PSTSWM Paragon Communication Protocol Performance

Performance Studies using

PSTSWM

Intel Paragon Protocol Performance

(transpose LT experiment II-A1 / O(log P) transpose algorithm)

Date/Person: May 13, 1998 / P. Worley
Platform: Intel Paragon XP/S 150 MP at Oak Ridge National Laboratory:
     1024 MP nodes (3 50-MHz iPSC/860 processors per node)
Environment: Paragon OSF/1 Release 1.0.4 Server 1.4 R1_4_5
f77/Paragon Paragon Version R5.0.3
Code Version: 6.3
Compilation Options: if77 -O4 -Mnodepchk -Knoieee -Msafealloc
Math Library: KAI
Communication Library: MPI
Parallel Algorithm: logtrans
Partition: 1x8, 1x16, or 1x32
Number of Timesteps: 12
Results:

1x16 Processors / Problem T21L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.0367e-01   0.22   0.26   0.51 
Three Fastest
Protocols
1st2nd3rd
  c2   a2   a1 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   6   12 

1x32 Processors / Problem T42L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.9685e-01   0.18   0.17   0.40 
Three Fastest
Protocols
1st2nd3rd
  c2   a3   a1 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   6   16 

1x8 Processors / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.3970e+00   0.11   0.11   0.26 
Three Fastest
Protocols
1st2nd3rd
  c2   c3   a2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   9   24 

1x16 Processors / Problem T85L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.1833e+00   0.05   0.06   0.21 
Three Fastest
Protocols
1st2nd3rd
  c2   a1   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  5   12   25 

1x32 Processors / Problem T85L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.4396e+00   0.15   0.17   0.33 
Three Fastest
Protocols
1st2nd3rd
  c3   c2   a2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   6   21 

1x8 Processors / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.6320e+01   0.08   0.09   0.17 
Three Fastest
Protocols
1st2nd3rd
  c3   c2   a2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   8   25 

DISCUSSION

Partitions of the Paragon processor grid were used that match the processor subsets that the parallel algorithms would run on in a two dimensional data decomposition: 1x8, 1x16, and 1x32.
Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:29:47 EDT.