Uploaded image for project: 'SAFe Program'
  1. SAFe Program
  2. SP-994

CUDA port of LEAP algorithm

Change Owns to Parent OfsSet start and due date...
    XporterXMLWordPrintable

Details

    • Data Processing
    • Hide

      A high performance implementation of the LEAP algorithm providing the capability to correct for direction-dependent ionosphere in tied-array beamforming will enable a more complete characterization of both its technical as well as scientific performance

      Show
      A high performance implementation of the LEAP algorithm providing the capability to correct for direction-dependent ionosphere in tied-array beamforming will enable a more complete characterization of both its technical as well as scientific performance
    • Hide
      • GPU (CUDA) implementation of the LEAP algorithm in a component oriented way.
      • demo of parallel workflow using an execution engine (DALiuGE). This is a stretch goal.

       

       

      Show
      GPU (CUDA) implementation of the LEAP algorithm in a component oriented way. demo of parallel workflow using an execution engine (DALiuGE). This is a stretch goal.    
    • 3
    • 3
    • 1.333
    • Team_YANDA
    • Sprint 5
    • Hide

      Design Notes:
      https://confluence.skatelescope.org/display/SE/LEAP-Cal+Optimized+SDD
      Code Repo:
      https://github.com/ICRAR/leap-accelerate

      Show
      Design Notes: https://confluence.skatelescope.org/display/SE/LEAP-Cal+Optimized+SDD Code Repo: https://github.com/ICRAR/leap-accelerate
    • 8.3
    • Stories Completed, Solution Intent Updated, Outcomes Reviewed, Accepted by FO

    • PI22 - UNCOVERED

    • Team_YANDA

    Description

      LEAP (Rioja, Dodson & Franzen 2018; MN 478, 2337) is a method for evaluating delays for a grid of sources across the sky, from which solutions can be interpolated to arbitrary directions and provided to CSP for beam-forming.The goal is to run it on ionospheric variation timescales, at least for compact configurations. This calls for a high performance implementation, that exploits data parallelism to suffice the real time constraint.

      For proof of concept a CPU-based prototype has been put together, which serves as a starting point and reference when porting it to CUDA.
       

      Attachments

        Issue Links

          is required by

          Feature - A Feature is a service that fulfills a stakeholder need. Each feature includes a benefit hypothesis and acceptance criteria, and is sized or split as necessary to be delivered by a single Agile Release Train (ART) in a Program Increment (PI). SP-1220 Finalize CUDA port of LEAP and characterize Performance

          • Not Assigned - Priority is not assigned yet.
          • Done
          is triggered by

          PI Risk - Program Increment risk for ROAMing ROAM-116 SP-994 - Delivery is highly dependent on new staff member

          • Retired
          relates to

          Enabler - An Enabler supports the activities needed to extend the Architectural Runway to provide future business functionality. These include exploration, architecture, infrastructure, and compliance. SP-1004 Evaluate use of LEAP for DD RCAL with SKA1 simulated data

          • Not Assigned - Priority is not assigned yet.
          • Done
          mentioned in

          Page Loading...

          Page Loading...

          Page Loading...

          Structure

            Activity

              People

                p.wortmann Wortmann, Peter
                m.dolensky Dolensky, Markus [X] (Inactive)
                Votes:
                0 Vote for this issue
                Watchers:
                5 Start watching this issue

                Feature Progress

                  Story Point Burn-up: (100.00%)

                  Feature Estimate: 3.0

                  IssuesStory Points
                  To Do00.0
                  In Progress   00.0
                  Complete512.0
                  Total512.0

                  Dates

                    Created:
                    Updated:
                    Resolved:

                    Structure Helper Panel