Debian Science Distributed Computing packages

The Modules package provides for the dynamic modification of a user's environment via modulefiles. Each modulefile contains the information needed to configure the shell for an application. Once the Modules package is initialized, the environment can be modified dynamically on a per-module basis using the module command which interprets modulefiles. Typically modulefiles instruct the module command to alter or set shell environment variables such as PATH, MANPATH, etc. modulefiles may be shared by many users on a system and users may have their own collection to supplement or replace the shared modulefiles. The modules environment is common on SGI/Crays and many workstation farms.

Grid Engine is software that facilitates "distributed resource management" (DRM). Far more than just simple load-balancing tools or batch scheduling mechanisms, DRM software typically provides the following key features across large sets of distributed resources:

• Policy based allocation of distributed resources (CPU time, software licenses, etc.)
• Batch queuing & scheduling
• Support diverse server hardware, OS and architectures
• Load balancing & remote job execution
• Detailed job accounting statistics
• Fine-grained user specifiable resources
• Suspend/resume/migrate jobs
• Tools for reporting Job/Host/Cluster status
• Job Arrays
• Integration & control of parallel jobs

This package contains the Grid Engine user utilities.

Grid Engine is software that facilitates "distributed resource management" (DRM). Far more than just simple load-balancing tools or batch scheduling mechanisms, DRM software typically provides the following key features across large sets of distributed resources:

• Policy based allocation of distributed resources (CPU time, software licenses, etc.)
• Batch queuing & scheduling
• Support diverse server hardware, OS and architectures
• Load balancing & remote job execution
• Detailed job accounting statistics
• Fine-grained user specifiable resources
• Suspend/resume/migrate jobs
• Tools for reporting Job/Host/Cluster status
• Job Arrays
• Integration & control of parallel jobs

This package contains the Grid Engine execution server.

Grid Engine is software that facilitates "distributed resource management" (DRM). Far more than just simple load-balancing tools or batch scheduling mechanisms, DRM software typically provides the following key features across large sets of distributed resources:

• Policy based allocation of distributed resources (CPU time, software licenses, etc.)
• Batch queuing & scheduling
• Support diverse server hardware, OS and architectures
• Load balancing & remote job execution
• Detailed job accounting statistics
• Fine-grained user specifiable resources
• Suspend/resume/migrate jobs
• Tools for reporting Job/Host/Cluster status
• Job Arrays
• Integration & control of parallel jobs

This package contains the Grid Engine master server.

Grid Engine is software that facilitates "distributed resource management" (DRM). Far more than just simple load-balancing tools or batch scheduling mechanisms, DRM software typically provides the following key features across large sets of distributed resources:

• Policy based allocation of distributed resources (CPU time, software licenses, etc.)
• Batch queuing & scheduling
• Support diverse server hardware, OS and architectures
• Load balancing & remote job execution
• Detailed job accounting statistics
• Fine-grained user specifiable resources
• Suspend/resume/migrate jobs
• Tools for reporting Job/Host/Cluster status
• Job Arrays
• Integration & control of parallel jobs

This package contains the graphical Grid Engine administration frontend.

This package aids upgrades of existing htcondor installations to the package name "condor". The package is empty and it can safely be removed.

IPython can be used as a replacement for the standard Python shell, or it can be used as a complete working environment for scientific computing (like Matlab or Mathematica) when paired with the standard Python scientific and numerical tools. It supports dynamic object introspections, numbered input/output prompts, a macro system, session logging, session restoring, complete system shell access, verbose and colored traceback reports, auto-parentheses, auto-quoting, and is embeddable in other Python programs.

This package contains the actual terminal shell for Python 3.

NorduGrid is a collaboration aiming at development, maintenance and support of the middleware, known as the Advanced Resource Connector (ARC).

This client package contains all the CLI tools that are needed to operate with x509 proxies, submit and manage jobs and handle data transfers.

Open MPI is a project combining technologies and resources from several other projects (FT-MPI, LA-MPI, LAM/MPI, and PACX-MPI) in order to build the best MPI library available. A completely new MPI-3.1 compliant implementation, Open MPI offers advantages for system and software vendors, application developers and computer science researchers.

Features:

• Full MPI-3.1 standards conformance
• Thread safety and concurrency
• Dynamic process spawning
• High performance on all platforms
• Reliable and fast job management
• Network and process fault tolerance
• Support network heterogeneity
• Single library supports all networks
• Run-time instrumentation
• Many job schedulers supported
• Internationalized error messages
• Component-based design, documented APIs

This package contains the Open MPI utility programs.

SCOOP (Scalable COncurrent Operations in Python) is a distributed task module allowing concurrent parallel programming on various environments, from heterogeneous grids to supercomputers.

This package contains the Python3 modules.

This is a collection of software that help users to share resources in a complex, heterogeneous, and unreliable computing environment. This includes:

• Chirp: A personal filesystem and I/O protocol that allows unprivileged users to share space securely, efficiently, and conveniently. When combined with Parrot, Chirp allows users to create custom wide-area distributed filesystems.
• Parrot: A transparent user-level virtual filesystem that allows any ordinary program to be attached to a remote storage device such as an FTP server or a Chirp server.
• Makeflow: A workflow system for parallel and distributed computing that uses a language very similar to Make.
• Work Queue: A system and API for building master-worker style programs that scale up to thousands of processors.
• All Pairs: A computational abstraction for running very large Cartesian products.
• Wavefront: A computational abstraction for running very large dynamic programming problems.
• The Fault Tolerant Shell: A high-level programming language that allows users to combine the ease of shell scripting, the power of distributed programming, and the precision of compiled languages. Basically, parallel programming and exception handling for scripts.

The High Performance Computing (HPC) Challenge benchmark runs a suite of 7 tests that measure the performance of CPU, memory and network for HPC clusters. Amongst others, it includes the High-Performance LINPACK (HPL) benchmark, used by the Top500 ranking (http://www.top500.org/).

MPI for Python (mpi4py) provides bindings of the Message Passing Interface (MPI) standard for the Python programming language, allowing any Python program to exploit multiple processors.

mpi4py is constructed on top of the MPI-1/MPI-2 specification and provides an object oriented interface which closely follows MPI-2 C++ bindings. It supports point-to-point (sends, receives) and collective (broadcasts, scatters, gathers) communications of any picklable Python object as well as optimized communications of Python object exposing the single-segment buffer interface (NumPy arrays, builtin bytes/string/array objects).

PSOM is a lightweight library to manage complex multi-stage data processing. A pipeline is a collection of jobs, i.e. Matlab or Octave code with a well identified set of options that are using files for inputs and outputs. To use PSOM, the only requirement is to generate a description of a pipeline in the form of a simple Matlab/Octave structure. PSOM then automatically offers the following services:

• Run jobs in parallel using multiple CPUs or within a distributed computing environment.
• Generate log files and keep track of the pipeline execution. These logs are detailed enough to fully reproduce the analysis.
• Handle job failures: successful completion of jobs is checked and failed jobs can be restarted.
• Handle updates of the pipeline: change options or add jobs and let PSOM figure out what to reprocess.