Software Engineering

High Performance Computing Software Engineering

Using modern clustering techniques, the OCF software engineering team turns a rack full of standalone servers into a ‘Supercomputer’. The OCF software engineering team has experience with all of the major HPC clustering management toolkits (including our own Software Stack based on XCAT and other open source tools), schedulers, compilers, high performance fabrics and the latest machine learning software stacks. Enabling our team to deliver world Top 500 supercomputers.

By following best practices and backing our clusters up with support and optional managed services OCF builds scalable, supportable, solutions that deliver maximum return on investment to researchers and businesses. 

Cluster Management

• XCAT
• Bright Computing – Bright Cluster Manager 
• Lenovo LiCO
• Linux OS and Application Installation

Monitoring

• ELK
• InfluxDB
• Log aggregation - syslog/logstash/beats
• Prometheus
• Grafana

HPC Schedulers

• SLURM (Community/SchedMD) 
• Adaptive Computing MOAB 
• GridEngine (Community/Univa Grid Engine) 
• Torque/Maui 
• IBM Spectrum LSF 

Automation & Configuration Management

• Ansible
• Saltstack
• Terraform

Artificial Intelligence (AI) & Machine Learning (ML)

• AI installation & configuration for machine learning & deep learning workloads 
• Caffe
• CUDA
• OpenCL
• TensorFlow
• Theano
• Torch

Containers

• Docker
• Kubernetes
• Podman
• Red Hat OpenShift and OKD
• Singularity

Virtualisation

• LXC/LXD
• oVirt
• Proxmox
• Red Hat Virtualization (RHEV)
• VMWare

Engineering Simulation Applications

• Installation and configuration of systems to support engineering simulation applications including ANSYS. 

Request a call-back from one of our experts to discuss how OCF can help.