Getting Started with Intel® MPI Benchmarks 2018

The Intel® MPI Benchmarks perform a set of MPI performance measurements for point-to-point and global communication operations for a range of message sizes. The generated benchmark data fully characterizes:

  • Performance of a cluster system, including node performance, network latency, and throughput
  • Efficiency of the MPI implementation used


Memory and Disk Space Requirements

The memory required to run the Intel MPI Benchmarks is determined by the number of active processes with the default settings (standard mode) or the maximum size of the MPI message with user-defined settings (optional mode). Those vary from static values of 80 MB or below to dynamic values of up to 8 MB * # of active processes. The Intel MPI Benchmarks User Guide has full descriptions for the memory requirements for each benchmark.

Software Requirements

To run the Intel® MPI Benchmarks, you need:

  • cpp, ANSI C compiler, gmake on Linux* OS or Unix* OS
  • Enclosed Microsoft Visual* C++ solutions as the basis for Microsoft Windows* OS
  • MPI installation, including a startup mechanism for parallel MPI programs

Launch the Intel MPI Benchmarks

Installing the benchmarks

The benchmarks are available for download at the Intel MPI Benchmarks GitHub repository.

They are also installed as part of:

  • Intel® MPI Library
  • Intel® Parallel Studio XE Cluster Edition

For more information on the installed files, see:



  • <install_dir> is the Intel Parallel Studio XE installation directory, by default C:\Program Files (x86)\IntelSWTools on Windows, and /opt/intel/ on Linux
  • <version> is the Intel MPI Benchmarks version

Building the benchmarks

Building the benchmarks on Linux* OS

To build the benchmarks on Linux, do the following:

host$ source <path to Intel Compilers directory>/composerxe/bin/ intel64
host$ source <path to Intel MPI Library directory>/intel64/bin/
host$ cd <path to Intel MPI Benchmarks directory>/src
host$ make -f make_ict

To build the benchmarks on Linux for Intel® Many Integrated Core Architecture (Intel® MIC Architecture), follow these steps:

#build the host executable as described in the previous step

#build the target executable as follows
#(make sure your environment is still setup as mentioned above)
host$ cd <path to Intel MPI Benchmarks directory>/src
host$ make -f make_ict_mic

Building the benchmarks on Windows OS*

Use the enclosed solution files located in the component-specific subdirectories under the WINDOWS/ directory. Click on the respective .vcproj or .vcxproj project file and use the Microsoft* Visual Studio* menu to run the associated benchmark application.

  1. Check that the Include, Lib, and Path environment variables are set as follows:
    • %I_MPI_ROOT%\intel64\include
    • %I_MPI_ROOT%\intel64\lib
    • %I_MPI_ROOT%\mpi\intel64\bin
    The %I_MPI_ROOT% environment variable is set to the Intel MPI Library installation directory. The default installation directory is C:\Program Files (x86)\Intel\mpi\<version>, where <version> is the product version.
  2. Open the .vcproj or .vcxproj file for the component you would like to build. From the Visual Studio Project panel:
    1. Change the Solution Platforms dialog box to x64
    2. Change the Solution Configurations dialog box to Release
    3. Check other settings as required, for example:
      • General > Project Defaults
        • Set Character Set to Use Multi-Byte Character Set
      • C/C++ > General
        • Set Additional Include Directories to $(I_MPI_ROOT)\intel64\include
        • Set Warning Level to Level 1 (/W1)
      • C/C++ > Preprocessor
        • For the Preprocessor definitions within the Visual Studio projects, add the conditional compilation macros WIN_IMB and _CRT_SECURE_NO_DEPRECATE. Depending on the components you intend to use, add one or more of the following macros: MPI1, EXT, MPIIO, NBC, RMA.
      • Linker > Input
        • Set Additional Dependencies to $(I_MPI_ROOT)\intel64\lib\impi.lib. Make sure to add quotes.
  3. Use F7 or Build > Build Solution to create an executable

Running the benchmarks

To run the Intel® MPI Benchmarks, use the following command-line syntax:

host$ mpirun -np <P> IMB-<component> [arguments]


  • P is the number of processes. P=1 is recommended for all I/O and message passing benchmarks except the single transfer ones.
  • <component> is the component-specific suffix that can take MPI1, EXT, IO, NBC, and RMA values

By default, all benchmarks run on Q active processes defined as follows: Q=[1,] 2, 4, 8, ..., largest 2x.

Key Features

The Intel® MPI Benchmarks package consists of the following components:

  • IMB-MPI1 - benchmarks for MPI-1 functions
  • Two components covering MPI-2 functionality:
    • IMB-EXT - one-sided communications benchmarks
    • IMB-IO - input/output (I/O) benchmarks
  • Two components covering MPI-3 functionality:
    • IMB-NBC - non-blocking collectives benchmarks that provide measurements of the computation/communication overlap and of the pure communication time
    • IMB-RMA - Remote Memory Access (RMA) benchmarks that use passive target communication to measure one-sided communication

Each component corresponds to a separate executable file. You can run all of the supported benchmarks, or specify a single executable file in the command line to get results for a specific subset of benchmarks.

Read the included IMB User's Guide for more information on all runtime options.  All documentation is available after you install the benchmarks, in the imb/doc directory.


Intel® MPI Benchmarks (Common Public License)

Common Public License Version 1.0



"Contribution" means:

  • in the case of the initial Contributor, the initial code and documentation distributed under this Agreement, and
  • in the case of each subsequent Contributor:
    • changes to the Program, and
    • additions to the Program; where such changes and/or additions to the Program originate from and are distributed by that particular Contributor. A Contribution 'originates' from a Contributor if it was added to the Program by such Contributor itself or anyone acting on such Contributor's behalf. Contributions do not include additions to the Program which: (i) are separate modules of software distributed in conjunction with the Program under their own license agreement, and (ii) are not derivative works of the Program.

"Contributor" means any person or entity that distributes the Program.

"Licensed Patents " mean patent claims licensable by a Contributor which are necessarily infringed by the use or sale of its Contribution alone or when combined with the Program.

"Program" means the Contributions distributed in accordance with this Agreement.

"Recipient" means anyone who receives the Program under this Agreement, including all Contributors.


Subject to the terms of this Agreement, each Contributor hereby grants Recipient a non-exclusive, worldwide, royalty-free copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, distribute and sublicense the Contribution of such Contributor, if any, and such derivative works, in source code and object code form.

Subject to the terms of this Agreement, each Contributor hereby grants Recipient a non-exclusive, worldwide, royalty-free patent license under Licensed Patents to make, use, sell, offer to sell, import and otherwise transfer the Contribution of such Contributor, if any, in source code and object code form. This patent license shall apply to the combination of the Contribution and the Program if, at the time the Contribution is added by the Contributor, such addition of the Contribution causes such combination to be covered by the Licensed Patents. The patent license shall not apply to any other combinations which include the Contribution. No hardware per se is licensed hereunder.

Recipient understands that although each Contributor grants the licenses to its Contributions set forth herein, no assurances are provided by any Contributor that the Program does not infringe the patent or other intellectual property rights of any other entity. Each Contributor disclaims any liability to Recipient for claims brought by any other entity based on infringement of intellectual property rights or otherwise. As a condition to exercising the rights and licenses granted hereunder, each Recipient hereby assumes sole responsibility to secure any other intellectual property rights needed, if any. For example, if a third party patent license is required to allow Recipient to distribute the Program, it is Recipient's responsibility to acquire that license before distributing the Program.

Each Contributor represents that to its knowledge it has sufficient copyright rights in its Contribution, if any, to grant the copyright license set forth in this Agreement.


A Contributor may choose to distribute the Program in object code form under its own license agreement, provided that:

  • it complies with the terms and conditions of this Agreement; and
  • its license agreement:
    • effectively disclaims on behalf of all Contributors all warranties and conditions, express and implied, including warranties or conditions of title and non-infringement, and implied warranties or conditions of merchantability and fitness for a particular purpose;
    • effectively excludes on behalf of all Contributors all liability for damages, including direct, indirect, special, incidental and consequential damages, such as lost profits;
    • states that any provisions which differ from this Agreement are offered by that Contributor alone and not by any other party; and
    • states that source code for the Program is available from such Contributor, and informs licensees how to obtain it in a reasonable manner on or through a medium customarily used for software exchange.

    When the Program is made available in source code form:

    • it must be made available under this Agreement; and
    • a copy of this Agreement must be included with each copy of the Program. Contributors may not remove or alter any copyright notices contained within the Program.

Each Contributor must identify itself as the originator of its Contribution, if any, in a manner that reasonably allows subsequent Recipients to identify the originator of the Contribution.


Commercial distributors of software may accept certain responsibilities with respect to end users, business partners and the like. While this license is intended to facilitate the commercial use of the Program, the Contributor who includes the Program in a commercial product offering should do so in a manner which does not create potential liability for other Contributors. Therefore, if a Contributor includes the Program in a commercial product offering, such Contributor ("Commercial Contributor") hereby agrees to defend and indemnify every other Contributor ("Indemnified Contributor") against any losses, damages and costs (collectively "Losses") arising from claims, lawsuits and other legal actions brought by a third party against the Indemnified Contributor to the extent caused by the acts or omissions of such Commercial Contributor in connection with its distribution of the Program in a commercial product offering. The obligations in this section do not apply to any claims or Losses relating to any actual or alleged intellectual property infringement. In order to qualify, an Indemnified Contributor must:

  • promptly notify the Commercial Contributor in writing of such claim, and
  • allow the Commercial Contributor to control, and cooperate with the Commercial Contributor in, the defense and any related settlement negotiations. The Indemnified Contributor may participate in any such claim at its own expense.

For example, a Contributor might include the Program in a commercial product offering, Product X. That Contributor is then a Commercial Contributor. If that Commercial Contributor then makes performance claims, or offers warranties related to Product X, those performance claims and warranties are such Commercial Contributor's responsibility alone. Under this section, the Commercial Contributor would have to defend claims against the other Contributors related to those performance claims and warranties, and if a court requires any other Contributor to pay any damages as a result, the Commercial Contributor must pay those damages.


EXCEPT AS EXPRESSLY SET FORTH IN THIS AGREEMENT, THE PROGRAM IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Each Recipient is solely responsible for determining the appropriateness of using and distributing the Program and assumes all risks associated with its exercise of rights under this Agreement, including but not limited to the risks and costs of program errors, compliance with applicable laws, damage to or loss of data, programs or equipment, and unavailability or interruption of operations.




If any provision of this Agreement is invalid or unenforceable under applicable law, it shall not affect the validity or enforceability of the remainder of the terms of this Agreement, and without further action by the parties hereto, such provision shall be reformed to the minimum extent necessary to make such provision valid and enforceable.

If Recipient institutes patent litigation against a Contributor with respect to a patent applicable to software (including a cross-claim or counterclaim in a lawsuit), then any patent licenses granted by that Contributor to such Recipient under this Agreement shall terminate as of the date such litigation is filed. In addition, if Recipient institutes patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Program itself (excluding combinations of the Program with other software or hardware) infringes such Recipient's patent(s), then such Recipient's rights granted under Section 2(b) shall terminate as of the date such litigation is filed.

All Recipient's rights under this Agreement shall terminate if it fails to comply with any of the material terms or conditions of this Agreement and does not cure such failure in a reasonable period of time after becoming aware of such noncompliance. If all Recipient's rights under this Agreement terminate, Recipient agrees to cease use and distribution of the Program as soon as reasonably practicable. However, Recipient's obligations under this Agreement and any licenses granted by Recipient relating to the Program shall continue and survive.

Everyone is permitted to copy and distribute copies of this Agreement, but in order to avoid inconsistency the Agreement is copyrighted and may only be modified in the following manner. The Agreement Steward reserves the right to publish new versions (including revisions) of this Agreement from time to time. No one other than the Agreement Steward has the right to modify this Agreement. IBM is the initial Agreement Steward. IBM may assign the responsibility to serve as the Agreement Steward to a suitable separate entity. Each new version of the Agreement will be given a distinguishing version number. The Program (including Contributions) may always be distributed subject to the version of the Agreement under which it was received. In addition, after a new version of the Agreement is published, Contributor may elect to distribute the Program (including its Contributions) under the new version. Except as expressly stated in Sections 2(a) and 2(b) above, Recipient receives no rights or licenses to the intellectual property of any Contributor under this Agreement, whether expressly, by implication, estoppel or otherwise. All rights in the Program not expressly granted under this Agreement are reserved.

This Agreement is governed by the laws of the State of New York and the intellectual property laws of the United States of America. No party to this Agreement will bring a legal action under this Agreement more than one year after the cause of action arose. Each party waives its rights to a jury trial in any resulting litigation.

License for Use of "Intel® MPI Benchmarks" Name and Trademark

In addition to the provisions of the Common Public License as included in the Intel® MPI Benchmarks distribution, Intel grants the recipient the right to use the name and trademark "Intel® MPI Benchmarks" in relation to disclosures or publications of results, provided that bespoke results were obtained by running the benchmarks generated from the original, unchanged source code as distributed by Intel.

Under no circumstances shall the recipient be permitted to use the name and trademark "Intel® MPI Benchmarks" in relation to results obtained by running benchmarks generated from source code that is different from the original source code as distributed by Intel, regardless of whether the differences are caused by modifying the existing benchmark components or by adding new components.

Visit the Intel MPI Benchmarks GitHub repository to download the benchmarks.

For more complete information about compiler optimizations, see our Optimization Notice.


Hi Gergana,

Hi Gergana,

I have a couple of quick questions.

Under the section titled "Running the benchmarks", the first comment under that section it mentions that P=1.  Was that intended, or am I misinterpreting that statement? Obviously you don't mean we should run the benchmark with 1 MPI rank.

IMB-NBC is only measuring non-blocking collectives (of course as the name suggests). Do you have a benchmark that for the measure communication overlap with just non-blocking send and receive routines?

Is it necessary to set MPICH_ASYNC_PROGRESS=1 to get asynchronous message progress for the NBC benchmark?

Is it necessary to set this environment variable for non blocking send/receive routines to get maximum overlap?



CRZFRThe data-check compile

The data-check compile-time option seems poorly debugged.

To reproduce:

1. Compile IMB-MPI1 with data-check enabled (-DCHECK)

2. Create a msg_lengths file (for L in `seq 0 100`; do echo $L >> msg_len.txt; done)

3. Run with your favorite MPI implementation using two processes, the simples possible way, with the following arguments to IMB-MPI1: 

   -msglen msg_len.txt -iter 1 Exchange

and terrible things happens.

For example, with Open MPI and the command line:

mpirun -np 2 --mca btl self,sm ./IMB-MPI1 -msglen msg_len.txt -iter 1 Exchange

I get:

mpirun noticed that process rank 1 with PID 17473 on node x.y.z  exited on signal 11 (Segmentation fault).



The Integer overflow bug has

The Integer overflow bug has been fixed in the latest IMB 4.0.

Rashawn, I would recommend you post your question to the Intel Clusters and HPC Technology forum:  That's a better location for support questions.  The first thing I would check is if OpenMPI 1.8.1 supports the new one-sided MPI-3 routines (implemented in IMB-RMA).


I have built IMB 4.0 with GCC

I have built IMB 4.0 with GCC 4.4.7 and OpenMPI 1.8.1 on a Centos 6.4 Linux machine.  I have been testing the benchmark suite on this machine, running only two MPI processes.  All the benchmarks run, but I encounter a segmentation fault in the aggregate mode of Get_accumulate in IMB-RMA.  The text of the segmentation fault error is:

[gino:00612] Failing at address: (nil)
[gino:00612] [ 0] /lib64/[0x3ad0c0f710]
[gino:00612] [ 1] /usr/lib64/openmpi-1.8.1/lib/openmpi/[0x7f0065cdb599]
[gino:00612] [ 2] /usr/lib64/openmpi-1.8.1/lib/openmpi/[0x7f0065cdbc90]
[gino:00612] [ 3] /usr/lib64/openmpi-1.8.1/lib/openmpi/[0x7f00667239d1]
[gino:00612] [ 4] /usr/lib64/openmpi-1.8.1/lib/openmpi/[0x7f0066725362]
[gino:00612] [ 5] /usr/lib64/openmpi-1.8.1/lib/openmpi/[0x7f0066d53c66]
[gino:00612] [ 6] /usr/lib64/openmpi-1.8.1/lib/[0x372c2283da]
[gino:00612] [ 7] /usr/lib64/openmpi-1.8.1/lib/[0x372ca4039d]
[gino:00612] [ 8] /usr/lib64/openmpi-1.8.1/lib/openmpi/[0x7f006568ee36]
[gino:00612] [ 9] /usr/lib64/openmpi-1.8.1/lib/openmpi/[0x7f00656988d0]
[gino:00612] [10] /usr/lib64/openmpi-1.8.1/lib/[0x372ca52742]
[gino:00612] [11] IMB-RMA[0x40dd6d]
[gino:00612] [12] IMB-RMA[0x4059d3]
[gino:00612] [13] IMB-RMA[0x4023b0]
[gino:00612] [14] /lib64/[0x3ad041ed1d]
[gino:00612] [15] IMB-RMA[0x401ed9]

I have added /usr/lib64/openmpi-1.8.1/lib and /usr/lib64/openmpi-1.8.1/lib/openmpi paths to my LD_LIBRARY_PATH environment variable.

Has anyone else encountered an error like this?  And how did you resolve it?

Thank you,

Rashawn K.


Hey Mike,

Hey Mike,

I don't have access to an Ubuntu machine but I just tested this on a Windows 8 machine and the unzip worked fine.  I was using a local copy of WinZip rather than pkunzip, which is what you have.  If you have a link of where I can download the pkunzip software, let me know and I'll give that a try.


Hi guys,

Hi guys,

you have an integer overflow bug in IMB for buffers over 2GB, in IMB_alloc_buf
for example in the code:

s_len = (size_t) init_size;

r_len = (size_t) c_info->num_procs*init_size;

c_info->num_procs and init_size are both ints. therefore the multiplication is 32 bit.
This is because the * operator has precedence over type-casting operator.
you wanted to do: r_len = c_info->num_procs*(size_t)init_size;