PSTSWM SP3-375 Communication Protocol Performance

Performance Studies using

PSTSWM

IBM SP3-375 Winterhawk II Protocol Performance

(distributed LT experiment A / recursive halving sum algorithm)

Date/Person: December 12, 1999 / P. Worley
Platform: IBM SP3 at Oak Ridge National Laboratory (bobcat.ccs.ornl.gov):
     62 4-way Winterhawk II SMP nodes (375 MHz POWER3 with 8MB L2 cache)
Environment: AIX 4.3.3;   PSSP 3.1.1
Code Version: 6.6.4
Compilation Options: mpxlf -O3 -qarch=auto -qtune=auto -qcache=auto
Link Options: -bmaxdata:0x70000000
Environment Variables: export MP_SHARED_MEMORY="yes"
Math Library: ESSL
Communication Library: MPI over the switch using user space for internode communication
MPI using shared memory for intranode communication
Parallel Algorithm: halfsum
Number of Timesteps: 12
Results:

1x16 Processors / Problem T21L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.9114e-02   0.21   0.24   0.41 
Three Fastest
Protocols
1st2nd3rd
  a6   c4   c2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   3   13 

1x32 Processors / Problem T42L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.3165e-02   0.37   0.32   0.68 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   d4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   2   4 

1x8 Processors / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  5.6686e-02   0.15   0.15   0.23 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   d5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   2   25 

1x16 Processors / Problem T85L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.0829e-01   0.15   0.18   0.25 
Three Fastest
Protocols
1st2nd3rd
  c5   c4   d4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   4   24 

1x32 Processors / Problem T85L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.0210e-01   0.11   0.12   0.20 
Three Fastest
Protocols
1st2nd3rd
  d4   c4   c5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  3   6   25 

1x8 Processors / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  5.0965e-01   0.03   0.02   0.13 
Three Fastest
Protocols
1st2nd3rd
  c5   c4   b4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  5   23   25 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:19:16 EDT.