table vector is selected based on vector K, is used to derive a vector P, which in turn is used to select another table vector. The minimum or maximum binary value is identified from the two selected table vectors.

Abstract: The present invention provides a RRAM communication system including at least one RRAM controller and a master controller. The master controller is communicatively coupled to each of at least one RRAM controller. The master controller is suitable for loading test input parameters into at least one RRAM controller, starting execution of a test and obtaining a result of test execution from at least one RRAM controller. Each of at least one RRAM controller is suitable for executing different tests depending on commands received from the master controller.

Abstract: A master controller for an RRAM subsystem. An interface communicates with at least one RRAM controller. A main control unit selects and implements test and repair operations on the RRAM subsystem through the RRAM controller. A timer determines a maximum number of test and repair operations that can be implemented within a given time. Thus, a master controller is included in the RRAM subsystem. The master controller has a relatively simple interface, and performs test and repair operations on the RRAM subsystem. The advantages of using the master controller include an elimination of additional test ports, simplification of the process of preparing the test vectors for RRAM testing, and the master controller is able to accumulate test results and initiate repairs based on those results. In this manner, the RRAM subsystem has a self-repair functionality.

Abstract: The present invention is directed to a method for generating a tech-library for a logic function. A logic function has many representations. For each representation, a circuit for realizing the representation is decomposed into a combination of instances. An instance is a component logic circuit of a general logic circuit. There are pre-created tech-libraries for the instances. For example, a pre-created tech-library is created by categorizing tech-descriptions for primitive physical circuits based on a negation index. Thus, tech-descriptions for a circuit for realizing a representation are calculated from a combination of elements of the pre-created tech-libraries. Each calculated tech-description is compared with each existing element of a tech-library for the logic function. When a calculated tech-description has at least one marked parameter better or smaller than that of all existing elements of the tech-library for the logic function, the calculated tech-description is added to the tech-library.

Abstract: A system for layout of a module in an integrated circuit layout pattern has a cell library and a cell placement system. The cell library includes a plurality of cells. The cell placement system is adapted to select one or more cells from the cell library and to locally place each selected cell within the module layout so that each cell pin of the selected cells and each port of the module layout occupies a unique vertical routing track within the module layout.

Abstract: The present invention provides a layout method for a top module including instances of a base module in a memory matrix such as a RRAM memory matrix, and the like. The top module and the base module may each include data pins and at least one control pin, or the top module and the base module may each include data pins only and may not include any control pins. The data pins of the instances of the base module are replicated in the top module. When at least one control pin is included in the top module and the base module, a control signal may be shared among the instances of the base module and the top module by tying together corresponding control pins of the instances and a corresponding control pin of the top module. The present method may include steps as follows. At a library preparation stage, data pins (and control pins, if applicable) of standard cells in the top module are extended vertically for easy access.

Abstract: Logic circuits for logical operations, based on a function fN=x1 OR (x2 AND (x3 OR (x4 AND . . . xN . . . ))) or f?N=x1 AND (x2 OR (x3 AND (x4 OR . . . xN . . . ))), are designed by defining a top portion of the logic circuit based on a pre-selected pattern of 2-input $ and @ gates. The top portion has N inputs and approximately N/3 outputs. A smaller logic circuit is defined having approximately N/3 inputs coupled to the outputs of the top portion. In one embodiment, the circuit is designed for a circuit having N? inputs, where N? is 3n or 2*3n, and the N??N most significant inputs are set to fixed values. The extra gates are removed resulting in a minimum depth circuit. In another embodiment, the depth is further reduced in some cases by designing a circuit for N?1 inputs and transforming the circuit to an N-input circuit. The $ and @ gates are converted to AND and/or OR gates, depending on the function.

Abstract: A plurality of user-defined memories are mapped to pre-defined basic memories, such as defined on a base platform. The user-defined memories are dividing into classes of similar memories. A mapping technique is selected for members of a selected class of user-defined memories that minimizes the ratio (maxi,j(USEDi,j/AVAILi,j)) of basic memories that have been mapped to basic memories that are available for mapping. If the number of different memory mappings is smaller than a threshold the mapping technique is applied to each user-defined memory. If the number of different memory mappings is greater than the threshold, the groups are arranged in ordered queues of single memory types based on a mapping price and the mapping technique is selected based on a memory of each group and is applied to each user-defined memory in the respective group.

Abstract: The present invention is directed to a FIFO memory with single port memory modules that may allow simultaneous read and write operations. In an exemplary aspect of the present invention, a method for employing a FIFO memory with single port memory modules of half capacity to perform simultaneous read and write operations includes the following steps: (a) providing a first single port memory module for an even address of a read or write operation; (b) providing a second single port memory module for an odd address of a read or write operation; (c) alternating even address and odd address; and (d) when both a read request and a write request reach either the first single port memory module or the second single port memory module at a clock cycle, fulfilling the read request at the current clock cycle and fulfilling the write request at the next clock cycle.

Abstract: The present invention is directed to a memory that allows two simultaneous read requests with improved density. In an aspect of the present invention, a memory module includes at least two primary memory sub-modules and an additional memory sub-module including a sum of values located in the at least two primary memory sub-modules at corresponding addresses. The sum of the additional memory module enables at least two simultaneous read requests to be performed.

Abstract: A routing multiplexer system provide p outputs based on a selected permutation of p inputs. Each of a plurality of modules has two inputs, two outputs and a control input and is arranged to supply signals at the two inputs to the two outputs in a direct or transposed order based on a value of a bit at the control input. A first p/2 group of the modules are coupled to the n inputs and a second p/2 group of the modules provide the n outputs. A plurality of control bit tables each contains a plurality of bits in an arrangement based on a respective permutation. The memory is responsive to a selected permutation to supply bits to the respective modules based on respective bit values of a respective control bit table, thereby establishing a selected and programmable permutation of the inputs to the outputs.

Abstract: Logic circuits for logical operations, based on a function fN=x1 OR (x2 AND (x3 OR (x4 AND . . . xN . . . ))) or f?N=x1 AND (x2 OR (x3 AND (x4 OR . . . xN . . . ))), are designed by defining a top portion of the logic circuit based on a pre-selected pattern of 2-input $ and @ gates. The top portion has N inputs and approximately N/3 outputs. A smaller logic circuit is defined having approximately N/3 inputs coupled to the outputs of the top portion. In one embodiment, the circuit is designed for a circuit having N? inputs, where N? is 3n or 2*3n, and the N?-N most significant inputs are set to fixed values. The extra gates are removed resulting in a minimum depth circuit. In another embodiment, the depth is further reduced in some cases by designing a circuit for N-1 inputs and transforming the circuit to an N-input circuit. The $ and @ gates are converted to AND and/or OR gates, depending on the function.

Abstract: The present invention is directed to a method for generating a tech-library for a logic function. A logic function has many representations. For each representation, a circuit for realizing the representation is decomposed into a combination of instances. An instance is a component logic circuit of a general logic circuit. There are pre-created tech-libraries for the instances. For example, a pre-created tech-library is created by categorizing tech-descriptions for primitive physical circuits based on a negation index. Thus, tech-descriptions for a circuit for realizing a representation are calculated from a combination of elements of the pre-created tech-libraries. Each calculated tech-description is compared with each existing element of a tech-library for the logic function. When a calculated tech-description has at least one marked parameter better or smaller than that of all existing elements of the tech-library for the logic function, the calculated tech-description is added to the tech-library.

Abstract: The present invention is directed to a sequential tester for longest prefix search engines. The tester may include a longest prefix search engine, an inputs generator for providing a nearly random flow of input commands to the longest prefix search engine and for outputting a floating rectangle which may represent a search table of the longest prefix search engine, a coding module for providing address and prefix information to the longest prefix search engine, a mapping module for providing data information to the longest prefix search engine, a super search engine for performing super search operations, and an analyzer for computing predicted outputs of the longest prefix search engine and for comparing the predicted outputs with actual outputs computed by the longest prefix search engine.

Abstract: Apparatus and process identifies a maximum or minimum value among a plurality of binary values on a plurality of a-bit wide wires in an integrated circuit module. An N-bit vector K is calculated based on n most significant bits of all a-bit binary signals, where N=2n. M N-bit vectors K—0, . . . ,K_(M−1) are calculated based on the n most significant and the m least significant bits of all a-bit binary signals, where M is at least 2m−1. A table is constructed from vectors K—0, . . . ,K(M−1) to create table vectors. A table vector is selected based on vector K, is used to derive a vector P, which in turn is used to select another table vector. The minimum or maximum binary value is identified from the two selected table vectors.

Abstract: The present invention is directed to a memory that allows two simultaneous read requests with improved density. In an aspect of the present invention, a memory module includes at least two primary memory sub-modules and an additional memory sub-module including a sum of values located in the at least two primary memory sub-modules at corresponding addresses. The sum of the additional memory module enables at least two simultaneous read requests to be performed.

Abstract: A memory manager for managing allocation of addresses in the memory is structured as a hierarchical tree having a top vertex, a bottom level and at least one intermediate level. The bottom level contains a plurality of bottom vertices each containing a plurality of representations of a Free or Taken status of respective addresses in the memory. Each intermediate contains at least one hierarchy vertex containing a plurality of labels such that each label is associated with a child vertex and defines whether or not a path that includes the respective child vertex ends in a respective bottom level vertex containing at least one Free representation. An allocation command changes the representation of the first Free address to Taken and a free command changes the representation of a specified address to Free. The labels in hierarchical vertices are changed to reflect the path conditions to the bottom vertices.

Abstract: A search engine architecture substitutes short indices for large data widths, thereby reducing widths required for input to and output from the search engine. The search engine system comprises a search engine responsive to an input address to access an index in the search engine. The index has a width no greater than logarithm on base 2 of the search engine capacity, thereby permitting the search engine to be embodied in an IC chip of reduced area. A driver responds to input commands and to the search engine status to manage indices in the search engine and enable the memory to access its addressable locations based on indices in the search engine.

Abstract: A search engine apparatus having a built-in functional test may include an input generator, a search engine, a pseudo search engine and a comparator. The inputs generator is suitable for generating outputs including commands and points associated with the commands. The search engine and the pseudo search engine are communicatively coupled to the inputs generator. The search engine suitable for performing search and edit operations and the pseudo search engine is suitable for simulating the search engine by generating pseudo search engine outputs. The comparator is communicatively coupled to the search engine and the pseudo search engine, and is suitable for comparing outputs received from the search engine and pseudo search engine.

Abstract: The present invention is a method and apparatus for optimizing the design of a combinational circuit. The method includes constructing a circuit sheaf for the combinational circuit and then performing vector optimization with domination. In the preferred embodiment, a complete BDD B is determined and, from that, a list of F-sets is computed. If the combinational circuit includes cells other than NOT, AND and XOR cells, the circuit is first transformed such that it only has those types of cells.