SEARCH · Engineering Papers

Results for “gpu”

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 955 records · Page 53

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Scaling the memory wall using mixed-precision - HPG-MxP on an exascale-class machine

Mixed-precision algorithms have been proposed as a way for scientific computing to benefit from some of the gains seen for AI on recent high performance computing (HPC) platforms. A few applications dominated by dense matrix operations have seen substantial speedups by utilizing low precision formats such as FP16. However, a majority of scientific simulation applications are memory bandwidth limited. Beyond preliminary studies, the practical gain from using mixed-precision algorithms on a given high-performance computing (HPC) system is largely unclear. The High Performance GMRES Mixed Precision (HPG-MxP) benchmark has been proposed to measure the useful performance of a HPC system on sparse matrix-based mixed-precision applications. In this work, we present an implementation of the HPG-MxP benchmark for an exascale system and describe our algorithm enhancements. We show for the first time a speedup of 1.6x using a combination of double- and single-precision keeping the same residual level on modern GPU-based supercomputers.

Kashi, Aditya [ORNL] (ORCID:0000000325893792)↗

DOE OSTI2025

Simulating many-engine spacecraft: Exceeding 1 quadrillion degrees of freedom via information geometric regularization

We present an optimized implementation of the recently proposed information geometric regularization (IGR) for unprecedented scale simulation of compressible fluid flows applied to multi-engine spacecraft boosters. We improve upon state-of-the-art computational fluid dynamics (CFD) techniques in terms of computational cost, memory footprint, and energy-to-solution metrics. Unified memory on coupled CPU–GPU or APU platforms increases problem size with negligible overhead. Mixed half/single-precision storage and computation are used on well-conditioned numerics. We simulate flow at 200 trillion grid points and 1 quadrillion degrees of freedom, exceeding the current record by a factor of 20. A factor of 4 wall-time speedup is achieved over optimized baselines. Ideal weak scaling is observed on OLCF Frontier, LLNL El Capitan, and CSCS Alps using the full systems. Strong scaling is near ideal at extreme conditions, including 80% efficiency on CSCS Alps with an 8 node baseline and stretching to the full system.

Wilfong, Benjamin [Georgia Institute of Technology↗

DOE OSTI2025

Cosmological Hydrodynamics at Exascale: A Trillion-Particle Leap in Capability

Resolving the most fundamental questions in cosmology requires simulations that match the scale, fidelity, and physical complexity demanded by next-generation sky surveys. To achieve the realism needed for this critical scientific partnership, detailed gas dynamics must be treated self-consistently with gravity for end-to-end modeling of structure formation. Exascale computing enables simulations that span survey-scale volumes while incorporating key astrophysical processes that shape complex cosmic structures. We present results from CRK-HACC, a cosmological hydrodynamics code built for extreme scalability. Using separation-of-scale techniques, GPU-resident tree solvers, in situ analysis pipelines, and multi-tiered I/O, CRK-HACCexecuted Frontier-E: a four trillion particle full-sky simulation, over an order of magnitude larger than previous efforts. The run achieved 513.1 PFLOPs peak performance, processing 46.6 billion particles per second and writing more than 100 PB of data in just over one week of runtime. Frontier-E marks a significant advance in predictive modeling for next-generation cosmological science.

Frontiere, Nicholas [Argonne National Laboratory (↗

DOE OSTI2025

Advancing Quantum Many-Body GW Calculations on Exascale Supercomputing Platforms

Advanced ab initio materials simulations face growing challenges as increasing systems and phenomena complexity requires higher accuracy, driving up computational demands. Quantum many-body GW methods are state-of-the-art for treating electronic excited states and couplings but often hindered due to the costly numerical complexity. Here, we present innovative implementations of advanced GW methods within the BerkeleyGW package, enabling large-scale simulations on Frontier and Aurora exascale platforms. Our approach demonstrates exceptional versatility for complex heterogeneous systems with up to 17,574 atoms, along with achieving true performance portability across GPU architectures. We demonstrate excellent strong and weak scaling to thousands of nodes, reaching double-precision core-kernel performance of 1.069 ExaFLOP/s on Frontier (9,408 nodes) and 707.52 PetaFLOP/s on Aurora (9,600 nodes), corresponding to 59.45% and 48.79% of peak, respectively. Our work demonstrates a breakthrough in utilizing exascale computing for quantum materials simulations, delivering unprecedented predictive capabilities for rational designs of future quantum technologies.

Zhang, Benran [University of Southern California, ↗

DOE OSTI2025

DIMPLES: Distributed Influence Maximization for Pandemic pLanning on Exascale Systems

We study exascale parallel algorithms for the selection of intervention or monitoring strategies in massive realistic socio-technical networks through scalable Influence Maximization (InfMax) algorithms. We employ novel techniques to enable efficient scaling on up to 8k nodes of OLCF Frontier, with 65k AMD GPUs and 458k AMD CPU cores. Current state-of-the-art InfMax tools are limited to networks with only a few million actors (vertices) and a few hundred million interactions (edges). By overcoming these limitations, we show that our approach is capable of processing a realistic social contact network of the United States with 285 million nodes and about 8 billion edges. This two orders-of-magnitude improvement over the previous state-of-the-art is obtained by leveraging algorithmic advancements for the InfMax problem and designing several problem-specific approaches to overlap communication with computation, improve GPU efficiency, and lower the application’s memory requirements. We evaluate strong scaling for computing 10k most influential seeds using up to 8k nodes of an exascale system, and weak scaling from 128 to 8k system nodes for seed sets ranging from 625 to 40k seeds. We achieve the fastest-known runtime of 25 minutes while performing 48 million diffusion simulations totaling 2.31 petabytes to identify 40k influential seeds using 8k nodes, and take 5.75 minutes to identify 10k seeds while using 4k nodes.

Minutoli, Marco [Pacific Northwest National Labora↗

DOE OSTI2025

Large-Message All-to-All Communication at Frontier Scale

Near the full scale of exascale supercomputers, latency can dominate the cost of all-to-all communication even for very large message sizes. We describe GPU-aware all-to-all implementations designed to reduce latency for large message sizes at extreme scales, and we present their performance using 65536 tasks (8192 nodes) on the Frontier supercomputer at the Oak Ridge Leadership Computing Facility. Two implementations perform best for different ranges of message size, and all outperform the vendor-provided MPI_Alltoall. Our results show promising options for improving implementations of MPI_Alltoall_init.

White, Trey [ORNL] (ORCID:000900052186075X)↗

DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗

DOE OSTI2025

Mojo: MLIR-based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem

We explore the performance and portability of the novel Mojo language for scientific computing workloads on GPUs. As the first language based on the LLVM’s Multi-Level Intermediate Representation (MLIR) compiler infrastructure, Mojo aims to close performance and productivity gaps by combining Python’s interoperability and CUDA-like syntax for compile-time portable GPU programming. We target four scientific workloads: a seven-point stencil (memory-bound), BabelStream (memory-bound), miniBUDE (compute-bound), and Hartree–Fock (compute-bound with atomic operations); and compare their performance against vendor baselines on NVIDIA H100 and AMD MI300A GPUs. We show that Mojo’s performance is competitive with CUDA and HIP for memory-bound kernels, whereas gaps exist on AMD GPUs for atomic operations and for fast-math compute-bound kernels on both AMD and NVIDIA GPUs. Although the learning curve and programming requirements are still fairly low-level, Mojo can close significant gaps in the fragmented Python ecosystem in the convergence of scientific computing and AI.

Godoy, William [ORNL] (ORCID:0000000225905178)↗

DOE OSTI2025

Accelerating Advanced Light Source Science Through Multi-Facility HPC Workflows

Synchrotron light sources support a wide array of techniques to investigate materials, often producing complex, high-volume data that challenge traditional workflows. At the Advanced Light Source (ALS), we developed infrastructure to move microtomography data over ESnet to ALCF and NERSC, where CPU- and GPU-based algorithms generate 3D reconstructed volumes of experimental samples. We employ two data movement and reconstruction models: real-time processing as data streams directly to NERSC compute nodes, and automated file transfer to NERSC and ALCF file systems. The streaming pipeline provides users with feedback in under ten seconds, while the file-based workflow produces high-quality reconstructions suitable for deeper analysis in 20-30 minutes. This infrastructure enables users to utilize HPC resources without direct access to backend systems. We plan to extend this architecture to more endstations, supporting our beamline scientists and users.

Abramov, David↗

DOE OSTI2025

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]↗

DOE OSTI2020

DiHydrogen

DiHydrogen is the second version of the Hydrogen fork of the well-known distributed linear algebra library, Elemental. DiHydrogen is a GPU-accelerated distributed multilinear algebra interface with a particular emphasis on the needs of the scalable distributed deep learning training and inference. DiHydrogen is part of the Livermore Big Artificial Neural Network (LBANN) software stack.

Maruyama, Naoya↗

DOE OSTI2020

ExaPF

ExaPF is a HPC package in Julia for solving power flow (PF) on a GPU. It currently solves PF using the Newton-Raphson algorithm on NVIDA GPUs.

SCHANEN, MICHEL↗

DOE OSTI2020

Parallel Lattice Subpaving Map (plsm)

Custom spatial subdivision of N-dimensional lattice region in GPU memory. An extension of the method of a hyper-octree is used to allow for arbitrary subdivision ratios in each dimension. In addition, the decision to refine (or select) a given sub-region is based on a user-provided callback, allowing for arbitrary refinement domains to be expressed either geometrically or programmatically.

Fackler, Philip↗

DOE OSTI2020

ExchCXX v0.1.0

ExchCXX is a modern C++ library for the evaluation of exchange-correlation (XC) functionals required for density functional theory (DFT) calculations. In addition to providing high-level wrappers for the ubiquitous Libxc library for the CPU evaluation of XC functionals, ExchCXX also provides locally developed implementations of a small subset of XC functionals which may be evaluated either on the host (CPU) or device (GPU, FPGA, etc).

Williams-Young, David↗

DOE OSTI2020

GauXC v0.1.0

GauXC is a modern, modular C++ library for the numerical exchange-correlation (XC) integration required for the Gaussian basis set discretization of Kohn-Sham density functional theory (DFT). The modular nature of GauXC allows for an extensible software design which enables performance portability on an array of CPU and GPU architectures.

Williams-Young, David↗

DOE OSTI2021

HiPACE++ v0.1

Hipace++ is the new implementation of the DESY-LBNL code Hipace (not distributed nor licensed) for plasma acceleration, relying on the quasi-static particle-in-cell (PIC) method, enabling fast and accurate simulations of plasma accelerators for problems satisfying the quasi-static approximation. Plasma acceleration is a priority in the ATAP division, and such problems represent a wide range of parameters. Hipace++ is an HPC (high-performance computing) code running on supercomputers and it provides the first efficient implementation of the quasi-static PIC method on Graphic Processing Units (GPU), showing 10x speedup and using much less resources than CPU implementations for production simulations. It currently runs on Nvidia GPUs and will ultimately be portable to more accelerated HPC platforms. The porting strategy is novel, and can be adapted to other flavors of quasi-static PIC. Besides, Hipace++ aims at using mesh refinement for higher efficiency, thus enabling simulations unfeasible today. For this purpose, Hipace++ depends on the open-source library AMReX (Adaptive Mesh Refinement at EXascale) developed at LBNL.

Vay, Jean-Luc↗

DOE OSTI2021

SW4 Curvilinear Kernels

Five computationally expensive stencil evaluation routines from SW4(https://github.com/geodynamics/sw4 GPL license) have been extracted and packaged with a driver to create a mini-app for evaluating compiler and GPU performance. The kernels can executed on AMD and Nvidia GPUs with and without RAJA. The kernel driver generates synthetic inputs, checks for correctness and measures kernel run times.

Pankajakshan, Ramesh↗

DOE OSTI2021

singularity-opac

singularity-opac is a library for providing a unified interface for opacities, emissivities, and scattering cross-sections for materials and use in simulation codes. It is designed to be performance portable and run on CPU and GPU.

Dolence, Joshua↗