HPCC Systems Community Edition For Linux

HPCC (High Performance Computing Cluster) Systems Community Edition is an open source, fast, scalable and simple massive parallel-processing computing platform for UNIX and Linux systems. HPCC is designed to solve large amounts of data problems, across disparate data sources. It a few seconds, the application is able to analyze and manipulate big data problems.

The High Performance Computing Cluster (HPCC) software is comprised of the several components, among which we can mention Thor (the Data Refinery Cluster), Roxie (the Query Cluster), ECL (Enterprise Control Language), ECL IDE (a modern IDE), and ESP (Enterprise Services Platform).

Key features of Thor include single-threaded, distributed file system, distributed parallel processing, support for scaling from 1 to 1000 nodes, state-of-the-art parallel processing programming language (ECL), and optimizations for Transformation, Linking, Extraction, Indexing, Loading, and Sorting.

While Roxie is multi-threaded and optimized for concurrent query processing, the ECL component is compiled into optimized C++, can be easily extended through C++ libraries, it is dataflow and non-procedural oriented, reusable, modular, and has an extensible syntax. Last but not least, ESP supports XML, SOAP, REST, HTTP, SAML, and several security standards.

To build the Community Edition of HPCC Systems on a GNU/Linux operating system, you must download the sources, save the archive on your Home directory, and unpack it. Open the extracted directory and create a folder called build. Open a Terminal application, and navigate to the location of the build folder (e.g. cd /home/softpedia/HPCC-Platform-community_5.0.0-3/build/).

Run the ‘cmake ~/HPCC-Platform-community_5.0.0-3’ command to build the make file. Then run the ‘make’ command to compile the program and build the executables, which will be generated in the /bin and /libs folders, a process that will take a few minutes. To create .deb or .rpm packages, run the ‘make package’ command.