MPI_Waitany-length

In this measurement we use the MPI_Waitany-routine to coordinate the incoming worker messages. This function does not guarantee a fair coordination of the workers, because possibly a worker's messages are always overtoken by the messages of its colleagues. But because of its simplicity it may be faster than the MPI_Waitsome.

We vary over the message length.

• Pattern: Master-Worker varied over message length.
• default values: 8 nodes, chunks 10, max. / act. time for suite disabled/0.42 min.
• Max. allowed standard error is 3.00 %.

	message length
X axis scale	logarithmic
Param. refinement	automatic x wide adaption
Argument range	1 - 1048560 units (s. below)
Argument stepwidth	1.414214

• Units: bytes in type: basetype 1 (MPI_INT), send-datatype 20: size 4 Bytes, extent 4 Bytes (user defined basetype 1 (MPI_INT)), receive-datatype 20: size 4 Bytes, extent 4 Bytes (user defined basetype 1 (MPI_INT))

• Latency at msg. length 0 units: 1304.1 $\mu$s
• Bandwidth at msg. length 0 units: 0 units/s
• Latency at msg. length 1023.98 * 1024 units: 894258 $\mu$s
• Bandwidth at msg. length 1023.98 * 1024 units: 11450.7 * 1024 units/s