For researchers with the largest-scale computational, analysis, and storage needs, requests for Maximize ACCESS allocations can be submitted during the period of March 15 - April 15. Approved allocations will begin or renew on July 1, 2023.
The following Maximize ACCESS cycle will happen with proposal submissions from June 15 to July 15, with awards starting October 1. Going forward, ACCESS Allocations will be moving to a semi-annual cycle for Maximize ACCESS requests with start dates in April and October. Researchers with existing large-scale XSEDE Research or earlier Maximize ACCESS should contact the Allocations team with any questions or concerns to determine the best option for aligning their project renewals with the semi-annual schedule.
When your request is ready to submit, you can do that here.
These XSEDE video presentations are provided to help you prepare your request. They will be updated later this year.
This presentation details all the steps and requirements needed for successful research allocation requests. Topics covered include computation methodologies, justification for SUs requested, and many others.
Recorded: April 4, 2023
Run time: 1 hour 29 minutes
Ken Hackworth from PSC and Lars Koesterke from TACC discuss the technical aspects of research allocation proposals including how best to gather and present scaling and code performance statistics and estimating SU requests in your allocation proposals.
Recorded: April 1, 2020
Run time: 1 hour 7 minutes
No other documents will be reviewed, and documents that exceed specified page limits will not be accepted by the XRAS system.
When writing your Research request, be clear and concise. We strive to have domain experts review every request, but they may not have deep expertise in your specific subdomain. Someone outside of your area should be able to understand the scientific objectives and understand why the chosen technique is preferred over another.
The documents required of a Research request have been requested by XRAC reviewers to ensure they can effectively determine how each request satisfies the XSEDE allocation Review Criteria. Requests need not use the full page limit in all documents; concise submissions are appreciated. No other documents will be reviewed.
The Main Document is the primary and most critical component of a successful request. Research requests must include a well-documented resource-use plan that describes how the requested allocations are necessary and sufficient to accomplish the project's research objectives. An effective resource-use plan must address the XSEDE allocation Review Criteria and, in particular, must include the following elements, with the bulk of the document focused on the Research Objectives and the Resource Usage Plan:
Page limits: 10 pages for less than 10 million SUs total; 15 pages for 10 million SUs or more
The Progress Report for Renewal requests should describe how the PI's current or prior allocation was used and summarize the findings or results; the results can be discussed with respect to the publications and other communications that the PI's team has entered in their XSEDE User Profiles and linked to this request. The Progress Report should also explain any significant digressions from the originally proposed resource usage plan for the prior period.
If a PI's allocation was significantly underutilized, the Progress Report should briefly describe the reasons for the underutilization and any mitigation by the PI to avoid the situation with the current allocation.
Page limit: 3 pages.
This REQUIRED document should contain code performance timings, resource usage details, and scaling information (for HPC resources) to support the calculation of the resource request.
For highly competitive HPC resources, the code performance data should be provided from benchmark runs on the resource requested, using the model configuration(s) needed for the computational plan proposed and demonstrating the scaling efficiency to the job size(s) planned. For smaller size requests, the panel may accept well-justified performance data from architecturally equivalent systems.
For less competitive systems or for non-traditional resources, this document should contain sufficient justification to convince the panel that you have a solid basis for calculating your allocation request.
Page limit: 5 pages.
Two-page (maximum) CVs for each PI and co-PI are required. The two-page NSF or NIH formats are highly recommended.
Page limit: 2 pages per individual
A PI may use this OPTIONAL document to separate a lengthy bibliography of cited work to take full advantage of the page limits in the Main Document. This bibliography is not the publications resulting from prior XSEDE support, which should be entered into the XSEDE publications database, but rather other citations referenced in describing or supporting the intellectual merit of the proposed work or the appropriateness of the proposed approach for addressing the research objectives.
Page limit: No limit.
This OPTIONAL document should be included if the completion of the Resource Usage Plan requires capabilities that fall outside a Service Provider's (SP's) standard user and usage environment. For example, jobs longer than the standard queue lengths, specific scheduling demands, or dedicated file system space. The XRAC is not required to read this document; the intended audience is the staff at the relevant SP.
Page limit: 1 page.
In addition to confirming user eligibility, reviewers evaluate the merits of each request according to three XSEDE allocation review criteria. PIs must provide justification, suitable to the nature of the request, that addresses these criteria; reviewers apply the criteria in the context of the request.
In addition to the computational review criteria, the panel also considers whether the work is aligned appropriately with any supporting grants for which the science has been merit-reviewed. If no such grants are identified, the panel will assess the intellectual merit of the work as well.
Intellectual Merit: Is the proposed work supported by a grant or grants that have undergone review for intellectual merit and/or broader impact (if relevant to the allocation)? If so, is the allocation request consistent with the objectives of the supporting grants and is the scale of resource use commensurate with the level and purpose of support? If a request is not supported by a merit-reviewed award, reviewers will assess the intellectual merit of the proposed work and factor that into their overall recommendation. Reviewers will also consider whether the identified support provides necessary and sufficient human resources to complete the proposed work.
To ensure all required and relevant aspects of each request are considered, the XRAC reviews and rates each request according to the rubric below. Submissions should address each of these elements within the required documents.
To ensure all required and relevant aspects of each request are considered, the XRAC reviews and rates each request according to the following rubric. Submissions should address each of these elements within the required documents.
Failure to address either of the following two items is grounds for rejection.
The Main Document should include the following components:
The Main Document will succinctly state the scientific objectives that will be facilitated by the allocation(s). (The existing merit-reviewed supporting grants should be listed in the submission forms.) Requests with merit-reviewed supporting grants will not be subject to further scientific review by the XRAC; however, the stated scientific objectives must match or be sub-goals of those described in the listed funding award(s). The description of the objectives should be sufficient to allow the reviewers to assess the resource usage plan.
If a request does not have merit-reviewed support, the Main Document should describe the science objectives in sufficient detail for the reviewers to evaluate the intellectual merit of the work covered by the allocation request. The XSEDE Allocations Coordinator will highlight such requests and the XRAC will review the scientific merit of the proposed work.
Next, an effective Main Document will identify the specific research questions that are covered by the allocation request. Within the context of the scientific background and supporting grants, these objectives and questions should be stated so that the reviewers can understand how elements of the resource plan will contribute to relevant answers. If you consider the allocation request in terms of computational experiments, the research objectives and questions define the experiments to be conducted.
The bulk of the Main Document should focus on the resource usage plan and allocation request. Inadequate justification for requested resources is the primary reason for most reduced or denied allocations. Once again, the PI should keep in mind the XSEDE allocation Review Criteria when describing and justifying the choice of resources and allocation amounts, and the Main Document should include appropriate justifications for all resources being requested.
The justification of allocation amounts takes the quantitative parameters from the resource usage plan and combines them with basic resource usage cost information (detailed in the Code Performance and Resource Cost document) to calculate the allocation needed. In terms of computational experiments, the justification should tabulate and calculate the costs of conducting each experiment for each resource and resource type.
Allocations for most resources are made in "Service Units" (SUs); however, the definition of an SU varies from resource to resource. Refer to the User Guide for each resource to determine how to calculate SUs (or other allocable units, if appropriate) for the resources in your request.
For compute resources, the request should address the appropriateness of the computational methodology, the architectural features or capabilities that make this problem a good fit for the requested systems, and the rationale for the number of runs being proposed. In terms of computational experiments, the Resource Usage Plan details the methodology, set-up, and conduct of each experiment.
For other types of resources, the request should address the appropriateness of the resource for the project's needs, the planned use and usage patterns, and the rationale for the allocation amount requested.
When faced with high demand for certain resources, the XRAC reviewers may make recommendations for allocations that could be migrated to less busy resources. This Main Document section should briefly detail the rationale for selecting the requested resources and highlight any resource features or capabilities that would constrain how the allocation might be moved.
For example, the rationale section could mention the need for specific visualization capabilities, the need for tightly integrated or specialized storage needs, the limited availability or compatibility of specific software, a code's ability to use specific resource features (such as GPUs or Xeon Phis), dedicated support for gateway access and usage, or the need to run at very large scale.
Conversely, this section can be used to highlight the PI's flexibility in using alternate resources, which may be advantageous for the PI if the selected resources are highly oversubscribed. (If your work permits, it is generally to your advantage to request less utilized resources directly, rather than simply noting your flexibility.)
Because of the high demand for XSEDE-allocated resources, XSEDE and the XRAC closely consider whether the PI has access to other, less constrained resources on which the proposed work could be conducted. All PIs must describe their local resources and other non-XSEDE resources available to them.
Research requests associated with Gateway projects (sometimes called "Community" projects when a formal gateway is not the primary access mechanism) are submitted and reviewed in the same quarterly process as single-investigator requests, and most of the guidance for single investigator requests also applies to gateway requests. However, some Main Document sections and supporting documents should be modified to address gateway-specific issues.
Main Document-Research questions: In this section, gateway projects would describe the general codes or other services provided and the broad classes of research questions that could be pursued via the gateway.
Main Document-Resource usage plan: Requests for Gateways or Community Services projects would typically use this section to describe the methods or applications provided, the expected or projected consumption of resources, and mechanisms for monitoring the users and usage of the service.
Progress Report: For Gateway projects, the Progress Report should include statistics and reports of community usage to help the reviewers understand how the prior allocation was effectively used and managed.
Code Performance and Scaling: For community or gateway requests, this document can be used to explain the methods used for extrapolating from prior gateway usage, to provide "typical" model performance on the requested or architecturally similar systems, and to explain expected user needs were projected to arrive at the allocation amounts requested.
All documents must satisfy the following minimum requirements. Documents that conform to NSF proposal format guidelines will satisfy these requirements.