PSTSWM Paragon Algorithm COmparison

Performance Studies using

PSTSWM

Intel Paragon Algorithm Comparison

(transpose FFT experiment A2)

Date/Person: October 21, 1994 / P. Worley
June 4, 1998 / P. Worley
Platform: Intel Paragon at Sandia National Laboratory (acoma):
     1824 GP nodes (2 50-MHz iPSC/860 processors per node)
Intel Paragon XP/S 150 MP at Oak Ridge National Laboratory:
     1024 MP nodes (3 50-MHz iPSC/860 processors per node)
Environment: SUNMOS 1.6.1
  f77/Paragon Paragon Version ???
Paragon OSF/1 Release 1.0.4 Server 1.4 R1_4_5
  f77/Paragon Paragon Version R5.0.3
Code Version: 3.2
Code Version: 6.3
Compilation Options: if77 -O4 -Mnodepchk -Knoieee -Msafealloc
Math Library: none
Communication Library: SUNMOS
NX
Partition: 4x2, 4x4, or 8x4
Results:

Transpose FFT (OSF/NX)
Algorithm Comparison
  T10L16    T10L16    T21L8     T21L32    T21L16    T42L16 
  P=32     P=16     P=8     P=32     P=16     P=8  
  optimal algorithm   swtrans  swtrans  srtrans  swtrans  swtrans  srtrans 
  (generic-min)/min     0.106    0.071    0.011    0.032    0.010    0.019 

Transpose FFT (SUNMOS)
Algorithm Comparison
  T10L16    T10L16    T21L8     T21L32    T21L16    T42L16 
  P=32     P=16     P=8     P=32     P=16     P=8  
  optimal algorithm   swtrans  swtrans  swtrans  swtrans  swtrans  srtrans 
  (generic-min)/min     0.203    0.090    0.011    0.048    0.021    0.003 

Transpose FFT (combined)
Communication Library Comparisons
  T10L16    T10L16    T21L8     T21L32    T21L16    T42L16 
  P=32     P=16     P=8     P=32     P=16     P=8  
  optimal library   sunmos  sunmos  sunmos  sunmos  sunmos  sunmos 
  (osfnx-min)/min     0.583    0.437    0.304    0.299    0.283    0.227 

DISCUSSION

The Paragon processor grid partitions were chosen to match those used for the October, 1994 SUNMOS data.
Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:29:22 EDT.