Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “high performance computing systems”

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 199 records · Page 11

Performance and power modeling and prediction using MuMMI and 10 machine learning methods

Energy-efficient scientific applications require insight into how high performance computing system features impact the applications' power and performance. This insight can result from the development of performance and power models. Here, in this article, we use the modeling and prediction tool MuMMI (Multiple Metrics Modeling Infrastructure) and 10 machine learning methods to model and predict performance and power consumption and compare their prediction error rates. We use an algorithm-based fault-tolerant linear algebra code and a multilevel checkpointing fault-tolerant heat distribution code to conduct our modeling and prediction study on the Cray XC40 Theta and IBM BG/Q Mira at Argonne National Laboratory and the Intel Haswell cluster Shepard at Sandia National Laboratories. Our experimental results show that the prediction error rates in performance and power using MuMMI are less than 10% for most cases. By utilizing the models for runtime, node power, CPU power, and memory power, we identify the most significant performance counters for potential application optimizations, and we predict theoretical outcomes of the optimizations. Based on two collected datasets, we analyze and compare the prediction accuracy in performance and power consumption using MuMMI and 10 machine learning methods.

97 MATHEMATICS AND COMPUTING↗

Distributed out-of-memory NMF on CPU/GPU architectures

We propose an efficient distributed out-of-memory implementation of the non-negative matrix factorization (NMF) algorithm for heterogeneous high-performance-computing systems. The proposed implementation is based on prior work on NMFk, which can perform automatic model selection and extract latent variables and patterns from data. In this work, we extend NMFk by adding support for dense and sparse matrix operation on multi-node, multi-GPU systems. The resulting algorithm is optimized for out-of-memory problems where the memory required to factorize a given matrix is greater than the available GPU memory. Memory complexity is reduced by batching/tiling strategies, and sparse and dense matrix operations are significantly accelerated with GPU cores (or tensor cores when available). Input/output latency associated with batch copies between host and device is hidden using CUDA streams to overlap data transfers and compute asynchronously, and latency associated with collective communications (both intra-node and inter-node) is reduced using optimized NVIDIA Collective Communication Library (NCCL) based communicators. Benchmark results show significant improvement, from 32X to 76x speedup, with the new implementation using GPUs over the CPU-based NMFk. Good weak scaling was demonstrated on up to 4096 multi-GPU cluster nodes with approximately 25,000 GPUs when decomposing a dense 340 Terabyte-size matrix and an 11 Exabyte-size sparse matrix of density 10 -6 .

97 MATHEMATICS AND COMPUTING↗

An automated and portable method for selecting an optimal GPU frequency

Power consumption poses a significant challenge in current and emerging graphics processing unit (GPU) enabled high-performance computing systems. In modern GPUs, dynamic voltage frequency scaling (DVFS) appears to be a reliable control to regulate power consumption and performance. However, the DVFS design space is large - hence, brute-force approaches are infeasible to select the optimal frequency. Furthermore, no single frequency can be universally optimal for applications with varying computational intensities. Thus, the application's complexity and the availability of a wide range of frequency settings are a challenge in selecting the optimal frequency configuration for a given GPU workload. To that end, this paper proposes a systematic approach that consists of three steps. The feature characterization study identifies the fine-grain GPU utilization metrics that influence the power consumption and execution time of a given workload. To understand the performance, power, and energy consumption behaviors of a workload across GPU's DVFS design space, we derived analytical power and performance models using the identified fine-grain features. Here, it is shown that the same set of GPU utilization metrics can estimate both the power consumption and execution time while being agnostic of changes to frequency and input sizes. Applying a power control with the single objective of reducing power may cause performance degradation, leading to more energy consumption. A multi-objective approach is proposed to select the optimal GPU DVFS configuration for a workload that reduces power consumption with negligible degradation in performance. The evaluation was conducted using SPEC ACCEL benchmarks and three real applications - NAMD LAMMPS, and LSTM on NVIDIA GV100, GA100, and AMD MI210 GPUs. On average, real applications showed 29.6% energy savings with a performance loss of 5.2% on GA100 and 22.6% energy savings with a performance loss of 4.7% on GV100. Moreover, the proposed models are portable to real applications, GPU architectures, and vendors, and require metric collection at only the default frequency rather than all supported DVFS configurations. Additionally, we conducted a comparison between our models and the GPU assembly instructions (PTX)-based static models. The results revealed a significant reduction in the average error rates, with a decrease from 19.7% to 3.1% for power models and from 29.4% to 5.2% for performance models.

97 MATHEMATICS AND COMPUTING↗

Extreme-scale workflows: A perspective from the JLESC international community

The Joint Laboratory for Extreme-Scale Computing (JLESC) focuses on software challenges in high-performance computing systems to meet the needs of today’s science campaigns, which often require large resources, consist of multiple tasks, and generate vast amounts of data. In this context, extreme-scale workflows have been the key factor in enabling scientific discoveries by helping scientists automate the dependencies and data exchanges between workflow tasks, instead of managing those manually. Here, in this paper, we present representative extreme-scale workflows and feature workflow systems developed by JLESC participating institutions. We present lessons learned while developing these tools, alongside with the open challenges and future research directions in the field of extreme-scale workflows.

97 MATHEMATICS AND COMPUTING↗

Scientific machine learning benchmarks

Deep learning has transformed the use of machine learning technologies for the analysis of large experimental datasets. In science, such datasets are typically generated by large-scale experimental facilities, and machine learning focuses on the identification of patterns, trends and anomalies to extract meaningful scientific insights from the data. In upcoming experimental facilities, such as the Extreme Photonics Application Centre (EPAC) in the UK or the international Square Kilometre Array (SKA), the rate of data generation and the scale of data volumes will increasingly require the use of more automated data analysis. Furthermore, at present, identifying the most appropriate machine learning algorithm for the analysis of any given scientific dataset is a challenge due to the potential applicability of many different machine learning frameworks, computer architectures and machine learning models. Historically, for modelling and simulation on high-performance computing systems, these issues have been addressed through benchmarking computer applications, algorithms and architectures. Extending such a benchmarking approach and identifying metrics for the application of machine learning methods to open, curated scientific datasets is a new challenge for both scientists and computer scientists. Here, we introduce the concept of machine learning benchmarks for science and review existing approaches. As an example, we describe the SciMLBench suite of scientific machine learning benchmarks.

42 ENGINEERING↗

The development of GPU-based parallel PRNG for Monte Carlo applications in CUDA Fortran

The implementation of Monte Carlo simulation on the CUDA Fortran requires a fast random number generation with good statistical properties on GPU. In this study, a GPU-based parallel pseudo random number generator (GPPRNG) have been proposed to use in high performance computing systems. According to the type of GPU memory usage, GPU scheme is divided into two work modes including GLOBAL-MODE and SHARED-MODE. To generate parallel random numbers based on the independent sequence method, the combination of middle-square method and chaotic map along with the Xorshift PRNG have been employed. Implementation of our developed PPRNG on a single GPU showed a speedup of 150x and 470x (with respect to the speed of PRNG on a single CPU core) for GLOBAL-MODE and SHARED-MODE, respectively. To evaluate the accuracy of our developed GPPRNG, its performance was compared to that of some other commercially available PPRNGs such as MATLAB, FORTRAN and Miller-Park algorithm through employing the specific standard tests. The results of this comparison showed that the developed GPPRNG in this study can be used as a fast and accurate tool for computational science applications.

97 MATHEMATICS AND COMPUTING↗

An open source analysis framework for large-scale building energy modeling

Full integration of building energy modelling into the design and retrofit process has long been a goal of building scientists and practitioners. However, significant barriers still exist. Among them are the lack of available: (1) configurable technology stacks for performing both small- and large-scale analyses, (2) different classes of algorithms compatible with common design workflows, and (3) analysis tools for effectively visualizing large-scale simulation results. This article discusses the OpenStudio® Analysis Framework: a scalable analysis framework for building energy modelling that was developed to overcome the three barriers listed above. The framework is open-source and scalable to facilitate wider adoption and has a clearly defined application programming interface upon which other applications can be built. It runs on high-performance computing systems, within cloud infrastructure, and on laptops, and uses a common workflow to enable different classes of algorithms. Lessons learned from previous development efforts are also discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Pre-conditioned BFGS-based uncertainty quantification in elastic full-waveform inversion

SUMMARY Full-waveform inversion has become an essential technique for mapping geophysical subsurface structures. However, proper uncertainty quantification is often lacking in current applications. In theory, uncertainty quantification is related to the inverse Hessian (or the posterior covariance matrix). Even for common geophysical inverse problems its calculation is beyond the computational and storage capacities of the largest high-performance computing systems. In this study, we amend the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm to perform uncertainty quantification for large-scale applications. For seismic inverse problems, the limited-memory BFGS (L-BFGS) method prevails as the most efficient quasi-Newton method. We aim to augment it further to obtain an approximate inverse Hessian for uncertainty quantification in FWI. To facilitate retrieval of the inverse Hessian, we combine BFGS (essentially a full-history L-BFGS) with randomized singular value decomposition to determine a low-rank approximation of the inverse Hessian. Setting the rank number equal to the number of iterations makes this solution efficient and memory-affordable even for large-scale problems. Furthermore, based on the Gauss–Newton method, we formulate different initial, diagonal Hessian matrices as pre-conditioners for the inverse scheme and compare their performances in elastic FWI applications. We highlight our approach with the elastic Marmousi benchmark model, demonstrating the applicability of pre-conditioned BFGS for large-scale FWI and uncertainty quantification.

58 GEOSCIENCES↗

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↗

Automatic Fault Characterization via Abnormality-Enhanced Classification

Enterprise and high-performance computing systems are growing extremely large and complex, employing hundreds to hundreds of thousands of processors and software/hardware stacks built by many people across many organizations. As the growing scale of these machines increases the frequency of faults, system complexity makes these faults difficult to detect and to diagnose. Current system management techniques, which focus primarily on efficient data access and query mechanisms, require system administrators to examine the behavior of various system services manually. Growing system complexity is making this manual process unmanageable: administrators require more effective management tools that can detect faults and help to identify their root causes. System administrators need timely notification when a fault is manifested that includes the type of fault, the time period in which it occurred and the processor on which it originated. Statistical modeling approaches can accurately characterize system behavior. However, the complex effects of system faults make these tools difficult to apply effectively. This paper investigates the application of classification and clustering algorithms to fault detection and characterization. We show experimentally that naively applying these methods achieves poor accuracy. Further, we design novel techniques that combine classification algorithms with information on the abnormality of application behavior to improve detection and characterization accuracy. Our experiments demonstrate that these techniques can detect and characterize faults with 65% accuracy, compared to just 5% accuracy for naive approaches.

97 MATHEMATICS AND COMPUTING↗

The role of non-volatile memory from an application perspective

Current, emerging, and future NVM (non-volatile memory) technologies give us hope that we will be able to architect HPC (high performance computing) systems that initially use them in a memory and storage hierarchy, and eventually use them as the memory and storage for the system, complete with ownership and protections as a HDD-based (hard-disk-drive-based) file system provides today.

97 MATHEMATICS AND COMPUTING↗

Designing Topology-Aware Collective Communication Algorithms for Large Scale InfiniBand Clusters: Case Studies with Scatter and Gather

Modern high performance computing systems are being increasingly deployed in a hierarchical fashion with multi-core computing platforms forming the base of the hierarchy. These systems are usually comprised of multiple racks, with each rack consisting of a finite number of chassis, with each chassis having multiple compute nodes or blades, based on multi-core architectures. The networks are also hierarchical with multiple levels of switches. Message exchange operations between processes that belong to different racks involve multiple hops across different switches and this directly affects the performance of collective operations. In this paper, we take on the challenges involved in detecting the topology of large scale InfiniBand clusters and leveraging this knowledge to design efficient topology-aware algorithms for collective operations. We also propose a communication model to analyze the communication costs involved in collective operations on large scale supercomputing systems. We have analyzed the performance characteristics of two collectives, MPI_Gather and MPI_Scatter on such systems and we have proposed topology-aware algorithms for these operations. Our experimental results have shown that the proposed algorithms can improve the performance of these collective operations by almost 54% at the micro-benchmark level.

97 MATHEMATICS AND COMPUTING↗

Co-design of Advanced Architectures for Graph Analytics using Machine Learning

A graph is an excellent way of representing relationships among entities. We can use graph analytics to synthesize and analyze such relational data, and extract relevant features that are useful for various tasks such as machine learning. Considering the crucial role of graph analytics in various domains, it is important and timely to investigate the right hardware configurations that can achieve optimal performance for graph workloads on future high-performance computing systems. Design space exploration studies facilitate the selection of appropriate configurations (e.g. memory) to achieve a desired system performance. Recently, the approach of accelerating graph analytics using persistent non-volatile memory has gained a lot of attention. Traditional system simulators such as Gem5 and NVMain can be used to explore the design space of these advanced memory architectures for graph workloads. However, these simulators are slow in execution thus limiting the efficiency of design space exploration studies. To overcome this challenge, we proposed a machine learning based approach to co-design advanced memory architectures for graph workloads. We tested our approach with DRAM, non-volatile memory, and hybrid memory (DRAM+NVM) using a breadth first search benchmark algorithm. Our results showed the applicability of the proposed machine learning based approach to the co-design of the advanced memory architectures. In this paper, we provide recommendations on selecting advanced memory architectures to achieve desired performance for graph workloads. We also discuss the performances of different machine learning models that were considered in this study.

Kurte, Kuldeep↗

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↗

Large-Scale Calculations for Material Sciences Using Accelerators to Improve Time- and Energy-to-Solution

A major impediment to deploying next-generation high-performance computational systems is the required electrical power, often measured in units of megawatts. The solution to this problem is driving the introduction of novel machine architectures, such as those employing many-core processors and specialized accelerators. In this article, we describe the use of a hybrid accelerated architecture to achieve both reduced time to solution and the associated reduction in the electrical cost for a state-of-the-art materials science computation.

36 MATERIALS SCIENCE↗

Accelerating DCA++ (Dynamical Cluster Approximation) Scientific Application on the Summit supercomputer

Optimizing scientific applications on today’s accelerator-based high performance computing systems can be challenging, especially when multiple GPUs and CPUs with heterogeneous memories and persistent non-volatile memories are present. An example is Summit, an accelerator-based system at the Oak Ridge Leadership Computing Facility (OLCF) that is rated as the world’s fastest supercomputer to-date. New strategies are thus needed to expose the parallelism in legacy applications, while being amenable to efficient mapping to the underlying architecture.In this paper we discuss our experiences and strategies to port a scientific application, DCA++, to Summit. DCA++ is a highperformance research application that solves quantum manybody problems with a cutting edge quantum cluster algorithm, the dynamical cluster approximation.Our strategies aim to synergize the strengths of the different programming models in the code. These include: (a) streamlining the interactions between the CPU threads and the GPUs, (b) implementing computing kernels on the GPUs and decreasing CPU-GPU memory transfers, (c) allowing asynchronous GPU communications, and (d) increasing compute intensity by combining linear algebraic operations.Full-scale production runs using all 4600 Summit nodes attained a peak performance of 73.5 PFLOPS with a mixed precision implementation.We observed a perfect strong and weak scaling for the quantum Monte Carlo solver in DCA++, while encountering about 2× input/output (I/O) and MPI communication overhead on the time-to-solution for the full machine run. Our hardware agnostic optimizations are designed to alleviate the communication and I/O challenges observed, while improving the compute intensity and obtaining optimal performance on a complex, hybrid architecture like Summit.

Balduzzi, Giovanni↗

zPerf: A Statistical Gray-Box Approach to Performance Modeling and Extrapolation for Scientific Lossy Compression

With the scaling up of simulation-based scientific discovery on high-performance computing systems, the disparity between compute and I/O has increased, forcing domain scientists to save only a small amount of simulation data to persistent storage. This can result in the loss of essential physics fields that are needed for data analysis. While error-bounded lossy compression has made tremendous progress in bridging the gap between compute and I/O, the lack of understanding of compression performance remains a key hurdle to its wide adoption. Here, in this work, we present zPerf, a statistical gray-box performance modeling approach for scientific lossy compression. Our contributions are threefold: 1) We develop zPerf to estimate the performance of lossy compression techniques, based on in-depth understanding and statistical modeling for data features and core compression metrics; 2) We demonstrate the in-detailed implementation of zPerf using two case studies, where we derive the performance modeling for SZ and ZFP, two leading lossy compressors; 3) We evaluate the effectiveness of zPerf on real-world datasets across various domains. Based on the evaluation, we demonstrate the efficacy of the zPerf performance model; 4) We further discuss three case studies where zPerf is applied to extrapolate the compression ratio of SZ and ZFP with alternative encoding schemes as well as ZFP with an alternative transform scheme. Through the case studies, we demonstrate the potential of zPerf for exploring the design space of lossy compression, which has hardly been studied in the literature.

97 MATHEMATICS AND COMPUTING↗

Scalable Contour Tree Computation by Data Parallel Peak Pruning

As data sets grow to exascale, automated data analysis and visualization 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. Furthermore, we report the first shared SMP algorithm for fully parallel contour tree computation, with formal guarantees of O(lg V lg t) parallel steps and O(V lg V) work for data with V samples and t contour tree supernodes, and implementations with more than 30× parallel speed up on both CPU using TBB and GPU using Thrust and up 70× speed up compared to the serial sweep and merge algorithm.

97 MATHEMATICS AND COMPUTING↗