PSTSWM SP3-200 Communication Protocol Performance

Performance Studies using

PSTSWM

IBM SP3-200 Protocol Performance

(distributed FFT experiment A1)

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: distributed FFT
Number of Timesteps: 12
Results:

16x1 Processors / Problem T21L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  5.0019e-02   0.39   0.42   0.87 
Three Fastest
Protocols
1st2nd3rd
  c2   c0   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   4   9 

32x1 Processors / Problem T42L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  7.5787e-02   0.33   0.34   0.65 
Three Fastest
Protocols
1st2nd3rd
  a4   a5   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   2   11 

8x1 Processors / Problem T42L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.3670e-01   0.19   0.18   0.60 
Three Fastest
Protocols
1st2nd3rd
  c5   d5   c3 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   4   17 

16x1 Processors / Problem T85L1
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.9688e-01   0.21   0.22   0.64 
Three Fastest
Protocols
1st2nd3rd
  c5   d5   c4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   2   16 

32x1 Processors / Problem T85L2
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  3.5738e-01   0.20   0.21   0.60 
Three Fastest
Protocols
1st2nd3rd
  c5   d5   d4 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  1   4   17 

8x1 Processors / Problem T85L4
Runtime Statistics
min(mean-min)/min(median-min)/min(max-min)/min
  2.1325e+00   0.12   0.13   0.62 
Three Fastest
Protocols
1st2nd3rd
  c5   c3   d5 
       Number of Proctocols With
Runtimes Within X% of Min
1%5%25%
  2   12   24 

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:14:51 EDT.