PSTSWM T3D Communication Protocol Performance

Performance Studies using

PSTSWM

SGI/Cray Research T3D Protocol Performance

(transpose LT experiment I-A / O(log P) transpose algorithm)

Date/Person: October 28, 1994 / P. Worley
Platform: T3D at Cray Research in Eagen, MN (rain):
   128 150-MHz DEC Alpha EV4 RISC processors
Environment: IS-9.0
Cray CF90 Version 0.1.2.3
Code Version: 6.1
Compilation Options: /mpp/bin/f90 -dp -Oscalar3
Math Library: none
Communication Library: SHMEM
Parallel Algorithm: logtrans
(assuming distributed FFT)
Number of Timesteps: 12
Results:

1x16 Processors / Problem T10L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.7437e-01   0.08   0.03   0.25 
Three Fastest
Protocols
1st2nd3rd
  a2   c2   b6 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   6   10 

1x8 Processors / Problem T21L8
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  7.2260e-01   0.06   0.02   0.17 
Three Fastest
Protocols
1st2nd3rd
  c2   a2   d2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   6   10 

1x16 Processors / Problem T21L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  7.9334e-01   0.07   0.01   0.21 
Three Fastest
Protocols
1st2nd3rd
  c2   a2   d2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   6   10 

1x32 Processors / Problem T21L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  8.2328e-01   0.08   0.03   0.26 
Three Fastest
Protocols
1st2nd3rd
  a2   c2   b6 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   6   9 

1x8 Processors / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  7.5213e+00   0.04   0.01   0.13 
Three Fastest
Protocols
1st2nd3rd
  a2   c2   b2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  6   6   10 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:23:58 EDT.