Abstract: Using a computer and storage, a circuit design process is executed to preserve overall design quality while obtaining quality placements for a full class of pipeline structure signatures. These signatures include classic latch to latch pipelines, as well as a variety of latch to latch and mixed logic pipelines. The process employs a method for optimizing pipeline structure placement in a circuit design, by initiating an analysis of pipeline logic structures for correcting poor quality of result (QOR) placements by identifying poor placements caused by placement algorithmic response to degenerate cases and in the process of analysis preserving high quality placements of global placement and timing to preserve preponderant non-degenerate cases in said circuit design.

Abstract: The present invention relates to creating a layout of an electronic circuit from a netlist of interconnected components, wherein the components can be represented by planar geometric shapes in the layout. The advantages of the present invention are achieved by tightly coupling placement and routing. An initial placement of shapes of extended size is succeeded by a routing step that tries to create wires between shapes of reduced size. If that fails, it is tried to wire shapes of extended size instead. The wiring can be combined with a delta-placement of shapes within shapes of extended size such that wires connected to shapes of extended size also connect to the shapes.

Abstract: A multiprocessor computer system has a plurality of processing nodes which use processor state information to determine which coherent caches in the system are required to examine a coherency transaction produced by a single originating processor's storage request. A node of the computer has dynamic coherency boundaries such that the hardware uses only a subset of the total processors in a large system for a single workload at any specific point in time and can optimize the cache coherency as the supervisor software or firmware expands and contracts the number of processors which are being used to run any single workload. Multiple instances of a node can be connected with a second level controller to create a large multiprocessor system. The node controller uses the mode bits to determine which processors must receive any given transaction that is received by the node controller.

Abstract: Disclosed is a method for constructing a Hybrid Cycle Simulation model comprising Compiled Data Units (CDUs) for use in design verification. The simulation model may contain a plurality of 1-cycle CDUs, optimized for simulation throughput, and 2-cycle CDUs, optimized for simulation accuracy, or a mixture thereof. Utilizing a netlist tool extracting hierarchical design source components for use, the construction checks that all inputs and outputs of any hierarchical design source components bind, and employs Object Traversal Directives for incorporating the selected CDUs into the simulation model. A data management method is used for tracking the validity of the components in the model. Additionally, a software entity (FACDDR) permits high bandwidth simulation of design components normally requiring cycle accurate simulation.

Abstract: A computer system apparatus for asynchronous data transfer between a source and sink without the use of an asynchronous control signal. includes metastability circuits, data change detection logic, a stability window delay counter, and a mux/register pair to allow for the holding of previous stable data during the transition. While the processing logic employed specifically applies to asynchronous logic, the logic can be extended to synchronous or untimed interfaces as well. Also disclosed is a programmable means to adjust the window delay.

Abstract: The output register of an array and the Multiple Input Signature Register (MISR) logic is implemented with one set of L1/L2 master/slave latches and single additional slave latch. This new combined logic uses less critical area on a chip without a performance impact on the array access time or circuit testing.

Abstract: A dual system shared cache directory structure for a cache memory performs the role of an inclusive shared system cache, i.e., data, and system control, i.e., coherency. The system includes two separate system cache directories in the shared system cache. The two separate cache directories are substantially equal in size and collectively large enough to contain all of the processor cache directory entries, but with only one of these separate cache directories hosting system-cache data to back the most recent fraction of data accessed by the processors. The other cache directory retains only addresses, including addresses of lines LRUed out from the first cache directory and the identity of the processor using the data. Thus by this expedient, only the directory known to be backed by system cached data will be evaluated for system cache memory data.

Abstract: In a hierarchical semiconductor digital unit comprised of a plurality of macro functional logic blocks, each of said macro functional logic blocks comprised of a plurality of leaf cells, each of said leaf cells accessed via an input terminal and an output terminal, the improvement wherein locating each input terminal provides access to a single leaf cell at a legal location proximate the leaf cell to which the input terminal provides access.

Abstract: A multiprocessor computer system has nodes which use processor state information to determine which coherent caches are required to examine a coherency transaction produced by a single originating processor's storage request. A node has dynamic coherency boundaries such that the hardware uses only a subset of the total processors for a single workload at any specific point in time and can optimize cache coherency as the supervisor software or firmware expands and contracts the number of processors used to run any single workload. Multiple instances of a node can be connected with a second level controller to create a larger multiprocessor system. The node controllers use the mode bits to determine which nodes must receive any given transaction. Logical partitions are mapped to allowable physical processors. Cache coherence regions and caches are chosen for their physical proximity. A distinct cache coherency region can be hypervisor defined for each partition.

Abstract: A memory element comprises a first number of electrodes and a second number of electrically conducting channels between sub-groups of two of said electrodes, the channels exhibiting an electrical resistance that is reversibly switchable between different states, wherein the first number is larger than two and the second number is larger than the first number divided by two. The electrically conducting channels may be provided in transition metal oxide material, which exhibits a reversibly switchable resistance that is attributed to a switching phenomenon at the interfaces between the electrodes and the transition metal oxide material.

Abstract: A domino SRAM global bit select circuit provides an interface between dual global read and write bit line pairs to a “local bit select” circuit.

Abstract: A hierarchical and modular clock programmable delay circuit structure is described that can achieve almost unlimited fine resolution and unlimited delay range. The same circuit may also be applied to critical circuits that require fine adjustment in timing applications. The modular design allows the circuit and its layout to be synthesized by software to achieve desired delay resolution and range. Constant capacitive load of internal node enhances the linearity of achieved delay by digital controls.

Abstract: Automated verification methodology parsing scripts auto generate testbench hardware design language, such as VHDL or Verilog, from the design source VHDL or Verilog. A formal verification model is then built comprising the testbench VHDL and the design under test. The resulting design verification tool then provides proofs and counterexamples for all of the rules, e.g., auto-generated rules, in the testbench.

Abstract: An apparatus and method for allowing for dynamic wordline repair in a clock running system in addition to allowing for programmable fuse support of combined Array Built-In Self-Test (ABIST) and Logic Built-In Self-Test (LBIST) testing. The method makes use of programmable fuses which contain Level Sensitive Scan Design (LSSD) latches which also have a system port. The system port allows for simpler reading of the fuses as well as for the dynamic updates of the programmable fuses for wordline and other repairs.

Abstract: Memory array built in self testing utilizing including a simple data history table. The table is used to track failing locations observed during any level of assembly test of processor or logic semiconductor chips where the chips contain SRAM macros with redundant elements for failure relief.

Abstract: Testing a model of a logic circuit model. The testing includes generating valid random input stimulus sequences for a logic circuit model. Enumerating critical resource requirements, enumerating critical resource availabilities does this, and selecting of stimulus sequences and determining legal times for execution of said stimulus sequences based on resource availability. This includes generating a plurality of possible combinations of input stimulus sequences and generating an array representation of critical resource requirements. These are used to generate an array representation of critical resources availabilities.

Abstract: The present invention relates to boot code processing of a computer system, and in particular to a method and respective system for managing boot code of a computer system, wherein the system comprises at least a first and a redundant second boot memory portion, and wherein the system is booted from one of said portions, referred to as the active booting portion, the other boot portion being in a stand-by mode and being referred to as inactive boot portion.

Abstract: A digital adder circuit comprising a plurality of logical stages in the carry logic of said adder circuit, for generating and propagating predetermined groups of operand bits, each stage implementing a predetermined logic function and processing input variables from a preceding stage and outputting result values to a succeeding stage with static and dynamic logic in the carry network of a 4-bit adder, and with output from the first stage fed directly as an input (60, 62) to the third stage of the carry network. Preferably, stages having normally relatively high switching activities are implemented in static logic. Preferably, the first stage of its carry network is implemented in a static logic, and the rest of the stages in dynamic logic.

Abstract: According to the present invention an automated method is provided for routing and designing an LSI (Large Scale Integrated Circuit). First, at least one generic of an instance of a book to be connected is located on the chip, wherein a generic of an instance is an area defined according to the measurements of said instance. Then, an initial route to said instance is generated by optimizing the route to the corresponding generic according to given design rules. Thereby, an optimized pin location is determined for said instance. Then, on the basis of said optimized pin location a layout for said instance is generated in place of the corresponding generic. Finally, the actually generated pin is connected with the corresponding end of the initial route.

Abstract: Buffered indexing for a computer's array such as a cache is used to synchronize parent entries with children and allow background invalidation (that is, suspending the invalidation should a new request of the array come in, resuming the invalidation after the request is satisfied) of the child entries. A method for synchronization uses linking of (multiple) entries in lower-level tables to single entries in a higher-level table with a buffered index value. This index value increments each time the higher-level entry is replaced or invalidated (and thus disassociated with its corresponding lower-level entries). Multiple sets of index values are maintained, so that when one set is exhausted, processing can continue with one of the other sets. All corresponding lower-level entries with index values from the old (dirty) set can then be scrubbed (invalidated) while new entries are built from the new (clean) set.