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 1,261 records · Page 70

Large-momentum effective theory

Since the parton model was introduced by Feynman more than 50 years ago, much has been learned about the partonic structure of the proton through a large body of high-energy experimental data and dedicated global fits. However, limited progress has been made in calculating partonic observables such as the parton distribution function (PDFs) from the fundamental theory of strong interactions, quantum chromodynamics (QCD). Recently some advocated for a formalism, large-momentum effective theory (LaMET), through which one can extract parton physics from the properties of the proton traveling at a moderate boost factor such as γ ~ 2 – 5 . The key observation behind this approach is that Lorentz symmetry allows the standard formalism of partons in terms of light-front operators to be replaced by an equivalent one with large-momentum states and time-independent operators of a universality class. With LaMET, the PDFs, generalized PDFs or generalized parton distributions, transverse-momentum-dependent PDFs, and light-front wave functions can all be extracted in principle from lattice simulations of QCD (or other nonperturbative methods) through standard effective field theory matching and running. Future lattice QCD calculations with exascale computational facilities could help one to understand the experimental data related to the hadronic structure, including those from the upcoming electron-ion colliders dedicated to exploring the partonic landscape of the proton. In this work, the progress made in the past few years in the development of the LaMET formalism and its applications is reviewed, with an emphasis on a demonstration of its effectiveness from initial lattice QCD simulations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Enhancing Photosynthesis Simulation Performance in ESMs with Machine Learning-Assisted Solvers

When simulating vegetation dynamics, photosynthesis accounts for a large fraction of the computational cost in most Earth System Models (ESMs). This is largely since photosynthesis is represented as a system of nonlinear equations, and the solution requires the use of an initial guess followed by many iterations of the numerical solver to obtain a solution. We use machine learning (ML) to replicate the response surface of the model’s numerical solver to improve the choice of initial guess, therefore requiring fewer iterations to obtain a final solution. We implemented this test on the leaf-level calculations as well as at the canopy scale, and for both we observed fewer iterations of the photosynthesis solver when a ML-based initial guess was implemented. The model tested here is the Energy Exascale Earth System Model - Land Model (ELM). The ML-based algorithms used here are trained on simulations from the model itself and used only to improve the initial guess for the solver; therefore, the model maintains its own set of physics to obtain the final solution. This work shows novel ways to utilize ML-based methods to improve the performance of numerical solvers in ESMs.

Massoud, Elias [ORNL] (ORCID:0000000217725361)↗

Experiences Applying Data Staging Technology in Unconventional Ways

Several efforts have shown the potential of using additional compute-area resources to enhance the IO path to storage. Efforts like data staging, IO forwarding, and similar techniques can accelerate IO performance and reduce the impact of IO time to a compute application. Hybrid staging enhanced this path by adding processing functionality to locations along the data path to storage. While these efforts have been effective, they have taken a somewhat limited view of the potential benefits using some additional compute resources can offer both to enhance a compute application as well as to offering a way to exploit HPC-style resources for non-traditional tasks. Over the last few years, we have been experimenting with the potential for other sorts of activities using a staging style approach to add or enable new functionality. The efforts in this area have yielded a collection of small projects that yield some insights into both the potential and limitations of this approach for both achieving exascale computing and for enabling alternative uses for HPC resources.

Computer Science↗

Scalable PGAS Metadata Management on Extreme Scale Systems

Programming models intended to run on exascale systems have a number of challenges to overcome, specially the sheer size of the system as measured by the number of concurrent software entities created and managed by the underlying runtime. It is clear from the size of these systems that any state maintained by the programming model has to be strictly sub-linear in size, in order not to overwhelm memory usage with pure overhead. A principal feature of Partitioned Global Address Space (PGAS) models is providing easy access to global-view distributed data structures. In order to provide efficient access to these distributed data structures, PGAS models must keep track of metadata such as where array sections are located with respect to processes/threads running on the HPC system. As PGAS models and applications become ubiquitous on very large transpetascale systems, a key component to their performance and scalability will be efficient and judicious use of memory for model overhead (metadata) compared to application data. We present an evaluation of several strategies to manage PGAS metadata that exhibit different space/time tradeoffs. We use two real-world PGAS applications to capture metadata usage patterns and gain insight into their communication behavior.

Global Arrays↗

An Efficient Silent Data Corruption Detection Method with Error-Feedback Control and Even Sampling for HPC Applications

The silent data corruption (SDC) problem is attracting more and more attentions because it is expected to have a great impact on exascale HPC applications. SDC faults are hazardous in that they pass unnoticed by hardware and can lead to wrong computation results. In this work, we formulate SDC detection as a runtime one-step-ahead prediction method, leveraging multiple linear prediction methods in order to improve the detection results. The contributions are twofold: (1) we propose an error feedback control model that can reduce the prediction errors for different linear prediction methods, and (2) we propose a spatial-data-based even-sampling method to minimize the detection overheads (including memory and computation cost). We implement our algorithms in the fault tolerance interface, a fault tolerance library with multiple checkpoint levels, such that users can conveniently protect their HPC applications against both SDC errors and fail-stop errors. We evaluate our approach by using large-scale traces from well-known, large-scale HPC applications, as well as by running those HPC applications on a real cluster environment. Experiments show that our error feedback control model can improve detection sensitivity by 34-189% for bit-flip memory errors injected with the bit positions in the range [20,30], without any degradation on detection accuracy. Furthermore, memory size can be reduced by 33% with our spatial-data even-sampling method, with only a slight and graceful degradation in the detection sensitivity.

Di, Sheng↗

Landrush: Rethinking In-Situ Analysis for GPGPU Workflows

In-situ analysis on the output data of scientific simulations has been made necessary by ever-growing output data volumes and increasing costs of data movement as supercomputing is moving towards exascale. With hardware accelerators like GPUs becoming increasingly common in high end machines, new opportunities arise to co-locate scientific simulations and online analysis performed on the scientific data generated by the simulations. However, the asynchronous nature of GPGPU programming models and the limited context-switching capabilities on the GPU pose challenges to co-locating the scientific simulation and analysis on the same GPU. This paper dives deeper into these challenges to understand how best to co-locate analysis with scientific simulations on the GPUs in HPC clusters. Specifically, our 'Landrush' approach to GPU sharing proposes a solution that utilizes idle cycles on the GPU to provide an improved time-to-answer, that is, the total time to run the scientific simulation and analysis of the generated data. Landrush is demonstrated with experimental results obtained from leadership high-end applications on ORNL's Titan supercomputer, which show that (i) GPU-based scientific simulations have varying degrees of idle cycles to afford useful analysis task co-location, and (ii) the inability to context switch on the GPU at instruction granularity can be overcome by careful control of the analysis kernel launches and software-controlled early completion of analysis kernel executions. Results show that Landrush is superior in terms of time-to-answer compared to serially running simulations followed by analysis or by relying on the GPU driver and hardwired thread dispatcher to run analysis concurrently on a single GPU.

Computer Science↗

Indicator-directed Dynamic Power Management for Iterative Workloads on GPU-Accelerated Systems

Modern high-performance and warehouse computing centers show strong interest in minimizing system power consumption while satisfying customers’ quality of service (QoS). Dynamic voltage and frequency scaling (DVFS) is effective for achieving this goal. Nevertheless, automating the process online and making it transparent to users must address three major challenges: (1) Complexity — today’s hardware components (e.g., CPUs, GPUs, memory, network, etc.) can be configured in several or dozens of frequency/voltage states for satisfying divergent system demands. Given their combination and the emergence of heterogeneity, searching the optimal configuration in the design space online can be timing consuming. (2) QoS guarantee — user-defined objectives such as power constraint and performance target must be monitored, predicted and ensured at the best effort. (3) Adaptability — various known and unknown workloads run on systems. Workloads characteristics should be quickly determined and configurations dynamically adjusted in accord with workloads and QoS. In this work, we focus on applications exhibiting an interesting feature – iterative or periodic, which is common among conventional HPC and emerging machine learning workloads. We propose an online dynamic power-performance (ODPP) management framework to dynamically adjust GPU DVFS configurations to meet performance and power objectives and constraints, without any code annotation or intrusion. Particularly, ODPP extracts the performance and power indicators for applications from their resources utilization profiles in a short episode. It further automatically constructs an accurate model that infers from the indicators how the application's performance and power vary with GPU core and memory frequencies. Aided with the model, for both seen and unseen applications, ODPP can quickly determine the most appropriate DVFS configuration for their execution. We evaluate ODPP on an NVIDIA GPU using multiple exascale computing (ECP) and deep learning applications.

Zou, Pengfei↗

DeepFreeze: Towards Scalable Asynchronous Checkpointing of Deep Learning Models

In the age of big data, deep learning has emerged as a powerful tool to extract insight and exploit its value, both in industry and scientific applications. One common pattern emerging in such applications is frequent checkpointing of the state of the learning model during training, needed in a variety of scenarios: analysis of intermediate states to explain features and correlations with training data, exploration strategies involving alternative models that share a common ancestor, knowledge transfer, resilience, etc. However, with increasing size of the learning models and popularity of distributed data-parallel training approaches, simple checkpointing techniques used so far face several limitations: low serialization performance, blocking I/O, stragglers due to the fact that only a single process is involved in checkpointing. This paper proposes a checkpointing technique specifically designed to address the aforementioned limitations, introducing efficient asynchronous techniques to hide the overhead of serialization and I/O, and distribute the load over all participating processes. Experiments with two deep learning applications (CANDLE and ResNet) on a pre-Exascale HPC platform (Theta) shows significant improvement over state-of-art, both in terms of checkpointing duration and runtime overhead.

checkpointing↗

Quartile and Outlier Detection on Heterogeneous Clusters Using Distributed Radix Sort.

In the past few years, performance improvements in CPUs and memory technologies have outpaced those of storage systems. When extrapolated to the exascale, this trend places strict limits on the amount of data that can be written to disk for full analysis, resulting in an increased reliance on characterizing in-memory data. Many of these characterizations are simple, but require sorted data. This paper explores an example of this type of characterization - the identification of quartiles and statistical outliers - and presents a performance analysis of a distributed heterogeneous radix sort as well as an assessment of current architectural bottlenecks.

Spafford, Kyle L↗

Improving I/O Throughput with PRIMACY: Preconditioning ID-Mapper for Compressing Incompressibility

The ability to efficiently handle massive amounts of data is necessary for the continuing development towards exascale scientific data-mining applications and database systems. Unfortunately, recent years have shown a growing gap between the size and complexity of data produced from scientific applications and the limited I/O bandwidth available on modern high-performance computing systems. Utilizing data compression in order to lower the degree of I/O activity offers a promising means to addressing this problem. However, the standard compression algorithms previously explored for such use offer limited gains on both the end-to-end throughput and storage fronts. In this paper, we introduce an in-situ compression scheme aimed at improving end-to-end I/O throughput as well as reduction of dataset size. Our technique, PRIMACY (Preconditioning Id-MApper for Compressing incompressibility), acts as a preconditioner for standard compression libraries by modifying representation of original floating-point scientific data to increase byte-level repeatability, allowing standard loss less compressors to take advantage of their entropy-based byte-level encoding schemes. We additionally present a theoretical model for compression efficiency in high-performance computing environments and evaluate the efficiency of our approach via comparative analysis. Based on our evaluations on 20 real-world scientific datasets, PRIMACY achieved up to 38% and 22% improvements upon standard end-to-end write and read throughputs respectively in addition to a 25% increase in compression ratios paired with 3-to-4-fold improvement in both compression and decompression throughput over general purpose compressors.

Computer Science↗

A Review of Lightweight Thread Approaches for High Performance Computing

High-level, directive-based solutions are becoming the programming models (PMs) of the multi/many-core architectures. Several solutions relying on operating system (OS) threads perfectly work with a moderate number of cores. However, exascale systems will spawn hundreds of thousands of threads in order to exploit their massive parallel architectures and thus conventional OS threads are too heavy for that purpose. Several lightweight thread (LWT) libraries have recently appeared offering lighter mechanisms to tackle massive concurrency. In order to examine the suitability of LWTs in high-level runtimes, we develop a set of microbenchmarks consisting of commonlyfound patterns in current parallel codes. Moreover, we study the semantics offered by some LWT libraries in order to expose the similarities between different LWT application programming interfaces. This study reveals that a reduced set of LWT functions can be sufficient to cover the common parallel code patterns and that those LWT libraries perform better than OS threads-based solutions in cases where task and nested parallelism are becoming more popular with new architectures.

Castello, Adrian↗

Evaluation of Topology-Aware Broadcast Algorithms for Dragonfly Networks

Two-tiered direct network topologies such as Dragonflies have been proposed for future post-petascale and exascale machines, since they provide a high-radix, low-diameter, fast interconnection network. Such topologies call for redesigning MPI collective communication algorithms in order to attain the best performance. Yet as increasingly more applications share a machine, it is not clear how these topology-aware algorithms will react to interference with concurrent jobs accessing the same network. In this paper, we study three topology-aware broadcast algorithms, including one designed by ourselves. We evaluate their performance through event-driven simulation for small- and large-sized broadcasts (in terms of both data size and number of processes). We study the effect of different routing mechanisms on the topology-aware collective algorithms, as well as their sensitivity to network contention with other jobs. Our results show that while topology-aware algorithms dramatically reduce link utilization, their advantage in terms of latency is more limited.

Dorier, Matthieu↗

Extending Skel to Support the Development and Optimization of Next Generation I/O Systems

As the memory and storage hierarchy get deeper and more complex, it is important to have new benchmarks and evaluation tools that allow us to explore the emerging middleware solutions to use this hierarchy. Skel is a tool aimed at automating and refining this process of studying HPC I/O performance. It works by generating application I/O kernel/benchmarks as determined by a domain-specific model. This paper provides some techniques for extending Skel to address new situations and to answer new research questions. For example, we document use cases as diverse as using Skel to troubleshoot I/O performance issues for remote users, refining an I/O system model, and facilitating the development and testing of a mechanism for runtime monitoring and performance analytics. We also discuss data oriented extensions to Skel to support the study of compression techniques for Exascale scientific data management.

97 MATHEMATICS AND COMPUTING↗

Parallel I/O Evaluation Techniques and Emerging HPC Workloads: A Perspective

Emerging workloads such as artificial intelligence, big data analytics and complex multi-step workflows alongside future exascale applications are anticipated future HPC workloads, which will result in a more diverse I/O system workload and even less predictable I/O behavior and access patterns. Along with the ever increasing gap between the compute and storage performance capabilities, the in-depth understanding of extreme-scale I/O behavior and the I/O performance modeling and prediction are essential tools of the large-scale I/O evaluation process for addressing the needs of extreme-scale hybrid workloads. In this survey article, we focus on the state-of-the-art of the I/O behavior and performance analysis process for HPC systems in a 5-year time window and identify future research challenges.

Neuwirth, Sarah↗

Early Evaluation of Fugaku A64FX Architecture Using Climate Workloads

The Energy Exascale Earth System Model (E3SM) Project is an ongoing, state-of-the-science Earth system modeling, simulation, and prediction project that targets efficient utilization of U.S. Department of Energy’s (DOE) supercomputers to meet the science needs of the nation and the mission needs of DOE. This work focuses on our early evaluation of the A64FX architecture on Fugaku supercomputer using E3SM benchmarks. We will present results that track hardware trends, facilitate architecture comparison and the specific impact on our workload using an atmospheric model benchmark. We have two variants of the code written in Fortran and C++/Kokkos respectively which were used to collect data on a variety of CPU and GPU platforms. Furthermore, we have conducted a comparative evaluation of the compilers on the A64FX architecture and found GNU to be the best performer for our workload. Our experience so far indicates that Fugaku/A64FX shows promising energy efficiency (performance/Watt) with further performance gains possible through architecture-aware optimization efforts.

Sreepathi, Sarat↗

Global Experiences with HPC Operational Data Measurement, Collection and Analysis

As we move into the exascale era, supercomputers grow larger, denser, more heterogeneous, and ever more complex. Operating such machines reliably and efficiently requires deep insight into the operational parameters of the machine itself as well as its supporting infrastructure. To fulfill this need, early adopter sites have started the development and deployment of Operational Data Analytics (ODA) frameworks allowing the continuous monitoring, archiving, and analysis of near realtime performance data from the machine and infrastructure levels, providing immediately actionable information for multiple operational uses. To understand their ODA goals, requirements, and use cases, we have conducted a survey among eight early adopter sites from the US, Europe, and Japan that operate top 50 high-performance computing systems. We have assessed the technologies leveraged to build their ODA frameworks, identified use cases and other push and pull factors that drive the sites' ODA activities, and report on their operational lessons.

Ott, Michael↗

A Co-Design Study Of Fusion Whole Device Modeling Using Code Coupling

Complex workflows consisting of multiple simulation and analysis codes running concurrently through in-memory coupling is becoming popular due to inherent advantages in online management of large-scale data, resilience, and the code development process. However, orchestrating such a multi-application workflow to efficiently utilize resources on a heterogeneous architecture is challenging. In this paper, we present our results with running the Fusion Whole Device Modeling benchmark workflow on Summit, a pre-exascale supercomputer at Oak Ridge National Laboratory. We explore various resource distribution and process placement mechanisms, including sharing compute nodes between processes from separate applications. We show that fine-grained process placement can have a significant impact towards efficient utilization of the compute power of a node on Summit, and conclude that sophisticated tools for performing co-design studies of multi-application workflows can play an important role towards efficient orchestration of such workflows.

Choi, Jong Youl↗

CoSim: A Simulator for Co-Scheduling of Batch and On-Demand Jobs in HPC Datacenters

The increasing scale and complexity of scientific applications are rapidly transforming the ecosystem of tools, methods, and workflows adopted by the high-performance computing (HPC) community. Big data analytics and deep learning are gaining traction as essential components in this ecosystem in a variety of scenarios, such as, steering of experimental instruments , acceleration of high-fidelity simulations through surrogate computations, and guided ensemble searches. In this context, the batch job model traditionally adopted by the supercomputing in-frastructures needs to be complemented with support to schedule opportunistic on-demand analytics jobs, leading to the problem of efficient preemption of batch jobs with minimum loss of progress. In this paper, we design and implement a simulator, CoSim, that enables on-the-fly analysis of the trade-offs arising between delaying the start of opportunistic on-demand jobs, which leads to longer analytics latency, and loss of progress due to preemption of batch jobs, which is necessary to make room for on-demand jobs. To this end, we propose an algorithm based on dynamic programming with predictable performance and scalability that enables supercomputing infrastructure schedulers to analyze the aforementioned trade-off and take decisions in near real-time. Compared with other state-of-art approaches using traces of the Theta pre-Exascale machine, our approach is capable of finding the optimal solution, while achieving high performance and scalability.

batch job preemption↗