PSTSWM Parallel Performance

Performance Studies using

PSTSWM

Experiment B Transpose FFT Performance

These results represent the minimum execution time for each platform, using the optimal parallel implementation, math libraries where available, and the best available compilers. The legends list the platforms in alphabetical order. Results are presented for both MPI-only experiments and best over all communication libraries.

Transpose FFT (mpi)
Platform Comparison
  T21L16    T21L16    T42L16    T42L32    T42L16    T85L32 
  P=32     P=16     P=8     P=32     P=16     P=8  
  best platform   sp3-200  t3e900  or2k-250  sp3-200-m6  or2k-250  or2k-250 
  best timing   .20741E+00  0.99561E-01  0.32368E+00  .58743E+00  0.29557E+00  0.26987E+01 

Transpose FFT (all)
Platform Comparison
  T21L16    T21L16    T42L16    T42L32    T42L16    T85L32 
  P=32     P=16     P=8     P=32     P=16     P=8  
  best platform   sp3-200  t3e900  t3e900  t3e900  t3e900  or2k-250 
  best library   mpi  shmem  shmem  shmem  shmem  shmem 
  best timing   .20741E+00  0.64804E-01  0.28032E+00  0.57313E+00  0.24797E+00  0.25719E+01 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 09:58:53 EDT.
81740 accesses since 1/2/96.