Network attached storage architecture
Communications of the ACM
Algorithmic transformations in the implementation of K- means clustering on reconfigurable hardware
FPGA '01 Proceedings of the 2001 ACM/SIGDA ninth international symposium on Field programmable gate arrays
Hyperspectral Images Clustering on Reconfigurable Hardware Using the K-Means Algorithm
SBCCI '03 Proceedings of the 16th symposium on Integrated circuits and systems design
Enabling active storage on parallel I/O software stacks
MSST '10 Proceedings of the 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)
| Hi-index | 0.00 |
High performance computing systems are often inhibited by the performance of their storage systems and their ability to deliver data. Active Storage Networks (ASN) provide an opportunity to optimize storage system and computational performance by offloading computation to the network switch. An ASN is based around an intelligent network switch that allows data processing to occur on data as it flows through the storage area network from storage nodes to client nodes. In this paper, we demonstrate an ASN used to accelerate K-means clustering. The K -means data clustering algorithm is a compute intensive scientific data processing algorithm. It is an iterative algorithm that groups a large set of multidimensional data points in to k distinct clusters. We investigate functional and data parallelism techniques as applied to the K-means clustering problem and show that the in-network processing of an ASN greatly improves performance.