Changes between Version 5 and Version 6 of DataParallel/BenchmarkStatus


Ignore:
Timestamp:
Feb 24, 2009 3:39:47 AM (5 years ago)
Author:
chak
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • DataParallel/BenchmarkStatus

    v5 v6  
    1515 
    1616|| '''Program''' || '''Problem size''' || '''sequential''' || '''1 core''' || '''2 cores''' || '''4 cores''' || '''8 cores''' || 
    17 || DotP, primitives || 10M elements || 823/823/824 || || || || || 
     17|| DotP, primitives || 10M elements || 823/823/824 || 812/813/815 || 408/408/409 || 220/223/227 || 210/214/221 || 
    1818|| DotP, vectorised || 10M elements || 823/824/824 || || || || || 
    1919 
    2020All results are in milliseconds, and the triples report best/average/worst execution case time (wall clock) of three runs.  The column marked "sequential" reports times when linked against `dph-seq` and the columns marked "N cores" report times when linked against `dph-par` and run in parallel on the specified number of processor cores. 
     21 
     22'''NB:''' At the moment, the CPU times goes up proportional to the number of cores added beyond four cores (hence, no wall clock speed up beyond four cores).  Not clear where this comes from. 
    2123 
    2224----