PSTSWM SP3-375 Communication Protocol Performance

Performance Studies using

PSTSWM

IBM SP3-375 Winterhawk II Protocol Performance

(transpose FFT experiment C / O(P) swap transpose 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: swtrans
Number of Timesteps: 12
Results:

16x4 Processors (Column Major Ordering) / Problem T21L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.5320e-01   0.52   0.52   0.99 
Three Fastest
Protocols
1st2nd3rd
  e5   e4   e3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   3   5 

32x2 Processors (Column Major Ordering) / Problem T21L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.6316e-01   0.52   0.52   0.98 
Three Fastest
Protocols
1st2nd3rd
  e4   e5   e3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   3   5 

8x8 Processors (Column Major Ordering) / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.0064e-01   0.07   0.05   0.16 
Three Fastest
Protocols
1st2nd3rd
  c4   a5   c5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  3   15   31 

16x4 Processors (Column Major Ordering) / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.1822e-01   0.15   0.13   0.32 
Three Fastest
Protocols
1st2nd3rd
  c4   e5   c5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   6   22 

32x2 Processors (Column Major Ordering) / Problem T42L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  6.1889e-01   0.19   0.17   0.42 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   a4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   3   21 

8x8 Processors (Column Major Ordering) / Problem T85L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.5714e+00   0.07   0.07   0.23 
Three Fastest
Protocols
1st2nd3rd
  a4   a5   a1 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  3   9   31 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:19:51 EDT.