PSTSWM SP3-200 Communication Protocol Performance

Performance Studies using

PSTSWM

IBM SP3-200 Protocol Performance

(distributed LT experiment C / recursive halving sum algorithm)

Date/Person: June 8, 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;   PSSP 3.1
Code Version: 6.5
Compilation Options: mpxlf -O3 -qarch=auto -qtune=auto -qcache=auto
Link Options: -bmaxdata:0x70000000
Math Library: ESSL
Communication Library: MPI over the switch using user space for internode communication
MPI using IP for intranode communication
Parallel Algorithm: halfsum
Number of Timesteps: 12
Results:

4x16 Processors (Column Major Ordering) / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.0574e-01   0.18   0.16   0.41 
Three Fastest
Protocols
1st2nd3rd
  c5   c4   a4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   3   18 

2x32 Processors (Column Major Ordering) / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  8.7506e-02   0.36   0.36   0.92 
Three Fastest
Protocols
1st2nd3rd
  c4   c5   a4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   2   7 

8x8 Processors (Column Major Ordering) / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.5300e-01   0.05   0.06   0.12 
Three Fastest
Protocols
1st2nd3rd
  c4   a4   a5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   12   25 

4x16 Processors (Column Major Ordering) / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.5332e-01   0.09   0.07   0.37 
Three Fastest
Protocols
1st2nd3rd
  a5   a1   c4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   5   24 

2x32 Processors (Column Major Ordering) / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  5.4111e-01   0.09   0.09   0.24 
Three Fastest
Protocols
1st2nd3rd
  c1   a4   a5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   5   25 

8x8 Processors (Column Major Ordering) / Problem T85L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.1268e+00   0.05   0.05   0.09 
Three Fastest
Protocols
1st2nd3rd
  c4   a4   a3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   11   25 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:15:21 EDT.