Adaptive Bubble Router: A Design to Improve Performance in Torus Networks
ICPP '99 Proceedings of the 1999 International Conference on Parallel Processing
The BlackWidow High-Radix Clos Network
Proceedings of the 33rd annual international symposium on Computer Architecture
Overview of the IBM Blue Gene/P project
IBM Journal of Research and Development
Technology-Driven, Highly-Scalable Dragonfly Topology
ISCA '08 Proceedings of the 35th Annual International Symposium on Computer Architecture
Optimization of All-to-All Communication on the Blue Gene/L Supercomputer
ICPP '08 Proceedings of the 2008 37th International Conference on Parallel Processing
HPCC RandomAccess benchmark for next generation supercomputers
IPDPS '09 Proceedings of the 2009 IEEE International Symposium on Parallel&Distributed Processing
Overview of the Blue Gene/L system architecture
IBM Journal of Research and Development
The PERCS High-Performance Interconnect
HOTI '10 Proceedings of the 2010 18th IEEE Symposium on High Performance Interconnects
The Gemini System Interconnect
HOTI '10 Proceedings of the 2010 18th IEEE Symposium on High Performance Interconnects
The IBM Blue Gene/Q interconnection network and message unit
Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis
The IBM Blue Gene/Q Compute Chip
IEEE Micro
PAMI: A Parallel Active Message Interface for the Blue Gene/Q Supercomputer
IPDPS '12 Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium
IEEE Micro
The IBM Blue Gene/Q Interconnection Fabric
IEEE Micro
Warp speed: executing time warp on 1,966,080 cores
Proceedings of the 2013 ACM SIGSIM conference on Principles of advanced discrete simulation
LEF: long edge first routing for two-dimensional mesh network on chip
Proceedings of the Sixth International Workshop on Network on Chip Architectures
| Hi-index | 0.00 |
This paper explores the performance and optimization of the IBM Blue Gene/Q (BG/Q) five dimensional torus network on up to 16K nodes. The BG/Q hardware supports multiple dynamic routing algorithms and different traffic patterns may require different algorithms to achieve best performance. Between 85% to 95% of peak network performance is achieved for all-to-all traffic, while over 85% of peak is obtained for challenging bisection pairings. A new software-controlled algorithm is developed for bisection traffic that selects which hardware algorithm to employ and achieves better performance than any individual hardware algorithm. The benefit of dynamic routing is shown for a highly non-uniform "transpose" traffic pattern. To evaluate memory and network performance, the HPCC Random Access benchmark was tuned for BG/Q and achieved 858 Giga Updates per Second (GUPS) on 16K nodes. To further accelerate message processing, the message libraries on BG/Q enable the offloading of messaging overhead onto dedicated communication threads. Several applications, including Algebraic Multigrid (AMG), exhibit from 3 to 20% gain using communication threads.