Massively parallel supercomputers of the “Blue Gene family” by IBM are nowadays among the most powerful and efficient (i.e. “environmentally sustainable”). In summer 2012 the newest member of Blue Gene family was installed at Cineca. This is Blue Gene/Q.
The present course intends to enable/support the scientific community to efficiently exploit the Blue Gene/Q system and it is aimed primarily at people using it for first time. More precisely, starting from a general overview concerning (massively parallel) supercomputers and HPC trends, the course aims at providing a full description of the Fermi configuration at Cineca, with special emphasis on main crucial aspects for users and application developers. For instance, details about compilation, debugging and optimization procedures will be provided, together with an overview of the available libraries, tools and applications currently available on the system. Examples of submission jobs will be discussed, together with scheduler (LoadLeveler) commands and queue definitions. A “practice session” is also planned.
Target Audience:
Users and developers on the FERMI Tier -0 system
Topics:
Overview of Blue Gene/Q architecture and software (hardware components, network and partitioning, type of nodes and software stack)
Developing applications for Blue Gene/Q (porting, debugging, spotting possible bottlenecks)
Running and monitoring jobs on Blue Gene/Q (the runjob command, environment variables, job script examples, LL commands, Available Debugging and Profiling Tools)
Software performance and scalability on Blue Gene/Q
Prerequisites:
Basic knowledge of linux/UNIX and experience on parallel programming.
The present course intends to enable/support the scientific community to efficiently exploit the Blue Gene/Q system and it is aimed primarily at people using it for first time. More precisely, starting from a general overview concerning (massively parallel) supercomputers and HPC trends, the course aims at providing a full description of the Fermi configuration at Cineca, with special emphasis on main crucial aspects for users and application developers. For instance, details about compilation, debugging and optimization procedures will be provided, together with an overview of the available libraries, tools and applications currently available on the system. Examples of submission jobs will be discussed, together with scheduler (LoadLeveler) commands and queue definitions. A “practice session” is also planned.
Target Audience:
Users and developers on the FERMI Tier -0 system
Topics:
Overview of Blue Gene/Q architecture and software (hardware components, network and partitioning, type of nodes and software stack)
Developing applications for Blue Gene/Q (porting, debugging, spotting possible bottlenecks)
Running and monitoring jobs on Blue Gene/Q (the runjob command, environment variables, job script examples, LL commands, Available Debugging and Profiling Tools)
Software performance and scalability on Blue Gene/Q
Prerequisites:
Basic knowledge of linux/UNIX and experience on parallel programming.