Changes between Version 67 and Version 68 of DataParallel/BenchmarkStatus


Ignore:
Timestamp:
Dec 2, 2010 8:08:10 AM (3 years ago)
Author:
benl
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • DataParallel/BenchmarkStatus

    v67 v68  
    3131  || '''name''' || '''runtime''' || '''speedup''' || '''efficiency''' || '''notes''' 
    3232  || repa.mmult.c.seq ||  3.792s || 1 || 1 || A || 
     33  || repa.mmult.par.N1 || 8.484s || 0.45 || 0.45 || || 
    3334  || repa.mmult.par.N4 || 2.147s || 1.77 || 0.44 || || 
     35  || repa.mmult.par.N8 || 1.097s || 3.46 || 0.43 || || 
     36 
    3437  A: Straightforward C program using triple nested loops. A cache-friendly block-based version would be faster. 
    3538 
     
    4346  || '''name''' || '''runtime''' || '''speedup''' || '''efficiency''' || '''notes''' || 
    4447  || repa.laplace.c.seq ||  1.299s || 1 || 1 || A || 
     48  || repa.laplace.par.N1 || 9.405s || 0.14 || 0.14 || || 
    4549  || repa.laplace.par.N4 || 2.521s || 0.51 || 0.13 || || 
     50  || repa.laplace.par.N8 || 2.124s || 0.61 || 0.08 || || 
    4651  A: Straightforward C program using triple nested loops. A cache-friendly block-based version would be faster. 
    4752