Abstract: Systems and methods in which trace data is efficiently managed are provided. An example system includes a memory, a first interface, and a processing resource communicably coupled to the first interface and to the memory. The processing resource includes a buffer, and a first controller to transmit a set of data from the buffer with associated trace information for the set of data to the memory. A second controller transmits the set of data with the associated trace information from the memory to a second interface.

Abstract: Systems and method are provided for flexibly configuring task schedulers and respectively associated data processing nodes to execute threads of tasks using a hardware thread scheduler (HTS). The data processing nodes may be hardware accelerators, channels of a direct memory access circuit and external nodes such as a processor executing software instructions. Each hardware accelerator is coupled to a respective hardware task scheduler, each channel is coupled to a respective channel task scheduler, and each external node is coupled to a proxy task scheduler. The task schedulers communicate via pending and decrement signals with a hardware scheduler crossbar. With this arrangement, the HTS couples a first subset of task schedulers in a first data processing order with the associated data processing nodes performing the tasks, and couples a second subset of task schedulers in a second data processing order with the associated data processing nodes performing the tasks.

Abstract: A system-on-chip (SoC) in which trace data is managed includes a first memory device, a first interface to couple the first memory to a second memory external to the system-on-chip, and a first processing resource coupled to the first interface and the first memory device. The first processing resource includes a data buffer and a first direct access memory (DMA) controller. The first DMA controller transmits data from the data buffer to the first interface over a first channel, and transmits the data from the data buffer with associated trace information for the data to the first memory device over a second channel.

Abstract: Techniques for executing machine learning (ML) models including receiving an indication to run an ML model on a processing core; receiving a static memory allocation for running the ML model on the processing core; determining that a layer of the ML model uses more memory than the static memory allocated; transmitting, to a shared memory, a memory request for blocks of the shared memory; receiving an allocation of the requested blocks; running the layer of the ML model using the static memory and the range of memory addresses; and outputting results of running the layer of the ML model.

Abstract: Devices, systems and techniques for implementing freedom from interference (FFI) access rules. In an example, a device includes a set of primary components, a set of secondary components, and an interconnected coupled between the two sets of components. Each primary component of the set of primary components has an access identifier, among multiple access attributes, and an access attribute, among multiple access modes. Each secondary component of the set of secondary components is protected by a firewall. Each firewall is configured to specify, for each specific combination of an access identifier and access attribute, whether access to the associated secondary component is permitted and what type of access is permitted.

Abstract: A data processing device is provided that includes a plurality of hardware data processing nodes, wherein each hardware data processing node performs a task, and a hardware thread scheduler including a plurality of hardware task schedulers configured to control execution of a respective task on a respective hardware data processing node of the plurality of hardware data processing nodes, and a proxy hardware task scheduler coupled to a data processing node external to the data processing device, wherein the proxy hardware task scheduler is configured to control execution of a task by the external data processing device, wherein the hardware thread scheduler is configurable to execute a thread of tasks, the tasks including the task controlled by the proxy hardware task scheduler and a first task controlled by a first hardware task scheduler of the plurality of hardware task schedulers.

Abstract: A method of enabling memory access freedom from interference (FFI) rules, comprising: determining a first safety privilege access ID (PrivID) for a first component of a system (e.g., based on Automotive Safety Integrity Level (ASIL) attributes of tasks executed by the first component); determining a first access attribute for a first software task executing on the first component; receiving, at a first firewall component of the system, a request from the first software task to access a first memory region of a second component of the system, wherein the request specifies the first PrivID and the first access attribute; and determining, by the first firewall component, whether to permit the first software task to access the first memory region based on the first PrivID, the first access attribute, and the first memory region.

Abstract: Techniques for executing machine learning (ML) models including receiving an indication to run an ML model on a processing core; receiving a static memory allocation for running the ML model on the processing core; determining that a layer of the ML model uses more memory than the static memory allocated; transmitting, to a shared memory, a memory request for blocks of the shared memory; receiving an allocation of the requested blocks; running the layer of the ML model using the static memory and the range of memory addresses; and outputting results of running the layer of the ML model.

Abstract: Systems, methods and devices that improve fault detection capability of an imaging/vision hardware accelerator are provided. One such system includes a hardware accelerator, a signature generator, a signature processor, and a controller. These components cooperate to generate first and second output frames based on first and second reference frames, respectively; generate a third output frame based on a use-case frame; generate first and second image signatures based on the first and second output frames, respectively; compare the first image signature to a stored first reference image signature and output a first result; and compare the second image signature to a stored second reference image signature and output a second result. The controller determines, based on the results, whether the hardware accelerator has a fault at either a first time or a second time. When no fault is detected at either time, the controller analyzes the use-case frame for designation as an adaptive reference frame.

Abstract: A system-on-chip (SoC) in which trace data is managed includes a first memory device, a first interface to couple the first memory to a second memory external to the system-on-chip, and a first processing resource coupled to the first interface and the first memory device. The first processing resource includes a data buffer and a first direct access memory (DMA) controller. The first DMA controller transmits data from the data buffer to the first interface over a first channel, and transmits the data from the data buffer with associated trace information for the data to the first memory device over a second channel.

Abstract: This disclosure relates to various implementations an embedded computing system. The embedded computing system comprises a hardware accelerator (HWA) thread user and a second HWA thread user that creates and sends out message requests. The HWA thread user and the second HWA thread user is communication with a microcontroller (MCU) subsystem. The embedded computing system also comprises a first inter-processor communication (IPC) interface between the HWA thread user and the MCU subsystem and a second IPC interface between the second HWA thread user and the MCU subsystem, where the first IPC interface is isolated from the second IPC interface. The MCU subsystem is also in communication with a first domain specific HWA and a second domain specific HWA.

Abstract: An electronic device may be configured to detect a fault in imaging and vision hardware accelerators. The electronic device may include a controller configured to select a first golden input frame of multiple golden input frames to perform a first self-test, and retrieve a first reference image signature corresponding to the first golden input frame. The electronic device may include a hardware accelerator module configured to obtain the first golden input frame, and generate a first output frame based on the first golden input frame. The electronic device may include a signature generator configured to generate a first generated image signature based on the first output frame. The electronic device may include a signature comparison module configured to compare the first generated image signature to the first reference image signature in order to determine whether the hardware accelerator module includes a fault at a first time.

Abstract: An embedded multiprocessor system is provided that includes a multiprocessor system on a chip (SOC), a memory coupled to the multiprocessor SOC, the memory storing application software partitioned into an initial boot stage and at least one additional boot stage, and a secondary boot loader configured to boot load the initial boot stage on at least one processor of the multiprocessor SOC, wherein the initial boot stage begins executing and flow of data from the initial boot stage to the at least one additional boot stage is disabled, wherein the application software is configured to boot load a second boot stage of the at least one additional boot stage on at least one other processor of the multiprocessor SOC and to enable flow of data between the initial boot stage and the second boot stage.

Abstract: A method of enabling memory access freedom from interference (FFI) rules, comprising: determining a first safety privilege access ID (PrivID) for a first component of a system (e.g., based on Automotive Safety Integrity Level (ASIL) attributes of tasks executed by the first component); determining a first access attribute for a first software task executing on the first component; receiving, at a first firewall component of the system, a request from the first software task to access a first memory region of a second component of the system, wherein the request specifies the first PrivID and the first access attribute; and determining, by the first firewall component, whether to permit the first software task to access the first memory region based on the first PrivID, the first access attribute, and the first memory region.

Abstract: This disclosure relates to various implementations an embedded computing system. The embedded computing system comprises a hardware accelerator (HWA) thread user and a second HWA thread user that creates and sends out message requests. The HWA thread user and the second HWA thread user is communication with a microcontroller (MCU) subsystem. The embedded computing system also comprises a first inter-processor communication (IPC) interface between the HWA thread user and the MCU subsystem and a second IPC interface between the second HWA thread user and the MCU subsystem, where the first IPC interface is isolated from the second IPC interface. The MCU subsystem is also in communication with a first domain specific HWA and a second domain specific HWA.

Abstract: Techniques for executing machine learning (ML) models including receiving an indication to run an ML model on a processing core; receiving a static memory allocation for running the ML model on the processing core; determining that a layer of the ML model uses more memory than the static memory allocated; transmitting, to a shared memory, a memory request for blocks of the shared memory; receiving an allocation of the requested blocks; running the layer of the ML model using the static memory and the range of memory addresses; and outputting results of running the layer of the ML model.

Abstract: Techniques for executing machine learning (ML) models including receiving an indication to run a ML model, receiving synchronization information for organizing the running of the ML model with other ML models, determining, based on the synchronization information, to delay running the ML model, delaying the running of the ML model, determining, based on the synchronization information, a time to run the ML model; and running the ML model at the time.

Abstract: Multi-application instance deployment in a containerized environment includes containerizing an instance of an application manager in a short-lived container and deploying into the container, both a bundle of different event handlers associated with one application instance of one application, and also a bundle of additional event handlers associated with a different application instance of a different application. Thereafter, the application manager manages inter-application communications between the one application instance and the different application instance, and routes events for both the one application instance and the different application instance in an event router included as part of the application manager. Hence, the application manager may be viewed as providing a virtualization layer on top of the short-lived container.

Abstract: Multi-application instance deployment in a containerized environment includes containerizing an instance of an application manager in a short-lived container and deploying into the container, both a bundle of different event handlers associated with one application instance of one application, and also a bundle of additional event handlers associated with a different application instance of a different application. Thereafter, the application manager manages inter-application communications between the one application instance and the different application instance, and routes events for both the one application instance and the different application instance in an event router included as part of the application manager. Hence, the application manager may be viewed as providing a virtualization layer on top of the short-lived container.

Abstract: A data processing system adapted for securely debugging multiple different application instances in a single short-lived container includes a host computing platform having one or more computers, each with memory and at least one processor. The system also includes a container manager executing in the host computing platform, such that during execution, the container manager manages a multiplicity of different containers of a containerized environment. Finally, the system includes a debug server containerized within one of the containers. The debug server authenticates with the container manager for the one of the containers and establishes a communicative link over a computer communications network with a debug client disposed externally to the containerized environment, so that the debug server then proxies debug directives received from the debug client to selected ones of different application instances each executing within the one of the containers.