NHR application rules – NHR@FAU

Since January 2021, NHR@FAU is one of now nine centers of the NHR Alliance.

There is a joint portal of all NHR centers for compute time applications (JARDS).

You’ll find all up-to-date information on the application process for NHR@FAU below.

Contacting NHR@FAU

You can reach NHR@FAU by email to hpc-support@fau.de. Availability by phone cannot be guaranteed as many of us are still partially working from at home.

Individual consulting using Zoom, BigBlueButton, or DFN-Conf can be arranged on short notice. Just send an email to hpc-support@fau.de.

Offerings of NHR@FAU

Scientific offerings

NHR@FAU offers support especially in the area of performance engineering and single-node performance analysis. The application focus is on atomistic simulations, i.e. molecular dynamics, chemistry, and certain areas of material sciences. Special experience is in particular available for Gromacs and Amber as well as VASP.

Compute resources

NHR@FAU offers two different types of compute resources:

• GPGPU cluster “Alex” with Nvidia A40 and Nvidia A100 GPGPUs (mainly for throughput-type of workload and not for multi-node GPU jobs)
• Parallel computer “Fritz” with Intel Xeon Platium 8360Y “IceLake” processors, 250 GB of main memory, and HDR100 interconnect within islands of 64 nodes (i.e. 4.608 cores). In addition there are a few large memory nodes with 1 or 2 TB of main memory.

Types of projects at NHR@FAU

Regular projects by default have a project runtime of 12 months. The review process typically takes less than 3 months. Test / porting projects will be decided within 3-4 weeks.

Project types and (annual) resource limits

Type of project	Possible resources on “Alex”	Possible resources on “Fritz”	Type of review	Remarks
test / porting project (typical project runtime: 3-4 months) starter project (project runtime: up to 12 months; a starter project can only be requested once per group)	up to 3.000 GPU hours (A40 or A100)	up to 500.000 core hours	technical review by NHR@FAU	Rolling call. A scientific advisor from NHR@FAU (liaison scientist) will be assigned.
normal compute time projects for granted DFG or BMBF projects	6.000 – 60.000 GPU hours (A40) 4.000 – 40.000 GPU hours (A100)	1 – 10 mio core hours	technical review by NHR@FAU 1 simplified scientific review	Rolling call. A scientific advisor from NHR@FAU (liaison scientist) can be requested
normal compute time projects built without  granted DFG or BMBF projects	6.000 – 60.000 GPU hours (A40) 4.000 – 40.000 GPU hours (A100)	1 – 10 mio core hours	technical review by NHR@FAU two external scientific reviews	Rolling call. A scientific advisor from NHR@FAU (liaison scientist) can be requested.
large compute time projects (usual project runtime: 12 months)	60.000 – 180.000 GPU hours (A40) 40.000 – 120.000 GPU hours (A100)	10 – 30 mio core hours	technical review by NHR@FAU two external scientific reviews	Deadlines for large-scale applications: January / April / July / October 1st. A scientific advisor from NHR@FAU (liaison scientist) will be assigned.
follow-up projects	as above	as above	technical review by NHR@FAU external scientific reviews of the proposal including an intermediate report	a scientific advisor from NHR@FAU (liaison scientist) can be requested

Projects falling into the “large compute time projects” category should also consider applying for compute time at one of the three federal Tier1 HPC centers of the Gauss Centre for Supercomputing (GCS).

Template for NHR@FAU compute time application proposals

You may still use our template for NHR@FAU compute time proposals and send it by email from your university account to hpc-support@fau.de.

The document contains detailed information on what to fill in. Depending on the project type, some sections are optional and the expected length of some sections may also vary; see the notes in the document for details and contact us via hpc-support@fau.de for further assistance.