Find the tools you need to drive your R&D and innovation projects forward.

Mahuika HPC Cluster (Milan nodes, Large-memory nodes, GPUs)

In 2022, the Mahuika HPC cluster was extended to allow a wider range of research communities to adopt HPC approaches and build digital skills within their research teams. With CPU capacity based on the AMD Milan architecture, its NVIDIA HGX 80GB A100 GPU cards support more analysis at scale, and expanded high-memory capabilities allow rapid simultaneous processing for faster results and insights.

Technical components:
- 64 dual socket HPE Apollo 2000 XL225n nodes (AMD EPYC Milan 7713, 64 core / 128 threads, 2.0GHz base clock, 3.675GHz max boost clock, 256MB L3 cache, 225W TDP). Of these, 56 have 512GB RAM and the remaining 8 have 1TB RAM. All have 1.92TB NVMe for swap and/or local scratch/temp, connected via HDR100 InfiniBand.
- Two Quantum 200Gb HDR InfiniBand managed switches
- 4 HPE Apollo 6500 XL645d 4-way NVLink 80GB A100 HGX nodes with single socket AMD Milan 7713, 512GB RAM, 2 6.4TB NVMe drives, HDR200 InfiniBand

Flexible High-Performance Cloud

Our Flexible High Performance Cloud and interactive cloud-native environments offer: 
- Virtual machines optimised for high-performance computational needs 
- Tailored operating systems, either ready-to-use or customised images you create and can contribute to a pool of community-developed images  
- Cloud native services on open-source container platform Kubernetes 
- Partnership-led approaches to enabling data sovereignty 
- Tailored institutional eResearch platforms (private clouds) 
- Opportunities for shared investment and benefits at national scale, including dedicated hardware tenancies with deep local integration  

Underpinning this platform is a collaborative culture and values, supporting national research communities and missions.

Mahuika Extension (2022)

In late 2022, the Mahuika HPC cluster was extended to allow a wider range of research communities to adopt HPC approaches and build digital skills within their research teams.

Designed with a reduced carbon footprint in mind, the extension included:

• Upgraded CPU nodes, based on AMD EPYC Milan architecture, to keep pace with ongoing growth in data, complexity of models, and a spread of computational maturity across research communities.
• NVIDIA A100 Graphics Processing Unit (GPU) cards, paired with specialised software and tools for machine learning, to support more analysis at scale.
• Specialised high-memory capabilities, to allow rapid simultaneous processing for faster results and insights.