PSTSWM SP3-375 Communication Protocol Performance

Performance Studies using

PSTSWM

IBM SP3-375 Winterhawk II Protocol Performance

(distributed LT experiment A / exchange 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: exchsum
Number of Timesteps: 12
Results:

1x16 Processors / Problem T21L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.9759e-02   0.20   0.17   0.34 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   a4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   2   16 

1x32 Processors / Problem T42L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  9.9573e-02   0.16   0.18   0.28 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   a5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   4   23 

1x8 Processors / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  9.8261e-02   0.10   0.11   0.19 
Three Fastest
Protocols
1st2nd3rd
  c5   c4   d4 
       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
  2.8408e-01   0.10   0.09   0.21 
Three Fastest
Protocols
1st2nd3rd
  c5   c4   c1 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   6   25 

1x32 Processors / Problem T85L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  7.4425e-01   0.12   0.08   0.32 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   a4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   6   21 

1x8 Processors / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  8.5385e-01   0.11   0.10   0.33 
Three Fastest
Protocols
1st2nd3rd
  a4   a1   a5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  3   10   24 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:19:13 EDT.