PSTSWM T3E-900 Point-to-Point Communication Performance

Performance Studies using

PSTSWM

SGI/Cray Research T3E-900 SWAP Performance

(unordered swap of 2MB message using SHMEM)

Date/Person: January 30, 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
PrgEnv 3
Cray CF90 Version 3.0.1.3
Communication Library: SHMEM
SWAP size: 262144 REAL*8 floating point values each direction
Message size: Largest - 262144 REAL*8 floating point values
Smallest - 256 REAL*8 floating point values
Processors: 0 and 1
Latency Definition:(T1024-T512)/512
Results:

unordered swap using nonblocking send
Data Statistics
bidirectional bandwidth estimated latency model error
(peak MByte/sec) (usec/msg) (max. rel. error)
1 iter. 543.72 6.96 5.2%
10 iter. 563.68 6.88 6.3%
1 iter. w/overlap 543.79 7.30 5.6%
10 iter. w/overlap 561.28 6.50 7.0%

unordered swap using nonblocking receive
Data Statistics
bidirectional bandwidth estimated latency model error
(peak MByte/sec) (usec/msg) (max. rel. error)
1 iter. 416.66 8.23 7.7%
10 iter. 424.12 8.31 8.5%
1 iter. w/overlap 421.91 8.46 9.1%
10 iter. w/overlap 428.85 7.59 8.1%

Patrick H. Worley / ( worleyph@ornl.gov)
Last Modified Monday, 15-Jul-2002 10:28:12 EDT.
86595 accesses since 1/2/96.