The Fluent Benchmarks can be used to compare performance of different
hardware platforms running the FLUENT flow solver. Due to large
computational requirements of many of the application problems,
a fixed number of iterations was used for the benchmark results.
Care was taken to select an iteration interval representative of
the overall performance of the flow simulation. For the parallel
simulations, all grid partitionings were predefined.
Definitions
Rating- Rating is the primary metric
used to report performance results of the Fluent Benchmarks. It
is defined as the number of benchmarks that can be run on a given
machine (in sequence) in a 24 hour period. It is computed by dividing
the number of seconds in a day (86400 seconds) by the number of
seconds required to run the benchmark. A higher rating means faster
performance.
Speedup - Speedup is the ratio of
wall-clock time required to complete a given calculation using
a single processor to that of the equivalent calculation performed
on a concurrent machine. Its value ranges from 0 to the number
of processors used for the parallel run. When the speedup is equal
to the number of processors used, the speedup is called perfect
or linear. Sometimes the speedup will exceed the number
of processors. This is referred to as super-linear speedup,
and is often caused by the availability and use of larger amounts
of "fast" memory (e.g. cache or local memory) compared to the
single processor run.
Efficiency - Efficiency is the
speedup normalized by the number of processors used, presented
as a percentage. It indicates the overall utilization of the CPUs
during a parallel calculation. An efficiency of 100% indicates
that each CPU is completely occupied with computation during the
course of a run, and corresponds to a linear speedup. An efficiency
of 60% indicates that each CPU is performing useful computation
only 60% of the time. The remaining time is spent waiting for
other functions, such as parallel communication or work on other
processors, to complete.
Redzone - The redzone is defined as the region
of greater than 66% efficiency. It is arbitrarily selected as
a region that it is favorable to perform a production run (to
limit the amount of time a processor is idle while waiting, for
example, for the communication phase of the calculation to complete).
Redzone Rating - The redzone
rating is defined as the maximum rating achieved with a parallel
run of a given benchmark and platform that occurs within the redzone.
Peak Rating - The peak rating
is defined as the maximum rating achieved for a parallel run of
a given benchmark and platform with any number of processors.
Table results are listed below alphabetically by
platform.
