PSTSWM SP3-200 Communication Protocol Performance

Performance Studies using

PSTSWM

IBM SP3-200 Protocol Performance

(transpose FFT experiment A1 / O(log P) transpose 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: logtrans
Number of Timesteps: 12
Results:

16x1 Processors / Problem T10L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.2093e-01   0.17   0.15   0.35 
Three Fastest
Protocols
1st2nd3rd
  c5   a4   c4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   3   19 

32x1 Processors / Problem T10L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.9346e-01   0.12   0.13   0.28 
Three Fastest
Protocols
1st2nd3rd
  c5   a5   a4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   4   24 

8x1 Processors / Problem T21L8
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.9843e-01   0.09   0.10   0.23 
Three Fastest
Protocols
1st2nd3rd
  a5   c5   a4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   10   25 

16x1 Processors / Problem T21L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.7121e-01   0.14   0.14   0.30 
Three Fastest
Protocols
1st2nd3rd
  c4   a4   a5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   5   23 

32x1 Processors / Problem T21L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.0503e-01   0.14   0.14   0.34 
Three Fastest
Protocols
1st2nd3rd
  a4   a5   a1 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   4   20 

8x1 Processors / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.5129e+00   0.06   0.07   0.18 
Three Fastest
Protocols
1st2nd3rd
  a4   a5   c4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  6   10   25 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:15:35 EDT.