AMROC Main     Blockstructured Adaptive Mesh Refinement in object-oriented C++

Backward facing step - 3 Grid Levels (density at time t = 0.75)

Problem description       Results:   2 Levels        3 Levels
previous     next



Contour lines of density on refinement grids (P=1)
 
Level 0
Level 1
Level 2
Grids
    2
   48
   111
Cells
67500
25792
187248




Benchmark

Task
P=1
P=2, GuC-Factor=2
P=4, GuC-Factor=2
P=2, GuC-Factor=1
P=4, GuC-Factor=1
s
%
s
%
s
%
s
%
s
%
Integration
 3930
 73.1
 1848
 62.0
  930
 53.5
 2077
 43.6
 1045
 38.3
Flux correction
   95
  1.8
   66
  2.2
   63
  3.6
   91
  1.9
   78
  2.9
Boundary setting
  657
 12.2
  660
 22.1
  463
 26.7
  704
 14.8
  458
 16.8
Recomposition
  271
  5.0
  231
  7.7
  176
 10.1
 1685
 35.4
 1015
 37.2
Clustering
  177
  3.3
   67
  2.2
   35
  2.0
   69
  1.4
   36
  1.3
Misc.
  243
  4.5
  110
  3.7
   70
  4.0
  131
  3.0
   85
  3.5
Total / Parallel Efficiency
 5373
100.0
 2982
 90.1
 1737
 77.3
 4756
 56.5
 2717
 49.4

If a relatively fine base grid is used, the choice of a larger GuC-Factor can decrease the overhead for partitioning and recomposition significantly. In this example, the partitioner can use up to 67500 units for GuC-Factor=1, while for GuC-Factor=2 only up to 16875 units are allowed.


top

Quickstart       Users Guide     Programmers Reference     Installation      Examples     Download


AMROC Main      Home      Contact
last update: 6/1/04