Abstract: The present invention provides a method for converting a netlist of an integrated circuit from a first library to a second library. The first library may include logic cells AND, OR and NOT, and the second library may include logic cells NAND and NOR. The method includes steps as follows. Logic cells of the netlist are topologically sorted from outputs to inputs. AND and OR cells of the netlist are replaced with NOT, NAND and NOR cells. Simplification of the netlist is performed in a topological order.

Abstract: An RRAM design having linear BIST memory and rectangular BIST memory, the improvement comprising at least one of the linear BIST memory and the rectangular BIST memory formed only of flipflops and logic cells.

Abstract: The present invention provides a method for mapping a netlist of an integrated circuit to a design. The method includes steps as follows. Chaos algorithm is used to obtain most favorable places in the design for cells from the netlist. Kuhn's algorithm is utilized to assign each cell of the netlist a cell in a template so that, for each cell of the netlist, its place in the template is as close as possible to its place obtained by the chaos algorithm. Simulating annealing optimization technique is applied to reduce a sum of wire length of the design.

Abstract: Cells are placed into an integrated circuit floorplan by creating clusters of cells in modules, each cluster being composed of cells in a path connected to at least one flip-flop in the module, or of cells that are not in a path connected to any flip-flop. Regions are defined in the floorplan for placement of modules, and the clusters are placed into optimal locations in modules and placing the modules into optimal locations in the regions. The coordinates for the wires, modules and clusters are selectively recalculated. The clusters are moved in the floorplan for more uniform density, and the modules are assigned to regions based on module coordinates.

Abstract: A method of generating a timing model for a customer memory configuration, by generating a plurality of template memory netlists for a given RRAM design. Timing models for the template memory netlists are produced and stored in a first database. The template memory netlists are stored in a second database. A netlist for the customer memory configuration is generated and compared to the template memory netlists to find a match. When a match is found, one of the timing models that is associated with the matching template memory netlist is used as the timing model for the customer memory configuration. When a match is not found, two of the template memory netlists that bound the customer netlist are found, according to at least one parameter, and the timing model for the customer memory configuration is interpolated based on the two bounding template memory netlists.

Abstract: An RRAM flip-flop rcell memory of the type having a write address decoder, a read address decoder, a set of n flip flops, one AND gate associated with each flip flop in the set, a set of w OR gates where each of the w OR gates in the set has n inputs, the improvement comprising only one write address decoder, and replacing the read address decoder and the set of AND gates and the set of OR gates with no more than one multiplexor, thereby providing a reduction in a path length from an rcell memory input to an rcell memory output and thereby improving timing of the rcell memory, while reducing fanout size of the rcell. In a preferred embodiment, the multiplexor includes fewer than w OR gates, and fewer than n AND gates, and two decoders, which are commonly connected to outputs of the n flip flops.

Abstract: A method of analyzing multimode delay in an integrated circuit design to produce a timing model for the integrated circuit design, by inputting a net list, IO arc delays, interconnection arc delays, and constant nets with assigned Boolean functions for the integrated circuit design, propagating the constant nets and assigning Boolean conditions to the IO arc delays and the interconnection arc delays, evaluating timing path delays and conditions for the integrated circuit design, creating the integrated circuit design timing model parameters, and outputting the integrated circuit design timing model. The method is especially desirable for netlists with very complicated mixing logics that include muxing of clocks. In particular, RRAMs are such netlists.

Abstract: A user-defined memory design is mapped to memories of a base platform for an IC that contains a plurality of memory sets, each containing a plurality of memories of a predetermined type. An optimal memory set is selected from the plurality of memory sets for the design by selecting a preference rate for each memory set from the plurality of sets based on the design and its connections to portions of the IC, and selectively assigning the design to one of the memory sets based on the preference rate. The design is optimally mapped to a plurality of memories of the selected memory set by defining an index of the position of each customer memory in the selected memory set. The customer memories in the selected memory set are arranged in an order, and successive numbers of memories of the selected memory set are assigned to each customer memory in order.

Abstract: A memory generation and placement flow system that receives a customer memory design and places the customer memory design within a customizable standardized integrated circuit design. The memory generation and placement flow system includes a memory librarian tool, a memory estimator tool, and a memory placer tool.

Abstract: Objects are assigned to points in a rectangle by dividing the rectangle is divided into a plurality of smaller rectangles and applying an object assignment procedure, such as Kuhn's algorithm, to initially assigned objects in each second rectangle. The initial assignment is performed by calculating a maximal cost of assignment of objects to points, and selecting an assignment of objects having a minimum value of maximal cost, identified by iteratively recalculating the maximal matching assignment based on a midpoint of between the minimum and maximum costs.

Abstract: Boolean circuits are designed with minimal depth by calculating the depth of an existing circuit. Those subtrees having a non-regular root cell (i.e., cells having other than one child or having a child of a type different from the cell) are balanced by constructing a new subtree. The cells are then iteratively transformed with parent and/or grandparent cells to reduce the depth of the circuit. The transformation may include balancing the subtree to make the parent cell the same type as the selected cell, or by creating a new cell as parent to the selected cell.

Abstract: The present invention is directed to a method and apparatus of IC implementation based on a C++ language description. In an exemplary aspect of the present invention, a method for evaluating a C++ description by an IC includes the following steps. First, a C++ description including a C++ program is provided. Then, the C++ program is stored in a first memory module (e.g., a ROM, or the like) of an IC. Next, a scalar input and/or an input array may be provided to the IC. Then, the C++ program may be executed by a control device module of the IC. Next, a scalar output and/or an output array may be read from the IC.

Abstract: The present invention provides a method of verification of a RRAM tiling netlist. The method may include steps as follows. Properties “memory_number”, “clock_number” and “netlist_part” of all nets and cells of a RRAM tiling netlist are set to a value 0. A boolean function 0 is assigned to all ground nets of the RRAM tiling netlist, and a boolean function 1 is assigned to all power nets of the RRAM tiling netlist. The RRAM tiling netlist is verified for each customer memory Memk, k=1, 2, . . . , N.

Abstract: A method of generating a timing model for a customer memory configuration, by generating a plurality of template memory netlists for a given RRAM design. Timing models for the template memory netlists are produced and stored in a first database. The template memory netlists are stored in a second database. A netlist for the customer memory configuration is generated and compared to the template memory netlists to find a match. When a match is found, one of the timing models that is associated with the matching template memory netlist is used as the timing model for the customer memory configuration. When a match is not found, two of the template memory netlists that bound the customer netlist are found, according to at least one parameter, and the timing model for the customer memory configuration is interpolated based on the two bounding template memory netlists.

Abstract: A memory generation and placement flow system that receives a customer memory design and places the customer memory design within a customizable standardized integrated circuit design. The memory generation and placement flow system includes a memory librarian tool, a memory estimator tool, and a memory placer tool.

Abstract: A decision function generator for a Viterbi decoder includes a compressor module for receiving arguments of a decision function and for evaluating functions of the arguments of the decision function, a memory module coupled to the compressor module for generating an intermediate function from the functions of the arguments, and a decompressor module coupled to the memory module for generating a sign value, an integer value, and a fractional value constituting a value of the decision function from the intermediate function.

Abstract: Objects are placed in a rectangle and their coordinates of the objects and are adjusted to establish a substantially uniform density of objects in the rectangle. The evaluation of coordinates is performed by placing the wires between cells coordinates and adjusting the cell coordinates to connect the cells to the wires. The substantially uniform density is achieved by dividing the rectangle into first and second rectangles having equal free areas and into third and fourth rectangles having equal areas of objects. The coordinates of the objects are adjusted based on boundaries between the first and second rectangles and between the third and fourth rectangles.

Abstract: The present invention is a method and system for outputting a sequence of commands and data described by a flowchart. In an exemplary aspect of the present invention, a method for outputting a sequence of commands and data described by a flowchart includes steps as follows. A flowchart describing a sequence of commands and data is received. The flowchart includes a plurality of flowchart symbols. Each of the plurality of flowchart symbols is assigned a ROM (read only memory) record. Assigned ROM records are stored in a ROM. A module (e.g., a CKD, or the like) is generated to include the ROM, wherein the module receives as input a CLOCK signal, a RESET signal, an ENABLE signal and N binary inputs x1, x2, . . . xN, and outputs the sequence of commands and data.

Abstract: A user-defined memory design is mapped to memories of a base platform for an IC that contains a plurality of memory sets, each containing a plurality of memories of a predetermined type. An optimal memory set is selected from the plurality of memory sets for the design by selecting a preference rate for each memory set from the plurality of sets based on the design and its connections to portions of the IC, and selectively assigning the design to one of the memory sets based on the preference rate. The design is optimally mapped to a plurality of memories of the selected memory set by defining an index of the position of each customer memory in the selected memory set. The customer memories in the selected memory set are arranged in an order, and successive numbers of memories of the selected memory set are assigned to each customer memory in order.

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.