PSTSWM T3E-900 Communication Protocol Performance

Performance Studies using

PSTSWM


SGI/Cray Research T3E-900 Protocol Performance

(transpose LT experiment I-B / O(P) swap transpose 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: swtrans
(assuming distributed FFT)
Number of Timesteps: 12
Results:

4x16 Processors (Row Major Ordering) / Problem T21L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.4011e-01   0.13   0.12   0.28 
Three Fastest
Protocols
1st2nd3rd
  a6   a0   e2 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   2   29 

2x32 Processors (Row Major Ordering) / Problem T21L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  1.8012e-01   0.17   0.14   0.39 
Three Fastest
Protocols
1st2nd3rd
  a6   a2   a0 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   1   23 

8x8 Processors (Row Major Ordering) / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.2778e-01   0.03   0.04   0.07 
Three Fastest
Protocols
1st2nd3rd
  e0   a0   e1 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  5   23   31 

4x16 Processors (Row Major Ordering) / Problem T42L16
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  4.0583e-01   0.05   0.06   0.10 
Three Fastest
Protocols
1st2nd3rd
  e0   a6   e2 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   14   31 

2x32 Processors (Row Major Ordering) / Problem T42L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  6.7894e-01   0.06   0.06   0.13 
Three Fastest
Protocols
1st2nd3rd
  a6   e2   a0 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  4   14   31 

8x8 Processors (Row Major Ordering) / Problem T85L32
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.6193e+00   0.01   0.01   0.02 
Three Fastest
Protocols
1st2nd3rd
  e0   e1   c1 
      Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  18   31   31 


Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:28:25 EDT.