Patent application number | Description | Published |
20080229006 | High Bandwidth Low-Latency Semaphore Mapped Protocol (SMP) For Multi-Core Systems On Chips - A system and method for dynamically managing movement of semaphore data within the system. The system includes, but is no limited to, a plurality of functional units communicating over the network, a memory device communication with the plurality of functional units over the network, and at least one semaphore storage unit communicating with the plurality of functional unites and the memory device over the network. The plurality of functional units include a plurality of functional unit memory locations. The memory device includes a plurality of memory device memory locations. The at least one semaphore storage unit includes a plurality of semaphore storage unit memory locations. The at least one semaphore storage unit controls dynamic movement of the semaphore data among the plurality of functional unit memory locations, the plurality of memory device memory locations, the plurality of semaphore storage unit memory locations, and any combinations therof. | 09-18-2008 |
20090031111 | METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR DYNAMICALLY SELECTING COMPILED INSTRUCTIONS - A method, apparatus, and computer program product dynamically select compiled instructions for execution. Static instructions for execution on a first execution and dynamic instructions for execution on a second execution unit are received. The throughput performance of the static instructions and the dynamic instructions is evaluated based on current states of the execution units. The static instructions or the dynamic instructions are selected for execution at runtime on the first execution unit or the second execution unit, respectively, based on the throughput performance of the instructions. | 01-29-2009 |
20090125704 | DESIGN STRUCTURE FOR DYNAMICALLY SELECTING COMPILED INSTRUCTIONS - A design structure embodied in a machine readable medium used in a design process includes an apparatus for dynamically selecting compiled instructions for execution, the apparatus including an input for receiving static instructions for execution on a first execution unit and receiving dynamic instructions for execution on a second execution unit; and an instruction selection element adapted to evaluate throughput performance of the static instructions and dynamic instructions based on current states of the execution units and select the static instructions or the dynamic instructions for execution at runtime on the first execution unit or the second execution unit, respectively, based on the throughput performance of the instructions. | 05-14-2009 |
Patent application number | Description | Published |
20080229074 | Design Structure for Localized Control Caching Resulting in Power Efficient Control Logic - A design structure for an integrated circuit (IC) including a decoder decoding instructions, shadow latches storing instructions as a localized loop, and a state machine controlling the decoder and the plurality of shadow latches. When the state machine identifies instructions that are the same as those stored in the localized loop, it deactivates the decoder and activates the plurality of shadow latches to retrieve and execute the localized loop in place of the instructions provided by the decoder. Additionally, a method of providing localized control caching operations in an IC to reduce power dissipation is provided. The method includes initializing a state machine to control the IC, providing a plurality of shadow latches, decoding a set of instructions, detecting a loop of decoded instructions, caching the loop of decoded instructions in the shadow latches as a localized loop, detecting a loop end signal for the loop and stopping the caching of the localized loop. | 09-18-2008 |
20080229265 | Design Structure for a Clock Distribution Network, Structure, and Method for Providing Balanced Loading in Integrated Circuit Clock Trees - Design structure for a clock distribution network, structure, and method for providing balanced loading is disclosed. In particular, a design structure for a clock distribution network may be formed of one or more clock fanout distribution levels. Each respective distribution level may include an equal number of buffer circuits and wiring routes that have substantially identical physical and electrical properties. Additionally, a final distribution level may include wiring routes that have substantially identical physical and electrical properties connecting buffer circuits to one or more logic leaf connection nodes. | 09-18-2008 |
20080229266 | Design Structure for a Clock Distribution Network, Structure, and Method for Providing Balanced Loading in Integrated Circuit Clock Trees - Design structure for a clock distribution network, structure, and method for providing balanced loading is disclosed. In particular, a clock distribution network may be formed of one or more clock fanout distribution levels. Each respective distribution level may include an equal number of buffer circuits and wiring routes that have substantially identical physical and electrical properties. Additionally, a final distribution level may include wiring routes that have substantially identical physical and electrical properties connecting buffer circuits to one or more logic leaf connection nodes. | 09-18-2008 |
20080290896 | System and Method for Dynamically Executing a Function in a Programmable Logic Array - A reconfigurable logic array (RLA) system that includes an RLA and a programmer for reprogramming the RLA on a cyclical basis. A function (F) requiring a larger amount of logic than contained in the RLA is partitioned into multiple functional blocks. The programmer contains software that partitions the RLA into a function region FR located between two storage regions SR | 11-27-2008 |
20090125744 | Structure for a System and Method of Predicting Power Events in an Intermittent Power Environment and Dispatching Computational Operations of an Integrated Circuit Accordingly - A design structure for a system and method of predicting power events in intermittent power environments and dispatching computational operations of an integrated circuit accordingly. A power management prediction system includes a controller executing a prediction algorithm, an arrangement of computation circuitry, a non-volatile storage device containing a power requirements log and a power history log, a clock generator, an intermittent power source, and a power monitor circuit. A method of predicting intermittent power events and dispatching computational operations includes: storing power requirements of each computational operation, monitoring the intermittent power source to generate a history log, predicting a subsequent power event based on the history log, retrieving actual power requirements of one or more computational operations, comparing the predicted power event with actual power requirements, determining whether actual power requirements are satisfied, dispatching one or more computational operations that correspond to one or more actual power events, or performing an error recovery operation. | 05-14-2009 |