SEARCH · Search NASA

Results for “Intel”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3

All sources NASA NTRS DOE OSTI

DOE OSTI2024

MAGMA: Enabling exascale performance with accelerated BLAS and LAPACK for diverse GPU architectures

MAGMA (Matrix Algebra for GPU and Multicore Architectures) is a pivotal open-source library in the landscape of GPU-enabled dense and sparse linear algebra computations. With a repertoire of approximately 750 numerical routines across four precisions, MAGMA is deeply ingrained in the DOE software stack, playing a crucial role in high-performance computing. Notable projects such as ExaConstit, HiOP, MARBL, and STRUMPACK, among others, directly harness the capabilities of MAGMA. In addition, the MAGMA development team has been acknowledged multiple times for contributing to the vendors’ numerical software stacks. Looking back over the time of the Exascale Computing Project (ECP), we highlight how MAGMA has adapted to recent changes in modern HPC systems, especially the growing gap between CPU and GPU compute capabilities, as well as the introduction of low precision arithmetic in modern GPUs. We also describe MAGMA’s direct impact on several ECP projects. Maintaining portable performance across NVIDIA and AMD GPUs, and with current efforts toward supporting Intel GPUs, MAGMA ensures its adaptability and relevance in the ever-evolving landscape of GPU architectures.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Evolution of the SLATE linear algebra library

SLATE (Software for Linear Algebra Targeting Exascale) is a distributed, dense linear algebra library targeting both CPU-only and GPU-accelerated systems, developed over the course of the Exascale Computing Project (ECP). While it began with several documents setting out its initial design, significant design changes occurred throughout its development. In some cases, these were anticipated: an early version used a simple consistency flag that was later replaced with a full-featured consistency protocol. In other cases, performance limitations and software and hardware changes prompted a redesign. Sequential communication tasks were parallelized; host-to-host MPI calls were replaced with GPU device-to-device MPI calls; more advanced algorithms such as Communication Avoiding LU and the Random Butterfly Transform (RBT) were introduced. Early choices that turned out to be cumbersome, error prone, or inflexible have been replaced with simpler, more intuitive, or more flexible designs. Applications have been a driving force, prompting a lighter weight queue class, nonuniform tile sizes, and more flexible MPI process grids. Of paramount importance has been building a portable library that works across several different GPU architectures – AMD, Intel, and NVIDIA – while keeping a clean and maintainable codebase. Here we explore the evolving design choices and their effects, both in terms of performance and software sustainability.

Gates, Mark↗

DOE OSTI2024

PaRSEC: Scalability, flexibility, and hybrid architecture support for task-based applications in ECP

This paper highlights the most significant enhancements made to PaRSEC, a scalable task-based runtime system designed for hybrid machines, during the Exascale Computing Project (ECP). The enhancements focus on expanding the capabilities of PaRSEC to address the evolving landscape of parallel computing. Notable achievements include the integration of support for three major types of accelerators (NVIDIA, AMD, and Intel GPUs), the refinement and increased flexibility of the communication subsystem, and the introduction of new programming interfaces tailored for irregular applications. Additionally, the project resulted in the development of powerful debugging and performance analysis tools aimed at assisting users in understanding and optimizing their applications. We present a comprehensive demonstration of these advancements through a series of benchmarks and applications within ECP and beyond, thereby showcasing the enhanced capabilities of PaRSEC across the diverse architectures within the ECP, providing valuable insights into the runtime system’s adaptability and performance across varied computing environments.

Bouteiller, Aurelien↗

DOE OSTI2024

An FPGA-based hardware accelerator supporting sensitive sequence homology filtering with profile hidden Markov models

Abstract Background Sequence alignment lies at the heart of genome sequence annotation. While the BLAST suite of alignment tools has long held an important role in alignment-based sequence database search, greater sensitivity is achieved through the use of profile hidden Markov models (pHMMs). Here, we describe an FPGA hardware accelerator, called HAVAC, that targets a key bottleneck step (SSV) in the analysis pipeline of the popular pHMM alignment tool, HMMER. Results The HAVAC kernel calculates the SSV matrix at 1739 GCUPS on a $$\sim$$ ∼ $3000 Xilinx Alveo U50 FPGA accelerator card, $$\sim$$ ∼ 227× faster than the optimized SSV implementation in nhmmer . Accounting for PCI-e data transfer data processing, HAVAC is 65× faster than nhmmer’s SSV with one thread and 35× faster than nhmmer with four threads, and uses $$\sim$$ ∼ 31% the energy of a traditional high end Intel CPU. Conclusions HAVAC demonstrates the potential offered by FPGA hardware accelerators to produce dramatic speed gains in sequence annotation and related bioinformatics applications. Because these computations are performed on a co-processor, the host CPU remains free to simultaneously compute other aspects of the analysis pipeline.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Milestone 49 Report: Batched Sparse LA Phase 5 Implementation

Batched sparse linear algebra operations in general, and solvers in particular, have become the major algorithmic development activity and foremost performance engineering effort in the numerical software libraries work on modern hardware with accelerators such as GPUs. Many applications, ECP and non-ECP alike, require simultaneous solutions of many small linear systems of equations that are structurally sparse in one form or another. In order to move towards high hardware utilization levels, it is important to provide these applications with appropriate interface designs to be both functionally efficient and performance portable and give full access to the appropriate batched sparse solvers running on modern hardware accelerators prevalent across DOE supercomputing sites since the inception of ECP. To this end, we present here a summary of recent advances on the interface designs in use by HPC software libraries supporting batched sparse linear algebra and the development of sparse batched kernel codes for solvers and preconditioners. We also address the potential interoperability opportunities to keep the corresponding software portable between the major hardware accelerators from AMD, Intel, and NVIDIA, while maintaining the appropriate disclosure levels conforming to the active NDA agreements. The presented interface specifications include a mix of batched band, sparse iterative, and sparse direct solvers with their accompanying functionality that is already required by the application codes or we anticipated to be needed in the near future. This report summarizes progress in Kokkos Kernels and the xSDK libraries MAGMA, Ginkgo, hypre, PETSc, and SuperLU.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Resilient Energy Delivery and Control Systems (REDCS) (Final Technical Report)

US critical infrastructure is increasingly the target of cyberattacks, where disturbances could cause considerable damage and disruption. To help provide a new layer of cyber-physical protection for one key energy delivery system, natural gas pipelines, GE Vernova Advanced Research along with partners Florida State University and Intel Corporation created an innovative technology called "Resilient Energy Delivery and Control Systems" (REDCS). This cybersecurity package helps detect anomalies caused by cyberattacks, isolate the subsystem being impacted by the attack, and provide functions that can allow for resiliency – giving better situational awareness to the operators and cybersecurity specialists or in the future perform closed loop control for continued operation while compromised.

03 NATURAL GAS↗

DOE OSTI2024

COG User's Manual: A Multiparticle Monte Carlo Transport Code (Sixth Edition)

COG is a high-resolution code for the Monte Carlo simulation of coupled particle transport in arbitrary 3-D geometry. COG will transport neutrons, protons, deuterons, alpha particles with energies up to hundreds of GeV, and photons with energy ranges limited by the available cross section sets and physics models. Electrons can be transported via the EGS5 electron transport kernel, electrons can also be transported. The COG code is a significant upgrade from earlier Monte Carlo transport codes and has been written specifically to make it more versatile, accurate, and easy to use. COG has provisions for calculating deep penetration (shielding) problems, criticality problems, and neutron activation problems while retains all of the standard capabilities found in other Monte Carlo transport codes. COG uses high-resolution pointwise cross-section databases and makes no compromises in the transport physics, so that the results of a COG run are limited only by the accuracy of the databases used. COG runs primarily on Linux Operating System workstations with MPICH software installed – currently, Red Hat 7 & 8, Windows 10 (Windows Subsystem for Linux –WSL), Ubuntu 16, 18 & 20, OpenSUSE Leap 15.2, Fedora 32, Apple Power Mac with Intel CPU (with MacPorts installed) workstations, and LLNL LC supercomputer CTS-1 cluster with TOSS 3 are supported.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2025

Argonne Leadership Computing Facility 2024 Operational Assessment Report

This Operational Assessment Report describes how the Argonne Leadership Computing Facility (ALCF) met or exceeded every goal set by DOE for the calendar year (CY) 2024. In CY 2024, the ALCF operated Polaris, an AMD and NVIDIA-based Hewlett Packard Enterprise (HPE) Apollo 6500 Gen10+ system that provides a powerful platform for breakthrough science and prepares applications and workloads for Aurora, Argonne National Laboratory’s Intel-HPE exascale computer. Since going into production in August 2022, Polaris has supported research teams from the DOE Exascale Computing Project (ECP), which concluded in 2024, and from ALCF’s Aurora Early Science Program (ESP). Polaris delivered a total of 2555.7K node-hours to 17 Innovative and Novel Computational Impact on Theory and Experiment (INCITE) 2024 projects and 601.6K node-hours to ASCR Leadership Computing Challenge (ALCC) projects (12 of which were awarded during the 2023–2024 ALCC year and 11 of which were awarded during the 2024–2025 ALCC year), as well as providing substantial time for Director’s Discretionary (DD) projects (966.2K node-hours). As Table ES.1 shows, Polaris performed exceptionally well in terms of overall availability (97.7 percent), scheduled availability (99.6 percent), and utilization (94.7 percent; Table 2.1). In CY 2024, ALCF supported more than 2,000 users. As of March 18, 2025, ALCF’s users have published 254 papers in peer-reviewed journals and technical proceedings.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Code Coverage Status of the ARC Code DIF3D

The Argonne Reactor Code (ARC) software system supports users in their fast reactor design goals by providing neutronic, thermal-hydraulic, and structural analysis capabilities. DIF3D plays a pivotal role in the ARC system as the primary homogenized assembly neutronic calculation methodology for fast reactor problems. Over its 40 years history, ARC software usage with DIF3D has been applied to numerous fast and thermal spectrum reactor analysis projects with good to excellent comparison against experiments. With continued improvement of computation resources, many of the geometry modeling capabilities in DIF3D that were primarily used in low order schemes are not really needed anymore. Today, the diffusion and transport capabilities of DIF3D-VARIANT are primarily used in the reactor design process with some scattered usage of DIF3D-FD and DIF3D-Nodal. In recent work, the DIF3D software verification was completed for DIF3D-FD and DIF3D-VARIANT on the geometry options used in the Versatile Test Reactor project. While we can be confident that these capabilities of DIF3D are well used and thus trusted, it does not demonstrate that all possible input options of DIF3D are actually working, but just those that were tested as part of VTR are and that they are correct. Thus, the purpose of the present work is to identify a set of test problems for DIF3D and assess the code coverage of DIF3D for those test problems. The goal is to document what parts of the existing DIF3D code are touched by the set of test problems and which are not. Because the verification work done on DIF3D-VARIANT and DIF3D-FD was focused on the most common uses of DIF3D for fast reactor analysis, the code coverage assessment of those capabilities is the highest priority. This will ensure that nothing is being missed by the existing verification test problems that DIF3D relies upon. The DIF3D-Nodal capability will also be inspected for code coverage as part of this work to further ensure that regular regression testing of DIF3D will trap any likely errors the end user might experience with the DIF3D software. The code coverage analysis of DIF3D was performed with the Code Coverage Tool of the Intel Fortran compiler which requires modifications to the compilation of DIF3D. The detailed coverage tables are given for each submodule of DIF3D separately, and for the submodules which are primarily developed for DIF3D, most of the source files could be at least partially touched. Most of the uncovered parts/files could be easily ignored, because they are either for error message and debugging output or obviously not needed by DIF3D. Out of the entire source codes of DIF3D, only a few uncovered modules deserve further investigation.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

Integrating Machine-learning-assisted Computer Vision with RICH System

Developments in artificial intelligence have vastly expanded the capabilities of robots. Currently, the Spallation Neutron Source (SNS) beamlines at Oak Ridge National Lab (ORNL) have robotic sample loaders to increase the efficiency of running experiments. However, they require retraining if anything about the situation changes, e.g., where the samples are, and cannot notice if errors occur. So, the viability of using computer vision and machine learning to enhance these sample loaders’ functionality was investigated. In this project, the RICH system with a Dobot CR3 6-axis robot present at the VULCAN beamline assisted by an Intel Realsense D435i camera, a unique camera that enables convenient translation of 2D pixel coordinates to 3D world points, was programmed to load ceramic crucibles into a thermogravimetric analyzer (TGA) furnace. An algorithm was constructed in Python with three major phases planned: (1) obtaining a sample, (2) moving it to the target location, and then (3) bringing the sample back to its original location once the experiment finished. In the first phase, the algorithm would dynamically detect sample locations using ArUco markers to recognize the samples’ general location and a custom-trained yolov5 object detection model to locate the crucibles’ centers. Afterward, the robot would be directed to pick up samples based on the crucibles’ calculated positions. In the second phase, the robot would move the sample to a secondary point, reorient its grip, and place the sample at the target location. In the final phase, the robot would determine whether the sample was intact and would bring it back to its original place if it was or raise an alarm. Using this algorithm, the robot was able to pick up different types of crucibles at varying positions. These results indicate that integrating machine-learning-assisted computer vision with robotic sample loaders can result in effective autonomous detection of samples.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Code Coverage Status of the ARC Code RCT

The Argonne Reactor Code (ARC) software system supports users in their fast reactor design goals by providing neutronic, thermal-hydraulic, and structural analysis capabilities. REBUS plays a pivotal role in the ARC system as the primary fuel cycle analysis capability for fast reactor problems. Over its 60 year history, ARC software usage with REBUS has been applied to numerous fast and thermal spectrum reactor analysis projects with good to excellent comparison against experiments. The RCT code is a later addition and uses the REBUS restart files to define its input. The RCT code was built to provide pin depletion details on EBR-II models and thus many features of RCT were specifically tailored to the needs of EBR-II models. Additional approximations were invoked which are likely only valid for the EBR-II reactor and the particular fuel management that was done for it. The purpose of the present work is to identify a set of test problems for RCT and assess the code coverage for those test problems. The goal is to document what parts of the existing RCT code are touched by the set of test problems and which are not. Because no detailed verification work has been done on RCT, the existing regression testing suite was chosen for the code coverage assessment. The code coverage analysis of RCT was performed with the Code Coverage Tool of the Intel Fortran compiler which requires modifications to the compilation of RCT. The detailed coverage tables are given for each part of RCT. As will be discussed and shown, some parts of the RCT capability that are known to be used by the EBR-II analysis work are not tested by the regression testing suite. These aspects should be resolved before major source code changes are taken for the RCT software. Because REBUS and DIF3D are not subroutines of RCT, the coverage changes in both of those codes is not altered by RCT. The same is true for all of the modules of DIF3D that are used by RCT such as SYSLIB and SEGLIB.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

Code Coverage Status of the ARC Code PERSENT

The Argonne Reactor Code (ARC) software system supports users in their fast reactor design goals by providing neutronic, thermal-hydraulic, and structural analysis capabilities. PERSENT fulfills the role of generating reactivity coefficients for a given time point of a REBUS calculation usable in a point kinetics based safety analysis capability. PERSENT also provides a sensitivity coefficient capability on eigenvalue, reactivity worth, and several other key coefficients that are used in the follow-on safety analysis. Given a co-variance matrix, PERSENT can carry out the uncertainty quantification to indicate the amount of error in the reactivity coefficients derived from the errors in the cross section measurements. With continued improvement of computational resources, many of the geometry modeling capabilities in DIF3D that were primarily used in low order schemes are not really needed anymore. Today, the diffusion and transport capabilities of DIF3D-VARIANT are primarily used in the reactor design process with some scattered usage of DIF3D-FD and DIF3D-Nodal. PERSENT is part of the ARC code system and is built around DIF3D-VARIANT and the flux solution it provides. The purpose of the present work is to identify a set of test problems for PERSENT and assess the code coverage of PERSENT for those test problems. PERSENT treats the DIF3D executable as an external executable and thus the code coverage considerations only need to focus on the PERSENT source code and only a fraction of the connected modules in the existing ARC software library. The goal is to document what parts of the existing PERSENT code are touched by the set of test problems and which are not. Because the verification work done on PERSENT was focused on the most common uses of PERSENT for fast reactor analysis, the code coverage assessment of those capabilities is the highest priority. This will ensure that nothing is being missed by the existing verification test problems that users of PERSENT rely upon. The code coverage analysis of PERSENT was performed with the Code Coverage Tool of the Intel Fortran compiler which requires modifications to the compilation of PERSENT. The detailed coverage tables are given for each submodule of PERSENT. Most of the uncovered parts/files could be easily ignored because they are either for error message and debugging output or not needed by PERSENT today. Only a few uncovered parts of PERSENT deserve extending the verification test suite.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

Code Coverage Status of the ARC code GAMSRC

The Argonne Reactor Code (ARC) software system supports users in their fast reactor design goals by providing neutronic, thermal-hydraulic, and structural analysis capabilities. GAMSOR serves as procedure to obtain the neutron and gamma power distribution information in the ARC code system. GAMSOR is a specially modified version of DIF3D (dif3d.x becomes dif3d_gamsor.x). After some work, it was determined that carrying out software on GAMSOR was impractical and would not fit well with commercial grade dedication. GAMSRC was written in the last decade to replace GAMSOR such that the user can rely soley upon the verified DIF3D (dif3d.x) code and GAMSRC to obtain the neutron and gamma power distribution information. GAMSRC is also fully verified and ready for commercial grade dedication. In the coming years, GAMSOR will be deprecated and GAMSRC will fully take over in the ARC code system. This document identifies the set of test problems used to assess the code coverage for GAMSRC. The goal is to document what parts of the existing GAMSRC code are touched by the set of test problems and which are not. The code coverage analysis of GAMSRC was performed with the Code Coverage Tool of the Intel Fortran compiler which requires modifications to the compilation of GAMSRC. The code coverage tables are given for each submodule of GAMSRC. Because GAMSRC links to modules in DIF3D, some details on coverage changes to the DIF3D lined files is provided. As will be seen, most of the uncovered parts/files can be ignored because they are either for error message and debugging output or obviously not needed by GAMSRC today.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

Code Coverage Status of the ARC Code DASSH-F

The Argonne Reactor Code (ARC) software system supports users in their fast reactor design goals by providing neutronic, thermal-hydraulic, and structural analysis capabilities. DASSH-F serves as a steady state thermal hydraulic capability within the ARC system and replaces the SE2-ANL software that preceded it. This document identifies the set of test problems used to assess the code coverage for DASSH-F. The goal is to document what parts of the existing DASSH-F code are touched by the set of test problems and which are not. Because the verification work remains to be done on DASSH-F, one can assume that most of these issues will be resolved as part of that work. The code coverage analysis of DASSH-F was performed with the Code Coverage Tool of the Intel Fortran compiler which requires modifications to the compilation of DASSH-F. The code coverage tables are given for each submodule of DASSH-F. Because DASSH-F links to modules in DIF3D, some details on coverage changes to the DIF3D linked files is provided. As will be seen, most of the uncovered parts/files can be ignored because they are either for error message and debugging output or obviously not needed by DASSH-F today. Seven features of the DASSH-F code were identified to not be covered by the existing testing suite and thus additional verification test problems are suggested to fully cover these sections.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2026

Entity—Hardware-agnostic Particle-in-cell Code for Plasma Astrophysics. I. Curvilinear Special Relativistic Module

Entity is a new-generation, fully open-source particle-in-cell (PIC) code developed to overcome key limitations in astrophysical plasma modeling, particularly the extreme separation of scales and the performance challenges associated with evolving, GPU-centric computing infrastructures. It achieves hardware-agnostic performance portability across various GPU and CPU architectures using the Kokkos library. Crucially, Entity maintains a high standard for usability, clarity, and customizability, offering a robust and easy-to-use framework for developing new algorithms and grid geometries, which allows extensive control without requiring edits to the core source code. This paper details the core general-coordinate special relativistic module. Entity is the first PIC code designed to solve the Vlasov–Maxwell system in general coordinates, enabling a coordinate-agnostic framework that provides the foundational structure for straightforward extension to arbitrary coordinate geometries. The core methodology achieves numerical stability by solving particle equations of motion in the global orthonormal Cartesian basis, despite using generalized coordinates like Cartesian, axisymmetric spherical, and quasi-spherical grids. Charge conservation is ensured via a specialized current deposition technique using conformal currents. The code exhibits robust scalability and performance portability on major GPU platforms (AMD MI250X, NVIDIA A100, and Intel Max Series), with the 3D particle pusher and the current deposition operating efficiently at about 2 ns per particle per time step. Functionality is validated through a comprehensive suite of standard Cartesian plasma tests and the accurate modeling of relativistic magnetospheres in curvilinear axisymmetric geometries.

Hakobyan, Hayk [Flatiron Institute, New York, NY (↗

DOE OSTI2025

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

We present hls4ml, a free and open-source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into full designs for field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). With its flexible and modular design, hls4ml supports a large number of deep learning frameworks and can target HLS compilers from several vendors, including Vitis HLS, Intel oneAPI and Catapult HLS. Together with a wider eco-system for software-hardware co-design, hls4ml has enabled the acceleration of ML inference in a wide range of commercial and scientific applications where low latency, resource usage, and power consumption are critical. In this paper, we describe the structure and functionality of the hls4ml platform. The overarching design considerations for the generated HLS code are discussed, together with selected performance results.

FOS: Computer and information sciences↗

DOE OSTI2025

NLR HPC Eagle Jobs Data and Additional Energy Metrics

Overview: Anonymized job-level records from the Eagle high-performance computing (HPC) system at the National Laboratory of the Rockies (NLR). Each record represents a Slurm batch job with scheduling metadata, resource requests, resource utilization, CPU/GPU energy consumption, and efficiency metrics. Sensitive fields (user, account, job name) are replaced with cryptographic hashes. System & Timeframe: Eagle was a 2,000-node, 8-petaflop system operated at NLR from 2019–2024. Data covers the full operational lifetime of the system. Slurm data was processed nightly; timestamps are in Mountain Time. Funding provided by the U.S. Department of Energy, EERE. Files: esif.hpc.eagle.job-anon.zip — Core anonymized job records (Hive-partitioned Parquet) esif.hpc.eagle.job-anon-energy-metrics.zip — Same records with additional iLO and Ganglia energy metrics datacard.md — Full dataset documentation ~13.8 million rows, 62 variables. Readable with PyArrow, pandas, DuckDB, Apache Spark, or any Parquet-compatible tool. Data Collection: Jobs collected via sacct through a pipeline: Eagle Jobs API → Redpanda → StreamSets → HPCMON API → PostgreSQL. Node-level power from iLO (HP Integrated Lights-Out); GPU power from Ganglia monitoring, joined to jobs via node lists and time ranges. Preprocessing: Anonymization of name, user, and account fields via cryptographic hashing Derived columns: queue_wait, cpu_eff, max_mem_eff Simplified job state mapping (e.g., "CANCELLED BY 12345" → "CANCELLED") QoS accounting rules (buy-in, standby, or Slurm QoS value) CPU energy estimated from TDP (200W, Intel Xeon Gold 6154, 18 cores) Timezone-aware columns (_tz) sourced from LEX accounting database to correctly handle DST transitions Key Variables: Scheduling: job_id, partition, state_simple, submit_time_tz, start_time_tz, end_time_tz, queue_waitResources: nodes_req/used, processors_req/used, memory_req, wallclock_req/used, gpus_requested Efficiency: cpu_eff, max_mem_eff Energy: cpu_energy_tdp_estimated_max/used_watt_hours, node_energy_total_watt_hours (iLO), gpu0/1_energy_total_watt_hours (Ganglia) Partitions: bigmem, bigmem-8600, bigscratch, csc, dav, ddn, debug, gpu, haswell, long, mono, short, standard Job States: CANCELLED, COMPLETED, FAILED, NODE_FAIL, OUT_OF_MEMORY, PENDING, RUNNING, TIMEOUT QoS Levels: Unknown, normal, buy-in, debug, penalty, high, standby Important Notes: Non-_tz timestamp columns may be off by one hour across DST boundaries; use _tz columns for time difference calculations Energy fields are null for jobs without monitoring coverage Job step records and raw Slurm JSONB fields are excluded from this extract Do not attempt to re-identify individuals from hashed fields

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

Schulte, Jan-Frederik [Purdue U.] (ORCID:000000034↗