Abstract: Technologies for signaling compression inside a partially unrolled decision feedback equalizer (DFE) are described. The signaling compression associated with partially unrolled DFE results in multiplexers selecting a 1-bit output value from one of two 1-bit input values, which are decoding the actual multi-bit candidate levels and transforming the selected 1-bit output value to a multi-bit sliced value by adding to it a pointer value of a pulse-amplitude modulation (PAM) level. The signaling compression reduces the power and area of an N-tap DFE, where N is a positive integer.

Abstract: Embodiments include herein are directed towards various circuit topologies. A self-correcting latch circuit may include a plurality of memory loops, a plurality of clock inputs, a plurality of data inputs, and a plurality of outputs. Each of the plurality of memory loops may be configured to store data in parallel.

Abstract: The present disclosure relates to a system and method for clock phase recovery. Embodiments may include sampling data using an in-phase clock and a quadrate phase clock. Embodiments may further include analyzing sampled data from the in-phase clock and the quadrate phase clock. Embodiments may also include determining a convergence point based upon, at least in part, the analyzed sampled data, wherein the convergence point corresponds to a point where a number of early sampled outcomes is approximately equal to a number of late sampled outcomes. Embodiments may also include dynamically updating an accumulator threshold based upon the convergence point.

Abstract: An approach is disclosed herein a sequence generation ecosystem using machine learning. The approach disclosed herein is a new approach to sequence generation in the context of validation that relies on machine learning to explore and identify ways to achieve different states. In particular, the approach divides the valid operations into different respective actions and action sequences. These actions are selected by machine learning models as they are being trained using online inference reinforcement learning. This online inference also is likely to result in the discovery of new states. Each state that has been identified is then used as a target to train a respective machine learning model. As part of this process a representation of all the states and actions or sequences of actions executed to reach those states is created. This representation, the respective machine learning models, or a combination thereof can then be used to generate different test sequences.

Abstract: Systems and methods of collecting performance metrics of an emulated design are disclosed. A method includes receiving, by a processor in the emulation system from a host system, configuration data including one or more user defined parameters, connecting, by the processor, a performance monitor to a port between communicatively connected components in the emulation system, initiating, by the processor, an emulation of the DUT, receiving, by the processor, emulation data from the emulation system, calculating, by the processor, performance data based on the configuration data, filtering, by the processor, the emulation data based on the performance data, and outputting, by the processor, the filtered emulation data to the host system.

Abstract: The present disclosure relates to electronic circuit design, and more specifically, to training a neural network to serve as the reward function for optimization-based approaches to PCB design automation. Embodiments may include generating, using a processor, one or more placed designs using a genetic optimization methodology including a reward function and adjusting the one or more placed designs and the reward function during the generating. Embodiments may further include routing the one or more placed designs using an auto-router to assign a routability score label and training a neural network, using the one or more placed designs and the routability score label, to extract one or more intermediate features from the one or more placed designs. Embodiments may also include predicting a routability of the PCB design based upon, at least in part, the one or more intermediate features.

Abstract: Embodiments included herein are directed towards a method for visualizing an electronic circuit design. Embodiments may include causing a display of a portion of an electronic design at a graphical user interface and receiving, at the graphical user interface, a selection of an object to be moved, wherein the object is displayed in a first color. In response to a user input, embodiments may include moving the object at the graphical user interface nearer a target location, displaying at least one target type in a second color and snapping the object to the target location.

Abstract: A technical solution is directed to a clock recovery apparatus for multi-level signaling on a single-lane communication interface. The apparatus can use bin-map logic to successfully recover a common clock per symbol received on the multi-level signal interface. The multi-level signal can be PAM4 signaling where two bits are encoded to represent four levels. The clock recovery apparatus can detect signal level through individual edge detectors for each of the two bits and can handle jitter up to half-clock period.

Abstract: Aspects of the present disclosure address systems and methods for routing an integrated circuit design based on a maximum turn constraint. Data describing an integrated circuit is accessed. The integrated circuit design comprises a net specifying a connection between a first pin and a second pin. A maximum turn constraint is accessed. The maximum turn constraint specifies a maximum number of turns for connection paths generated in routing the integrated circuit design. The net is routed based on the maximum turn constraint. The routing of the net results in a routed net comprising a connection path between the first pin and the second pin that includes a number of turns that satisfy the maximum turn constraint. A layout instance for the integrated circuit design is generated based in part on the routed net.

Abstract: Methods and systems are provided for transmitting data using thin-oxide devices. The methods and system generate a first bias voltage and a second bias voltage based on a power supply voltage of the second voltage domain, the first bias voltage value representing a high-level voltage signal of the first voltage domain, and the second bias voltage representing a low-level voltage signal of the second voltage domain and its value corresponds to a difference between the second voltage domain and the first voltage domain. The methods and systems generate an output of the thin-oxide device interface using first and second thin-oxide devices, the output of the thin-oxide device interface having a range corresponding to the second voltage domain.

Abstract: Various embodiments described herein provide for a read data strobe (RDQS) path having variation compensation (e.g., voltage and temperature compensation), delay lines, or both, where the RDQS path can be included by a physical (PHY) interface for a memory device, such as a Double Data Rate (DDR) Dynamic Random-Access Memory (DRAM) memory device.

Abstract: Embodiments included herein are directed towards sampling circuits and methods of using the same. Embodiments may include a data sense amplifier circuit and a reference sense amplifier circuit directly connected with the data sense amplifier circuit. Embodiments may further include a latch circuit configured to receive a first input from the data sense amplifier circuit and a second input from the reference sense amplifier circuit. The latch circuit may be further configured to generate a least significant bit output based upon, at least in part, the first input and the second input.

Abstract: An approach for verifying a cross-connection of lanes in a multi-lane environment using a single testbench-is provided. The approach may include providing a physical receiver lane index associated with a local device and providing a physical transmitter lane index associated with a peer device. The approach may further include randomizing a number of connected receiver lanes associated with the local device and a number of connected receiver lanes associated with the peer device. The approach may further include randomizing the physical receiver lane index and the physical transmitter lane index to generate a unique cross connection including randomized values. The approach may also include assigning the randomized values to one or more randomized cross connection defines. The approach may further include passing the cross connection defines to the single testbench and verifying each possible cross connection using a protocol specific mechanism.

Abstract: A method can include obtaining, at a physical communication layer integrated with a communication interface, a data packet, detecting, by a detection circuit integrated with the physical communication layer, a portion of data in the data packet corresponding to a marker identifying the data packet, linking, by the physical communication layer based on the marker, a timestamp with the data packet, and transmitting, by the physical communication layer, the data packet linked with the timestamp.

Abstract: A system for generating a single design data file may include a processor and a memory. The processor may obtain design data including a plurality of design units. The processor may determine a first order of the plurality of design units. The processor may translate each of the plurality of design units into a corresponding file fragment by executing multiple threads of a first process. The processor may aggregate each of the plurality of file fragments into the single design data file in the first order by executing a second process in parallel to the first process.

Abstract: The present disclosure describes a circuit that may include a first amplifier portion configured to receive a first input signal corresponding to a first clock signal and a second input signal corresponding to a second clock signal. The circuit may include a first amplifier of the first amplifier portion. The first amplifier may be configured to receive a first amplifier input signal and a second amplifier input signal. The circuit may include a second amplifier portion configured to receive a first output signal from the first amplifier portion. In a first mode, the first amplifier input signal may be based upon the second input signal and the second amplifier input signal may be based upon the first input signal. In a second mode, the first amplifier input signal may be based upon the first input signal and the second amplifier input signal may be based upon the second input signal.

Abstract: The present disclosure relates to a system and method for duty cycle correction is provided. The method may include receiving a signal at a duty cycle adjuster and performing serializer clock duty cycle correction at the duty cycle adjuster. The method may further include performing true clock duty cycle correction at a transmitter duty cycle adjuster and performing complementary duty cycle distortion correction at the transmitter duty cycle adjuster.

Abstract: A shared memory is provided between simulation processors and emulation processors within an emulation chip. The shared memory is configured to enable the simulation processors and the emulation processors to exchange simulation data and emulation data respectively with each other during simulation and emulation operations. The simulation processors and the emulation processors may update their respective simulation and emulation operations in response to the simulation data and the emulation data exchanged via the shared memory.

Abstract: Embodiments are directed towards a method for creating a relational memory designed for one or more key parameters in at least one memory part configurations library. The method may include identifying one or more high-level parameters (HLPs) within the at least one memory part configurations library, assigning each non-HLP parameter an HLP key, using the assigned HLP keys as a frame of reference to cross-correlate each non-HLP parameter with every other non-HLP parameter in the at least one memory part configurations library. The method may also include extracting a complete relational memory attribute set from the cross-correlated parameters in the at least one memory part configurations library, generating memory configuration metadata equivalent to the at least one memory part configurations library from the complete relational memory attribute set, and providing memory part automation from the generated memory configuration metadata.

Abstract: A memory circuit may include both an array circuit and multiple register circuits, where the power to retrieve data from one of the register circuits may be less than the power to retrieve data from the array circuit. The array circuit may store multiple data words, and the multiple register circuits may be configured to store a subset of the multiple data words. During a first cycle, a read command and an address may be received. In response to a determination that the address corresponds to a given data word included in the subset of the multiple data words, the array circuit may be de-activated in a second cycle subsequent to the first cycle and an output signal may be generated by selecting data retrieved from a particular register circuit of the multiple register circuits in which the given data word may be stored.