Download List

Project Description

mpiBLAST is an MPI based parallel implementation
of NCBI BLAST. It consists of a pair of programs
that replace formatdb and blastall with versions
that execute BLAST jobs in parallel on a cluster
of computers with MPI installed. There are two
primary advantages to using mpiBLAST versus
traditional BLAST. First, mpiBLAST splits the
database across each node in the cluster. Because
each node's segment of the database is smaller it
can usually reside in the buffer-cache, yielding a
significant speedup due to the elimination of disk
I/O. Second, it allows BLAST users to take
advantage of efficient, low-cost Beowulf clusters
because interprocessor communication demands are
low. mpiBLAST achieves super-linear speedup in
situations where the database is too large to fit
into RAM, and near linear speedup in other
situations. It does not require a dedicated cluster.

System Requirements

System requirement is not defined
Information regarding Project Releases and Project Resources. Note that the information here is a quote from Freecode.com page, and the downloads themselves may not be hosted on OSDN.

2008-04-03 05:14
1.5.0-PIO

Assorted minor bugfixes and cleanups were done.
Tags: Minor bugfixes

2007-12-19 20:02
1.5.0-beta1

Assorted enhancements and bugfixes. Updated dependencies on the NCBI toolkit.
Tags: Minor feature enhancements

2007-06-26 23:36
1.4.0-pio

This release adds parallel I/O.
Tags: Minor feature enhancements

2005-07-11 20:54
1.4.0

This release contains several critical enhancements to mpiBLAST's performance, scalability, and stability. It has a 305x speedup in searching the NT database with 128 worker CPUs. The previous fastest release gives only 180x speedup on the same data set. Other improvements include result ordering that matches NCBI's blastall, and a variety of bugfixes to features like database updating and database removal. Support for MPICH 2 has been added. A new program called mpiblast_cleanup removes mpiblast-related data from each node's filesystem.
Tags: Major feature enhancements

2004-12-08 22:57
1.3.0

This release improves reliability, performance, and accuracy. Streaming results output reduces memory requirements for large query sets. Database pipelining speeds up data distribution by limiting contention for a shared filesystem. This release calculates exact E-value statistics using both the effective query and effective database lengths.
Tags: Major feature enhancements

Project Resources