Validated Patterns

About OpenShift cluster sizing for the Intel AMX accelerated Medical Diagnosis pattern

The minimum requirements for an OpenShift Container Platform cluster depend on your installation platform, for example:

To understand cluster sizing requirements for the Intel AMX accelerated Medical Diagnosis pattern, consider the following components that the Intel AMX accelerated Medical Diagnosis pattern deploys on the datacenter or the hub OpenShift cluster:

NameKindNamespaceDescription

Medical Diagnosis Hub

Application

medical-diagnosis-hub

Hub GitOps management

Red Hat OpenShift GitOps

Operator

openshift-operators

OpenShift GitOps

Red Hat OpenShift Data Foundation

Operator

openshift-storage

Cloud Native storage solution

Red Hat AMQ Streams

Operator

openshift-operators

AMQ Streams provides Apache Kafka access

Red Hat OpenShift Serverless

Operator

- knative-serving (knative-eventing)

Provides access to Knative Serving and Eventing functions

Node Feature Discovery Operator

Operator

openshift-nfd

Manages the detection and labeling of hardware features and configuration (for example Intel AMX)

The Intel AMX accelerated Medical Diagnosis pattern also includes the Red Hat Advanced Cluster Management (RHACM) supporting operator that is installed by OpenShift GitOps using Argo CD.

For information about requirements for additional platforms, see OpenShift Container Platform documentation.

About Intel AMX accelerated Medical Diagnosis pattern OpenShift cluster size

The OpenShift cluster is a standard deployment of 3 control plane nodes and 3 or more worker nodes.

The recommended hardware setup:

Node typeNumber of nodesCPUMemoryStorage

Control Planes

3

2x 5th Generation Intel Xeon Gold 6526Y (16 cores at 2.8 GHz base with Intel AMX) or better

128 GB (8 x 16 GB DDR5 4800) or more

NVME SSD 3TB or more

Workers

3

2x 5th Generation Intel Xeon Gold 6538Y+ (32 cores at 2.2 GHz base with Intel AMX) or better

256 GB (16 x 16 GB) or 512 GB (16 x 32GB) DDR5-4800

NVME SSD 3TB or more

You might want to add resources when more developers are working on building their applications.

The pattern was tested in the on-premises environment with following hardware configuration (per cluster):

Node typeNumber of nodesCPUMemoryStorage

Control Planes + Workers

3 + 3

2x 5th Generation Intel Xeon Platinum 8568Y+ (48 cores at 2.3 GHz base with Intel AMX)

512 GB (16x32GB DDR5 5600)

4x 3.84TB U.2 NVMe PCIe Gen4