ALCF Theta Early Science Program: Proposal Instructions

 

Theta ESP CFP is Closed
Aurora ESP CFP Coming in Early July 2016!

 

General Information and Submission Instructions

Our intent is for Theta Early Science Program (ESP) proposals to be relatively simple and short—a stripped-down version of an INCITE proposal. The sections of the proposal are

  1. PI and co-PI information
  2. Project Summary
    • Executive Summary
    • Benefit to Community
    • Science Summary
    • Application Sumary
  3. Estimate of Resources Required
  4. Portability
  5. Project Team Members

For details on how proposals will be evaluated, see the Theta ESP Proposal webpage.

Submission

  • Submission deadline: May 22, 2015 at 11:59 PM US Central Time
  • Prepare your proposal using the instructions below
  • Submit as a single PDF document
  • To submit, email the PDF as an attachment to earlyscience@alcf.anl.gov, with a subject:
    • PI_Lastname ALCF Theta ESP Proposal Submission
    • You may resubmit with revisions as needed up until the deadline.

Please direct any questions to earlyscience@alcf.anl.gov. If needed, contact Tim Williams at 630-252-1154.

Proposal Instructions

Please create your proposal document with a project title, and the section headings noted below:

Section 1: PI and co-PI Information

1a. Principal Investigator (PI) Information

  • Last Name, First Name, Title (Dr., Mr., Ms., etc.)
  • Institution
  • Street address
  • Email address

1b. Co-Principal Investigator (co-PI) Information

For each co-investigator:

  • Last name, first name, title (Dr., Mr., Ms., etc.)
  • Institution
  • Street address
  • Email address

Section 2: Project Summary

2a. Executive Summary

Write an executive summary that accurately describes your proposed research and the high-impact scientific advances you will achieve with access to early resources at the ALCF (1/2 page).

2b. Benefit to Community

Write a description of the benefit your project will provide to the science and HPC community (1/2 page).

2c. Impact Statement

Provide a two-sentence project summary that can be used to describe the impact of your project to the public (50 words maximum).

2d. Science Summary

Write a description of the science problem you would like to address in the 2017 time frame. Include research that will need to be completed in the next two years to lead up to this work (1 page).

2e. Application Summary

2e.i. Application Requirements

Write a list of your application requirements, including languages, libraries, and current parallel method (MPI, OpenMP, etc.) (1 page).

2e.ii. Application Description

Write a description of the current application, including methods, parallelization, I/O, etc. (1 page).

2e.iii. Application Development Needed

Write a description of the code and/or algorithmic development you believe will be necessary to exploit an increase in parallelism per-node and an increase in overall levels of parallelism. Include work that will be needed in MPI parallelism. Consider here how you might use the memory hierarchy on the KNL nodes—the 16 GB of high-bandwidth on-package memory (MCDRAM) and the 192 GB of traditional off-package DRAM. There's a presentation from Intel that discusses the three modes of using the MCDRAM (cache for DRAM, flat, or hybrid). Memory bandwidth bound applications with good strong scaling may consider running entirely from the MCDRAM. The simplest and possibly best approach for some codes might be using the entire MCDRAM automatically as a cache for DRAM. (1 page).

Section 3: Estimate of Resources Requested

If you haven't already, you should look at the slide presentation "ALCF-3 Early Science Program", which has some relevant machine performance information. You'll be making two CPU resource requests.

The first request is for development time on our current BG/Q machine, which should be a modest request of on the order of one or a few million BG/Q core­hours at most. This is development work that does not depend strongly on having the new hardware: implementing new algorithms, adding new physics modules, introducing or scaling up of threads, etc.

The second request is for Early Science period time on our next­generation machine, Theta. This is a large request, for the CPU time you'll need to run your proposed science problem. The total amount of Theta CPU time available for Early Science is on the order of 350 million KNL core hours, and there will be only 6-8 projects awarded; use this to check whether your Theta time request is in the right ballpark. If you have an estimate of how many current­generation BG/Q core hours your science runs would consume, one reasonable conversion factor to use is the estimate from the aforementioned slides: Theta applications can expect a 15x performance increase per node compared to BG/Q nodes (based on ratio of peak speeds of 0.204 and ~3 TFLOPS). Since BG/Q has 16 cores per node, and KNL has 60 cores per node (or more, but assume 60 for your proposal), you'll need to keep that factor of 3.75 in mind in expressing your time estimates in core hours. However you make your estimates, please explain your estimation method; the "brief schedule" documents from your proposal are a good place to do this explanation.

Express your CPU time requests in millions of core hours (BG/Q core hours for the first request and KNL core hours for the second request.

3a. Current-Generation System (Mira) Resources:

  • Mira time in core-hours
  • Disk space in TB
  • Tape archive space in TB
  • Brief schedule for how you would use that time on Mira to prepare for early access to next-generation hardware and the final next-generation system: scaling tests, development (e.g. algorithms, physics modules), verification, parameter sweeps, etc. Assume that your Mira access begins on 1 July 2015 and continues until the start of the Early Science period on Theta (1 January 2017). Break this down into milestones as appropriate for your project (1/2 page).

3b. Next-Generation System (Theta) Resources:

  • Theta time in core-hours
  • Disk space in TB
  • Tape archive space in TB
  • Breakdown for how you would use time on Theta to make final preparations for science runs, and for the science runs themselves. Preparations might include final scaling tests, science problem spin-up runs, etc. For the science runs themselves, estimate the total core-hours and breakdown into separate components/milestones as appropriate. You should plan for completing all of this during the (approximately) three-month Early Science period, when you and the other Theta ESP projects will have dedicated pre-production access. Early Science starts on 1 January 2017. You will have continued access after that three months, but you will be sharing it with all our production users then, and may run at lower priority (1/2 page).

Section 4: Portability

An important focus of the DOE Leadership Computing Facility going forward is application portability. We see two basic architectural tracks going forward from today’s supercomputers (Mira at ALCF and Titan at OLCF) to the next generation (Theta/Aurora at ALCF and Summit at OLCF), and on to exascale from there. After Aurora and Summit, the next-generation LCF systems will be exascale machines. Mira, Theta, and Aurora represent what we’ll call the many-core CPU track; Titan and Summit represent the CPU-GPU track.

4a. Portability Approach

Discuss briefly your plans, if any, to achieve portability of your projects application(s) across different supercomputer architectures, at least the two aforementioned tracks (1/2 page).

4b. Participation in Other Applications-Readiness Programs

Indicate whether your team, or others you are aware of using the same code base, have projects under the NERSC NESAP program, or have submitted proposals to the OLCF CAAR program.

Section 5: Project Team Members

5a. Names and Levels of Effort

List the names and levels of effort (as a percentage of full-time) for all team members you expect to do work on the ESP project.

For each person, include a CV. If you have trouble getting all of the CVs into the PDF proposal document you are submitting, attach them individually to the email you use to submit the proposal, or email earlyscience@alcf.anl.gov for assistance.

Good Luck!