Synopsys, Inc.

Atrenta, Inc.

Vaibhav Jain

Solaiman Rahim

Mohammad Homayoun Movahed-Ezazi

Shekaripuram V Venkatesh

Siddharth Guha

Chaofan Wang

Qing Su

Alexander John Wakefield

Jitendra Kumar Gupta

Myunghoon Yoon

Rahul Jain

Shweta Bansal

A method includes generating a plurality of input vectors based on input signals to an electric circuit, selecting a subset of the plurality of input vectors, and determining a plurality of datapoints based on the selected subset of the plurality of input vectors. Each datapoint of the plurality of datapoints indicates a power consumption of the electric circuit corresponding to an input vector of the selected subset of the input vectors. The method also includes generating, by a processor, a plurality of vector sequences based on the selected subset of the plurality of input vectors. Each vector sequence of the plurality of vector sequences includes a portion of the selected subset of the plurality of input vectors arranged chronologically. The method further includes training a machine learning model based on a first subset of the plurality of vector sequences and a corresponding first subset of the plurality of datapoints.

Power estimation using input vectors and deep recurrent neural networks

Glitch source identification and ranking is provided by: identifying a plurality of glitch sources in a circuit layout; back referencing the plurality of glitch sources to corresponding lines in a Resistor Transistor Logic (RTL) file defining the plurality of glitch sources; identifying, in the circuit layout, a plurality of glitch terminuses associated with the plurality of glitch sources; determining a plurality of glitch power consumption values associated with the plurality of glitch sources based on fanouts in the circuit layout extending from the plurality of glitch sources to the plurality of glitch terminuses; ranking, by a processor, the plurality of glitch sources based on corresponding glitch power consumption values of the plurality of glitch power consumption values corresponding to individual glitch sources of the plurality of glitch sources; and reporting the corresponding lines in the RTL file associated with the ranked plurality of glitch sources.

Glitch source identification and ranking

A method includes generating a plurality of vector sequences based on input signals of an electric circuit design and encoding the plurality of vector sequences. The method also includes clustering the plurality of encoded vector sequences into a plurality of clusters and selecting a set of encoded vector sequences from the plurality of clusters. The method further includes selecting a first set of vector sequences corresponding to the selected set of encoded vector sequences, selecting a second set of vector sequences from the plurality of vector sequences not in the first set of encoded vector sequences, and training, by a processing device, a machine learning model to predict power consumption using the first and second sets of vector sequences.

Selecting a subset of training data from a data pool for a power prediction model

A system is disclosed that includes a memory and a processor configured to perform operations stored in the memory. The processor performs the operations to select a master clock for a plurality of clocks in a design logic circuit. The processor further performs the operations to align a clock edge of a clock of the plurality of clocks with a corresponding nearest clock transition of the master clock. The aligned clock edge of the clock limits a number of emulation cycles for the design logic to a fixed number of emulation cycles required for the master clock The processor further performs the operation to determine a clock period for measuring power required for the design logic circuit and estimate, at the aligned clock edge, the power required for the design logic circuit corresponding to the determined clock period, which corresponds to a clock selected from the plurality of clocks and the master clock.

System and method for power analysis for design logic circuit with irregular clock

A system and method enable strengthening of flip-Flops (FFs) in an integrated circuit (IC) for the purpose of reducing power consumption. This is achieved by using stability condition (STC) and observability don't-care (ODC) techniques. Strengthening enable is defined as ensuring that a FF later in the fan-out is enabled only when a FF earlier in the fan-out is driving a signal to that later FF. In an embodiment the fan-in of a FF is traversed and the STC or ODC is determined for the FF. Dependent on the determination a STC controller or an ODC controller is added to control the FF's enable signal. In an embodiment the power savings is checked and a controller is added only if there is a reduction in overall power consumption resulting from the addition of the controller.

Growing community of inventors

Cupertino, CA, United States of America

Vaibhav Jain