GPU610/Team DAG

From CDOT Wiki
Revision as of 13:28, 4 March 2013 by Christopher Schreiber (talk | contribs) (Assignment 1)
Jump to: navigation, search


GPU610/DPS915 | Student List | Group and Project Index | Student Resources | Glossary

Team DAG

Team Members

  1. Chris Schreiber, Team Lead

Email All

Progress

Assignment 1

Project selection discussed with Chris Szalwinski. Configuring local working environment and hardware for working with the CERN project source code.

Profile of the Drive_God_lin program utilizing only 1 core/thread on the CPU (forcing serialized execution of all OpenMP Pragmas in the C+ and Fortran code) showed 4 primary targets to rewrite using CUDA kernels. All 4 of these procedure calls are part of the Fortran library included for executing the analysis. There are some portions of the 'main' method in the Drive_God_lin.c code which include a parallel OpenMP pragma, and this could also be tuned for some improvement for initialization of the data arrays, but may not provide improvement for the reading of the data file.


(Each sample counts as 0.01 seconds.)


Methods most likely to offer parallel improvements via CUDA kernels (Top 5 based on Flat Profile). (Each sample counts as 0.01 seconds.)
 %Time Cum Sec Self Sec Calls Self ms/Call Total ms/call Name
47.66 9.99 9.99 314400 0.03 0.03 zfunr_
30.45 16.73 6.38 524 12.18 12.18 ordres_
10.84 18.64 2.27 314400 0.01 0.01 cfft_
3.53 19.38 0.74 314400 0.00 0.04 tunelasr_
3.34 20.08 0.70 1048 0.67 13.42 spectrum_

The method call with the highest time per call is the ordres_ method. This indicates it may be the best target for a parallel implementation.

Assignment 2

Assignment 3