Native Implementation of TensorFlow-Trained Deep and Bayesian Neural Networks in Fortran
Explore the source record for details and available documents.
Furlong, Aidan [North Carolina State University]↗
SEARCH · Engineering Papers
Results for “Fortran”
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.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
To Interoperability And Beyond: Interoperable Types Through the Promises of C and C++ and ABI Abuse [Slides]
This presentation presents a technique that allows passing of Fortran nested-type hierarchies interoperably to C++. The technique is motivated by the Eulerian Application Project’s need to port code from Fortran to C++ to utilize the Kokkos performance portability library. The resulting method allows hierarchies of types to become interoperable while at the same time transforming Fortran array members of the original Fortran type into Kokkos::Views in the resulting C++ type.
97 MATHEMATICS AND COMPUTING↗
Large language model evaluation for high–performance computing software development
We apply AI-assisted large language model (LLM) capabilities of GPT-3 targeting high-performance computing (HPC) kernels for (i) code generation, and (ii) auto-parallelization of serial code in C ++, Fortran, Python and Julia. Our scope includes the following fundamental numerical kernels: AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG, and language/programming models: (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). Kernel implementations are generated using GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code given simple + + prompt variants. To quantify and compare the generated results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. For auto-parallelization, we use ChatGPT interactively giving simple prompts as in a dialogue with another human including simple “prompt engineering” follow ups. Results suggest that correct outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general-purpose Python can benefit from adding language keywords, while Julia prompts perform acceptably well for its Threads and CUDA.jl programming models. Finally, we expect to provide an initial quantifiable point of reference for code generation in each programming model using a state-of-the-art LLM. Overall, understanding the convergence of LLMs, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.
97 MATHEMATICS AND COMPUTING↗
Using a Large Language Model as a Building Block to Generate Usable Validation and Verification Suite for OpenMP
In the HPC area, both hardware and software move quickly. Often new hardware is developed and deployed, the corresponding software stack, including compilers and other tools, are under active development while leading edge software developers are working to port and tune their applications, all at the same time. While the software ecosystem is in flux, one of the key challenges for users is obtaining insight into the state of implementation of key features in the programming languages and models their applications are using – whether they have been implemented, and whether the implementation conforms to the specification, especially for newly implemented features (less tested by widespread use). OpenMP is one of the most prominent shared memory programming models used for on-node programming in HPC. With the shift towards accelerators (such as GPUs and FPGAs) and heterogeneous programming OpenMP features are getting more complex. It is natural to ask whether generative AI approaches, and large language models (LLMs) in particular, can help in producing validation and verification test suites to allow users better and faster insights into the availability and correctness of OpenMP features of interest. In this work, we explore the use of ChatGPT-4 to generate a suite of tests for OpenMP features. We have chosen a set of directives and clauses, a total of 78 combinations, which first appeared in OpenMP 3.0 (released in May 2008) but are also relevant for accelerators. We prompted ChatGPT to generate tests in the C and Fortran languages, for both host (CPU) and device (accelerator). On the Summit super-computer using the GNU implementation, we found that, of the 78 generated tests 67 C tests and 43 Fortran tests compiled successfully and fewer than those executed to completion. On further analysis we show that not all generated tests are valid. We document the process, results, and provide detailed analysis regarding the quality of tests generated. With the aim of providing input to a production quality validation and verification suite, we manually implement the corrections required to make the tests valid according to the current OpenMP specification. We quantify this effort as small, medium, or large, and record the lines of code changed to correct the invalid tests. With the corrected tests we validate recent implementations from HPE, AMD, and GNU on the Frontier supercomputer. Our experiment and subsequent analysis show that although LLMs are capable of producing HPC specific codes, they are limited by their understanding of the deeper semantics and restrictions of programming models such as OpenMP. Unsurprisingly more commonly used features have better support, while some OpenMP 3.0 directives such as sections and tasking are not universally supported on accelerators. We demonstrate that successful compilation and execution to completion are inadequate metrics for evaluating generated code and that, at this time, commodity LLMs require expert intervention for code verification. This points to gaps in the training data that is currently available for HPC. We demonstrate that with "small" effort 37% of generated invalid C tests and 63% of generated invalid Fortran tests could be corrected. This improves productivity of test generation as we circumvent writing from scratch and the common programming errors associated with it.
Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗
Julienne v1.0.0
Julienne is a compiler-portable unit-testing framework for Fortran software projects, including those that use the parallel/accelerator-programming features of Fortran 2023. Julienne achieves portability across compilers through minimalism and isolation. The minimal design ensures that Julienne uses only features supported by the majority of Fortran compilers. The isolation through zero dependencies ensures that no other projects block Julienne from building with a particular compiler. Julienne also contains with additional services that support its unit-testing code. These include functions for manipulating strings, command lines and input/output format strings; and a user-defined collective subroutine for verifying that all processes pass a test in parallel testing. Julienne's name derives from the term for vegetables sliced into thin strings: julienne vegetables. Julienne captures the authors' most frequently used thin slice of the Veggies and Sourcery software repositories while avoiding certain compiler limitations of the those two packages.
Rouson, Damian↗
CodeScribe Agent
SF-26-086 CodeScribe introduces a structured, multi-stage pipeline that combines deterministic program analysis with LLM-powered translation to enable incremental, testable Fortran-to-C++ migration. First, `code-scribe index` traverses the project directory tree and produces `scribe.yaml` metadata files recording all modules, subroutines, and functions at each level, giving the LLM accurate structural context instead of a hallucinated codebase model. Second, `code-scribe draft` performs the deterministic portion of translation — converting Fortran types to C++ equivalents, replacing `use` statements with `#include` and `using namespace` directives, and detecting constructs requiring special handling — while embedding`scribe-prompt` annotations that guide the LLM through non-trivial cases such as statement-function-to-lambda conversions and `extern "C"` wrapper generation. Third, `code-scribe translate` applies project-specific TOML-based few-shot prompt templates and submits the composed prompt to a pluggable LLM backend (OpenAI, Anthropic, Argonne ARGO, any OpenAI-compatible endpoint, or local Hugging Face checkpoints), producing a C++ source file, a header, and a Fortran-C++ interface file for each translated routine so the codebase compiles and runs correctly throughout the migration. Beyond translation, CodeScribe includes a tool-using coding agent (`code-scribe agent`) with read, bash, edit, and write capabilities, and a bounded loop mode (`code-scribe loop`) that runs repeated stateless agent sessions over a task file with restricted tool access — enabling sustained, auditable software development workflows for broader scientific computing tasks.
Dhruv, Akash [Argonne National Laboratory (ANL), A↗
Fiats: Functional inference and training for surrogates
Fiats provides a platform for research on the training and deployment of neural-network surrogate models for computational science. Fiats also supports exploring, advancing, and combining functional, object-oriented, and parallel programming patterns in Fortran 2023. As such, the Fiats name has dual expansions: “Functional Inference And Training for Surrogates” or “Fortran Inference And Training for Science.” Fiats inference and training procedures are pure and therefore satisfy a language constraint imposed on procedure invocations inside Fortran’s parallel loop construct: do concurrent. Furthermore, the Fiats training procedures are built around a do concurrent parallel reduction. Several compilers can automatically parallelize do concurrent on Central Processing Units (CPUs) or Graphics Processing Units (GPUs). Fiats thus aims to achieve performance portability through standard language mechanisms.
Rouson, Damian [Lawrence Berkeley National Laborat↗
Coupling Noah-Multiparameterization land-surface Model with Energy Research and Forecasting Model
The Energy Research and Forecasting (ERF) model is a high-performance atmospheric model built on the AMReX adaptive mesh refinement (AMR) framework, enabling efficient simulations on heterogeneous computing platforms that combine multicore processors with hardware accelerators. To support land–atmosphere interactions within ERF’s AMR-based environment, a land-surface model must be capable of operating directly on hierarchically refined meshes. In this work, we present a methodology for coupling the Fortran-based Noah-Multiparameterization (Noah-MP) land-surface model with ERF’s C++ codebase. Rather than rewriting Noah-MP, we construct a Fortran–C interoperability layer using CodeScribe, a tool that leverages large language models (LLMs) to automate the generation of interface code. CodeScribe applies structured prompting techniques to generate bindings that support efficient data exchange and function calls between ERF and Noah-MP. The coupling framework also incorporates AMR-aware data handling strategies, allowing NoahMP to operate seamlessly within ERF’s hierarchical mesh structure. This work provides a structured approach for integrating legacy Fortran models into modern C++-based modeling systems using LLM-assisted code generation.
54 ENVIRONMENTAL SCIENCES↗
RGM: Random Geological Model Generation Package
This Fortran code is to accompany a manuscript to be submitted to Computers & Geosciences, a high-impact, peer-reviewed journal in computer methods for geosciences research. This Fortran code focuses on generation of synthetic geological models using a multi-randomization strategy. Generating high-fidelity synthetic geological models, including realistic seismic reflector migration images, faults, salt bodies, and relative geological time images, is the key for many supervised machine learning methods that aim to delineate faults and other geological properties of interest from seismic migration images. Our package contains two major functionalities: generating 2D synthetic random geological models and generating 3D synthetic random geological models. In each step of the generation process, we set random values for key properties of a geological model to improve the fidelity of the resulting geological model. The package also includes example codes on how to use the random geological model generation subroutines. We name this package RGM – Random Geological Model generation package.
Gao, Kai↗
fpm-find v0.1.0
This program searches the fortran-lang community's package index (https://github.com/fortran-lang/webpage/blob/main/data/package_index.yml). The program is designed for use as a Fortran Package Manager (fpm) plugin.
Rouson, Damian [Lawrence Berkeley National Laborat↗
Equilipy: a python package for calculating phase equilibria
The CALPHAD (CALculation of PHAse Diagram) approach (Nigel Saunders & Miodownik, 1998) provides predictions for thermodynamically stable phases in multicomponent-multiphase materials across a wide range of temperatures. Consequently, the CALPHAD calculations became an essential tool in materials and process design (Luo, 2015). Such design tasks frequently require navigating a high-dimensional space due to multiple components involved in the system. This increasing complexity demands high-throughput CALPHAD calculations, especially in the rapidly evolving field of alloy design. In response to the need, we developed Equilipy an open-source Python package designed for calculating phase equilibria of multicomponent-multiphase systems. Equilipy is specifically tailored for high-throughput CALPHAD calculations, offering parallel computations across multiple processors and nodes with the given NPT input conditions namely elemental compositions (N), pressure (P), and temperature (T). Equilipy utilizes the program structure and Gibbs energy functions from the Fortran-based program, Thermochimica (Piro et al., 2013), with incorporating a new Gibbs energy minimization algorithm. This algorithm, originally developed by Capitani and Brown in 1987 (Capitani & Brown, 1987), has been revised and implemented to enhance the stability and performance of calculations. The Fortran codes are precompiled and interfaced with Python via F2PY, ensuring high computation speed. Benchmark tests shown in Figure 1 demonstrate that Equilipy’s computation speed is comparable to those of established commercial software, TC-Python and PanPython. This result highlights its efficiency and potential applications in various scientific and industrial fields.
97 MATHEMATICS AND COMPUTING↗
Deflagration to Detonation Transition Update: XDDT Code Modularization
A legacy FORTRAN 77 implementation of the Baer–Nunziato two-phase mixture theory for deflagration-to-detonation transition (DDT) in reactive granular materials—hereafter the XDDT (eXplosive DDT) code—has been modularized to Fortran 90 with modular structure, external input files, and adaptive mesh capability. During validation, two code defects were identified and corrected: an inconsistency in the nodal solid pressure evaluation and a nonphysical burn-front tracking criterion. The ignition criterion was also corrected to use the granular surface temperature from the interface heat transfer model, matching the original Baer implementation. An initial attempt to validate against Figure 3 of the original Baer and Nunziato (1986) paper revealed that the code’s detonation velocity on a 201-node mesh (5.5 km/s) was approximately 21% below the expected Chapman–Jouguet value for 70% TMD HMX (∼7 km/s). Validation was redirected to the piston-driven DDT experiments of McAfee et al. (1989), Shot B-9036, for which well-characterized ionization-pin data are available. With the compaction-burn coefficient calibrated to 𝐶 𝛼 = 75, the XDDT code reproduces the DDT transition time to within 0.4% and produces a steady-state detonation velocity within 4% of the McAfee experimental value of 6.36 km/s. The burn model was generalized to support pressure-dependent exponents, enabling application to nitrocellulose-based ball propellants (TS3659) with a cube-root pressure dependence. Validation against the Sandusky/Baer PDC82 piston-impact experiment yielded a reactive wave velocity of 2.3–2.8 km/s, in good agreement with the experimental value of ∼2.2 km/s, and wave coalescence within 5% of the experimental timing. The mathematical model, input parameter requirements, and a roadmap for extending XDDT to PETN with an autocatalytic burn model are presented.
45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
Precision of ENDF and ENDL Formatted Data Files
The purpose is to ensure that today’s processing codes produced output to meet today’s accuracy needs. Since 1958 ENDL and about 1965 ENDF have each used a text format to define nuclear and atomic data in 11 columns for each data field. When these formats originated this was judged to be adequate to reproduce the accuracy of data at the time and to meet the needs of our applications. When these formats originated the dominant computer language of the day was FORTRAN and if written using an E11.4 format it would include only 4 or 5 digits of precision, e.g., 0.1234E-03 or 1.2345E-02, varying from one computer/system to another the result was not even unique. In the case of ENDF the 4 digit precision was not even adequate to uniquely define the atomic weight of the target, e.g., U238 = 92238 = 0.9224E+5 = WRONG! From its inceptions the ENDF format had a precision problem. One of my first tasks when in 1967 fresh out of graduate school I joined what later became the National Nuclear Data Center (NNDC), was to address this precision problem. By working with ENDF producers and users throughout the U.S. we verified, 1) E or D is not required to define FORTRAN readable numbers, e.g., E+4 or +4 are both o.k. 2) With ENDF energy eV and cross section in barns, 2 digit exponents are almost never required. 3) Since energy is never negative we could use the first of the 11 columns for a digit. Knowing this allowed us to produce ENDF/B-II to 6 or 7 digit precision, e.g., blank, decimal point, 2 or 3 digit exponent, e.g., ^1.23456-12 or ^1.234567-3. Below is an example of the actual ENDF/B-II data released. Note, the date 1970 and the atomic weight, ZA, uniquely defined to 6-digit accuracy, ^9.22350+ 4.
73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
On a Simplified Approach to Achieve Parallel Performance and Portability Across CPU and GPU Architectures
This paper presents software advances to easily exploit computer architectures consisting of a multi-core CPU and CPU+GPU to accelerate diverse types of high-performance computing (HPC) applications using a single code implementation. The paper describes and demonstrates the performance of the open-source C++ matrix and array (MATAR) library that uniquely offers: (1) a straightforward syntax for programming productivity, (2) usable data structures for data-oriented programming (DOP) for performance, and (3) a simple interface to the open-source C++ Kokkos library for portability and memory management across CPUs and GPUs. The portability across architectures with a single code implementation is achieved by automatically switching between diverse fine-grained parallelism backends (e.g., CUDA, HIP, OpenMP, pthreads, etc.) at compile time. The MATAR library solves many longstanding challenges associated with easily writing software that can run in parallel on any computer architecture. This work benefits projects seeking to write new C++ codes while also addressing the challenges of quickly making existing Fortran codes performant and portable over modern computer architectures with minimal syntactical changes from Fortran to C++. We demonstrate the feasibility of readily writing new C++ codes and modernizing existing codes with MATAR to be performant, parallel, and portable across diverse computer architectures.
97 MATHEMATICS AND COMPUTING↗
CI/CD Efforts for Validation, Verification and Benchmarking OpenMP Implementations
Software developers must adapt to keep up with the changing capabilities of platforms so that they can utilize the power of High-Performance Computers (HPC), including exascale systems. OpenMP, a directive-based parallel programming model, allows developers to include directives to existing C, C++, or Fortran code to allow node level parallelism without compromising performance. This paper describes our CI/CD efforts to provide easy evaluation of the support of OpenMP across different compilers using existing testsuites and benchmark suites on HPC platforms. Our main contributions include (1) the set of a Continuous Integration (CI) and Continuous Development (CD) workflow that captures bugs and provides faster feedback to compiler developers, (2) an evaluation of OpenMP (offloading) implementations supported by AMD, HPE, GNU, LLVM, and Intel, and (3) evaluation of the quality of compilers across different heterogeneous HPC platforms. With the comprehensive testing through the CI/CD workflow, we aim to provide a comprehensive understanding of the current state of OpenMP (offloading) support in different compilers and heterogeneous platforms consisting of CPUs and GPUs from NVIDIA, AMD, and Intel.
Jarmusch, Aaron↗
Implementing a unified solver for nonlinearly constrained optimization
SQP and interior-point methods (also referred to as Lagrange-Newton methods) typically share key algorithmic components, such as strategies for computing descent directions and mechanisms that promote global convergence. Building on this insight, we introduce a unifying framework with eight building blocks that abstracts the workflows of Lagrange-Newton methods. We then present Uno, a modular C++ solver that implements our unifying framework and allows the automatic combination of a wide range of strategies with no programming effort from the user. Uno is meant to (1) organize mathematical optimization strategies into a coherent hierarchy; (2) offer a wide range of efficient and robust methods that can be compared for a given instance; (3) enable researchers to experiment with novel optimization strategies; and (4) reduce the cost of development and maintenance of multiple optimization solvers. Uno’s software design allows user to compose new customized solvers for emerging optimization areas such as robust optimization or optimization problems with complementarity constraints, while building on reliable nonlinear optimization techniques. We demonstrate that Uno is highly competitive against state-of-the-art solvers filterSQP, IPOPT, SNOPT, MINOS, LANCELOT, LOQO, and CONOPT on a subset of 429 small problems from the CUTE collection. Uno is available as open-source software under the MIT license at https://github.com/cvanaret/Uno and via its C, Julia, Python, Fortran, and AMPL interfaces.
97 MATHEMATICS AND COMPUTING↗
Extending TOUGH + HYDRATE with a parallel particle transport simulator: numerical investigation of sand production during gas production from hydrate deposits
A new parallel code for simulating particle transport in porous media is integrated with the TOUGH + HYDRATE simulator to investigate sand production associated with gas production from unconsolidated gas hydrate-bearing sediments (HBS). Here, the parallel coupled simulator is named THMPT and uses the integral finite difference method to describe the Darcian and non-Darcian flow of fluids and heat transport, the finite element method to describe the associated geomechanical changes, and the discrete element method to track the trajectory of individual sand particles within the HBS. The THMPT simulator is written in Fortran, incorporates multiple optimized algorithms, and can comprehensively address the coupled flow, thermal, chemical, geomechanical, and particle transport processes that characterize the system behaviors during gas production from HBS. The simulator can capture all processes involved in sand particle transport in porous media, including sand detachment, collision, clogging (i.e., bridging), and migration. A benchmark case study of sand production in the course of depressurization-induced gas production from a representative HBS reveals various distinct microscopic particle migration mechanisms and the adverse impact of sand particle detachment, transport, and clogging. The numerical investigation also examines the effect of bottomhole pressure on mitigating sand production. The simulation results indicate that sand clogging near the wellbore significantly reduces permeability, decreasing gas production by at least 50%. Lastly, the efficiency of gravel packing in mitigating sand production is numerically evaluated, revealing that the structure of the porous media appears to profoundly influence the macroscopic motion behavior of sand particles and sand clogging characteristics.
discrete element method↗
Generation of random geological models using multi-randomization for machine learning
Generating high-fidelity geological models is essential for advancing machine learning (ML) methods in automated seismic interpretation. For instance, seismic images paired with corresponding fault labels are foundational for ML-based fault detection from seismic migration sections. While several open-access datasets of random geological models exist, open-source tools specifically designed to produce large volumes of such models for ML applications remain scarce. To address this gap, we present RGM (Random Geological Model), an open-source software package for efficiently generating 2D and 3D synthetic geological models tailored for ML workflows. RGM supports the creation of diverse model components, including medium property distributions (P-/S-wave velocities and density), seismic reflectivity images (i.e., synthetic migration sections), relative geological time, and discrete fault attributes such as probability, dip, strike, rake, and displacement. It also accommodates the creation of complex geological features such as salt bodies and unconformities. The model generation algorithm employs a multi-randomization strategy, yielding an effectively infinite-dimensional model space that encompasses a wide range of geological scenarios and associated seismic features. Furthermore, RGM incorporates a method to generate synthetic elastic migration images using analytical elastic reflection coefficients combined with frequency-dependent scaling. This functionality enables the creation of training datasets for ML models that leverage elastic seismic images. RGM is implemented in modern object-oriented Fortran, allowing users to flexibly control statistical parameters governing model variability. We demonstrate the capability, performance, and geological realism of the package through comprehensive 2D and 3D examples.
58 GEOSCIENCES↗