Parul Singh

Currently, the energy consumption metrics are only available at node levels. There is no way to obtain container-level energy consumption. Autoscalers and schedulers really need pod-level metrics data in order to obtain energy savings from resizing or migrating containers.

The presentation introduces Kubernetes-based Efficient Power Level Exporter (Kepler) and its integration with Kubernetes. By leveraging eBPF programs, Kepler probes per container energy consumption related system counters and exports them as metrics. These metrics help end users observe their containers’ energy consumption and allow cluster admins to make intelligent decisions on achieving energy conservation goals. The presentation shows that Kepler can be easily integrated into Prometheus and render time series metrics into Grafana.

At last, we will demonstrate sustainable management of clusters by leveraging Cloud-native patterns, Observability and Kubernetes features like node selector, node labels, node name, affinity and anti-affinity to achieve carbon intensity aware placement of workloads in a Kubernetes cluster.

Unlike GPU cards, quantum acceleration is unlikely to be available as a personal computer in the near future. Right now all the known quantum computers are owned by major players. The lack of availability of quantum computers makes it beneficial to centralize the power of quantum computers, using a SaaS model to democratize access to them, therefore making the cloud a suitable home for quantum computing.

The first part of the session introduces an open-source co-processor model where classical computers can offload specialized tasks that are better suited to quantum computers thus lowering the onramp to incorporating quantum computing into applications today.

The next part of the sessions demonstrate how to build a co-processor model on the cloud using two community operators that provide quantum acceleration by leveraging Qiskit, an open-source SDK for developing quantum circuits, classical components powered by Red Hat OpenShift and IBM Quantum Experience as the quantum backend

The session concludes with a small demonstration of how to run a quantum circuit on the cloud using the co-processor model.