PSTSWM T3E-900 Algorithm Comparison

Performance Studies using

PSTSWM

SGI/Cray Research T3E-900 Algorithm Comparison

(distributed FFT experiment A)

Date/Person: May 11, 1998 / P. Worley
Platform: T3E-900 at National Energy Research Scientific Computing Center (mcurie.nersc.gov):
   532 450-MHz DEC Alpha EV5 RISC processors
Environment: UNICOS/mk 2.0.2.28
mpt 1.2.0.2
Cray CF90 Version 3.0.2.1
Code Version: 6.3
Compilation Options: -dp -Oscalar3 -Wl,-Dstreams=on
Math Library: libsci
Communication Library: MPI
SHMEM
Number of Timesteps: 12
Results:

Distributed FFT (mpi)
Algorithm Comparison
  T42L1     T21L2     T42L2     T85L2     T85L1     T85L4  
  P=32     P=16     P=8     P=32     P=16     P=8  
  optimal algorithm   generic  dfft  dfft  dfft  dfft  dfft 
  (generic-min)/min     0.000    0.024    0.008    0.012    0.019    0.008 

Distributed FFT (shmem)
Algorithm Comparison
  T42L1     T21L2     T42L2     T85L2     T85L1     T85L4  
  P=32     P=16     P=8     P=32     P=16     P=8  
  optimal algorithm   dfft  dfft  dfft  dfft  dfft  dfft 
  (generic-min)/min     0.128    0.174    0.108    0.087    0.085    0.084 

Distributed FFT (combined)
Communication Library Comparisons
  T42L1     T21L2     T42L2     T85L2     T85L1     T85L4  
  P=32     P=16     P=8     P=32     P=16     P=8  
  optimal library   shmem  shmem  shmem  shmem  shmem  shmem 
  (mpi-min)/min     0.397    0.471    0.144    0.145    0.154    0.088 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:24:37 EDT.