2012 NSC and NCAR ASD Call

2012 Call for Proposals from NCAR Researchers for NSC and ASD Resources

This submission opportunity is now closed.

NCAR is pleased to announce the NCAR Strategic Capability (NSC) program, which will provide very large allocations of computational resources to NCAR-led research. Requests for resources under the NSC program for the coming year are due on March 5, 2012. Please note that NSC and NCAR ASD requests should be submitted via the 2012 NSC/ASD submission form.

The opportunity to apply for Accelerated Scientific Discovery (ASD) resources also is available to NCAR researchers as part of the initial NSC submission. Approximately three to five NCAR ASD projects will be chosen from among the NSC submissions. The ASD initiative will run from approximately August through September 2012. The NSC projects will have early access in August 2012 with full-scale access in October 2012.

Yellowstone Specs: The Yellowstone system will be a 1.6-petaflops IBM iDataPlex cluster with 74,592 Intel Sandy Bridge EP cores, 149.2 TB of memory, 11 PB of parallel disk storage. Yellowstone is capable of 30 times the workload throughput of NCAR’s current Bluefire supercomputer. See the Yellowstone documentation for more details.

Comparison between NSC and ASD programs

  NCAR Strategic Capability (NSC) NCAR Accelerated Scientific Discovery (ASD)
Computing platform Yellowstone Yellowstone
Application process Submit 2012 NSC form and attach PDF with proposal details Submit 2012 NSC form and attach PDF with proposal details; designate for ASD consideration on form and describe readiness in proposal.
Frequency of application Annually One-time; ASD only held when Yellowstone is installed.
Production start date Early access, August 2012; full access, October 2012. Continuation of allocation requires consistent, high level of usage August 3, 2012; assumes 1st access to Yellowstone is July 21, 2012.
End date September 30, 2013; a few projects may receive multi-year allocations. October 2012
Minimum request size 5 million core-hours 5 million core-hours
Resources available during program ~100 million core-hours for 12 months 70 million core-hours
Allocation notification date April 2012 April 2012
Benchmark requirements Yes; dates will be announced later. Yes; June 29 and July 30, 2012 deadlines for benchmark submissions; assumes 1st access to Yellowstone is July 21, 2012; loss of 90% of allocation if benchmark deadlines not met.
Testing period August/September 2012 on Yellowstone. May/June 2012 on test system; starts July 21, 2012 on Yellowstone.

NSC and 2012 ASD eligibility

See the NCAR Strategic Capability (NSC) program description for eligibility requirements.

NSC and ASD requirements

To be successful, a proposed project must study a challenging and important science problem in atmospheric science, space weather, oceanic science or computational science (in support of atmospheric or oceanic science or space weather). CISL is particularly interested in submissions for groundbreaking projects in line with the breakthrough computations described in the NWSC Community Science Objectives.

In addition to a challenging scientific problem, NSC and ASD projects also must:

  • Require 5 million core-hours or more for the set of computational experiments proposed. Very large requests are encouraged. For estimating Yellowstone core-hours, users can assume that 1 GAU is equivalent to 0.47 core-hours on Yellowstone. That is, GAUs * 0.47 = Yellowstone core-hours needed. Equivalently, 1 core-hour on Bluefire is equal to 0.65 core-hours on Yellowstone.

  • Utilize production-ready codes that can scale effectively and efficiently up to thousands of processors, or efficiently use an ensemble of comparable size.

Additionally ASD projects must:

  • Have the staff time and experience to complete the computational experiments within 12 weeks.

Guidelines, submission, and schedule

All NCAR submissions must follow the NSC instructions and be submitted via the 2012 NSC form by March 5, 2012. Applicants will be notified in April 2012. See NCAR Strategic Capability (NSC) for details on the review process. The NCAR ASD review process is conducted as part of the NSC review process.

Both NSC and ASD teams will be required to meet benchmark and production deadlines as well as reporting deadlines. The deadlines for ASD are given below. The NSC deadlines will be communicated at a later date.

Special ASD requirements

NCAR ASD teams that are recommended for award should be prepared to submit a preliminary benchmark on a smaller test system by June 29, 2012 and a production benchmark that demonstrates efficient use of Yellowstone no later July 30, 2012.  These dates assume that first access to Yellowstone is on July 21, 2012.   CISL HPC consultants will be available to provide tuning guidance and advice for ASD projects during the benchmark process.

Projects must begin production runs no later than August 3, 2012, and continue rapidly to completion by the end of October 2012.  If a project is unable to meet these benchmark and production deadlines and guidelines, the ASD allocation will be reduced to 10% of the original allocation, and CISL will reallocate the resources.

CISL staff will contact recommended ASD projects to discuss data analysis and visualization options and opportunities prior to the project’s start on Yellowstone. ASD projects will be granted data analysis and visualization allocations through June 28 , 2013.

ASD projects must provide a short preliminary progress report by November 5, 2012, and a final accomplishment report by July 1, 2013, of no more than five pages that describe the research results, the computational experiments performed, the code efficiency, and scientific papers submitted or published as a result of the ASD computations. Please acknowledge support from NSF and NCAR/CISL for the provision of computational resources in your publications.

2012 NSC and NCAR ASD proposal instructions

All NSC and NCAR ASD proposals must be submitted by March 5, 2012, via the NSC web form; email or postal mail submissions will not be accepted. Please fill out the web form and attach the ASD Proposal Document, described below, as a PDF file. Note: University researchers wishing to apply for ASD resources should refer to the 2012 University ASD Call for Proposals.

NSC proposal document (ASD applicants follow same format)

Proposals should be five pages or less for Sections A–E below; the data management plan, accomplishment reports, references, and figures (Sections F–I) should be an additional five pages or less. The proposal should address each numbered item; please retain the section and item numbering and order in your responses.

Note: The request document must identify all PIs and Co-Is on any associated awards. In addition, the web submission form must include the names and affiliations of all PIs and Co-Is on the supporting NSF grant(s) and a complete list of collaborators and their institutions.

A. Project title and PIs

On the first page of the NSC/ASD proposal document please include the following:

  • Project title

  • Project PIs and Co-Is along with institutional affiliations

  • Total HPC core-hours requested

  • Specify NSC request only, ASD only or consideration requested for both programs

B. Scientific objectives

Describe the scientific problem that will be studied and its importance. This section should include discussion of related work recently completed by the PIs and other scientists along with supporting references. Describe the linkages between any NSF award(s) or other agency awards and the proposed NSC/ASD activity. See the NCAR Strategic Capability for more discussion on linkages. Also indicate the relationship to or alignment with NWSC Community Science Objectives, if any.

C. Computational plan

Discussion of your planned computational experiments and the resources needed should comprise the bulk of the five-page proposal.

  1. Describe the numerical approach or models to be used. (For a non-standard or non-community model, the numerical description should briefly describe the approximations and other methods proposed to obtain valid solutions to the problem.)

  2. Describe the numerical experiments being proposed and how they relate to the scientific objectives in sufficient detail for reviewers to confirm the estimate of system resources required.

  3. Describe the number of core-hours required for each proposed experiment and the total resources for the request, including the total data written to disk, sufficient for reviewers to assess the project’s ability to co-exist with other NSC/ASD projects, and the data destined for the HPSS archive, sufficient for reviewers to assess the appropriateness and efficiency of the data storage plan. Explain how the number of core-hours per simulated year was determined.

  4. Provide a table summarizing the number of core-hours, disk space, and archive space required for the proposed set of computational experiments. The table should give the core-hours per simulated year (or per appropriate time period) for each experimental configuration.

D. Code requirements and production-readiness

The reviewers will use this section to assess the production-readiness of the code and to determine if the code will perform well on Yellowstone.

  1. Describe the code to be used in few sentences, including an assessment of its current production-readiness. ASD applicants should refer to the aggressive ASD schedule and provide sufficient detail for the reviewers to evaluate readiness to meet the deadlines. Please include the name of the code. You may cite a web page where the code is described.

  2. Programming environment and runtime requirements.

    1. Programming language: Fortran only? C or C++?

    2. Parallel paradigm used: MPI only? MPI and OpenMP?

    3. Memory usage per core or node:

    4. Required libraries/binaries:

    5. Wall-clock time needed per run:

    6. Scratch disk space needed per run:

    7. Restart capability?

  3. Benchmarks and scalability

    1. Benchmarking system and results: Please summarize benchmark details or reference web page.

    2. Describe the job and code scalability. Discuss the number of processors/nodes currently used (specify platform) and estimate the maximum number of Yellowstone nodes that could be used efficiently.

  4. Other special code requirements

E. Data analysis and visualization

Yellowstone is complemented by two data analysis and visualization systems, Geyser and Caldera. NSC/ASD projects will be granted allocations on Geyser and Caldera that can be used after Yellowstone runs have been completed. CISL will provide help in constructing visualizations to improve understanding and presentation of results. Please describe plans or estimated needs for data analysis and visualization resources following the ASD project period on Yellowstone.

Supporting information

Sections F–I together should be an additional five pages or less.

F. Data management plan

Because of the potential for large-scale Yellowstone projects to produce extensive data output, the project’s short-term disk storage needs and the NSC/ASD project data targeted for longer-term storage should be described in Section C. The Data Management Plan should be used to provide additional explanation of the project’s data needs and plans.

  1. Disk space: Describethe project’s medium-term disk needs for data analysis and visualization following completion of the primary HPC runs through the submission of the final report in February 2013.

  2. Archival storage: NCAR will provide archive space, commensurate with review panel recommendations, for up to one year after the ASD project ends. Describe any longer-term needs for archival storage and/or relevant plans for sharing or managing the resulting data over the longer term.

  3. Offsite Data Transfer: Discuss the amount of data to be transferred to another center and the frequency of transfers.

G. Accomplishment report on prior large allocations

The reviewers will use the accomplishment report to judge the proposing team’s experience with large-scale computations and their likelihood of NSC/ASD success on Yellowstone. The accomplishment report should focus on research in the past five years conducted with large (merit-reviewed) computing allocations at NCAR or other HPC centers. In addition to summarizing the computational experiments and scientific outcomes, the accomplishment report should include (a) the scientific publications produced, (b) the number of graduate students that worked on each large allocation project, (c) the theses produced.

H. References

Please limit references to those directly related to the proposed project.

I. Figures and captions

Optional. Figures may be embedded within the first five pages of the proposal document; however, embedded figures will count against the five-page limit.

Questions

Questions on the NSC and NCAR ASD allocation and selection process may be directed to Dave Hart at alloc@ucar.edu or 303-497-1234. Questions on the new computer, Yellowstone, and the user transition process may be directed to cislhelp@ucar.edu.