Changeset 3198


Ignore:
Timestamp:
Jun 22, 2006, 12:55:34 PM (18 years ago)
Author:
jack
Message:

Fixed some spelling errors.

File:
1 edited

Legend:

Unmodified
Added
Removed

  • inundation/parallel/documentation/results.tex

    r3185 r3198  
    44
    55To evaluate the performance of the code on a parallel machine we ran some examples on a cluster of four nodes connected with PathScale InfiniPath HTX.
    6 Each node has two AMD Opteron 275 (Dual-core 2.2 GHz Processors) and 4 GB of main memory. The system achieves 60 Gigaflops with the Linpack benchmark, which is about 85% of peak performance.
     6Each node has two AMD Opteron 275 (Dual-core 2.2 GHz Processors) and 4 GB of main memory. The system achieves 60 Gigaflops with the Linpack benchmark, which is about 85\% of peak performance.
    77
    88For each test run we evaluated the parallel efficiency
    … …  
    3535Tables \ref{tbl:rpa40}, \ref{tbl:rpa80} and \ref{tbl:rpa160} show the efficiency results for different values of \code{N} and \code{M}. The examples where $n \le 4$ were run on one node containing 4 processors, the $n = 8$ example was run on 2 nodes. The communication within a node is faster than the communication across nodes, so we would expect to see a decrease in efficiency when we jump from 4 to 8 nodes. Furthermore, as \code{N} and \code{M} are increased the ratio of ghost triangles to other triangles decreases. Or anothr way to think of it is that the size of the boundary layer decreses. Hence the amount of communication relative the amount of computation decreases and thus the efficiency should increase.
    3636
    37 The efficiency results shown here are competative.
     37The efficiency results shown here are competitive.
    3838
    3939\begin{table}
    … …  
    8080Another way of measuring the performance of the code on a parallel machine is
    8181to increase the problem size as the number of processors are increased so that
    82 the number of triangles per processor remains roughly the same.  We have node
     82the number of triangles per processor remains roughly the same.  We have not
    8383carried out measurements of this kind as we usually have static grids and it
    8484is not possible to increase the number of triangles.
Note: See TracChangeset for help on using the changeset viewer.