The Ralph Regula School of Computational Science at the Ohio Supercomputer Center is a statewide virtual school focused on the exciting new area of computational science -- the use of computer modeling and simulation to solve complex business, technical and academic research problems.
Conquering the OSC Batch Environment
“Why Must I Get in Line? I Want to Run Now!”
Q-Chem is a general purpose ab initio electronic structure program. Its latest version emphasizes Self-Consistent Field, especially Density Functional Theory, post Hartree-Fock, and innovative algorithms for fast performance and reduced scaling calculations.
Boost is a set of C++ libraries that provide helpful data structures and numerous support functions in a wide range of aspects of programming, such as, image processing, gpu programming, concurrent programming, along with many algorithms. Boost is portable and performs well on a wide variety of platforms.
The July 2014 HPC Tech Talk (Tuesday, July 22nd from 4-5PM) will provide a talk about OSC Roadmap, which includes OSC business model and service catalog, "Condo" pilot project, Ruby cluster, and FY15 capital budget. To get the WebEX information and add a calendar entry, go here. Slides are available below.
The Ruby cluster is composed of both standard Intel Xeon CPUs as well as new Xeon Phi coprocessors. Special considerations must be taken both when compiling for and running software on the Phi coprocessors. This guide provides general information on the Phi coprocessors and breaks down the different types of programming models available for them. For detailed information on compiling software for our Phis, please refer to our Phi Compiling Guide.
This document was created to guide users through the compiling and execution of programs for Ruby's Phi coprocessors. It is not intended to help determine which of the Phi usage models to use. No special actions are needed for programs running exclusively on the host For more general information on Ruby and its Phi coprocessors see our Ruby FAQ page. Only Fortran, C, and C++ code can be compiled to run on the Phi coprocessors. Code to be run on Ruby or the Xeon Phi coprocessors should be compiled on Ruby.
The Ruby login nodes do not have Phi coprocessors. To get access to to a Phi coprocessor you will need to submit a job requesting a Phi coprocessor . For debugging and short interactive work you can submit a job to the debug queue which has Phi equiped nodes.
June 5th, 2014
10:00 a.m.: Coffee and Tea (BALE Conference)
10:15 a.m.: Committee Meetings
Hardware and Operations (BALE Conference)