PSTSWM T3E-900 Point-to-Point Communication Performance

Performance Studies using

PSTSWM

SGI/Cray Research T3E-900 SWAP Performance

(unordered swap of 8KB message using SHMEM)

(performance measured per processor when all processors in node communicating)

Date/Person:	September 30, 1999 / 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 2.0.3.41
	mpt 1.2.1.3
	Cray CF90 Version 3.1.0.3
Communication Library:	SHMEM
SWAP size:	1024 REAL*8 floating point values each direction
Message size:	Largest - 1024 REAL*8 floating point values
	Smallest - 1 REAL*8 floating point value
Processors:	0 and 2
	1 and 3
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. 261.06 8.26 31.4%

10 iter. 405.16 6.85 16.9%

1 iter. w/overlap 243.04 6.89 10.2%

10 iter. w/overlap 393.93 6.34 15.3%

unordered swap using nonblocking receive

Data Statistics
bidirectional bandwidth estimated latency model error

(peak MByte/sec) (usec/msg) (max. rel. error)

1 iter. 250.57 7.53 11.5%

10 iter. 307.91 5.96 29.0%

1 iter. w/overlap 235.81 6.90 9.9%

10 iter. w/overlap 366.82 6.00 13.4%

DISCUSSION

In these tests, we examine SHMEM communication performance between two pairs of processors, looking for signs of performance degradation due to network contention. A real test for network contention would use realistic communication patterns and more than four processors. However, this test is used as a control study for the tests on the systems using shared memory nodes, in which contention and other degradation occurs almost immediately.