Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “EXASCALE”

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 1,297 records · Page 72

Comparative Study of Large Language Model Architectures on Frontier

Large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-trained Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However, these variants have undergone pre-training under diverse conditions, including variations in input data, data preprocessing, and training methodologies, resulting in a lack of controlled comparative studies. Here we meticulously examine two prominent open-sourced GPT architectures, GPT-NeoX and LLaMA, leveraging the computational power of Frontier, the world’s first Exascale supercomputer. Employing the same materials science text corpus and a comprehensive end-to-end pipeline, we conduct a comparative analysis of their training and downstream performance. Our efforts culminate in achieving state-of-the-art performance on a challenging materials science benchmark. Furthermore, we investigate the computation and energy efficiency, and propose a computationally efficient method for architecture design. To our knowledge, these pre-trained models represent the largest available for materials science. Our findings provide practical guidance for building LLMs on HPC platforms.

Yin, Junqi↗

The Artificial Scientist: in-Transit Machine Learning of Plasma Simulations

Large-scale simulations or scientific experiments produce petabytes of data per run. This poses massive challenges for I/O and storage when scientific analysis workflows are run manually offline. Unsupervised deep learning-based techniques to extract patterns and non-linear relations from these large amounts of data provide a way to build scientific understanding from raw data, reducing the need for manual pre-selection of analysis steps, but require exascale compute and memory to process the full dataset available. In this paper, we demonstrate a heterogeneous streaming workflow in which plasma simulation data is streamed directly to a Machine Learning (ML) application training a model on the simulation data in-transit, completely circumventing the capacity-constrained filesystem bottleneck. This workflow employs openPMD to provide a high level interface to describe scientific data and also uses ADIOS2, to transfer volumes of data that exceed the capabilities of the filesystem. We employ experience replay to avoid catastrophic forgetting in learning from this non-steady state process in a continual manner and adapt it to improve model convergence while learning in-transit. As a proof-of-concept, we approach the ill-posed inverse problem of predicting particle dynamics from radiation in a particle-incell (PIConGPU) simulation of the Kelvin-Helmholtz instability (KHI). We detail hardware-software co-design challenges as we scale PIConGPU to full Frontier, the Top-1 system as of June 2024 Top500 list.

Kelling, Jeffrey [Helmholtz-Zentrum Dresden Rossen↗

Systemwide Power Management with Argo

The Argo project is a DOE initiative for designing a modular operating system/runtime for the next generation of supercomputers. A key focus area in this project is power management, which is one of the main challenges on the path to exascale. In this paper, we discuss ideas for systemwide power management in the Argo project. We present a hierarchical and scalable approach to maintain a power bound at scale, and we highlight some early results.

Ellsworth, Daniel↗

AHEAD: A Tool for Projecting Next-Generation Hardware Enhancements on GPU-Accelerated Systems

Starting with the Titan supercomputer (at the Oak Ridge Leadership Computing Facility, OLCF) in 2012, top supercomputers have Increasingly leveraged the performance of GPUs to support large-scale computational science. The current No. 1 machine, the 200 petaflop Summit system at OLCF, is a GPU-based machine. Accelerator-based architectures, however, add additional complexity due to node heterogeneity. To inform procurement decisions, supercomputing centers need the tools to quickly model the impact of changes of the node architectures on application performance. We present AHEAD, a profiling and modeling tool to quantify the impact of intra-node communication mechanism (e.g., PCI or NVLink) on application performance. Our experiments show average weighted relative errors of ~19% and ~23% for five CORAL-2 (a collaboration between multiple US Department of Energy, DOE, labs to procure Exascale systems) and 12 Rodinia benchmarks respectively, without running the applications on the target future node.

Abdelhafez, Hazem A.↗

Efficient Asynchronous I/O with Request Merging

With the advancement of exascale computing, the amount of scientific data is increasing day by day. Efficient data access is necessary for scientific discoveries. Unfortunately, the I/O performance is not improved, like the CPU and network speed. So, I/O operations take longer time than data generation or analysis. Asynchronous I/O has been proposed to extenuate the I/O bottleneck by overlapping I/O and computation time. However, multiple small write operations can diminish the benefits of asynchronous I/O, as the I/O time becomes significantly longer than the compute time, with little time to overlap with. To overcome these issues, we present an optimization technique to merge small contiguous write operations. We integrated our solution into the HDF5 asynchronous I/O VOL connector and demonstrated the effectiveness of merging HDF5 write operations automatically and transparently without requiring any code change from the application.

Chowdhury, Kamal Hossain↗

Pretraining Billion-Scale Geospatial Foundational Models on Frontier

As AI workloads increase in scope, generalization capability becomes challenging for small task-specific models and their demand for large amounts of labeled training samples increases. On the contrary, Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning and have been shown to adapt to various tasks with minimal fine-tuning. Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators. Current satellite constellations collect 100+TBs of data a day, resulting in images that are billions of pixels and multimodal in nature. Such geospatial data poses unique challenges opening up new opportunities to develop FMs. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. We studied from end-to-end the performance and impact in the solution by scaling the model size. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy when comparing a 100M parameter model. Moreover, we detail performance experiments on the Frontier supercomputer, America's first exascale system, where we study different model and data parallel approaches using PyTorch's Fully Sharded Data Parallel library. Specifically, we study variants of the Vision Transformer architecture (ViT), conducting performance analysis for ViT models with size up to 15B parameters. By discussing throughput and performance bottlenecks under different parallelism configurations, we offer insights on how to leverage such leadership-class HPC resources when developing large models for geospatial imagery applications.

Tsaris, Aristeidis (aris)↗

Autotuning in High-Performance Computing Applications

Autotuning refers to the automatic generation of a search space of possible implementations of a computation that are evaluated through models and/or empirical measurement to identify the most desirable implementation. Autotuning has the potential to dramatically improve the performance portability of petascale and exascale applications. To date, autotuning has been used primarily in high-performance applications through tunable libraries or previously tuned application code that is integrated directly into the application. This paper draws on the authors' extensive experience applying autotuning to high-performance applications, describing both successes and future challenges. If autotuning is to be widely used in the HPC community, researchers must address the software engineering challenges, manage configuration overheads, and continue to demonstrate significant performance gains and portability across architectures. In particular, tools that configure the application must be integrated into the application build process so that tuning can be reapplied as the application and target architectures evolve.

97 MATHEMATICS AND COMPUTING↗

Parallel peak pruning for scalable SMP contour tree computation

As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. Here in this paper, we report the first shared SMP algorithm for fully parallel contour tree computation, withfor-mal guarantees of O(lgnlgt) parallel steps and O(n lgn) work, and implementations with up to 10x parallel speed up in OpenMP and up to 50x speed up in NVIDIA Thrust.

97 MATHEMATICS AND COMPUTING↗

Low-Overhead In Situ Visualization Using Halo Replay

In situ visualization and analysis is of increasing importance as the compute and I/O gap further widens with the advance to exascale capable computing. Yet, in situ methods impose resource constraints leading to the difficult task of balancing simulation code performance and the quality of analysis. Applications with tightly-coupled in situ visualization often achieve performance through spatial and temporal downsampling, a tradeoff which risks not capturing transient phenomena at sufficient fidelity. Determining a priori visualization parameters such as sampling rate is difficult without time and resource intensive experimentation. We present a method for reducing resource contention between in situ visualization and stencil codes on heterogeneous systems. This method permits full resolution replay through recording halos and the communication-free reconstruction of interior values uncoupled from the main simulation. We apply this method in the computational fluid dynamics (CFD) code HARVEY [1] on the Summit supercomputer. We demonstrate minimal-overhead, in situ visualization relative to simulation alone, and compare the Halo Replay performance to tightly-coupled in situ approaches.

Ames, Jeff↗

Clacc: Translating OpenACC to OpenMP in Clang

OpenACC was launched in 2010 as a portable programming model for heterogeneous accelerators. Although various implementations already exist, no extensible, open-source, production-quality compiler support is available to the community. This deficiency poses a serious risk for HPC application developers targeting GPUs and other accelerators, and it limits experimentation and progress for the OpenACC specification. To address this deficiency, Clacc is a recent effort funded by the US Exascale Computing Project to develop production OpenACC compiler support for Clang and LLVM. A key feature of the Clacc design is to translate OpenACC to OpenMP to build on Clang's existing OpenMP compiler and runtime support. In this paper, we describe the Clacc goals and design. We also describe the challenges that we have encountered so far in our prototyping efforts, and we present some early performance results.

Denny, Joel↗

Toward Managing HPC Burst Buffers Effectively: Draining Strategy to Regulate Bursty I/O Behavior

HPC (high-performance computing) applications usually show bursty I/O behaviors. In order to expedite the applications, permanent storage systems are usually provisioned to serve such I/O bursts. Approaching the era of exascale computing, non-volatile RAM is introduced as burst buffers, to absorb the bursty bulk data and relax the I/O provisioning requirement of the permanent storage systems. However, without judiciously draining the burst buffers, I/O bursts are passed down to the underlying storage systems, which causes severe I/O contention issues.In order to minimize the I/O provisioning requirement and resolve the issues caused by I/O bursts, we propose a proactive draining scheme to manage the draining process of distributed node-local burst buffers. In addition, we develop an I/O provisioning model to predict the minimized I/O provisioning requirement for permanent storage systems. Evaluation results show that applying the proactive draining scheme largely relaxes the I/O provisioning requirement while preserving the I/O performance of underlying storage systems.

97 MATHEMATICS AND COMPUTING↗

Prometheus: Coherent Exploration of Hardware and Software Optimizations using Aspen

With the dramatic increase in scale expected for Exascale computing, there is a dire need for tuning of hardware configurations and software optimizations such that they are in unison. However, the expected increase in tunable hardware parameters makes searching through the design space for optimal hardware-and-software configurations much more challenging. Towards this end, we propose a composable hardware-software optimization framework called Prometheus. Prometheus uses a combination of analytical and machine-learning techniques to capture application characteristics and subsequently determine the hardware-software configuration for near-optimal performance. We evaluate Prometheus for its efficacy using four widely used proxy applications: LULESH, CoMD, CG and CoEVP. We demonstrate that Prometheus identifies near-optimal hardwaresoftware configurations and verify the results via brute-force search of the design space.

Umar, Mariam↗

The TOP500 List and Progress in High-Performance Computing

The TOP500 list has enjoyed incredible success as a metric for supercomputing performance and as a source of data for identifying technological trends, for more than two decades. Here, the project's editors reflect on its usefulness and limitations for guiding large-scale scientific computing into the exascale era.

97 MATHEMATICS AND COMPUTING↗

Quantum Computing and Visualization: A Disruptive Technological Change Ahead

The focus of this Visualization Viewpoints article is to provide some background on quantum computing (QC), to explore ideas related to how visualization helps in understanding QC, and examine how QC might be useful for visualization with the growth and maturation of both technologies in the future. In a quickly evolving technology landscape, QC is emerging as a promising pathway to overcome the growth limits in classical computing. In some cases, QC platforms offer the potential to vastly outperform the familiar classical computer by solving problems more quickly or that may be intractable on any known classical platform. As further performance gains for classical computing platforms are limited by diminishing Moore’s Law scaling, QC platforms might be viewed as a potential successor to the current field of exascale-class platforms. Importantly, while present-day QC hardware platforms are still limited in scale, the field of quantum computing is robust and rapidly advancing in terms of hardware capabilities, software environments for developing quantum algorithms, and educational programs for training the next generation of scientists and engineers. After a brief introduction to QC concepts, the focus of this article is to explore the interplay between the fields of visualization and QC. First, visualization has played a role in QC by providing the means to show representations of the quantum state of single-qubits in superposition states and multiple-qubits in entangled states. Second, there are a number of ways in which the field of visual data exploration and analysis may potentially benefit from this disruptive new technology though there are challenges going forward.

97 MATHEMATICS AND COMPUTING↗

Feature Analysis, Tracking, and Data Reduction: An Application to Multiphase Reactor Simulation MFiX-Exa for In-Situ Use Case

As we enter the exascale computing regime, powerful supercomputers continue to produce much higher amounts of data than what can be stored for offline data processing. To utilize such high compute capabilities on these machines, much of the data processing needs to happen in situ, when the full high-resolution data is available at the supercomputer memory. In this article, we discuss our MFiX-Exa simulation, which models multiphase flow by tracking a very large number of particles through the simulation domain. In one of the use cases, the carbon particles interact with air to produce carbon dioxide bubbles from the reactor. These bubbles are of primary interest to the domain experts for these simulations. For this particle-based simulation, we propose a streaming technique that can be deployed in situ to efficiently identify the bubbles, track them over time, and use them to down-sample the data with minimal loss in these features.

97 MATHEMATICS AND COMPUTING↗

Creating Continuous Integration Infrastructure for Software Development on U.S. Department of Energy High-Performance Computing Systems

The Exascale Computing Project (ECP) software deployment effort developed and advanced DevOps capabilities. One goal was to enable robust continuous integration (CI) workflows that span the protected high performance computing (HPC) environments found within many of the Department of Energy’s (DOE) national laboratories. This article highlights several challenges encountered with enabling automation, such as charging models for CI jobs, and meeting individualized security requirements that revolve around strongly associating running code with a human identity. Here, it also describes how the Jacamar CI tool evolved to meet latter requirements and became a key aspect of the solutions currently offered. Derived from this experience, we offer a conceptual framework for understanding current and future CI challenges at DOE facilities and offer suggestions for long-term solutions.

97 MATHEMATICS AND COMPUTING↗

COSMIC DAWN: Distributed Analysis of Wireless at Nextscale

Distributed Analysis of Wireless at Nextscale (DAWN) is a novel simulation framework for large-scale design-space exploration (DSE) of unmodified software-defined radio (SDR) applications interacting in a scalable, high-fidelity, virtual physics environment. The software-defined nature of the coupled software-physics simulation leverages hardware emulation to permit in-depth examination and modification of not only the electromagnetic environment, including each signal in flight, but also the precise state of system software and components. DAWN supports modular, customizable physics environments allowing realistic propagation effects so that computationally efficient empirical models, reduced order/surrogate models, or large-scale, high-fidelity, site-specific simulations can be used as a propagation medium based on scenario requirements. This paper introduces DAWN’s design and initial implementation, detailing key architectural components, including the Physics Realization Engine (PhyRE), Runtime Infrastructure for Simulation Environments (RISE), and the design space exploration (DSE) suite. It concludes with demonstrations using unmodified 4G/LTE software available from srsRAN on computing resources ranging from a small cluster to ORNL’s Frontier Exascale system.

Wise, Mike [ORNL] (ORCID:0000000266120641)↗

Exploring the use of novel programming models in land surface models

A wide range of programming models are currently under rapid development to meet the needs of application developers looking to work on more complex machines. These models fill a variety of roles. Some look to abstract supercomputer architecture, including both processors and memory, to present a strategy for portable performance across a wide range of machines. Others look to expose concurrency by explicitly constructing task-driven dependency graphs that allow a scheduler to find parallelism. Here we explore the implications for application codes of adopting two such programming models, Kokkos and Legion, one from each class of models. We specifically focus on the software design implications on refactoring existing applications, rather than the performance and performance tuning of these models. We identify a strategy for refactoring the Energy Exascale Earth System Model's Land Surface Model, an extremely complex code for climate applications, and prototype a series of mini-apps that explore the adoption of Kokkos and Legion. In doing this, we identify commonalities across the models, leading to a series of conclusions about application software design and refactoring for the adoption of novel programming models.

Coon, Ethan↗