Changes between Version 13 and Version 14 of DataParallel/BenchmarkStatus


Ignore:
Timestamp:
Mar 5, 2009 12:30:29 AM (5 years ago)
Author:
chak
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • DataParallel/BenchmarkStatus

    v13 v14  
    2828All 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. 
    2929 
    30 '''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. 
     30==== Observations regarding DotP ==== 
     31 
     32Performance is memory bound, and hence, the benchmark stops scaling once the memory bus saturated.  As a consequence, the wall-clock execution time of the Haskell programs and the C reference implementation are the same when all available parallelism is exploited.  The parallel DPH library delivers the same single core performance as the sequential one in this benchmark. 
    3133 
    3234----