The SPEC MPI® 2007 benchmark suite
is for evaluating MPI-parallel, floating point, compute intensive
performance across a wide range of cluster and SMP hardware.
This suite continues the SPEC tradition of giving users the most
objective and representative benchmark suite for measuring and
comparing high-performance computer systems.
SPEC MPI® 2007 focuses on performance of
compute intensive applications using the Message-Passing Interface (MPI),
which means this benchmark emphasizes the performance of:
- the type of computer processor (CPU),
- the number of computer processors,
- the MPI Library,
- the communication interconnect,
- the memory architecture,
- the compilers, and
- the shared file system.
It is important to remember the contribution of all these components.
Performance intentionally depends on more than just the
processor; the benchmark is not intended to stress other computer
components such as the operating system, graphics, or the I/O system.
The current release of the benchmark is V2.0.1 and it is available for
purchase via the SPEC order form.
This release (February 2010) adds the new suite MPI® L2007
to the SPEC MPI® 2007 benchmark suites. The new
MPI® L2007 suite is designed for larger clusters,
scaling up to 2048 ranks (cores). For an overview of the changes, see
Changes in V2.0.
Results from V2.0 for the MPI® M2007 suite are comparable to those from
V1.1 or V1.0. Results from the MPI® L2007 suite are not comparable to
results from the MPI®M2007 suite and these results may continue to be
submitted using V1.1 for the foreseeable future.
This maintenance release (October 2008) adds updates to benchmarks to
improve portability and code correctness; improvements to report
readability; clarifications and additions to the Run and Reporting Rules;
documentation of the monitor hooks; and easier investigation of alternate
sources or workloads. For a full list of updates, see
Changes in V1.1. Existing licensees
will receive a complimentary upgrade DVD.
Results from V1.0 are comparable to those from V1.1. As of January 1, 2009
all submissions must use version 1.1.
SPEC MPI Benchmark Suite Highlights
- The benchmark programs are developed from native MPI-parallel
end-user applications, as opposed to being synthetic benchmarks
or even parallelized versions of sequential benchmarks.
- The benchmark is highly portable.
- Multiple vendors use the suite and support it.
- Submitted Results
- Text, HTML, CSV, PDF, and Configuration file outputs;
includes all of the results submitted to SPEC from
member companies and other licensees of the benchmark.
- Explanations of the meaning of the flags in the results'
SPEC's HPG group recently voted to not allow the use of automatic
parallelization compiler flags in SPEC MPI® 2007. This change effectively
renders the benchmark as a pure MPI benchmark and is stated as such in newly-added
section 1.1.4 of the run rules.
Any reference to auto parallelization has been removed from the document and the
reporting field "auto_parallel" in the results must always be set to "no" for a compliant
Fortunately, none of the results reviewed and published so far use the auto parallel
option. Furthermore, please note that any "estimated" result, not reviewed
by SPEC HPG, that makes use of the auto parallel option will no longer be compliant.
Licensees of SPEC MPI® 2007 are encouraged to download the
latest version of the Run & Reporting rules.
If you have any questions, please contact the SPEC office.
- SPEC MPI® 2007 documentation
- The most current versions of the software documentation, including
system requirements, installation and set up instructions, run and
reporting rules, and explanation of fields in the result file.
- Frequently-asked questions about MPI® 2007
- Known issues
- Currently-known issues with the benchmark. See also the technical
- SPEC MPI®2007 Benchmark Descriptions
- A survey of the included benchmarks
Journal articles, papers, and other publications related to the benchmark.