Results for “Data Movement” — Page 10

DOE OSTI2016

PATHA: Performance Analysis Tool for HPC Applications

Large science projects rely on complex workflows to analyze terabytes or petabytes of data. These jobs are often running over thousands of CPU cores and simultaneously performing data accesses, data movements, and computation. It is difficult to identify bottlenecks or to debug the performance issues in these large workflows. In order to address these challenges, we have developed Performance Analysis Tool for HPC Applications (PATHA) using the state-of-art open source big data processing tools. Our framework can ingest system logs to extract key performance measures, and apply the most sophisticated statistical tools and data mining methods on the performance data. Furthermore, it utilizes an efficient data processing engine to allow users to interactively analyze a large amount of different types of logs and measurements. To illustrate the functionality of PATHA, we conduct a case study on the workflows from an astronomy project known as the Palomar Transient Factory (PTF). This study processed 1.6 TB of system logs collected on the NERSC supercomputer Edison. Using PATHA, we were able to identify performance bottlenecks, which reside in three tasks of PTF workflow with the dependency on the density of celestial objects.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

NASA NTRS2005

An information maximization model of eye movements

We propose a sequential information maximization model as a general strategy for programming eye movements. The model reconstructs high-resolution visual information from a sequence of fixations, taking into account the fall-off in resolution from the fovea to the periphery. From this framework we get a simple rule for predicting fixation sequences: after each fixation, fixate next at the location that minimizes uncertainty (maximizes information) about the stimulus. By comparing our model performance to human eye movement data and to predictions from a saliency and random model, we demonstrate that our model is best at predicting fixation locations. Modeling additional biological constraints will improve the prediction of fixation sequences. Our results suggest that information maximization is a useful principle for programming eye movements.

NASA Discipline Neuroscience↗

DOE OSTI2016

High Energy Physics Exascale Requirements Review. An Office of Science review sponsored jointly by Advanced Scientific Computing Research and High Energy Physics, June 10-12, 2015, Bethesda, Maryland

The U.S. Department of Energy (DOE) Office of Science (SC) Offices of High Energy Physics (HEP) and Advanced Scientific Computing Research (ASCR) convened a programmatic Exascale Requirements Review on June 10–12, 2015, in Bethesda, Maryland. This report summarizes the findings, results, and recommendations derived from that meeting. The high-level findings and observations are as follows. Larger, more capable computing and data facilities are needed to support HEP science goals in all three frontiers: Energy, Intensity, and Cosmic. The expected scale of the demand at the 2025 timescale is at least two orders of magnitude — and in some cases greater — than that available currently. The growth rate of data produced by simulations is overwhelming the current ability of both facilities and researchers to store and analyze it. Additional resources and new techniques for data analysis are urgently needed. Data rates and volumes from experimental facilities are also straining the current HEP infrastructure in its ability to store and analyze large and complex data volumes. Appropriately configured leadership-class facilities can play a transformational role in enabling scientific discovery from these datasets. A close integration of high-performance computing (HPC) simulation and data analysis will greatly aid in interpreting the results of HEP experiments. Such an integration will minimize data movement and facilitate interdependent workflows. Long-range planning between HEP and ASCR will be required to meet HEP’s research needs. To best use ASCR HPC resources, the experimental HEP program needs (1) an established, long-term plan for access to ASCR computational and data resources, (2) the ability to map workflows to HPC resources, (3) the ability for ASCR facilities to accommodate workflows run by collaborations potentially comprising thousands of individual members, (4) to transition codes to the next-generation HPC platforms that will be available at ASCR facilities, (5) to build up and train a workforce capable of developing and using simulations and analysis to support HEP scientific research on next-generation systems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2017

ASCR/HEP Exascale Requirements Review Report

This draft report summarizes and details the findings, results, and recommendations derived from the ASCR/HEP Exascale Requirements Review meeting held in June, 2015. The main conclusions are as follows. 1) Larger, more capable computing and data facilities are needed to support HEP science goals in all three frontiers: Energy, Intensity, and Cosmic. The expected scale of the demand at the 2025 timescale is at least two orders of magnitude -- and in some cases greater -- than that available currently. 2) The growth rate of data produced by simulations is overwhelming the current ability, of both facilities and researchers, to store and analyze it. Additional resources and new techniques for data analysis are urgently needed. 3) Data rates and volumes from HEP experimental facilities are also straining the ability to store and analyze large and complex data volumes. Appropriately configured leadership-class facilities can play a transformational role in enabling scientific discovery from these datasets. 4) A close integration of HPC simulation and data analysis will aid greatly in interpreting results from HEP experiments. Such an integration will minimize data movement and facilitate interdependent workflows. 5) Long-range planning between HEP and ASCR will be required to meet HEP's research needs. To best use ASCR HPC resources the experimental HEP program needs a) an established long-term plan for access to ASCR computational and data resources, b) an ability to map workflows onto HPC resources, c) the ability for ASCR facilities to accommodate workflows run by collaborations that can have thousands of individual members, d) to transition codes to the next-generation HPC platforms that will be available at ASCR facilities, e) to build up and train a workforce capable of developing and using simulations and analysis to support HEP scientific research on next-generation systems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2016

ASCR/HEP Exascale Requirements Review Report

This draft report summarizes and details the findings, results, and recommendations derived from the ASCR/HEP Exascale Requirements Review meeting held in June, 2015. The main conclusions are as follows. 1) Larger, more capable computing and data facilities are needed to support HEP science goals in all three frontiers: Energy, Intensity, and Cosmic. The expected scale of the demand at the 2025 timescale is at least two orders of magnitude -- and in some cases greater -- than that available currently. 2) The growth rate of data produced by simulations is overwhelming the current ability, of both facilities and researchers, to store and analyze it. Additional resources and new techniques for data analysis are urgently needed. 3) Data rates and volumes from HEP experimental facilities are also straining the ability to store and analyze large and complex data volumes. Appropriately configured leadership-class facilities can play a transformational role in enabling scientific discovery from these datasets. 4) A close integration of HPC simulation and data analysis will aid greatly in interpreting results from HEP experiments. Such an integration will minimize data movement and facilitate interdependent workflows. 5) Long-range planning between HEP and ASCR will be required to meet HEP's research needs. To best use ASCR HPC resources the experimental HEP program needs a) an established long-term plan for access to ASCR computational and data resources, b) an ability to map workflows onto HPC resources, c) the ability for ASCR facilities to accommodate workflows run by collaborations that can have thousands of individual members, d) to transition codes to the next-generation HPC platforms that will be available at ASCR facilities, e) to build up and train a workforce capable of developing and using simulations and analysis to support HEP scientific research on next-generation systems.

Habib, Salman↗

DOE OSTI2019

PaKman: Scalable Assembly of Large Genomes on Distributed Memory Machines

De novo genome assembly is a fundamental problem in the field of bioinformatics, that aims to assemble the DNA sequence of an unknown genome from numerous short DNA fragments (aka reads) obtained from it. With the advent of high-throughput sequencing technologies, billions of reads can be generated in a matter of hours, necessitating efficient parallelization of the assembly process. While multiple parallel solutions have been proposed in the past, conducting a large- scale assembly at scale remains a challenging problem because of the inherent complexities associated with data movement, and irregular access footprints of memory and I/O operations. In this paper, we present a novel algorithm, called PaKman, to address the problem of performing large-scale genome assemblies on a distributed memory parallel computer. Our approach focuses on improving performance through a combination of novel data structures and algorithmic strategies for reducing the communication and I/O footprint during the assembly process. A key aspect of our algorithm is its graph data structure, which comprises fat nodes (or what we call "macro-nodes") that reduce the communication burden during contig generation. We present an extensive performance and qualitative evaluation of our algorithm, including comparisons to other state-of-the-art parallel assemblers. Our results demonstrate the ability to achieve near-linear speedups on up to 8K cores (tested); outperform state-of-the-art distributed memory and shared memory tools in performance while delivering comparable (if not better) quality; and reduce time to solution significantly. For instance, PaKman is able to complete an assembly of the full human genome in just over a minute on 8K cores.

Ghosh, Priyanka↗

DOE OSTI2021

Efficient exascale discretizations: High-order finite element methods

Efficient exploitation of exascale architectures requires rethinking of the numerical algorithms used in many large-scale applications. These architectures favor algorithms that expose ultra fine-grain parallelism and maximize the ratio of floating point operations to energy intensive data movement. One of the few viable approaches to achieve high efficiency in the area of PDE discretizations on unstructured grids is to use matrix-free/partially assembled high-order finite element methods, since these methods can increase the accuracy and/or lower the computational time due to reduced data motion. In this paper we provide an overview of the research and development activities in the Center for Efficient Exascale Discretizations (CEED), a co-design center in the Exascale Computing Project that is focused on the development of next-generation discretization software and algorithms to enable a wide range of finite element applications to run efficiently on future hardware. CEED is a research partnership involving more than 30 computational scientists from two US national labs and five universities, including members of the Nek5000, MFEM, MAGMA and PETSc projects. We discuss the CEED co-design activities based on targeted benchmarks, miniapps and discretization libraries and our work on performance optimizations for large-scale GPU architectures. We also provide a broad overview of research and development activities in areas such as unstructured adaptive mesh refinement algorithms, matrix-free linear solvers, high-order data visualization, and list examples of collaborations with several ECP and external applications.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2015

Machine Learning and Understanding for Intelligent Extreme Scale Scientific Computing and Discovery. DOE Workshop Report, January 7–9, 2015, Rockville, MD

Large-scale parallel simulations and data analysis drive scientific discovery across many disciplines. To drive larger and more detailed simulations, and deal with larger data volumes, exascale machines capable of 1018 operations per second are expected within the next five to ten years. However, the complexity of developing and adapting modern simulation codes for these architectures is increasing rapidly. Workloads on exascale machines will be billion-way parallel. Exploiting the full capability of the machine will require carefully assigning application tasks to cores, accelerators, deep memories, and other heterogeneous compute resources, while simultaneously optimizing for time to solution, data movement, power, and resilience. Optimizations that improve performance on one machine may slow down another. Worse, applications themselves are dauntingly complex. Production simulations comprise millions of lines of code and use sophisticated, adaptive algorithms whose performance is input-dependent. Complex workflows can couple multi-physics simulation with data preprocessing and post-processing modules.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

DaCe - Data Centric Parallel Programming

DaCe is a parallel programming framework that takes code in Python/NumPy and other programming languages, and maps it to high-performance CPU, GPU, and FPGA programs, which can be optimized to achieve state-of-the-art. Internally, DaCe uses the Stateful DataFlow multiGraph (SDFG) data-centric intermediate representation: A transformable, interactive representation of code based on data movement. Since the input code and the SDFG are separate, it is possible to optimize a program without changing its source, so that it stays readable. On the other hand, transformations are customizable and user-extensible, so they can be written once and reused in many applications. With data-centric parallel programming, we enable direct knowledge transfer of performance optimization, regardless of the application or the target processor.

Ben-Nun, Tal↗

DOE OSTI2021

Large Vessel Activity and Low-Frequency Underwater Sound Benchmarks in United States Waters

Chronic low-frequency noise from commercial shipping is a worldwide threat to marine animals that rely on sound for essential life functions. Although the U.S. National Oceanic and Atmospheric Administration recognizes the potential negative impacts of shipping noise in marine environments, there are currently no standard metrics to monitor and quantify shipping noise in U.S. marine waters. However, one-third octave band acoustic measurements centered at 63 and 125 Hz are used as international (European Union Marine Strategy Framework Directive) indicators for underwater ambient noise levels driven by shipping activity. We apply these metrics to passive acoustic monitoring data collected over 20 months in 2016–2017 at five dispersed sites throughout the U.S. Exclusive Economic Zone: Alaskan Arctic, Hawaii, Gulf of Mexico, Northeast Canyons and Seamounts Marine National Monument (Northwest Atlantic), and Cordell Bank National Marine Sanctuary (Northeast Pacific). To verify the relationship between shipping activity and underwater sound levels, vessel movement data from the Automatic Identification System (AIS) were paired to each passive acoustic monitoring site. Daily average sound levels were consistently near to or higher than 100 dB re 1 μPa in both the 63 and 125 Hz one-third octave bands at sites with high levels of shipping traffic (Gulf of Mexico, Northeast Canyons and Seamounts, and Cordell Bank). Where cargo vessels were less common (the Arctic and Hawaii), daily average sound levels were comparatively lower. Specifically, sound levels were ~20 dB lower year-round in Hawaii and ~10-20 dB lower in the Alaskan Arctic, depending on the season. Although these band-level measurements can only generally facilitate differentiation of sound sources, these results demonstrate that international acoustic indicators of commercial shipping can be applied to data collected in U.S. waters as a unified metric to approximate the influence of shipping as a driver of ambient noise levels, provide critical information to managers and policy makers about the status of marine environments, and to identify places and times for more detailed investigation regarding environmental impacts.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS1978

Models for extracting vertical crustal movements from leveling data

Various adjustment strategies are being used in North America to obtain vertical crustal movements from repeated leveling. The more successful models utilize polynomials or multiquadric analysis to describe elevation change with a velocity surface. Other features permit determination of nonlinear motions, motions associated with earthquakes or episodes, and vertical motions of blocks where boundaries are prespecified. The preferred models for estimating crustal motions permit the use of detached segments of releveling to govern the shape of a velocity surface and allow for input from nonleveling sources such as tide gages and paired lake gages. Some models for extracting vertical crustal movements from releveling data are also excellent for adjusting leveling networks, and permit mixing old and new data in areas exhibiting vertical motion. The new adjustment techniques are more general than older static models and will undoubtedly be used routinely in the future as the constitution of level networks becomes mainly relevelings.

Holdahl, S. H.↗

DOE OSTI2017

A Pervasive Parallel Processing Framework for Data Visualization and Analysis at Extreme Scale

Most of today’s visualization libraries and applications are based off of what is known today as the visualization pipeline. In the visualization pipeline model, algorithms are encapsulated as “filtering” components with inputs and outputs. These components can be combined by connecting the outputs of one filter to the inputs of another filter. The visualization pipeline model is popular because it provides a convenient abstraction that allows users to combine algorithms in powerful ways. Unfortunately, the visualization pipeline cannot run effectively on exascale computers. Experts agree that the exascale machine will comprise processors that contain many cores. Furthermore, physical limitations will prevent data movement in and out of the chip (that is, between main memory and the processing cores) from keeping pace with improvements in overall compute performance. To use these processors to their fullest capability, it is essential to carefully consider memory access. This is where the visualization pipeline fails. Each filtering component in the visualization library is expected to take a data set in its entirety, perform some computation across all of the elements, and output the complete results. The process of iterating over all elements must be repeated in each filter, which is one of the worst possible ways to traverse memory when trying to maximize the number of executions per memory access. This project investigates a new type of visualization framework that exhibits a pervasive parallelism necessary to run on exascale machines. Our framework achieves this by defining algorithms in terms of functors, which are localized, stateless operations. Functors can be composited in much the same way as filters in the visualization pipeline. But, functors’ design allows them to be concurrently running on massive amounts of lightweight threads. Only with such fine-grained parallelism can we hope to fill the billions of threads we expect will be necessary for efficient computation on an exascale computer. This project concludes with a functional prototype containing pervasively parallel algorithms that perform demonstratively well on many-core processors. These algorithms are fundamental for performing data analysis and visualization at extreme scale.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Joint Genome Institute Analysis Workflow Service (JAWS) v2.7

The U.S. Department of Energy Joint Genome Institute (JGI) has developed the JGI Analysis Workflow Service (JAWS) as a distributed framework to run computational workflows across diverse high-performance computing (HPC) and cloud environments. JAWS enhances the reusability, scalability, and robustness of scientific workflows by orchestrating data movement, code execution, and results retrieval across multiple DOE facilities. At its core, JAWS integrates the Cromwell workflow engine to run workflows expressed in the Workflow Description Language (WDL), ensuring portability and interoperability. To provide consistent runtime environments, JAWS employs container technologies such as Shifter, Apptainer, and Docker. Workflow tasks are managed via HTCondor on HPC backends, while Globus ensures secure and efficient data transfer between sites. JAWS is deployed as a multi-site workflow manager across national laboratory computing facilities, with dedicated instances supporting community projects such as the National Microbiome Data Collaborative (NMDC) and KBase. This distributed, service-oriented architecture enables users to "write once, run anywhere," providing scalable, production-quality workflow execution.

Kirton, Edward↗

DOE OSTI2016

Optimizing End-to-End Big Data Transfers over Terabits Network Infrastructure

While future terabit networks hold the promise of significantly improving big-data motion among geographically distributed data centers, significant challenges must be overcome even on today's 100 gigabit networks to realize end-to-end performance. Multiple bottlenecks exist along the end-to-end path from source to sink, for instance, the data storage infrastructure at both the source and sink and its interplay with the wide-area network are increasingly the bottleneck to achieving high performance. In this study, we identify the issues that lead to congestion on the path of an end-to-end data transfer in the terabit network environment, and we present a new bulk data movement framework for terabit networks, called LADS. LADS exploits the underlying storage layout at each endpoint to maximize throughput without negatively impacting the performance of shared storage resources for other users. LADS also uses the Common Communication Interface (CCI) in lieu of the sockets interface to benefit from hardware-level zero-copy, and operating system bypass capabilities when available. It can further improve data transfer performance under congestion on the end systems using buffering at the source using flash storage. With our evaluations, we show that LADS can avoid congested storage elements within the shared storage resource, improving input/output bandwidth, and data transfer rates across the high speed networks. We also investigate the performance degradation problems of LADS due to I/O contention on the parallel file system (PFS), when multiple LADS tools share the PFS. We design and evaluate a meta-scheduler to coordinate multiple I/O streams while sharing the PFS, to minimize the I/O contention on the PFS. Finally, with our evaluations, we observe that LADS with meta-scheduling can further improve the performance by up to 14 percent relative to LADS without meta-scheduling.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

iez: Resource Contention Aware Load Balancing for Large-Scale Parallel File Systems

Parallel I/O performance is crucial to sustaining scientific applications on large-scale High-Performance Computing (HPC) systems. However, I/O load imbalance in the underlying distributed and shared storage systems can significantly reduce overall application performance. There are two conflicting challenges to mitigate this load imbalance: (i) optimizing systemwide data placement to maximize the bandwidth advantages of distributed storage servers, i.e., allocating I/O resources efficiently across applications and job runs; and (ii) optimizing client-centric data movement to minimize I/O load request latency between clients and servers, i.e., allocating I/O resources efficiently in service to a single application and job run. Moreover, existing approaches that require application changes limit wide-spread adoption in commercial or proprietary deployments. We propose iez, an “end-to-end control plane” where clients transparently and adaptively write to a set of selected I/O servers to achieve balanced data placement. Our control plane leverages realtime load information for distributed storage server global data placement while our design model leverages trace-based optimization techniques to minimize I/O load request latency between clients and servers. We evaluate our proposed system on an experimental cluster for two common use cases: synthetic I/O benchmark IOR for large sequential writes and a scientific application I/O kernel, HACC-I/O. Results show read and write performance improvements of up to 34% and 32%, respectively, compared to the state of the art.

Wadhwa, Bharti↗

DOE OSTI2022

NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

DOE OSTI2022

28 NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning: Preprint

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

DOE OSTI2021

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

Today's high-performance computing (HPC) applications are producing vast volumes of data, which are challenging to store and transfer efficiently during the execution, such that data compression is becoming a critical technique to mitigate the storage burden and data movement cost. Huffman coding is arguably the most efficient Entropy coding algorithm in information theory, such that it could be found as a fundamental step in many modern compression algorithms such as DEFLATE. On the other hand, today's HPC applications are more and more relying on the accelerators such as GPU on supercomputers, while Huffman encoding suffers from low throughput on GPUs, resulting in a significant bottleneck in the entire data processing. In this paper, we propose and implement an efficient Huffman encoding approach based on modern GPU architectures, which addresses two key challenges: (1) how to parallelize the entire Huffman encoding algorithm, including codebook construction, and (2) how to fully utilize the high memory-bandwidth feature of modern GPU architectures. The detailed contribution is fourfold. (1) We develop an efficient parallel codebook construction on GPUs that scales effectively with the number of input symbols. (2) We propose a novel reduction based encoding scheme that can efficiently merge the codewords on GPUs. (3) We optimize the overall GPU performance by leveraging the state-of-the-art CUDA APIs such as Cooperative Groups. (4) We evaluate our Huffman encoder thoroughly using six real-world application datasets on two advanced GPUs and compare with our implemented multi-threaded Huffman encoder. Experiments show that our solution can improve the encoding throughput by up to 5.0x and 6.8x on NVIDIA RTX 5000 and V100, respectively, over the state-of-the-art GPU Huffman encoder, and by up to 3.3x over the multi-thread encoder on two 28-core Xeon Platinum 8280 CPUs.

Tian, Jiannan↗