LMLaura Monroe

Laura Monroe

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Laura Monroe has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Abstract: A Family of Post-Exascale Networks

    by Laura Monroe, Kartik Lakhotia, Kelly Isham, Fabrizio Petrini

  • Open Access

    PolarStar: Expanding the Horizon of Diameter-3 Networks

    by Kartik Lakhotia, Laura Monroe, Kelly Isham, Maciej Besta, Nils Blach, Torsten Hoefler, Fabrizio Petrini

    We present PolarStar, a novel family of diameter-3 network topologies derived from the star product of low-diameter factor graphs. PolarStar gives the largest known diameter-3 network topologies for almost all radixes, thus providing the best known scalable diameter-3 network. Compared to current state-of-the-art diameter-3 networks, PolarStar achieves 1.3x geometric mean increase in scale over Bundlefly, 1.9x over Dragonfly, and 6.7x over 3-D HyperX. PolarStar has many other desirable properties, including a modular layout, large bisection, high resilience to link failures and a large number of feasible configurations for every radix. We give a detailed evaluation with simulations of synthetic and real-world traffic patterns and show that PolarStar exhibits comparable or better performance than current diameter-3 networks.


  • Open Access

    In-network Allreduce with Multiple Spanning Trees on PolarFly

    by Kartik Lakhotia, Kelly Isham, Laura Monroe, Maciej Besta, Torsten Hoefler, Fabrizio Petrini

    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. We develop, compare and contrast two different sets of Allreduce spanning trees embedded into PolarFly, a high-performance diameter-2 network topology. Both of our solutions offer theoretically guaranteed near-optimal performance, boosting Allreduce bandwidth by a factor equal to half the network radix of nodes. While our first set offers low-latency with trees of depth-3, the second set offers congestion-free implementation which reduces complexity and resource requirements of in-network computing units. In doing so, we also distinguish PolarFly as a highly suitable network for distributed deep learning and other applications that employ throughput-bound large Allreductions.


  • Open Access

    PolarFly: A Cost-Effective and Flexible Low-Diameter Topology

    by Kartik Lakhotia, Maciej Besta, Laura Monroe, Kelly Isham, Patrick Iff, Torsten Hoefler, Fabrizio Petrini

    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 a highly scalable low-diameter 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.

  • SIMD-Optimized Search Over Sorted Data

    by Benjamin P Mastripolito, Nicholas A. Koskelo, Dylan A. Weatherred, David A Pimentel, Daniel G. Sheppard, Anna Pietarila Graham, Laura M Monroe, Robert Robey

    Applications often require a fast, single-threaded search algorithm over sorted data, typical in table-lookup operations. We explore various search algorithms for a large number of search candidates over a relatively small array of logarithmically-distributed sorted data. These include an innovative hash-based search that takes advantage of floating point representation to bin data by the exponent. Algorithms that can be optimized to take advantage of SIMD vector instructions are of particular interest. We then conduct a case study applying our results and analyzing algorithmic performance with the EOSPAC package. EOSPAC is a table look-up library for manipulation and interpolation of SESAME equation-of-state data. Our investigation results in a couple of algorithms with better performance with a best case eight times speedup over the original EOSPAC Hunt-and-Locate implementation. Our techniques should generalize to other instances of search algorithms seeking to get a performance boost from vectorization.


  • Open Access

    Binary Signed-Digit Integers and the Stern Diatomic Sequence

    by Laura Monroe

    Stern's diatomic sequence is a well-studied and simply defined sequence with many fascinating characteristics. The binary signed-digit representation of integers is an alternative representation of integers with much use in efficient computation, coding theory and cryptography. We link these two ideas here, showing that the number of $i$-bit binary signed-digit representations of an integer $n$ with $n<2^i$ is the $(2^i-n)^\text{th}$ element in Stern's diatomic sequence. This correspondence makes the vast range of results known for Stern's diatomic sequence available for consideration in the study of binary signed-digit integers.

  • Survey of Tools to Assess Reduced Precision on Floating Point Applications

    by Quinn T Dibble, Terence Alexander Grove, Laura Monroe

    The U.S. Department of Energy's Office of Scientific and Technical Information

  • Open Access

    Computationally Inequivalent Summations and Their Parenthetic Forms

    by Laura Monroe, Vanessa Job

    Floating-point addition on a finite-precision machine is not associative, so not all mathematically equivalent summations are computationally equivalent. Making this assumption can lead to numerical error in computations. Proper ordering and parenthesizing is a low-overhead way of mitigating such error in a floating point summation. Ordered and parenthesized summations fall into equivalence classes. We describe these classes, and the parenthetic forms summations in these classes take. We provide summation-related interpretations for sequences known in other contexts, and give new recursive and closed formulas for sequences not previously related to summation. We also introduce a data structure that facilitates understanding of these objects, and use it to consider certain forms of summation used by default in widely used computer languages. Finally, we relate this data structure to other mathematical constructs from the fields of mathematical analysis and algorithmic analysis.