摘要:
Methods of designing and testing restore logic for restoring values to storage elements of power-managed logic circuitry. In one implementation, a design method disclosed includes providing a design of the logic circuitry that, when instantiated, will have a number of states it can be returned to upon repowering-up the logic circuitry. Values held by the storage elements are determined and utilized to categorize the storage elements into categories that allow the development of restore logic that will restore the state of the power-managed logic circuitry that is appropriate to the particular powering-up. The restore logic design is tested by modeling it and the power-managed logic circuitry in a hardware description language and simulating the number of states over a number of test cases. If the design and testing are successful, the restore logic can be optimized for instantiation into an actual integrated circuit.
摘要:
Multi-state restore circuitry that allows storage elements of a power-managed functional block to be loaded when the functional block is repowered up so that the functional block is ready for operation virtually immediately after voltage ramp-up of the functional block. The multi-state restore circuitry includes a restore-state detector for determining which one of a plurality of restore states of the functional block is applicable to a particular repowering-up of the functional block. The multi-state restore circuitry also includes restore logic that loads the storage elements as a function of the restore state determined by the restore-state detector.
摘要:
Methods of designing and testing restore logic for restoring values to storage elements of power-managed logic circuitry. In one implementation, a design method disclosed includes providing a design of the logic circuitry that, when instantiated, will have a number of states it can be returned to upon repowering-up the logic circuitry. Values held by the storage elements are determined and utilized to categorize the storage elements into categories that allow the development of restore logic that will restore the state of the power-managed logic circuitry that is appropriate to the particular powering-up. The restore logic design is tested by modeling it and the power-managed logic circuitry in a hardware description language and simulating the number of states over a number of test cases. If the design and testing are successful, the restore logic can be optimized for instantiation into an actual integrated circuit.
摘要:
Multi-state restore circuitry that allows storage elements of a power-managed functional block to be loaded when the functional block is repowered up so that the functional block is ready for operation virtually immediately after voltage ramp-up of the functional block. The multi-state restore circuitry includes a restore-state detector for determining which one of a plurality of restore states of the functional block is applicable to a particular repowering-up of the functional block. The multi-state restore circuitry also includes restore logic that loads the storage elements as a function of the restore state determined by the restore-state detector.
摘要:
A design structure embodied in a machine readable, non-transitory storage medium used in a design process includes a system for dynamically varying the pipeline depth of a computing device. The system includes a state machine that determines an optimum length of a pipeline architecture based on a processing function to be performed. A pipeline sequence controller, responsive to the state machine, varies the depth of the pipeline based on the optimum length. A plurality of clock splitter elements, each associated with a corresponding plurality of latch stages in the pipeline architecture, are coupled to the pipeline sequence controller and adapted to operate in a functional mode, one or more clock gating modes, and a pass-through flush mode. For each of the clock splitter elements operating in the pass-through flush mode, data is passed through the associated latch stage without oscillation of clock signals associated therewith.
摘要:
A design structure embodied in a machine readable, non-transitory storage medium used in a design process includes a system for dynamically varying the pipeline depth of a computing device. The system includes a state machine that determines an optimum length of a pipeline architecture based on a processing function to be performed. A pipeline sequence controller, responsive to the state machine, varies the depth of the pipeline based on the optimum length. A plurality of clock splitter elements, each associated with a corresponding plurality of latch stages in the pipeline architecture, are coupled to the pipeline sequence controller and adapted to operate in a functional mode, one or more clock gating modes, and a pass-through flush mode. For each of the clock splitter elements operating in the pass-through flush mode, data is passed through the associated latch stage without oscillation of clock signals associated therewith.
摘要:
A system for dynamically varying the pipeline depth of a computing device, depending upon at least one of computing function and workload, includes a state machine is configured to determine an optimum length of a pipeline architecture based on a processing function to be performed, and a pipeline sequence controller, responsive to the state machine, the pipeline sequence controller configured to vary the depth of the pipeline based on the determined optimum length. A plurality of clock splitter elements is associated with a corresponding plurality of latch stages in the pipeline architecture, the clock splitter elements coupled to the pipeline sequence controller and adapted to operate in a functional mode, one or more clock gating modes, and a pass-through flush mode. For each of the clock splitter elements operating in the pass-through flush mode, data is passed through the associated latch stage without oscillation of clock signals associated therewith.
摘要:
Both logical and physical construction of voltage islands is disclosed. A semiconductor chip design is partitioned into “bins”, which are areas of the design. In this way, a semiconductor chip design may be “sliced” into various areas and the areas may then be assigned to various voltage levels. Each bin may be thought of as a voltage island. Circuits in the design can be added to or removed from the various bins, thereby increasing or decreasing the speed and power of the circuits: the speed and power increase if a circuit is placed into a bin assigned a higher voltage, and the speed and power decrease if a circuit is placed into a bin having a lower voltage. The size and location of the bins may also be changed. By iterating these steps, the optimum power consumption may be met while still meeting speed constraints and other criteria. The present invention is applicable to any placement environment, such as an annealing placement tool, that proceeds through successive refinement of the locations of the circuits on the design and in which the placement process may be interrupted to make changes in placement of the logic.
摘要:
A design structure embodied in a machine readable, non-transitory storage medium used in a design process includes a system for dynamically varying the pipeline depth of a computing device. The system includes a state machine that determines an optimum length of a pipeline architecture based on a processing function to be performed. A pipeline sequence controller, responsive to the state machine, varies the depth of the pipeline based on the optimum length. A plurality of clock splitter elements, each associated with a corresponding plurality of latch stages in the pipeline architecture, are coupled to the pipeline sequence controller and adapted to operate in a functional mode, one or more clock gating modes, and a pass-through flush mode. For each of the clock splitter elements operating in the pass-through flush mode, data is passed through the associated latch stage without oscillation of clock signals associated therewith.
摘要:
A method, test system and computer program product and system for voltage binning integrated circuit chips. The method includes selecting or changing a voltage bin of a set of voltages bins corresponding to frequency specification limits of an integrated circuit chip using functional testing of data paths of the integrated circuit chip.