PSTSWM T3E-900 Communication Protocol Performance

Performance Studies using

PSTSWM


SGI/Cray Research T3E-900 Protocol Performance

(distributed LT experiment B / recursive halving sum algorithm)

Date/Person: May 11, 1998 / P. Worley
Platform: T3E-900 at National Energy Research Scientific Computing Center (mcurie.nersc.gov):
   532 450-MHz DEC Alpha EV5 RISC processors
Environment: UNICOS/mk 2.0.2.28
mpt 1.2.0.2
Cray CF90 Version 3.0.2.1
Code Version: 6.3
Compilation Options: -dp -Oscalar3 -Wl,-Dstreams=on
Math Library: libsci
Communication Library: MPI
Parallel Algorithm: halfsum
Number of Timesteps: 12
Results:

4x16 Processors (Row Major Ordering) / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  6.6021e-02   0.12   0.13   0.23 
Three Fastest
Protocols
1st2nd3rd
  a6   a0   a1 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   4   25 

2x32 Processors (Row Major Ordering) / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  6.9551e-02   0.14   0.17   0.31 
Three Fastest
Protocols
1st2nd3rd
  a6   c1   a1 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   6   23 

8x8 Processors (Row Major Ordering) / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.2918e-01   0.03   0.03   0.06 
Three Fastest
Protocols
1st2nd3rd
  a6   a0   c2 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  5   24   25 

4x16 Processors (Row Major Ordering) / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.4586e-01   0.05   0.07   0.08 
Three Fastest
Protocols
1st2nd3rd
  a0   a6   a1 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   12   25 

2x32 Processors (Row Major Ordering) / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.9801e-01   0.07   0.11   0.14 
Three Fastest
Protocols
1st2nd3rd
  a0   c1   c2 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   12   25 

8x8 Processors (Row Major Ordering) / Problem T85L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.8889e+00   0.02   0.02   0.04 
Three Fastest
Protocols
1st2nd3rd
  c2   c1   c4 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  5   25   25 


Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:24:52 EDT.