Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Hardware acceleration”

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.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗
DOE OSTI2025

Hardware acceleration for HPS algorithms in two and three dimensions

We provide a flexible, open-source framework for hardware acceleration, namely massively-parallel execution on general-purpose graphics processing units (GPUs), applied to the hierarchical Poincaré–Steklov (HPS) family of algorithms for building fast direct solvers for linear elliptic partial differential equations. To take full advantage of the power of hardware acceleration, we propose two variants of HPS algorithms to improve performance on two- and three-dimensional problems. In the two-dimensional setting, we introduce a novel recomputation strategy that minimizes costly data transfers to and from the GPU; in three dimensions, we modify and extend the adaptive discretization technique of Geldermans and Gillman [1] to greatly reduce peak memory usage. We provide an open-source implementation of these methods written in JAX, a high-level accelerated linear algebra package, which allows for the first integration of a high-order fast direct solver with automatic differentiation tools. We conclude with extensive numerical examples showing our methods are fast and accurate on two- and three-dimensional problems.

Fast direct solvers↗
DOE OSTI2026

Towards a Verifiable Domain-Specific Language for Hardware-Accelerated Stencils

Defining a domain-specific language (DSL) that supports vector-calculus abstractions eases the porting of partial differential equation (PDE) solvers to specialized architectures. Sufficiently high-level abstractions empower users to express universal laws with sufficient generality that the laws must always hold true within their domain of validity. A broad class of PDE solvers employs stencil-based algorithms, the target domain of Berkeley Lab's stencil accelerator chip co-design project. First released as open-source in January 2026, the Formal software framework lays a foundation for defining an embedded DSL based on composable operators that implement mimetic numerical methods -- stencil algorithms that guarantee satisfaction of discrete versions of important vector calculus theorems. The Formal DSL will be the frontend to a new class of stencil-PDE accelerators developed jointly by LBNL, UHCL, and UC Berkeley through the DOE Competitive Portfolios for Computer Science Project. This offers the potential of an order of magnitude acceleration for this important category of computational methods to serve the DOE mission. Future work on the Formal DSL will facilitate software verification via type-safe templates that enable problem-specific correctness proofs relying upon generic function theory and carefully crafted unit tests.

Rouson, Damian↗
DOE OSTI2024

Modernizing Fermilab's Accelerator Control Hardware

Modernizing the Fermilab accelerator control system is essential to future operations of the laboratory's accelerator complex. The existing control system has evolved over four decades and uses hardware that is no longer available.The Accelerator Controls Operations Research Network (ACORN) Project will modernize the control system and replace end-of-life power supplies to enable future accelerator complex operations with megawatt particle beams. The ACORN project is planning to replace Fermilab s obsolete CAMAC crate-and-card controls hardware with modern MicroTCA hardware. There are over 2,000 CAMAC cards and over 250 CAMAC crates serving various functions in Fermilab s control system. We will review the existing CAMAC hardware and provide updates on the status of the ACORN project, which includes the conceptual design of the MicroTCA replacement hardware and software tools for supporting the installation of hundreds of MicroTCA crates.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Regional Energy Hardware Innovation Accelerator

E4 Carolinas, Inc., along with the Joules Accelerator and Savannah River National Laboratory received a grant from the DOE Office of Technology Commercialization as part of its Energy Program for Innovation Clusters (EPIC) program to develop a Regional Energy Hardware Innovation Accelerator. The project objective was to create a regional energy hardware cluster innovation and accelerator ecosystem (Accelerator) to enhance commercialization opportunities for U.S. energy startups (Ventures) and Corporate Ventures (a new venture originating within an established company).

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

A Synthesis Methodology for Intelligent Memory Interfaces in Accelerator Systems

Domain-specific systems improve the performance of a specific set of applications compared to general-purpose processing systems by deploying custom hardware accelerators. These hardware accelerators are generated using high-level synthesis (HLS) tools. The HLS tools enable a comprehensive design space exploration to optimize the compute performance of the generated accelerators. However, they often ignore the challenges of implementing the accelerators in a system-on-chip, particularly how the accelerators access memory. Our work introduces a buffering system design that improves accelerators' memory accesses by intelligently employing burst transactions to prefetch useful data from external memory to on-chip local buffers. Our design is dynamic, parametric, and transparent to the accelerators generated by HLS tools. We derive the buffering system parameters using appropriate compiler-based analysis passes and memory channel latency constraints. The proposed buffering system design results in, on average, 8.8x performance improvements while lowering memory channel utilization on average by 53.2% for a set of PolyBench kernels.

Limaye, Ankur M. (ORCID:0000000194062584)↗
DOE OSTI2025

A Study on the Impact of Temperature-Dependent Ferroelectric Switching Behavior in 3D Memory Architecture

The flourishing development of neural networks that require exponentially growing amounts of data has presented an elevated demand for memory footprint. To address this, researchers have been exploring hardware accelerators with innovative memory architectures like 3D memory. These 3D memory architectures offer enhanced storage capacity and processing capabilities, at a cost of rising on-chip temperature during operation. Hafnium Zirconium Oxide (HZO) based Ferroelectric Random Access Memory (FeRAM) is a promising nonvolatile memory candidate in neural network hardware accelerators for its outstanding write performance and reliability. However, its implementation in the architecture regarding the temperature-dependent ferroelectric switching behavior has not been well studied. In this work, we study the thermal impacts on polarization switching through experimental devices and simulation results. We conduct the circuit and architecture-level simulations to showcase that one can exploit this temperature rise to reduce FeRAM's write voltage and write energy due to its unique temperature-activated polarization switching mechanisms. As the on-chip temperature increases to 351K (ambient temperature at 300K) due to neural network workloads, the access energy per bit can be reduced by 27.6% when a dynamic write voltage is applied.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Preparing MPICH for exascale

The advent of exascale supercomputers heralds a new era of scientific discovery, yet it introduces significant architectural challenges that must be overcome for MPI applications to fully exploit its potential. Among these challenges is the adoption of heterogeneous architectures, particularly the integration of GPUs to accelerate computation. Additionally, the complexity of multithreaded programming models has also become a critical factor in achieving performance at scale. The efficient utilization of hardware acceleration for communication, provided by modern NICs, is also essential for achieving low latency and high throughput communication in such complex systems. In response to these challenges, the MPICH library, a high-performance and widely used Message Passing Interface (MPI) implementation, has undergone significant enhancements. Here, this paper presents four major contributions that prepare MPICH for the exascale transition. First, we describe a lightweight communication stack that leverages the advanced features of modern NICs to maximize hardware acceleration. Second, our work showcases a highly scalable multithreaded communication model that addresses the complexities of concurrent environments. Third, we introduce GPU-aware communication capabilities that optimize data movement in GPU-integrated systems. Finally, we present a new datatype engine aimed at accelerating the use of MPI derived datatypes on GPUs. These improvements in the MPICH library not only address the immediate needs of exascale computing architectures but also set a foundation for exploiting future innovations in high-performance computing. By embracing these new designs and approaches, MPICH-derived libraries from HPE Cray and Intel were able to achieve real exascale performance on OLCF Frontier and ALCF Aurora respectively.

Guo, Yanfei [Argonne National Laboratory (ANL), Ar↗
DOE OSTI2025

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators

Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose significant challenges, requiring efficient hardware acceleration. Benchmarking the performance of LLMs across diverse hardware platforms is crucial to understanding their scalability and throughput characteristics. We introduce LLM-Inference-Bench, a comprehensive benchmarking suite to evaluate the hardware inference performance of LLMs. We thoroughly analyze diverse hardware platforms, including GPUs from Nvidia and AMD and specialized AI accelerators, Intel Habana and SambaNova. Our evaluation includes several LLM inference frameworks and models from LLaMA, Mistral, and Qwen families with 7B and 70B parameters. Our benchmarking results reveal the strengths and limitations of various models, hardware platforms, and inference frameworks. We provide an interactive dashboard to help identify configurations for optimal performance for a given hardware platform.

Chitty-Venkata, Krishna Teja↗
DOE OSTI2026

A Benchmark Suite for Evaluating Scientific AI Workloads on GPUs

AI applications have been steadily increasing in the allocation portfolio among leadership computing facilities. These applications depend on deep learning frameworks with hardware acceleration and underlying software systems. With the rapid development of applications, software stacks, and hardware devices, it is essential to evaluate the performance of core operations in AI workloads for direction of optimizations and procurement of next-generation high-performance computing (HPC) infrastructures. Currently, most benchmarks lack scientific AI workloads. So, we present DeepKernelBench and the experimental results of evaluating the benchmark suite for early observations and performance comparisons on datacenter GPUs using representative workloads for scientific AI, including Attentions, General matrix multiplications, Geometrics and Fourier neural operations.

Jin, Zheming [Advanced Micro Devices (AMD)]↗
DOE OSTI2024

FiberFlex: Real-time FPGA-based Intelligent and Distributed Fiber Sensor System for Pedestrian Recognition

In recent years, security monitoring of public places and critical infrastructure has heavily relied on the widespread use of cameras, raising concerns about personal privacy violations. To balance the need for effective security monitoring with the protection of personal privacy, we explore the potential of optical fiber sensors for this application. This article proposes FiberFlex, an intelligent and distributed fiber sensor system. Ultizing Field Programmable Gate Arrays (FPGA) high-level synthesis (HLS) acceleration, FiberFlex offers real-time pedestrian detection by co-designing the entire pipeline of optical signal acquisition, processing, and recognition networks based on the principles of optical fiber sensing. As a promising alternative to traditional camera-based monitoring systems, FiberFlex achieves pedestrian detection by analyzing the vibration patterns caused by pedestrian footsteps, enabling security monitoring while preserving individual privacy. FiberFlex comprises three modules: First , fiber-optic sensing system: A fiber-optic distributed acoustic sensing (DAS) system is built and used to measure the ground vibration waves generated by people walking. Second , algorithms: We first collect the training data by measuring the ground vibration waves, label the data, and use the data to train the neural network models to perform pedestrian recognition. Third , hardware accelerators: We use HLS tools to design hardware modules on FPGA for data collection and pre-processing and integrate them with the downstream neural network accelerators to perform in-line real-time pedestrian detection. The final detection results are sent back from FPGA to the host CPU. We implement our system FiberFlex with the in-house built DAS system and AMD/Xilinx Kintex7 FPGA KC705 board and verify the whole system using the real-world collected data. We conduct recognition tests on five test subjects of varying ages, heights, and weights in a fixed sensing area. Each subject experienced 20 real-time recognition tests using their daily walking habits, and the subjects were given adequate rest between tests. After 100 tests on five test subjects, the overall real-time recognition accuracy exceeded \(88.0\%\) . The whole system uses 55 W of power, 33 W in the optical DAS system and 22 W in the FPGA. Relying on its end-to-end interdisciplinary design, FiberFlex seamlessly combines fiber-optic sensors with FPGA accelerators to enable low-power real-time security monitoring without compromising privacy, making it a valuable addition to the existing security monitoring network. According to FiberFlex, more valuable research can be conducted in the future, such as fall monitoring for the elderly, migration of identification networks between different application scenarios, and improvement of anti-interference performance in more complex environments. In future perception networks, where the “eyes” are not feasible, let’s use fiber optic touch instead.

Distributed↗
DOE OSTI2025

A cross-platform execution engine for the quantum intermediate representation

Hybrid languages like the quantum intermediate representation (QIR) are essential for programming systems that mix quantum and conventional computing models, while execution of these programs is often deferred to a system-specific implementation. Here, we develop the QIR Execution Engine (QIR-EE) for parsing, interpreting, and executing QIR across multiple hardware platforms. QIR-EE uses LLVM to execute hybrid instructions specifying quantum programs and, by design, presents extension points that support customized runtime and hardware environments. We demonstrate an implementation that uses the XACC quantum hardware-accelerator library to dispatch prototypical quantum programs on different commercial quantum platforms and numerical simulators, and we validate execution of QIR-EE on IonQ, Quantinuum, and IBM hardware. Our results highlight the efficiency of hybrid executable architectures for handling mixed instructions, managing mixed data, and integrating with quantum computing frameworks to realize cross-platform execution.

LLVM↗
DOE OSTI2025

Understanding and Estimating Error Propagation in Neural Networks for Scientific Data Analysis

Neural networks are increasingly integrated into scientific discovery, where input data reduction and model quantization play a key role in accelerating inference. However, understanding and mitigating the impact of these techniques on output error is critical for ensuring reliable results, particularly in tasks demanding high numerical precision. This paper introduces a comprehensive framework for optimizing neural network inference in scientific computing by combining data reduction and weight quantization while maintaining error-controlled outcomes. We develop theoretical analyses to bound error propagation under these reductions and propose a framework that balances computational performance with error constraints. Evaluation on real-world learning-based combustion simulations and satellite image classification demonstrates that our derived error bounds accurately predict observed errors while enabling significant computational speedup under our framework. This work highlights the potential for further leveraging advancements in modern lossy compression algorithms and hardware accelerators that support lower-precision formats.

He, Weiming [New Jersey Institute of Technology]↗
DOE OSTI2026

PowerMappeR: Power-Optimized Mapping of SNNs onto ReRAM Crossbars coupled via Packet-Switched NoCs

Many recent efforts in developing hardware-accelerated spiking neural networks (SNNs) are characterized by deep co-design between algorithms, architectures, and devices. Architectural advances overcome device constraints by coupling together many small resistive-RAM (ReRAM) crossbars via a network-on-chip (NoC) for neuromorphic component operation. Concurrently, improved SNN training methods increase accuracy and structural sparsity in networks despite growing problem sizes. Finally, compilers leverage these attributes to minimize area and inter-crossbar communication while mapping large SNNs to sophisticated architectures. However, for compiler-driven co-design to realize increasingly complex and profitable optimizations, a compile-time view of power consumption is critical. We present PowerMappeR to express and optimize over mapping-, architecture-, and device-specific power consumption information. By modeling the dynamic power of well-established components, we develop an integer linear programming (ILP)-based, encoding-agnostic, parametric power estimation model. Using this model, we demonstrate practical improvements in area and inter-crossbar communication by 0%–9.5% and 1.4%–5.1%, respectively. We also limit hotspot formation during optimization, achieving comparable or better results in targeted metrics with up to 96.4%–97.1% restriction of hotspot magnitude. Finally, we introduce profile-guided formulations to reduce worst-case and expected-case hotspot magnitude by 40.7%–69.5% and 40.6%–56.3%, respectively. Optimizing worst-case hotspot magnitude incidentally improves expected-case magnitude by 10.85%–33.45%. Reciprocally, optimizing expected-case magnitude incidentally improves worst-case magnitude by 4.33%–39.87%. Validation against hardware simulators confirms that PowerMappeR can decrease dynamic power consumption by 12.6%–27.3%.

Pohl, Devin [ORNL] (ORCID:0009000040149027)↗
DOE OSTI2025

Fully implicit crystal plasticity models representing orientations with modified Rodrigues parameters

Here, this work describes a crystal plasticity formulation combining several mathematical, numerical, and implementation choices to produce a highly efficient model. Specifically, the key choices in the implementation are (1) representing orientations with modified Rodrigues parameters, (2) implementing a fully coupled implicit time integration for the elastic stretch, the crystal orientations, and the model internal variables, (3) implementing the model in the NEML2 constitutive modeling framework, based on PyTorch, to vectorize the calculations and port the computation to GPUs and other hardware accelerators, and (4) an exact implementation of the consistent tangent matrix, even for arbitrary coupling to other field variables beyond the displacements, like temperature, neutron fluence, etc. The first two features of the model are, to our knowledge, novel. The paper considers each of these choices individually as well as the final model as a whole. This includes a full description of modified Rodrigues parameters, their advantages over other representations of orientations, the mathematical formulae and tools required to implement a model with modified Rodrigues parameters, and a detailed description of the geometry of the space of modified Rodrigues parameters (in an appendix). It also includes a description of a fully implicit time integration scheme for the orientations and the advantages in representing orientations with modified Rodrigues parameters in implementing such a model. The work then assess, via numerical examples, the advantages of fully coupled implicit time integration versus more common decoupled and explicit time integration schemes. These studies demonstrate the computational advantages of fully coupled integration versus other time integration algorithms, though the performance of the competing models depends on the complexity of the underlying single crystal model. The study concludes by demonstrating that the choice of time integration method affects the sharpness of the predicted texture, with explicit methods for integrating the orientations overestimating texture sharpness and implicit methods underestimating texture sharpness.

Crystal plasticity↗
DOE OSTI2024

Iterative methods in GPU-resident linear solvers for nonlinear constrained optimization

Linear solvers are major computational bottlenecks in a wide range of decision support and optimization computations. The challenges become even more pronounced on heterogeneous hardware, where traditional sparse numerical linear algebra methods are often inefficient. For example, methods for solving ill-conditioned linear systems have relied on conditional branching, which degrades performance on hardware accelerators such as graphical processing units (GPUs). To improve the efficiency of solving ill-conditioned systems, our computational strategy separates computations that are efficient on GPUs from those that need to run on traditional central processing units (CPUs). Our strategy maximizes the reuse of expensive CPU computations. Iterative methods, which thus far have not been broadly used for ill-conditioned linear systems, play an important role in our approach. In particular, we extend ideas from Arioli et al., (2007) to implement iterative refinement using inexact LU factors and flexible generalized minimal residual (FGMRES), with the aim of efficient performance on GPUs. In conclusion, we focus on solutions that are effective within broader application contexts, and discuss how early performance tests could be improved to be more predictive of the performance in a realistic environment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

GPU-friendly surface model for Monte-Carlo detector simulations

The demands for Monte-Carlo simulation are drastically increasing with the Large Hadron Collider’s high-luminosity upgrade, and are expected to exceed the currently available compute resources. At the same time, modern high-performance computing has adopted powerful hardware accelerators, particularly GPUs. The AdePT and Celeritas projects aim to address the demanding computational needs by leveraging these heterogeneous computing architectures. While both have successfully ported realistic detector simulations to GPUs using the VecGeom library, the complexity of geometry modeling emerged as a bottleneck. Thread divergence and high register usage were degrading the GPU performance. Therefore, a new, GPU-friendly surface-based model has been introduced in the VecGeom library that decomposes the divergent code of the 3D primitive solids into simpler and more balanced surface algorithms. In this work, we present the latest developments, focusing on the additions required to efficiently model complex setups like the CMS Phase-2 geometry. This includes memory reduction techniques, and adding accelerating structures for faster traversal.

Diederichs, Severin [CERN]↗
DOE OSTI2024

A Performance and Energy Study of GPU-Resident Preconditioners for Conjugate Gradient Solvers: In the Context of Existing and Novel Approaches

Optimizing a particular subprogram out of the set of Basic (sparse) Linear Algebra Subprograms (BLAS) for a given architecture is a common topic of research. In applications, however, these BLAS functions rarely appear in isolation; usually, many of them are used together, in various combinations and with varying inputs. As the need to solve a large, sparse linear system is ubiquitous throughout HPC applications, linear solvers constitute a realistic, sufficiently complex and well-defined representative use case for composite BLAS routines. To this end, based on a representative set of matrices drawn from a diverse set of fields, we present a framework to study, from the performance and energy perspective, the efficacy of GPU- resident parallel Conjugate Gradient (CG) linear solver with different preconditioner options, including Gauss-Seidel, Jacobi, and incomplete Cholesky. We also propose a novel GPU-based preconditioner, in which the triangular solves are approximated by an iterative process. The development of this preconditioner was motivated by solving large graph Laplacian linear systems, for which the existing preconditioners either perform slow on GPU-based platforms or are not applicable. We compare the performance of these preconditioners on different hardware accelerator architectures, i.e., AMD MI250X, MI100, Nvidia A100, V100, and Jetson. Our experiments reveal performance trade-offs and provide information on how to select the best strategy for the given linear system, dictated by its properties, and the platform of interest. We demonstrate the application of our novel preconditioner for solving CG and graph Laplacian systems. Overall, the framework can be utilized as a benchmark to guide informed decisions in choosing a specific preconditioner, i.e., whether it is better to rely on the performance of a triangular solver or on the performance of sparse matrix-vector product. Finally, by considering power consumption to solve the linear systems, we report the energy footprint for the solvers.

Preconditioned Conjugate Gradient, GPUs, iterative↗