PSTSWM Paragon Communication Protocol Performance

Performance Studies using

PSTSWM

Intel Paragon Protocol Performance

(transpose FFT experiment 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
Results:

16x1 Processors / Problem T10L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  5.2077e-01   0.33   0.16   1.03 
Three Fastest
Protocols
1st2nd3rd
  c2   b0   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   7   13 

32x1 Processors / Problem T10L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  7.9148e-01   0.26   0.18   0.89 
Three Fastest
Protocols
1st2nd3rd
  b0   c3   a3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   12   13 

8x1 Processors / Problem T21L8
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.2835e+00   0.10   0.10   0.41 
Three Fastest
Protocols
1st2nd3rd
  c2   c4   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  3   10   24 

16x1 Processors / Problem T21L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.5905e+00   0.17   0.18   0.51 
Three Fastest
Protocols
1st2nd3rd
  c2   c4   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   8   18 

32x1 Processors / Problem T21L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.1553e+00   0.41   0.49   0.96 
Three Fastest
Protocols
1st2nd3rd
  c2   c3   c4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   10   10 

8x1 Processors / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.1801e+01   0.03   0.01   0.36 
Three Fastest
Protocols
1st2nd3rd
  c4   c3   d2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  8   24   24 

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 10:29:43 EDT.