A star-product operation may be used to create large graphs from smaller factor graphs. Network topologies based on star-products demonstrate several advantages including lowdiameter, high scalability, modularity and others. Many state-of-the-art diameter-2 and −3 topologies (Slim Fly, Bundlefly, PolarStar etc.) can be represented as star products. In this paper, we explore constructions of edge-disjoint spanning trees (EDSTs) in star-product topologies. EDSTs expose multiple parallel disjoint pathways in the network and can be leveraged to accelerate collective communication, enhance fault tolerance and network recovery, and manage congestion. Our EDSTs have provably maximum or near-maximum cardinality which amplifies their benefits. We further analyze their depths and show that for one of our constructions, all trees have order of the depth of the EDSTs of the factor graphs, and for all other constructions, a large subset of the trees have that depth.

Allreduce is a fundamental collective used in parallel computing and distributed training of machine learning models, and can become a performance bottleneck on large systems. In-network computing improves Allreduce performance by reducing packets on the fly using network routers. However, the throughput of current innetwork solutions is limited to a single link bandwidth.

In this paper we present PolarFly, a diameter-2 network topology based on the Erdos-Renyi family of polarity graphs from finite geometry. This is the first known diameter-2 topology that asymptotically reaches the Moore bound on the number of nodes for a given network degree and diameter. PolarFly achieves high Moore bound efficiency even for the moderate radixes commonly seen in current and near-future routers, reaching more than 96% of the theoretical peak. It also offers more feasible router degrees than the state-of-the-art solutions, greatly adding to the selection of scalable diameter-2 networks. PolarFly enjoys many other topological properties highly relevant in practice, such as a modular design and expandability that allow incremental growth in network size without rewiring the whole network. Our evaluation shows that PolarFly outperforms competitive networks in terms of scalability, cost and performance for various traffic patterns.

Approximate computing addresses many of the identified challenges for exascale computing, leading to performance improvements that may include changes in fidelity of calculation. In this paper, we examine approximate approaches for a range of DOE-relevant computational problems run on a variety of architectures as a proxy for the wider set of exascaleclass applications.We show anticipated improvements in computational and memory performance and in power savings. We also assess application correctness when operating under conditions of reduced precision, and show that this is within acceptable bounds. Finally, we discuss the trade space between performance, power, precision and resolution for these mini-apps, and optimized solutions attained within given constraints, with positive implications for application of approximate computing to exascale-class problems.

The U.S. Department of Energy's (DOE) Office of Environmental Management (DOE/EM) currently supports an effort to understand and predict the fate of nuclear contaminants and their transport in natural and engineered systems. Geologists, hydrologists, physicists and computer scientists are working together to create models of existing nuclear waste sites, to simulate their behavior and to extrapolate it into the future. We use visualization as an integral part in each step of this process. In the first step, visualization is used to verify model setup and to estimate critical parameters. High-performance computing simulations of contaminant transport produces massive amounts of data, which is then analyzed using visualization software specifically designed for parallel processing of large amounts of structured and unstructured data. Finally, simulation results are validated by comparing simulation results to measured current and historical field data. We describe in this article how visual analysis is used as an integral part of the decision-making process in the planning of ongoing and future treatment options for the contaminated nuclear waste sites. Lessons learned from visually analyzing our large-scale simulation runs will also have an impact on deciding on treatment measures for other contaminated sites.

This paper describes the first use of a Network Processing Unit (NPU) to perform hardware-based image composition in a distributed rendering system. The image composition step is a notorious bottleneck in a clustered rendering system. Furthermore, image compositing algorithms do not necessarily scale as data size and number of nodes increase. Previous researchers have addressed the composition problem via software and/or custom-built hardware. We used the heterogeneous multicore computation architecture of the Intel IXP28XX NPU, a fully programmable commercial off-the-shelf (COTS) technology, to perform the image composition step. With this design, we have attained a nearly four-times performance increase over traditional software-based compositing methods, achieving sustained compositing rates of 22-28 fps on a 1,024 x 1,024 image. This system is fully scalable with a negligible penalty in frame rate, is entirely COTS, and is flexible with regard to operating system, rendering software, graphics cards, and node architecture. The NPU-based compositor has the additional advantage of being a modular compositing component that is eminently suitable for integration into existing distributed software visualization packages.

Los Alamos National Laboratory (LANL) has deployed a 43- megapixel multi-panel immersive environment, La Cueva Grande (LCG), to be used in visualizing the terabytes of data produced by simulations. This paper briefly discusses some of the technical challenges encountered and overcome during the deployment of a 43-million pixel immersive visualization environment.