Overview of the Blue Gene/L system architecture
A Gara, MA Blumrich, D Chen, GLT Chiu… - IBM Journal of …, 2005 - ieeexplore.ieee.org
The Blue Gene®/L computer is a massively parallel supercomputer based on IBM system-on-
a-chip technology. It is designed to scale to 65,536 dual-processor nodes, with a peak …
a-chip technology. It is designed to scale to 65,536 dual-processor nodes, with a peak …
Computer architecture: Challenges and opportunities for the next decade
T Agerwala, S Chatterjee - IEEE Micro, 2005 - ieeexplore.ieee.org
Computer architecture forms the bridge between application needs and the capabilities of
the underlying technologies. As application demands change and technologies cross …
the underlying technologies. As application demands change and technologies cross …
A performance model of the parallel ocean program
DJ Kerbyson, PW Jones - The International Journal of High …, 2005 - journals.sagepub.com
In this paper we describe a performance model of the Parallel Ocean Program (POP). In
particular, the latest version of POP (v2. 0) is considered, which has similarities and …
particular, the latest version of POP (v2. 0) is considered, which has similarities and …
Exploiting geometric partitioning in task map** for parallel computers
We present a new method for map** applications' MPI tasks to cores of a parallel
computer such that communication and execution time are reduced. We consider the case of …
computer such that communication and execution time are reduced. We consider the case of …
Map** applications with collectives over sub-communicators on torus networks
The placement of tasks in a parallel application on specific nodes of a supercomputer can
significantly impact performance. Traditionally, this task map** has focused on reducing …
significantly impact performance. Traditionally, this task map** has focused on reducing …
Fast and high quality topology-aware task map**
Considering the large number of processors and the size of the interconnection networks on
exactable-capable supercomputers, map** concurrently executable and communicating …
exactable-capable supercomputers, map** concurrently executable and communicating …
Designing a highly-scalable operating system: The Blue Gene/L story
J Moreira, M Brutman, J Castanos… - Proceedings of the …, 2006 - dl.acm.org
Blue Gene/L is currently the world's fastest and most scalable supercomputer. It has
demonstrated essentially linear scaling all the way to 131,072 processors in several …
demonstrated essentially linear scaling all the way to 131,072 processors in several …
Using the TOP500 to trace and project technology and architecture trends
PM Kogge, TJ Dysart - Proceedings of 2011 International Conference for …, 2011 - dl.acm.org
The TOP500 is a treasure trove of information on the leading edge of high performance
computing. It was used in the 2008 DARPA Exascale technology report to isolate out the …
computing. It was used in the 2008 DARPA Exascale technology report to isolate out the …
[HTML][HTML] The importance of being low power in high performance computing
W Feng - Cyberinfrastructure Technology Watch Quarterly …, 2005 - icl.utk.edu
Conclusion Power consumption has become an increasingly important issue in HPC.
Ignoring power consumption as a design constraint results in a HPC system with high …
Ignoring power consumption as a design constraint results in a HPC system with high …
[BOOK][B] Automating topology aware map** for supercomputers
A Bhatele - 2010 - search.proquest.com
Petascale machines with hundreds of thousands of cores are being built. These machines
have varying interconnect topologies and large network diameters. Computation is cheap …
have varying interconnect topologies and large network diameters. Computation is cheap …