G06F30/396

Static voltage drop (SIR) violation prediction systems and methods

Systems and methods are provided for predicting static voltage (SIR) drop violations in a clock-tree synthesis (CTS) layout before routing is performed on the CTS layout. A static voltage (SIR) drop violation prediction system includes SIR drop violation prediction circuitry. The SIR drop violation prediction circuitry receives CTS data associated with a CTS layout. The SIR drop violation prediction circuitry inspects the CTS layout data associated with the CTS layout, and the CTS layout data may include data associated with a plurality of regions of the CTS layout, which may be inspected on a region-by-region basis. The SIR drop violation prediction circuitry predicts whether one or more SIR drop violations would be present in the CTS layout due to a subsequent routing of the CTS layout.

Static voltage drop (SIR) violation prediction systems and methods

Systems and methods are provided for predicting static voltage (SIR) drop violations in a clock-tree synthesis (CTS) layout before routing is performed on the CTS layout. A static voltage (SIR) drop violation prediction system includes SIR drop violation prediction circuitry. The SIR drop violation prediction circuitry receives CTS data associated with a CTS layout. The SIR drop violation prediction circuitry inspects the CTS layout data associated with the CTS layout, and the CTS layout data may include data associated with a plurality of regions of the CTS layout, which may be inspected on a region-by-region basis. The SIR drop violation prediction circuitry predicts whether one or more SIR drop violations would be present in the CTS layout due to a subsequent routing of the CTS layout.

CLOCK MAPPING IN AN INTEGRATED CIRCUIT DESIGN

A processor receives, as input, a first hardware description language (HDL) file defining an entity of a modular circuit design. The first HDL file instantiates, by a storage element declaration in a hardware description language, a storage element within the entity. The first HDL file omits a port map for the storage element. Based on the first HDL file, the processor automatically fully elaborates a port map for the storage element. The processor stores, in data storage, a derived second HDL file defining the entity and including the port map.

LOGICAL CLOCK CONNECTION IN AN INTEGRATED CIRCUIT DESIGN

A first plurality of hardware description language (HDL) files describe a hierarchical integrated circuit design utilizing a simplified HDL syntax that omits specification of logical clock connections for at least some entities in the hierarchical integrated circuit design. The hierarchical integrated circuit design as described by the first plurality of HDL files is processed to automatically add logical clock connections for entities in the hierarchical integrated circuit design for which specification of logical clock connections are omitted in the first plurality of HDL files. Based on the processing, a second plurality of HDL files defining the hierarchical integrated circuit design is generated.

AUTOMATING ADDITION OF POWER SUPPLY RAILS, FENCES, AND LEVEL TRANSLATORS TO A MODULAR CIRCUIT DESIGN

A specification for a modular circuit design includes a mapping from global clock domains to global voltage domains. A processor assigns, to a first instance of a clocked primitive component, a global voltage domain based on which global clock domain clocks the first instance, automatically adds, to the modular circuit design, first power supply rails to power the first instance, and connects the first power supply rails from the first instance to a first power supply for a first global voltage domain. The processor assigns, to a second instance of the clocked primitive component, a second global voltage domain based on which global clock domain clocks the second instance, automatically adds second power supply rails to power the second instance, and connects the second power supply rails to a second power supply for a second global voltage domain. The processor may perform further processing on the updated modular circuit design.

AUTOMATING ADDITION OF POWER SUPPLY RAILS, FENCES, AND LEVEL TRANSLATORS TO A MODULAR CIRCUIT DESIGN

A specification for a modular circuit design includes a mapping from global clock domains to global voltage domains. A processor assigns, to a first instance of a clocked primitive component, a global voltage domain based on which global clock domain clocks the first instance, automatically adds, to the modular circuit design, first power supply rails to power the first instance, and connects the first power supply rails from the first instance to a first power supply for a first global voltage domain. The processor assigns, to a second instance of the clocked primitive component, a second global voltage domain based on which global clock domain clocks the second instance, automatically adds second power supply rails to power the second instance, and connects the second power supply rails to a second power supply for a second global voltage domain. The processor may perform further processing on the updated modular circuit design.

Structural matching for fast re-synthesis of electronic circuits

Techniques include retrieving a first structural netlist (SN1) that indicates electronic components, values of programmable parameters, and connections for a first electronic circuit, and retrieving a first placed and routed netlist (PR1) that indicates physical placement of the electronic components and physical routing of connections for SN1. Also retrieved is a second structural netlist (SN2) for a different second electronic circuit. For each component in SN2, a matching component, if any, is found in SN1 based on type of component and inputs that are output from other matching components. A different second placed and routed netlist (PR2) is generated for the second circuit by deriving new placement and routing for only for non-matching components in SN2.

Structural matching for fast re-synthesis of electronic circuits

Techniques include retrieving a first structural netlist (SN1) that indicates electronic components, values of programmable parameters, and connections for a first electronic circuit, and retrieving a first placed and routed netlist (PR1) that indicates physical placement of the electronic components and physical routing of connections for SN1. Also retrieved is a second structural netlist (SN2) for a different second electronic circuit. For each component in SN2, a matching component, if any, is found in SN1 based on type of component and inputs that are output from other matching components. A different second placed and routed netlist (PR2) is generated for the second circuit by deriving new placement and routing for only for non-matching components in SN2.

Apparatus, Device, Method, and Computer Program for Generating Logic to be Performed by Computing Circuitry of a Computing Architecture

Examples relate to an apparatus, device, method, and computer program for generating logic to be performed by computing circuitry of a computing architecture. The apparatus is configured to determine a performance-critical compute path of a compute kernel to be executed on a plurality of units of computing circuitry of a computing architecture, the compute kernel comprising a plurality of interdependent groups of computational instructions, with the performance-critical compute path being based on a subset of the interdependent groups of computational instructions. The apparatus is configured to determine, for at least one group of computational instructions outside the performance-critical compute path, a reduced clock frequency being lower than a maximally feasible clock frequency of the respective group of computational instructions. The apparatus is configured to generate logic to be performed by one or more of the plurality of separately controllable units of computing circuitry based on the compute kernel, wherein a portion of the logic that is generated to be performed by the plurality of separately controllable units of computing circuitry outside the performance-critical compute path is generated based at least in part on the reduced clock frequency.

Circuit layout

Generating a circuit layout is provided. A circuit layout associated with a circuit is received. A parallel pattern recognition is performed on the circuit layout. Performing the parallel pattern recognition includes determining that there is a parallel pattern in the circuit layout. In response to determining that there is a parallel pattern in the circuit layout, a cell swap for a first cell associated with the parallel pattern with a second cell is performed. After the cell swap for the first cell, engineering change order routing is performed to connect the second cell in the circuit layout. An updated circuit layout having the second cell is provided.