Free mpi implementation software for linux

Procinfo NG is a ground-up rewrite of the procinfo program. Procinfo NGs goal is to make the code more readable (and reusable) and to restore broken functionality of the original program.
The original program was written for Linux 1.0, and updated through 2.2. This version is for 2.6.
Enhancements:
- Updates were made to match what some Linux distributions have done to procinfo-18.
- Support for MSI and XEN interrupts were added.
- Some non-x86 architectures are handled.
- Assorted bugs and 80-character console nonsense were fixed.

Suffix tree implementation library is a C library, an implementation of the suffix trees algorithm to store/retrieve key/data pairs.
The main advantages are a linear indexing time, little memory usage, and very fast retrieving.
It has been developped on FreeBSD/gcc but should be fairly portable.
The source code "testsfx.c" show an example of how to use the library both for inserting, retrieving, and deleting data. There arent many functions and comments should be enough to give you an idea of how to use the library. (read the header of the source file)
You should edit sfxdisk.h to suit your needs: you can change the alphabet size and the offset type. It should be OK to use "long long" 64 bits ints instead of long, in fact I tested it succesfully but havent gone to the point of filling more than 2 GB of data (needless to say you need a 64 bits filesystem).
Two "tools" come with the library (new with version 1.2): dumpsfx and loadsfx. dumpsfx is used to dump the database: dumpsfx [-s separator] if you want to output the result as readable text or dumpsfx < file.sfx > -h to output it for reloading with loadsfx.
dumpsfx outputs on stdout and loadsfx reads from stdin. loadsfx < suffix tree file to create > < dumped_file
Enhancements:
- removed an useless offset incrementation in STwritenode

Objective Modula-2 programming language is a hybrid between Smalltalk and Modula-2 based on the object model and runtime of Objective-C.
The design is an example how native Cocoa/GNUstep support can be added to static imperative programming languages without implementing a bridge.
Objective Modula-2s scope encompasses the design of the Objective Modula-2 programming language and the implementation of a compiler to implement it. The initial compiler will generate Objective-C source code.
Enhancements:
- This code is used to verify ideas and concepts which come up in the course of defining the language.
- It is in an early stage, incomplete and subject to frequent changes.

MPICH (MVAPICH2) software delivers best performance, scalability and fault tolerance for high-end computing systems and servers using InfiniBand, iWARP and other RDMA-enabled interconnect networking technologies. This software is being used by more than 540 organizations world-wide (Current Users) to extract the potential of these emerging networking technologies for modern systems. This software is also being distributed by many InfiniBand, iWARP and RDMA-enabled interconnect vendors in their software distributions. MVAPICH and MVAPICH2 are also available with Open Fabrics Enterprise Distribution (OFED) stack.
MVAPICH software is powering several supercomputers in the TOP 500 list. Examples (from the June 07 ranking) include:
- 15th, 5848-core Dell PowerEdge Intel EM64T 2.66 GHz cluster at Texas Advanced Computing Center/Univ. of Texas
- 19th, 9216-core Appro Quad Opteron dual Core 2.4 GHz at Lawrence Livermore National Laboratory
- 71st, 2200-processors Apple Xserve 2.3 GHz cluster at Virginia Tech
Enhancements:
- New message coalesing, hot-spot avoidance, application-initiated systems-level checkpointing, APM support, multi-rail support for iWARP, on-demand connection management for iWARP and uDAPL (including Solaris), RDMA read, and blocking support.
- The software was also updated to MPICH2 1.0.5p4.

MPICH2 is a robust and flexible implementation of the MPI (Message Passing Interface). Message Passing Interface is often used with parallel or distributed computing projects.

MPICH2 is a multi-platform, configurable system (development, execution, libraries, etc) for MPI. It can acheive parallelism using networked machines or using mulitasking on a single machine.

Parallel MPI BZIP2 is a parallel implementation of the bzip2 block-sorting file compressor that uses MPI and achieves significant speedup on cluster machines.

The output of this version is fully compatible with bzip2 v1.0.2 or newer (ie: anything compressed with mpibzip2 can be decompressed with bzip2). MPIBZIP2 should work on any system that has a pthreads compatible C++ compiler (such as gcc). It has been tested on: Linux and Solaris.

NOTE: If you are looking for a parallel BZIP2 that works on multi-processor/muti-core/SMP machines, you should check out PBZIP2 which was designed for a multi-threaded shared-memory architecture.

Usage:

Run mpibzip2 for the help listing.
==================================================================
Usage: mpibzip2 [-1 .. -9] [-b#cdfktvV] < filename > < filename2 > < filenameN >

-b#: where # is the file block size in 100k (default 9 = 900k)
-c : output to standard out (stdout)
-d : decompress file
-f : force, overwrite existing output file
-k : keep input file, dont delete
-t : test compressed file integrity
-v : verbose mode
-V : display version info for mpibzip2 then exit
-1 .. -9 : set BWT block size to 100k .. 900k (default 900k)

Example: mpibzip2 -b15k myfile.tar
Example: mpibzip2 -v -5 myfile.tar second*.txt
Example: mpibzip2 -d myfile.tar.bz2

GridMPI is a new open-source free-software implementation of the standard MPI (Message Passing Interface) library designed for the Grid. GridMPI project enables unmodified applications to run on cluster computers distributed across the Grid environment.
GridMPI team found that it is feasible to connect cluster computers and to run ordinary scientific applications in distance upto 500 miles. Simple experiment has shown that most MPI benchmarks scale fine upto 20 millisecond round-trip latency which corresponds to about 500 miles in distance, when the clusters are connected by fast 1 to 10 Gbps networks. 500 miles covers the major cities between Tokyo--Osaka in Japan.
Thus, applications which are too large to run on a local cluster should run on multiple clusters in the Grid environment with acceptable performance. However, it is only feasible when using an efficient MPI implementation [1]. Existing implementations are not efficient enough mainly because of the two reasons: their focus on security features and TCP performance problems.
GridMPI skips security layers assuming dedicated secure links. The institutes housing large clusters tend to have their own networks to connect to other institutes in most cases. GridMPI so focuses on the performance on TCP. Since existing implementations are in most cases designed for MPP machines and recently clusters with special hardware, their performance on TCP with Ethernet is not optimal.
Also TCP performance itself is not optimal for the work load of the MPI traffic. In addition, support for heterogeneous combinations of computers of the existing MPI implementations is not satisfactory. Thus, GridMPI is designed and implemented from the scratch. GridMPI is carefully coded and tested with heterogeneity in mind.
Main features:
- Full conformance to the standard: GridMPI passes 100% of the functional tests of the large test suites from ANL and Intel (MPI-1.2 level).
- Full heterogeneity support: GridMPI is fully tested with combinations of processors of 32bit/64bit and big/little-endian.
- Primary support of TCP/IP and sockets: GridMPI is written from scratch and it is new and clean. It is efficient with sockets, and thus suitable for the Grid as well as ordinary Ethernet-based clusters.
- Cooperation with Grid job submission: GridMPI can be used with Globus, Unicore, tool from NAREGI project, etc.
- Checkpointing support: GridMPI supports checkpointing on Linux/IA32 platforms to restart long-running applications from failure.
- Vendor MPI support: GridMPI supports IBM-MPI, Fujitsu-Solaris-MPI, Intel-MPI, and any MPICH-based MPI for clusters with special communication hardware.
Enhancements:
- Minor bugfixes were made.

LAM/MPI is an implementation of the Message Passing Interface (MPI) parallel standard that is especially friendly to clusters. It includes a persistent runtime environment for parallel programs, support for all of MPI-1, and a good chunk of MPI-2, such as all of the dynamic functions, C++ bindings, one-way communication and MPI-IO.
LAM/MPI is now in a maintenance mode. Bug fixes and critical patches are still being applied, but little real "new" work is happening in LAM/MPI. This is a direct result of the LAM/MPI Team spending the vast majority of their time working on our next-generation MPI implementation -- Open MPI.
Although LAM is not going to go away any time soon (we certainly would not abondon our user base!) -- the web pages, user lists, and all the other resources will continue to be available indefinitely -- we would encourage all users to try migrating to Open MPI. Since its an MPI implementation, you should be able to simply recompile and re-link your applications to Open MPI -- they should "just work." Open MPI contains many features and performance enhancements that are not available in LAM/MPI.
Enhancements:
- Man page cleanups.
- Fixes for when tkill is not in the default location.
- A fix for hangs in 64-bit builds on Mac OS X systems.
- Localhost searches have changed to 127.0.0.0/8.
- Support for Fortran types MPI_REAL{4,8,16} for predefined floating point operations.
- A compile error in "ib" RPI, a problem with MPI_COMM_ACCEPT on Fedora Core 4, name clashes with FreeBSD symbols, Cygwin installation symlinks, an issue with hostfile comments, and Totalview shared object support on OS X have been fixed.
- The restart logic in the "self" CR module has been cleaned up.
- A lot of checkpoint/restart documentation has been added.