PSTSWM SP3-200 Communication Protocol Performance

Performance Studies using

PSTSWM

IBM SP3-200 Protocol Performance

(distributed LT experiment A1 / ring sum algorithm)

Date/Person: November 28, 1999 / P. Worley
Platform: IBM SP3 at Oak Ridge National Laboratory (morgan.ccs.ornl.gov):
     62 2-way Winterhawk I SMP nodes (200 MHz POWER3 with 4MB L2 cache, equivalent to RS/6000 Model 260)
Environment: AIX 4.3.2.2;   PSSP 3.1
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: ringsum
Number of Timesteps: 12
Results:

1x16 Processors / Problem T21L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.9180e-02   0.50   0.59   1.24 
Three Fastest
Protocols
1st2nd3rd
  a6   a0   c4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   4   10 

1x32 Processors / Problem T42L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  7.7994e-02   0.56   0.61   1.37 
Three Fastest
Protocols
1st2nd3rd
  a6   c2   c4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   3   9 

1x8 Processors / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.0992e-01   0.29   0.27   0.72 
Three Fastest
Protocols
1st2nd3rd
  c5   c4   a6 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   2   12 

1x16 Processors / Problem T85L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.8423e-01   0.41   0.35   0.80 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   c2 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   1   4 

1x32 Processors / Problem T85L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.0216e-01   0.53   0.45   0.92 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   1   2 

1x8 Processors / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.0220e+00   0.08   0.07   0.74 
Three Fastest
Protocols
1st2nd3rd
  c4   a6   a3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   10   24 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:16:33 EDT.