| Abstract: |
|
The principal focus areas for system software on Blue Gene/Q include ultra-scalability, high reliability, and delivering the full performance capability of the hardware to applications. The Blue Gene/Q system software has achieved these goals while adding functionality and flexibility over what was offered in previous versions of Blue Gene. While part of the software stack was improved with innovative evolutionary progress, such as unified sub-blocks and the ability to overcommit hardware threads, other areas, such as transactional memory and speculative execution, represent a revolutionary step forward. In this paper, we describe the overall software architecture for Blue Gene/Q. We then describe each of the main components of the software stack. In each area, we focus on the major enhancements introduced in the Blue Gene/Q system software stack. |
|
