Hewlett Packard Enterprise Development LP

Mohan Parthasarathy

Srinivasan Varadarajan Sahasranamam

Soumitra Chatterjee

Jitendra Onkar Kolhe

Renganathan Meenakshisundaram

Pawan Kumar

Lavanya Munivenkatappa

Vinay Venugopal

Matthew James Muggeridge

Rupa Ramakrishna

One aspect of the instant application can provide a system and method for replacing a faulty or failing memory device during runtime. During operation, a host device of a plurality of coupled memory devices can detect an error-containing memory device and select, from a pool of standby memory devices, a replacement memory device. The host device can migrate data from the error-containing memory device to the replacement memory device during runtime of applications executing on the host device, replicate host physical address (HPA) address-mapping from the error-containing memory device to the replacement memory device, and replace the error-containing memory device with the replacement memory device.

Adaptive replacement of CXL memory device

Example techniques for causing execution of neural networks are described. A neural network includes a first part and a second part. A determination is made that a first physical resource in a first computing device is to execute the first part and that a second physical resource in a second computing device is to execute the second part. The determination is based on a latency in communication between the first physical resource and the second physical resource. The first computing device and the second computing device are part of a cluster.

Distributed execution of neural networks

Examples described herein relate to a management node and a method for managing deployment of a workload. The management node may obtain values of resource labels related to platform characteristics of a plurality of worker nodes. Further, the management node may determine values of one or more custom resource labels for each of the plurality of worker nodes, wherein a value of each custom resource label of the one or more custom resource labels is determined based on values of a respective set of resource labels of the resource labels. Furthermore, the management node may receive a workload deployment request including a workload description of a workload. Moreover, the management node may deploy the workload on a worker node of the plurality of worker nodes based on the workload description and the values of the one or more custom resource labels.

Managing deployment of workloads

In some examples, a system includes a plurality of electronic devices each comprising a respective management processor and a baseboard management controller (BMC). A management processor of a cluster of management processors is a primary management processor to act as a management controller for the plurality of electronic devices. The management controller interacts with the BMC in a respective electronic device to perform management of the respective electronic device. The cluster of management processors performs failover responsive to a fault of the primary management processor to select another management processor of the cluster of the management processors as the management controller.

Growing community of inventors

Karnataka, India

Mohan Parthasarathy