The dragonfly topology has been proposed as an efficient alternative to the fat tree. This talk presents a study of the blocking and scalability characteristics of the dragonfly, and compares this to the well-known fat tree topology.
In this video from the HPC Advisory Council Spain Conference 2013, Pedro J. Garcia presents: High-Performance Interconnection Networks on the Road to Exascale HPC: Challenges and Solutions. One of the challenges of that interconnect researchers face today is how to efficiently interconnect the huge number of processors expected to be present in future exascale systems. […]
This week Mellanox announced that its end-to-end, FDR 56Gb/s InfiniBand interconnect solutions provide industry-leading performance for compute-intensive applications running on the new Intel Xeon processor E5-2600 v2 product family. With up to 30 percent better performance, applications running on Ivy Bridge processors and Mellanox’s FDR 56Gb/s InfiniBand solutions do more, faster, thereby lowering product design […]
In this Chip Chat podcast, Victor Krutul from Intel discusses the company’s collaboration with Corning on the new MXC optical interconnect. The new technology is capable of 1.6 terabits per second at 300 meters, which will help enable rack and system disaggregation in the 21st century data center. Read the Full Story.