MPICH2 Home Page
Information for Developers
Bug Reports


MPICH2 is an implementation of the Message-Passing Interface (MPI). The goals of MPICH2 are to provide an MPI implementation for important platforms, including clusters, SMPs, and massively parallel processors. It also provides a vehicle for MPI implementation research and for developing new and better parallel programming environments.

Download MPICH2

The current version of MPICH2 is 1.0, released on November 9, 2004. MPICH2 is distributed as source (with an open-source, freely available license). It has been extensively tested on several platforms, including Linux (on IA32 and IA64), and Windows. See the RELEASE_NOTES file in the distribution for more details. If you have any questions, comments, or difficulties, please contact us at

MPICH2 is provided in source form as a single, gzip'ed tar file. This is a unified source distribution, and may be used for both UNIX and Microsoft Windows. Binary distributions for Microsoft Windows are also provided.

All (source) mpich2-1.0.tar.gz http ftp 12.2MB 1.0
Win32 IA32 mpich2-1.0-1-win32-ia32.msi http ftp 1.7MB 1.0
Win64 AMD64 http ftp 1.8MB 1.0
Win64 IA64 http ftp 3.3MB 1.0

In addition to the distributions provided by the MPICH2 Development Team, distributions of MPICH2 for other operating systems and packing environments are available below. Many thanks go out to those individuals who have graciously contributed their time and energy to create these distributions.

PlatformAuthor(s)Email AddressDownloadSizeVersion
Debian Zach Lowry mpich2_1.0-1_i386.deb http ftp 1.6MB 1.0


User's Guide N/A N/A http ftp
Installer's Guide N/A N/A http ftp

Information for Developers

Information for developers, including the state of the current development version and information on the tools and procedures used to manage MPICH2 development.

Related Projects

Two goals of MPICH2 are to enable research into MPI implementations and to encourage the development of MPI implementations for other platforms. Some of these projects are listed below.
Cray Red Storm
IBM BlueGene/Light
OSU InfiniBand
MVAPICH2 is a high performance implementation of MPICH2 for the emerging InfiniBand interconnect standard. Current implementation is based on support at the RDMA channel interface level. This implementation is developed at the Ohio State University.
Chemnitz InfiniBand
MPICH2-CH3 Device for InfiniBand is based on the Verbs interface, currently using the Mellanox Verbs implementation VAPI. This implementation is developed at Technische Universitšt Chemnitz.
ATOLL is a high-performance interconnect and has an MPI based on MPICH2.
MCS Division Argonne National Laboratory University of Chicago