The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
High Performance Computing(HPC) applications are highly optimized to maximize allocated resources for the job such as compute resources, memory and storage. Optimal performance for MPI applications requires the best possible affinity across all the allocated resources. Typically, setting process affinity to compute resources is well defined, i.e MPI processes on a compute node have processor affinity...
This paper presents an evaluation and comparison of three topologies that are popular for building interconnection networks in large-scale supercomputers: torus, fat-tree, and dragonfly. To perform this evaluation, we propose a comprehensive methodology and present a scalable packet-level network simulator, TraceR. Our methodology includes design of prototype systems that are being evaluated, use...
End-to-end network latency has become an important issue for parallel application on large-scale high performance computing (HPC) systems. It has been reported that randomly-connected inter-switch networks can lower the end-to-end network latency. The trade-off is a large amount of routing information. For irregular networks, minimal routing is achieved by using routing tables for all destinations...
In this paper, we investigate the problem of providing highly available, decentralized, dynamic path selection in high performance computing networking. We look at a use case for dynamic path selection that better utilizes bandwidth available in the network. The network architecture we propose is a partial mesh grid whereby each host is directly connected to four forwarding devices. We propose an...
Two prime network interconnection topology used today in High Performance computing (HPC) are the fat tree and the torus topology. But due to the various advantages of torus network over fat tree, currently many HPC networks using fat tree are turning to the torus topology. In fat tree topology the switches have high end functionalities. Suppose a packet is traversing from the source to destination...
High performance computing (HPC) means the aggregation of computational power to increase the ability of processing large problems in science, engineering, and business. HPC on the cloud allows performing on demand HPC tasks by high performance clusters in a cloud environment. The connection structure of the nodes in HPC clusters should provide fast internode communication. It is important that scalability...
Distributed routing methods with small routing tables are scalable design on irregular networks for large-scale High Performance Computing (HPC) systems. Recently proposed compact routing methods, however, do not guarantee deadlock-freedom. Cyclic channel dependencies on arbitrary routing are typically removed with multiple Virtual Channels (VCs). However, challenges still remain to provide good trade-offs...
In exascale platforms, faults are likely to occur more and more frequently due to the huge number of components. To handle them, the BXI fabric management uses a generic architecture that specifies two distinct modes of operations: offline mode computes, validates and uploads nominal routing tables, while online mode reacts at runtime to failures and recoveries by computing small patches and by uploading...
With each technology improvement, parallel systems get larger, and the impact of interconnection networks becomes more prominent. Random topologies and their variants received more and more attention lately due to their low diameter, low average shortest path length and high scalability. However, existing supercomputers still prefer torus and fat-tree topologies, because a number of existing parallel...
With each technology improvement, parallel systems get larger, and the impact of interconnection networks becomes more prominent. Random topologies and their variants received more and more attention lately due to their low diameter, low average shortest path length and high scalability. However, existing supercomputers still prefer torus and fat-tree topologies, because a number of existing parallel...
The most demanding tenants of shared clouds require complete isolation from their neighbors, in order to guarantee that their application performance is not affected by other tenants. Unfortunately, while shared clouds can offer an option whereby tenants obtain dedicated servers, they do not offer any network provisioning service, which would shield these tenants from network interference. In this...
In this paper, we present research work related to processing and analysis of big trajectory and Twitter data streams using Apache Storm framework. We present the TrafficStorm application implemented as Storm topology, and describe its implementation on a cluster of commodity computers. TrafficStorm performs processing of big trajectory data streams related to users moving over a street network, as...
BXI, Bull eXascale Interconnect, is the new inter-connection network developed by Atos for High Performance Computing. It has been designed to meet the requirements of exascale supercomputers. At such scale, faults have to be expected and dealt with transparently so that applications remain unaffected by them. BXI features various mechanisms for this purpose, one of which is the BXI routing component...
HPC systems are growing in number of connected endnodes, making the network a main issue in their design. In order to interconnect large systems, dragonfly topologies have become very popular in the latest years as they achieve high scalability by exploiting high-radix switches. However, dragonfly high performance may drop severely due to the Head-of-Line (HoL) blocking effect derived from congestion...
The Intel® Omni-Path Architecture (Intel® OPA) is designed to enable a broad class of computations requiring scalable, tightly coupled CPU, memory, and storage resources. Integration between devices in the Intel® OPA family and Intel® CPUs enable improvements in system level packaging and network efficiency. When coupled with the new user-focused open standard APIs developed by the OpenFabrics Alliance...
Studies have shown that understanding of interprocess communication patterns is an enabler to effective analysis of high performance computing (HPC) applications. In previous work, we presented an algorithm for recovering communication patterns from traces of HPC systems. The algorithm worked well on small cases but it suffered from low accuracy when applied to large (and most interesting) traces...
This paper presents the underlying theory and the performance of a cluster using a new 2-hop network topology. This topology is constructed using a symmetric equation and Singer Difference Sets and is called SymSig. The degree of connections at each node with SymSig is about half compared to previous methods using Singer Difference Sets. A comparison with a cluster of Clos topology shows significant...
Parallelizing serial software systems in order to run in a High Performance Computing (HPC) environment presents many challenges to developers. In particular, the extant literature suggests the task of decomposing large-scale data applications is particularly complex and time-consuming. In order to take stock of the state of practice of data decomposition in HPC, we conducted a two-phased study. Firstly,...
As the scales of supercomputers increase total cable length becomes enormous, e.g., up to thousands of kilometers. Recent high-radix switches with dozens of ports make switch layout and system packaging more complex. In this study, we study the optimization of the physical layout of topologies of switches on a machine room floor with the goal of reducing cable length. For a given topology, using graph...
Recently, a new environment for high performance peer-to-peer distributed computing was proposed. This environment, named P2PDC, addresses stable or volatile systems communicating in a decentralized manner using the self-adaptive protocol P2PSAP. P2PDC is devoted to task parallel applications like numerical simulation problems or optimization problems solved via parallel or distributed iterative algorithms...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.