Skip to content
Andrew Tauferner edited this page Mar 22, 2017 · 18 revisions

What is mOS for HPC

mOS for HPC is an active research project at Intel that remains under development. These materials are being made available to interested parties to explore, to test drive, and to provide feedback through the mailing list. Consider the quality level to be pre-alpha and as-is. It is not intended to be used in production or for business critical uses. The required knowledge level of users is expected to be expert for Linux internals and for operating system principles. Support is limited by the development team's ability to respond through the mailing list. Please note that these are the only mechanisms for interaction with Intel on this project.

Platform requirements

The development platform for mOS v0.4 has been on Intel(R) Xeon Phi(TM) CPU 7250 processor with at least 64GiB of DRAM and 16GiB of MCDRAM and booted in SNC-4 cluster mode, Flat memory mode. Your mileage may vary on other platforms and configurations in terms of functionality and performance: If you use Intel (R) Xeon Phi(TM) CPU 7230 processors, then Quadrant cluster mode, Flat memory mode is recommended. Your mileage may vary on other cluster modes that have not been tested. Specifically, the development team has observed lower performance of mOS for HPC in cache modes, which is not necessarily attributed to hardware. Limited testing has been performed on Intel (R) Xeon (R) E7-88xx processors. Processors outside of the x86_64 architecture designation in Linux are unsupported – the kernel code will not configure and build. The Linux distribution used by the development team for building, installing, and testing mOS has been CentOS 7. Other distributions have had almost no testing, and may require that you adapt the build, install instructions to your environment. Unfortunately, the developers will not be able to assist in this work, but you can ask on the mailing list. mOS has been tested using Intel(R) Parallel Studio XE 2017 Update 1 for Linux*, which includes Intel(R) MPI Library for Linux* OS, Version 2017 Update 1 Build 20161016 (id: 16418). Additionally, some testing has been done using MPICH as the MPI runtime, using Intel compilers as the underlying compiler and runtime. Almost no testing using other compilers (e.g. gcc) or MPI runtimes (e.g. mvapich or OpenMPI) has been done. The development team plans to track the Intel(R) Software Tools 2018 Beta programs as they become available.

Where to get code

The mOS for HPC source can be checked out from GitHub at https://github.com/01org/mOS. Please see the mOS for HPC v0.4 Administrator's Guide for further instructions.

Where to report issues or ask questions

Register for the mOS for HPC mailing list at https://lists.01.org/mailman/listinfo/mos-devel. Submit feedback and follow discussions through this list. Please note that this is the only mechanism for interactions with Intel on this project.