Abstract: Scheduling kernels on a system with heterogeneous compute circuits includes receiving, by a hardware processor, a plurality of kernels and a graph including a plurality of nodes corresponding to the plurality of kernels. The graph defines a control flow and a data flow for the plurality of kernels. The kernels are implemented within different ones of a plurality of compute circuits coupled to the hardware processor. A set of buffers for performing a job for the graph are allocated based, at least in part, on the data flow specified by the graph. Different ones of the kernels as implemented in the compute circuits are invoked based on the control flow defined by the graph.

Abstract: An example operation includes one or more of monitoring, via a vehicle, a behavior of an occupant of the vehicle, responsive to the behavior being above a threshold, generating via an application of the vehicle, a first suggested action intended for the occupant based on the behavior and an amount the behavior is above the threshold, monitoring, by the vehicle, whether the first suggested action is being performed by the occupant, determining an alternate action is being performed by the occupant, generating a second suggested action based on the alternate action and the first suggested action, and providing a value to an occupant device associated with the occupant responsive to the second action being detected by the transport.

Abstract: An example operation includes one or more of receiving a first response, from an application associated with a vehicle, including one or more factual statements determined by the application based on a set of data, retrieving vehicle data from the vehicle related to the factual statements, parsing the first response into one or more portions of the one or more factual statements, comparing the one or more portions to other portions of other factual statements included in a first knowledgebase containing other factual statements, wherein the other factual statements are based on the vehicle data, and receiving a second response, from the application, including one or more amended factual statements based on the comparing.

Abstract: An example operation includes one or more of identifying, via a vehicle application of a vehicle, one or more topics of interest associated with a vehicle occupant based one or more vehicle occupant behaviors detected by the vehicle, applying, via the vehicle application, one or more enhanced services to a device associated with vehicle occupant based on the one or more topics of interest and an occupant profile, and modifying, via the vehicle application, the one or more enhanced services based on the device location and changes to the one or more vehicle occupant behaviors.

Abstract: An example operation includes one or more of determining, by a first node, that an event has occurred in a geographic area, predicting, by the first node, a severity of the event, a duration of the event, and at least one vehicle associated with the event, sending, by the first node, the prediction to a second node and a time the at least one vehicle will be proximate the second node, and sending by the second node, notifications to other vehicles proximate the second node to maneuver based on the prediction, prior to the time.

Abstract: An example operation includes one or more of determining, by a vehicle, that an occupant assist application is operating in the vehicle to assist a vehicle occupant during vehicle operation, determining, by the vehicle, that an unsafe driving condition is likely to occur via a monitoring application, prior to a time that the unsafe driving condition is expected to occur, ceasing, by the vehicle, the occupant assist application, and executing, by the vehicle, a driving assist application to assist with the vehicle operation during the unsafe driving condition.

Abstract: An example operation includes one or more of accessing, by an application providing assistance to a vehicle, sensor data associated with an environment inside and outside of a vehicle and profile data associated with a vehicle occupant, determining, by the application, an initial condition of the vehicle occupant based on the sensor data and the profile data, responsive to the initial condition being above a health condition threshold, accessing, by the application, health data associated with the vehicle occupant from a mobile device, determining, by the application, an updated condition of the vehicle occupant based on the health data, creating, by the application, an alert to notify the occupant based on the updated condition and one or more current driving conditions of the vehicle identified by the sensor data, and performing, by the vehicle, one or more vehicle actions based on the alert and the one or more current driving conditions.

Abstract: An example operation includes one or more of receiving information at a vehicle in proximity to a first node from the first node, sending information from the vehicle to the first node, analyzing the sent information by the first node, determining by the first node that the vehicle will be in proximity to an adjacent node to the first node, after the vehicle is no longer in proximity to the first node, receiving the analyzed information from the first node at the adjacent node, constructing information related to the received analyzed information at the adjacent node, and sending the constructed information to the vehicle from the adjacent node.

Abstract: An example operation includes one or more of determining data to be provided to a vehicle, determining data to be retrieved from the vehicle, determining a route for the vehicle based on an amount of time the data is provided to the vehicle and the data is retrieved from the vehicle, a speed of the vehicle, and a location of at least one computing node that is configured to provide and retrieve the data.

Abstract: An example operation includes one or more of determining by a primary computing node that an en route vehicle will be delayed for a time-sensitive event, coordinating by the primary computing node with a secondary computing node at an event location and the en route vehicle to provide a real-time event experience to at least one device in the en route vehicle, managing by the primary computing node the real-time event experience between the secondary computing node and the at least one device in the en route vehicle, transferring by the primary computing node the real-time event experience to the secondary computing node when a device of the at least one device is in proximity to the secondary computing node, and terminating by the secondary computing node the real-time event experience when the at least one device reaches a specific location within the event location.

Abstract: An example operation includes one or more of establishing a communication between a first vehicle and a computing node, determining data to be transmitted from the computing node to the first vehicle responsive to a portion of the data being stored on a second vehicle, determining the second vehicle will be in proximity to the first vehicle, and transmitting the portion of the data from the second vehicle to the first vehicle when the vehicles are in proximity and a remaining portion of the data from the computing node to the first vehicle.

Abstract: A design for a programmable integrated circuit (IC) is synthesized and includes an inference engine and a data transformer. A portion of the design including the data transformer is designated as a dynamic function exchange (DFX) module. The inference engine is excluded from the DFX module. The design is implemented, by placing and routing, such that the DFX module is confined to a defined physical area of the programmable integrated circuit. An abstract shell for the design specifying boundary connections of the DFX module as placed and routed is generated. A locked version of the design as placed and routed with the DFX module removed is generated. The method includes implementing a different data transformer as a further DFX module for the design using the abstract shell.

Abstract: Processing of a neural network specification includes gathering first layers of a neural network graph into groups of layers based on profiled compute times of the layers and equalized compute times between the groups. Each group is a subgraph of one or more of the layers of the neural network. The neural network graph is compiled into instructions for pipelined execution of the neural network graph by compute circuits. The compiling includes designating, for each first subgraph of the subgraphs having output activations that are input activations of a second subgraph of the subgraphs, operations of the first subgraph to be performed by a first compute circuit and operations of the second subgraph to be performed by a second compute circuit. The compute circuits are configured to execute the instructions.

Abstract: Provided herein are system, apparatus, device, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for generating an output indicating differences in the data stored in disparate data storage devices and/or for reconciling data stored in disparate data storage devices. In an embodiment, a server loads a first subset of a first set of data corresponding to one or more first columns and a second subset of a second set of data corresponding to one or more second columns into a data repository. The server identifies one or more differences between the first subset of data and the second subset of data in the data repository, and causes display of the one or more differences. The server may generate an output including the first and second sets of data, and a visual indicator indicating each of the one or more differences and causes display of the output.

Abstract: Scheduling work of a machine learning application includes instantiating kernel objects by a computer processor in response to input of kernel definitions. Each kernel object is of a kernel type indicating a compute circuit. The computer processor generates a graph in a memory. Each node represents a task and specifies an assignment of the task to one or more of the kernel objects, and each edge represents a data dependency. Task queues are created in the memory and assigned to queue tasks represented by the nodes. Kernel objects are assigned to the task queues, and the tasks are enqueued by threads executing the kernel objects, based on assignments of the kernel objects to the task queues and assignments of the tasks to the kernel objects. Tasks are dequeued by the threads, and the compute circuits are activated to initiate processing of the dequeued tasks.

Abstract: Strategies are stored in a memory arrangement, and each strategy includes a set of parameter settings for a design tool. The design tool identifies a set of features of an input circuit design and applies classification models to the input circuit design. Each classification model indicates one the strategies, and application of each classification model indicates a likelihood that use of the strategy would improve a metric of the input circuit design based on the set of features of the input circuit design. One strategy of the plurality of strategies is selected based on the likelihood that use of the one strategy would improve the metric of the input circuit design, and the design tool is configured with the set of parameter settings of the one strategy. The design tool then processes the input circuit design into implementation data that is suitable for making an integrated circuit (IC).

Abstract: Disclosed approaches for guiding actions in processing a circuit design include a design tool identifying first violations of design checks and determining severity levels of the first violations. The design tool determines for each violation, suggested actions associated with the violation and presents on a display, first data indicative of the suggested actions in order of the severity levels of the first violations. The first data include selectable objects, and each selectable object has an associated executable procedure. The design tool can execute the procedure associated with one of the selectable objects in response to selection and modify the circuit design in response to execution of the procedure.

Abstract: Core processing and parameterization may include detecting, using a processor, a super parameter within a core, and, responsive to the detecting, automatically creating, using the processor, a data structure within a memory element having a hierarchy and having a parameter of the core. The data structure may be set as a value of the super parameter of the core.

Abstract: Implementing a circuit design may include, responsive to a user input selecting a design, executing an implementation script of the design using the processor. Executing the implementation script may generate instructions for generating a circuit design from the design. Responsive to the instructions and using the processor, cores of the design may be automatically instantiated and connected.

Abstract: A method of processing a circuit design in a circuit design tool includes: identifying selection of a parameterized core to be instantiated in a description of the circuit design managed by the circuit design tool and configured for implementation in target hardware; processing a configuration file for the parameterized core to select a set of parameter values from a plurality of sets of parameter values dynamically based at least in part on the target hardware; creating an instance of the parameterized core in the circuit design having the selected set of parameter values; and implementing the circuit design for the target hardware.