arXiv subjects

Jeremy Kepner

Publications and source records attributed to Jeremy Kepner.

At least 19 recordsLinked to original sources

arXiv2026

TX-Digital Twin: Visualizing Supercomputer GPU Performance Data Stream

Supercomputers are complex, dynamic systems that serve thousands of users and are built with thousands of compute nodes. Due to the vast amounts of system and performance data needed to accurately capture their status, supercomputers require complex methods to monitor, maintain, and optimize. Data visualization is a powerful technique for overseeing these large streams of data in an easily interpretable way. The MIT Lincoln Laboratory Supercomputing Center (LLSC) enables effective monitoring through combining 3D gaming technology with compound data streams in the TX-Digital Twin, a 3D simulation of the supercomputer. The TX-Digital Twin offers both live and historical data, in visual and text formats, and tracks a multitude of revealing performance metrics. Recent increasing interest in GPU-accelerated computing has driven a need for monitoring and maintenance of GPU-accelerated resources in supercomputers. In this paper, we build on our previous solution by integrating the visualization of additional GPU metrics, such as GPU memory usage, temperature, and power draw, into the TX-Digital Twin. Using techniques in draw call optimization, we add clear and effective displays of the new metrics while keeping the effects on performance minimal.

cs.DC↗

arXiv2026

Improving the Graph Challenge Reference Implementation

The MIT/IEEE/Amazon Graph Challenge provides a venue for individuals and teams to showcase new innovations in large-scale graph and sparse data analysis. The Anonymized Network Sensing Graph Challenge processes over 100 billion network packets to construct privacy-preserving traffic matrices, with a GraphBLAS reference implementation demonstrating how hypersparse matrices can be applied to this problem. This work presents a refactoring and benchmarking of a section of the reference code to improve clarity, adaptability, and performance. The original Python implementation spanning approximately 1000 lines across 3 files has been streamlined to 325 lines across two focused modules, achieving a 67% reduction in code size while maintaining full functionality. Using pMatlab and pPython distributed array programming libraries, the addition of parallel maps allowed for parallel benchmarking of the data. Scalable performance is demonstrated for large-scale summation and analysis of traffic matrices. The resulting implementation increases the potential impact of the Graph Challenge by providing a clear and efficient foundation for participants.

cs.NI↗

arXiv2025

Complexity of One-Dimensional ReLU DNNs

We study the expressivity of one-dimensional (1D) ReLU deep neural networks through the lens of their linear regions. For randomly initialized, fully connected 1D ReLU networks (He scaling with nonzero bias) in the infinite-width limit, we prove that the expected number of linear regions grows as $\sum_{i = 1}^L n_i + \mathop{{o}}\left(\sum_{i = 1}^L{n_i}\right) + 1$, where $n_\ell$ denotes the number of neurons in the $\ell$-th hidden layer. We also propose a function-adaptive notion of sparsity that compares the expected regions used by the network to the minimal number needed to approximate a target within a fixed tolerance.

cs.LG↗

arXiv2025

Advancing AI Challenges for the United States Department of the Air Force

The DAF-MIT AI Accelerator is a collaboration between the United States Department of the Air Force (DAF) and the Massachusetts Institute of Technology (MIT). This program pioneers fundamental advances in artificial intelligence (AI) to expand the competitive advantage of the United States in the defense and civilian sectors. In recent years, AI Accelerator projects have developed and launched public challenge problems aimed at advancing AI research in priority areas. Hallmarks of AI Accelerator challenges include large, publicly available, and AI-ready datasets to stimulate open-source solutions and engage the wider academic and private sector AI ecosystem. This article supplements our previous publication, which introduced AI Accelerator challenges. We provide an update on how ongoing and new challenges have successfully contributed to AI research and applications of AI technologies.

cs.AI↗

arXiv2025

Lincoln AI Computing Survey (LAICS) and Trends

In the past year, generative AI (GenAI) models have received a tremendous amount of attention, which in turn has increased attention to computing systems for training and inference for GenAI. Hence, an update to this survey is due. This paper is an update of the survey of AI accelerators and processors from past seven years, which is called the Lincoln AI Computing Survey -- LAICS (pronounced "lace"). This multi-year survey collects and summarizes the current commercial accelerators that have been publicly announced with peak performance and peak power consumption numbers. In the same tradition of past papers of this survey, the performance and power values are plotted on a scatter graph, and a number of dimensions and observations from the trends on this plot are again discussed and analyzed. Market segments are highlighted on the scatter plot, and zoomed plots of each segment are also included. A brief description of each of the new accelerators that have been added in the survey this year is included, and this update features a new categorization of computing architectures that implement each of the accelerators.

cs.DC↗

arXiv2025

Comprehensive Ab Initio Quantum Computations of CO$_{\rm 2}$-H$_{\rm 2}$ and CO$_{\rm 2}$-He Collisional Properties

We present comprehensive \textsl{ab initio} fully quantum calculations of CO$_{\rm 2}$--H$_{\rm 2}$ and CO$_{\rm 2}$--He collisional properties. Our framework combines CCSD(T) potential-energy-surface calculations with close-coupling dynamical scattering in the \YUMI~framework to derive elastic and inelastic cross sections, rate coefficients, and pressure broadening parameters. We characterize the rotational dependence of the broadening coefficients up to $j=25$ for CO$_{\rm 2}$--H$_{\rm 2}$ and $j=40$ for CO$_{\rm 2}$--He, and their temperature dependence over 40--800 K. We also provide Pad\'e fits as a function of rotational quantum number, enabling extrapolation and integration into spectroscopic databases including HITRAN and HITEMP. The resulting pressure broadening coefficients reproduce available experimental measurements on an absolute scale, without empirical correction factors, and meet the $\sim$10\% precision requirement identified for \textit{JWST}-era exoplanet atmospheric studies. This represents a substantial improvement over previously available parameters, which at higher temperatures ($T>400$ K) can fall outside the desired precision by up to a factor of five. All derivations, computed collisional properties, and database-ready products are provided with this manuscript. Together, these results establish a comprehensive \textsl{ab initio}, parameter-free, fully quantum foundation for CO$_2$ collisional broadening by H$_2$ and He, while demonstrating the transformative potential of the ab-initio approach for next-generation spectroscopic needs across planetary atmospheres, combustion, health sciences, and fusion-plasma diagnostics.

physics.chem-ph↗

arXiv2025

Performance and Numerical Aspects of Decompositional Factorizations with FP64 Floating-Point Emulation in INT8

Mixing precisions for performance has been an ongoing trend as the modern hardware accelerators started including new, and mostly lower-precision, data formats. The advantage of using them is a great potential of performance gain and energy savings. The disadvantage are the numerical issues not present in the standard-mandated floating-point formats. Split integer emulation of FP64 takes this to an extreme with the computation performed only by fixed-point tensor core units. We present the new issues the emulation faces for practical cases involving dense linear solver. We show extensive numerical tests indicating the effect of extended numerical range of matrix entries. We also scaled the input sizes to study the performance and numerical profiles on the NVIDIA Hopper GPUs.

math.NA↗

arXiv2025

GraphBLAS Mathematical Opportunities: Parallel Hypersparse, Matrix Based Graph Streaming, and Complex-Index Matrices

The GraphBLAS high performance library standard has yielded capabilities beyond enabling graph algorithms to be readily expressed in the language of linear algebra. These GraphBLAS capabilities enable new performant ways of thinking about algorithms that include leveraging hypersparse matrices for parallel computation, matrix-based graph streaming, and complex-index matrices. Formalizing these concepts mathematically provides additional opportunities to apply GraphBLAS to new areas. This paper formally develops parallel hypersparse matrices, matrix-based graph streaming, and complex-index matrices and illustrates these concepts with various examples to demonstrate their potential merits.

cs.DS↗

arXiv2025

DBOS Network Sensing: A Web Services Approach to Collaborative Awareness

DBOS (DataBase Operating System) is a novel capability that integrates web services, operating system functions, and database features to significantly reduce web-deployment effort while increasing resilience. Integration of high performance network sensing enables DBOS web services to collaboratively create a shared awareness of their network environments to enhance their collective resilience and security. Network sensing is added to DBOS using GraphBLAS hypersparse traffic matrices via two approaches: (1) Python-GraphBLAS and (2) OneSparse PostgreSQL. These capabilities are demonstrated using the workflow and analytics from the IEEE/MIT/Amazon Anonymized Network Sensing Graph Challenge. The system was parallelized using pPython and benchmarked using 64 compute nodes on the MIT SuperCloud. The web request rate sustained by a single DBOS instance was ${>}10^5$, well above the required maximum, indicating that network sensing can be added to DBOS with negligible overhead. For collaborative awareness, many DBOS instances were connected to a single DBOS aggregator. The Python-GraphBLAS and OneSparse PostgreSQL implementations scaled linearly up to 64 and 32 nodes respectively. These results suggest that DBOS collaborative network awareness can be achieved with a negligible increase in computing resources.

cs.NI↗

arXiv2025

Accelerating AI Development with Cyber Arenas

AI development requires high fidelity testing environments to effectively transition from the laboratory to operations. The flexibility offered by cyber arenas presents a novel opportunity to test new artificial intelligence (AI) capabilities with users. Cyber arenas are designed to expose end-users to real-world situations and must rapidly incorporate evolving capabilities to meet their core objectives. To explore this concept the MIT/IEEE/Amazon Graph Challenge Anonymized Network Sensor was deployed in a cyber arena during a National Guard exercise.

cs.CR↗

arXiv2025

The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS)

This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 with the goal of understanding how the MPS domains (Astronomy, Chemistry, Materials Research, Mathematical Sciences, and Physics) can best capitalize on, and contribute to, the future of AI. We present here a summary and snapshot of the MPS community's perspective, as of Spring/Summer 2025, in a rapidly developing field. The link between AI and MPS is becoming increasingly inextricable; now is a crucial moment to strengthen the link between AI and Science by pursuing a strategy that proactively and thoughtfully leverages the potential of AI for scientific discovery and optimizes opportunities to impact the development of AI by applying concepts from fundamental science. To achieve this, we propose activities and strategic priorities that: (1) enable AI+MPS research in both directions; (2) build up an interdisciplinary community of AI+MPS researchers; and (3) foster education and workforce development in AI for MPS researchers and students. We conclude with a summary of suggested priorities for funding agencies, educational institutions, and individual researchers to help position the MPS community to be a leader in, and take full advantage of, the transformative potential of AI+MPS.

cs.AI↗

arXiv2025

Easy Acceleration with Distributed Arrays

High level programming languages and GPU accelerators are powerful enablers for a wide range of applications. Achieving scalable vertical (within a compute node), horizontal (across compute nodes), and temporal (over different generations of hardware) performance while retaining productivity requires effective abstractions. Distributed arrays are one such abstraction that enables high level programming to achieve highly scalable performance. Distributed arrays achieve this performance by deriving parallelism from data locality, which naturally leads to high memory bandwidth efficiency. This paper explores distributed array performance using the STREAM memory bandwidth benchmark on a variety of hardware. Scalable performance is demonstrated within and across CPU cores, CPU nodes, and GPU nodes. Horizontal scaling across multiple nodes was linear. The hardware used spans decades and allows a direct comparison of hardware improvements for memory bandwidth over this time range; showing a 10x increase in CPU core bandwidth over 20 years, 100x increase in CPU node bandwidth over 20 years, and 5x increase in GPU node bandwidth over 5 years. Running on hundreds of MIT SuperCloud nodes simultaneously achieved a sustained bandwidth $>$1 PB/s.

cs.DC↗

arXiv2025

Cyber Orbits of Large Scale Network Traffic

The advent of high-performance graph libraries, such as the GraphBLAS, has enabled the analysis of massive network data sets and revealed new models for their behavior. Physical analogies for complicated network behavior can be a useful aid to understanding these newly discovered network phenomena. Prior work leveraged the canonical Gull's Lighthouse problem and developed a computational heuristic for modeling large scale network traffic using this model. A general solution using this approach requires overcoming the essential mathematical singularities in the resulting differential equations. Further investigation reveals a simpler physical interpretation that alleviates the need for solving challenging differential equations. Specifically, that the probability of observing a source at a temporal ``distance'' $r(t)$ at time $t$ is $p(t) \propto 1/r(t)^2$. This analogy aligns with many physical phenomena and can be a rich source of intuition. Applying this physical analogy to the observed source correlations in the Anonymized Network Sensing Graph Challenge data leads to an elegant cyber orbit analogy that may assist with the understanding network behavior.

physics.soc-ph↗

arXiv2025

Echoes of the hidden: Uncovering coordination beyond network structure

The study of connectivity and coordination has drawn increasing attention in recent decades due to their central role in driving markets, shaping societal dynamics, and influencing biological systems. Traditionally, observable connections, such as phone calls, financial transactions, or social media connections, have been used to infer coordination and connectivity. However, incomplete, encrypted, or fragmented data, alongside the ubiquity of communication platforms and deliberate obfuscation, often leave many real-world connections hidden. In this study, we demonstrate that coordinating individuals exhibit shared bursty activity patterns, enabling their detection even when observable links between them are sparse or entirely absent. We further propose a generative model based on the network of networks formalism to account for the mechanisms driving this collaborative burstiness, attributing it to shock propagation across networks rather than isolated individual behavior. Model simulations demonstrate that when observable connection density is below 70\%, burstiness significantly improves coordination detection compared to state-of-the-art temporal and structural methods. This work provides a new perspective on community and coordination dynamics, advancing both theoretical understanding and practical detection. By laying the foundation for identifying hidden connections beyond observable network structures, it enables detection across different platforms, alongside enhancing system behavior understanding, informed decision-making, and risk mitigation.

cs.SI↗

arXiv2024

GPU Sharing with Triples Mode

There is a tremendous amount of interest in AI/ML technologies due to the proliferation of generative AI applications such as ChatGPT. This trend has significantly increased demand on GPUs, which are the workhorses for training AI models. Due to the high costs of GPUs and lacking supply, it has become of interest to optimize GPU usage in HPC centers. MIT Lincoln Laboratory Supercomputing Center (LLSC) has developed an easy-to-use GPU sharing feature supported by LLSC-developed tools including LLsub and LLMapReduce. This approach overcomes some of the limitations with the existing methods for GPU sharing. This allows users to apply GPU sharing whenever possible while they are developing their AI/ML models and/or doing parametric study on their AI models or executing other GPU applications. Based on our initial experimental results with GPU sharing, GPU sharing with triples mode is easy to use and achieved significant improvement in GPU usage and throughput performance for certain types of AI applications.

cs.DC↗

arXiv2024

LLload: An Easy-to-Use HPC Utilization Tool

The increasing use and cost of high performance computing (HPC) requires new easy-to-use tools to enable HPC users and HPC systems engineers to transparently understand the utilization of resources. The MIT Lincoln Laboratory Supercomputing Center (LLSC) has developed a simple command, LLload, to monitor and characterize HPC workloads. LLload plays an important role in identifying opportunities for better utilization of compute resources. LLload can be used to monitor jobs both programmatically and interactively. LLload can characterize users' jobs using various LLload options to achieve better efficiency. This information can be used to inform the user to optimize HPC workloads and improve both CPU and GPU utilization. This includes improvements using judicious oversubscription of the computing resources. Preliminary results suggest significant improvement in GPU utilization and overall throughput performance with GPU overloading in some cases. By enabling users to observe and fix incorrect job submission and/or inappropriate execution setups, LLload can increase the resource usage and improve the overall throughput performance. LLload is a light-weight, easy-to-use tool for both HPC users and HPC systems engineers to monitor HPC workloads to improve system utilization and efficiency.

cs.PF↗

arXiv2024

Supercomputer 3D Digital Twin for User Focused Real-Time Monitoring

Real-time supercomputing performance analysis is a critical aspect of evaluating and optimizing computational systems in a dynamic user environment. The operation of supercomputers produce vast quantities of analytic data from multiple sources and of varying types so compiling this data in an efficient matter is critical to the process. MIT Lincoln Laboratory Supercomputing Center has been utilizing the Unity 3D game engine to create a Digital Twin of our supercomputing systems for several years to perform system monitoring. Unity offers robust visualization capabilities making it ideal for creating a sophisticated representation of the computational processes. As we scale the systems to include a diversity of resources such as accelerators and the addition of more users, we need to implement new analysis tools for the monitoring system. The workloads in research continuously change, as does the capability of Unity, and this allows us to adapt our monitoring tools to scale and incorporate features enabling efficient replay of system wide events, user isolation, and machine level granularity. Our system fully takes advantage of the modern capabilities of the Unity Engine in a way that intuitively represents the real time workload performed on a supercomputer. It allows HPC system engineers to quickly diagnose usage related errors with its responsive user interface which scales efficiently with large data sets.

cs.DC↗

arXiv2024

Hypersparse Traffic Matrices from Suricata Network Flows using GraphBLAS

Hypersparse traffic matrices constructed from network packet source and destination addresses is a powerful tool for gaining insights into network traffic. SuiteSparse: GraphBLAS, an open source package or building, manipulating, and analyzing large hypersparse matrices, is one approach to constructing these traffic matrices. Suricata is a widely used open source network intrusion detection software package. This work demonstrates how Suricata network flow records can be used to efficiently construct hypersparse matrices using GraphBLAS.

cs.DC↗