MPI_Allreduce-length

Here we also measure the performance of MPI_Allreduce. This time we vary over the message length.

• Pattern: Collective varied over message length.
• default values: 8 nodes, max. / act. time for suite disabled/0.86 min.
• Max. allowed standard error is 3.00 %.

	message length
X axis scale	logarithmic
Param. refinement	automatic x wide adaption
Argument range	1 - 2796192 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: 222 $\mu$s
• Agglomerated bandwidth at msg. length 0 units: 0 units/s
• Latency at msg. length 2730.66 * 1024 units: 1.66818e+06 $\mu$s
• Agglomerated bandwidth at msg. length 2730.66 * 1024 units: 91666.6 * 1024 units/s