Please submit the complete project proposal for a compute project at NHR@ZIB via the JARDS portal. A project proposal contains four parts which are described in the sections below.

1. meta data
2. main proposal
3. public abstract
4. signed proposal summary

After submission, the proposal is reviewed by the external Scientific Board. Each reviewer obtains access to

...

• needs to be uploaded as a prepared document in PDF format,
• is written in English,

• should be written in LaTeX based on the main_proposal_template_v1.45.zip. This template includes all relevant aspects like project description, computational facets and resource estimation. The LaTeX template includes both proposal types: initial and follow-up.

We recommend to use the following layout (The here integrated PDF viewer hides elements - please download the PDFs.):

• Initial proposal: sample.pdf
• Follow-up proposal: sample.pdf

Anker
WhitelistStatus WhitelistStatus

The LaTeX template / PDF samples internally differentiate between a normal and a short version in case of whitelist status.
Whitelist status is granted by the scientific review board under three conditions:

• 1^st, you apply for a NHR "Normal project" which is defined by less than 5M core-hours per quarter (see Compute Project)as described in our JARDS guide: Compute Project#guideandassistance. NHR "Large projects" are excluded from the whitelist.
• 2^nd,  you are part of an active DFG/BMBF/NHR/GCS or EU project, which explicitly describes HPC resource requirements in its proposalproject by the DFG, any German federal ministry (e.g. BMBF), EU (e.g. Horizon), or VolkswagenStiftung. The proposal corresponding to this project needs to describe HPC resource requirements and discuss numerical methods.
• 3^rd, as evidence, you need to upload the corresponding project proposal and its review report to the JARDS online portal. We keep it confidential. If an upload is not possible due to confidentiality requirements, whitelisting is unfortunately not possible. 

...

• Imprecise or incomprehensible estimation of requested computational resources (especially core-hours); for example, missing arguments to justify a certain number of N runs instead of a smaller number. One page is our recommended minimum.
• No proof, that the software to be used is suitable and efficient for parallel execution (and parallel I/O) on our current HPC systems architecture. Recycling a scalability demo by a third party is meaningless, without showing that your planned production run is fully comparable to it (algorithm selection within the software, I/O pattern, machine architecture, problem size per core).
• The overall aim and/or motivation behind the project is unclear.
• The applicant lacks HPC/Unix skills and an experienced co-applicant is missing.
• Insufficiency of the applicant's local resources is not indicated.
• The NHR NHR@ZIB computing center was not mentioned in relevant publications.Cut & paste previous/parallel proposals; instead, refer to these.

In case of questions, please contact your consultant.

...