A method for distributed neural network processing, the method may include detecting, by a local neural network that belongs to a local device, and based on sensed information, an occurrence of a triggering event for executing or completing a classification or detection process; sending to a remote device, a request for executing or completing the classification or detection process by a remote device that comprises a remote neural network; wherein the remote neural network has more computational resources than the local neural network; determining by the remote device whether to accept the request; and executing or completing, by the remote device, the classification or detection process when determining to accept the request; wherein the executing or completing involves utilizing the remote neural network.

Embodiments disclosed systems and methods to broadcast a message to one or more virtual data processing (DP) accelerators. In response to receiving a broadcast instruction from an application, the broadcast instruction designating one or more virtual DP accelerators of a plurality of virtual DP accelerators to receive a broadcast message, the system encrypts the broadcast message based on a broadcast session key for a broadcast communication session. The system determines one or more public keys of one or more security key pairs each associated with one of the designated virtual DP accelerators. The system encrypts the broadcast session key based on the determined one or more public keys. The system broadcasts the encrypted broadcast message, and the one or more encrypted broadcast session keys to adjacent virtual DP accelerators for propagation.

Described are examples for monitoring performance metrics of one or more workloads in a cloud-computing environment and reallocating compute resources based on the monitoring. Reallocating compute resources can include migrating workloads among nodes or other resources in the cloud-computing environment, reallocating hardware accelerator resources, adjusting transmit power for virtual radio access network (vRAN) workloads, and/or the like.

Systems and methods are provided for offloading a task from a central processor in a radio access network (RAN) server to one or more heterogeneous accelerators. For example, a task associated with one or more operational partitions (or a service application) associated with processing data traffic in the RAN is dynamically allocated for offloading from the central processor based on workload status information. One or more accelerators are dynamically allocated for executing the task, where the accelerators may be heterogeneous and my not comprise pre-programming for executing the task. The disclosed technology further enables generating specific application programs for execution on the respective heterogeneous accelerators based on a single set of program instructions. The methods automatically generate the specific application programs by identifying common functional blocks for processing data traffic and mapping the functional blocks to the single set of program instructions to generate code native to the respective accelerators.

Systems and methods are provided for offloading a task from a central processor in a radio access network (RAN) server to one or more heterogeneous accelerators. For example, a task associated with one or more operational partitions (or a service application) associated with processing data traffic in the RAN is dynamically allocated for offloading from the central processor based on workload status information. One or more accelerators are dynamically allocated for executing the task, where the accelerators may be heterogeneous and may not comprise pre-programming for executing the task. The disclosed technology further enables generating specific application programs for execution on the respective heterogeneous accelerators based on a single set of program instructions. The methods automatically generate the specific application programs by identifying common functional blocks for processing data traffic and mapping the functional blocks to the single set of program instructions to generate code native to the respective accelerators.

A console includes a CPU and a GPU. Of the CPU and GPU, the CPU acquires an image to be processed, which is an object to be subjected to a support process that is a diagnosis support process or an imaging support process, and distributes a process to any one of the CPU, the GPU, or another GPU to execute the support process according to the content of the support process executed for the image to be processed.

Pooling computing resources based on inferences about a plurality of hardware devices. The method includes identifying inference information about the plurality of devices. The method further includes based on the inference information optimizing resource usage of the plurality of hardware devices.

A physical server with an offload card including a SoC (system-on-chip) and a FPGA (field programmable gate array) is disclosed. According to one set of embodiments, the SoC can be configured to offload one or more hypervisor functions from a CPU complex of the server that are suited for execution in software, and the FPGA can be configured to offload one or more hypervisor functions from the CPU complex that are suited for execution in hardware.

An instruction offload manager receives, by a processing device, a first request to execute a program, identifies one or more instructions of the program to be offloaded to a second processing device, where the second processing device includes a same instruction set architecture as the processing device, and provides the one or more instructions to a memory module comprising the second processing device. Responsive to detecting an indication to execute the one or more instructions, the instruction offload manager provides an indication to the second processing device to cause the second processing device to execute the one or more instructions, the one or more instructions to update a portion of a memory space associated with the memory module.

An apparatus and method for scheduling threads on local and remote processing resources. For example, one embodiment of an apparatus comprises: a local graphics processor to execute threads of an application; graphics processor virtualization circuitry and/or logic to generate a virtualized representation of a local processor; a scheduler to identify a first subset of the threads for execution on a local graphics processor and a second subset of the threads for execution on a virtualized representation of a local processor; the scheduler to schedule the first subset of threads on the local graphics processor and the second subset of the threads by transmitting the threads or a representation thereof to Cloud-based processing resources associated with the virtualized representation of the local processor; and the local graphics processor to combine first results of executing the first subset of threads on the local graphics processor with second results of executing the second subset of threads on the Cloud-based processing resources to render an image frame.