CNF:CNF Data Generation: Difference between revisions

From crtc.cs.odu.edu
Jump to navigation Jump to search
Spyridon97 (talk | contribs)
Spyridon97 (talk | contribs)
Line 41: Line 41:


== Fall 2020 ==
== Fall 2020 ==
# Fix Axis ordering
# Fix max connections problem with the same username on the database. (TODO)
# Fix max connections problem with the same username on the database. (TODO)
# Update vtk to 9.0.1 inside the container. (TODO)
# Update vtk to 9.0.1 inside the container. (TODO)
# Explore if it's possible/worthy to do an exclusive allocation of cores rather than nodes. (TODO)
# Explore if it's possible/worthy to do an exclusive allocation of cores rather than nodes. (TODO)

Revision as of 21:54, 3 September 2020

Repository

  1. Github

Documentation

Summer 2020

  1. Add README.md file ✔

Code

Summer 2020

  1. Set up a MySQL server on Wahab for partons ✔
  2. Create a container with all the required dependencies ✔
  3. Split Mitch's Code into:
    1. A program that splits kinematic values for each core using:
      1. Uniform Data ✔
      2. Mesh Points ✔
      3. Splitting way
        1. First implementation: split the kinematics dataset like. This way we create areas of kinematics. ✔
          1. N0_0... N0_m-1,
          2. N1_0... N1_m-1,
          3. N2_0... N2_m-1,
          4. ...,
          5. Nn-1_0... Nn-1_m-1.
        2. Second implementation: split the kinematics dataset by creating chunks of size 1 until each kinematics dataset for each node is filled. This way all nodes will have points of similar kinematics. ✔
          1. N0_0, N1_0, N2_0 .. Nn-1_0,
          2. N0_1, N1_1, N2_1 .. Nn-1_1,
          3. N0_2, N1_2, N2_2 .. Nn-1_2,
          4. ...,
          5. N0_m-1, N1_m-1, N2_m-1 .. Nn-1_m-1
    2. A program that computes the Partons Data per core using the kinematics values and the models:
      1. Compton Form Factors ✔
      2. Cross-Sections (TODO)
    3. A program that merges the results of each core into one file ✔
    4. A program that updates the weights of a mesh using partonsData ✔
  4. Enable shared memory parallelization using CPU affinity, which means pinning a process to a specific core. ✔
  5. Create a script that runs partons in parallel using shared memory ✔
  6. Create a script that runs partons in parallel using distributed + shared memory ✔
  7. Speedup:
    1. File:partons-speedup.png

Fall 2020

  1. Fix Axis ordering
  2. Fix max connections problem with the same username on the database. (TODO)
  3. Update vtk to 9.0.1 inside the container. (TODO)
  4. Explore if it's possible/worthy to do an exclusive allocation of cores rather than nodes. (TODO)