arXiv subjects

Shantenu Jha

Publications and source records attributed to Shantenu Jha.

At least 91 records · Page 5Linked to original sources

arXiv2019

Designing Workflow Systems Using Building Blocks

We suggest there is a need for a fresh perspective on the design and development of workflow systems and argue for a building blocks approach. We outline a description of this approach and define the properties of software building blocks. We discuss RADICAL-Cybertools as one implementation of the building blocks concept, showing how they have been designed and developed in accordance with this approach. Four case studies are presented, covering a dozen science problems. We discuss how RADICAL-Cybertools have been used to develop new workflow systems capabilities and integrated to enhance existing ones, illustrating the applicability and potential of software building blocks. In doing so, we have begun an investigation of an alternative approach to thinking about the design and implementation of workflow systems.

cs.SE↗

arXiv2019

RADICAL-Cybertools: Middleware Building Blocks for Scalable Science

RADICAL-Cybertools (RCT) are a set of software systems that serve as middleware to develop efficient and effective tools for scientific computing. Specifically, RCT enable executing many-task applications at extreme scale and on a variety of computing infrastructures. RCT are building blocks, designed to work as stand-alone systems, integrated among themselves or integrated with third-party systems. RCT enables innovative science in multiple domains, including but not limited to biophysics, climate science and particle physics, consuming hundreds of millions of core hours. This paper provides an overview of RCT systems, their impact, and the architectural principles and software engineering underlying RCT

cs.SE↗

arXiv2019

Learning Everywhere: Pervasive Machine Learning for Effective High-Performance Computation

The convergence of HPC and data-intensive methodologies provide a promising approach to major performance improvements. This paper provides a general description of the interaction between traditional HPC and ML approaches and motivates the Learning Everywhere paradigm for HPC. We introduce the concept of effective performance that one can achieve by combining learning methodologies with simulation-based approaches, and distinguish between traditional performance as measured by benchmark scores. To support the promise of integrating HPC and learning methods, this paper examines specific examples and opportunities across a series of domains. It concludes with a series of open computer science and cyberinfrastructure questions and challenges that the Learning Everywhere paradigm presents.

cs.DC↗

arXiv2019

Supporting High-Performance and High-Throughput Computing for Experimental Science

The advent of experimental science facilities-instruments and observatories, such as the Large Hadron Collider, the Laser Interferometer Gravitational Wave Observatory, and the upcoming Large Synoptic Survey Telescope-has brought about challenging, large-scale computational and data processing requirements. Traditionally, the computing infrastructure to support these facility's requirements were organized into separate infrastructure that supported their high-throughput needs and those that supported their high-performance computing needs. We argue that to enable and accelerate scientific discovery at the scale and sophistication that is now needed, this separation between high-performance computing and high-throughput computing must be bridged and an integrated, unified infrastructure provided. In this paper, we discuss several case studies where such infrastructure has been implemented. These case studies span different science domains, software systems, and application requirements as well as levels of sustainability. A further aim of this paper is to provide a basis to determine the common characteristics and requirements of such infrastructure, as well as to begin a discussion of how best to support the computing requirements of existing and future experimental science facilities.

cs.DC↗

arXiv2018

Pilot-Streaming: A Stream Processing Framework for High-Performance Computing

An increasing number of scientific applications rely on stream processing for generating timely insights from data feeds of scientific instruments, simulations, and Internet-of-Thing (IoT) sensors. The development of streaming applications is a complex task and requires the integration of heterogeneous, distributed infrastructure, frameworks, middleware and application components. Different application components are often written in different languages using different abstractions and frameworks. Often, additional components, such as a message broker (e.g. Kafka), are required to decouple data production and consumptions and avoiding issues, such as back-pressure. Streaming applications may be extremely dynamic due to factors, such as variable data rates caused by the data source, adaptive sampling techniques or network congestions, variable processing loads caused by usage of different machine learning algorithms. As a result application-level resource management that can respond to changes in one of these factors is critical. We propose Pilot-Streaming, a framework for supporting streaming frameworks, applications and their resource management needs on HPC infrastructure. Pilot-Streaming is based on the Pilot-Job concept and enables developers to manage distributed computing and data resources for complex streaming applications. It enables applications to dynamically respond to resource requirements by adding/removing resources at runtime. This capability is critical for balancing complex streaming pipelines. To address the complexity in developing and characterization of streaming applications, we present the Streaming Mini- App framework, which supports different plug-able algorithms for data generation and processing, e.g., for reconstructing light source images using different techniques. We utilize the Mini-App framework to conduct an evaluation of Pilot-Streaming.

cs.DC↗

arXiv2018

Concurrent and Adaptive Extreme Scale Binding Free Energy Calculations

The efficacy of drug treatments depends on how tightly small molecules bind to their target proteins. The rapid and accurate quantification of the strength of these interactions (as measured by binding affinity) is a grand challenge of computational chemistry, surmounting which could revolutionize drug design and provide the platform for patient-specific medicine. Recent evidence suggests that molecular dynamics (MD) can achieve useful predictive accuracy (< 1 kcal/mol). For this predictive accuracy to impact clinical decision making, binding free energy computational campaigns must provide results rapidly and without loss of accuracy. This demands advances in algorithms, scalable software systems, and efficient utilization of supercomputing resources. We introduce a framework called HTBAC, designed to support accurate and scalable drug binding affinity calculations, while marshaling large simulation campaigns. We show that HTBAC supports the specification and execution of free-energy protocols at scale. This paper makes three main contributions: (1) shows the importance of adaptive execution for ensemble-based free energy protocols to improve binding affinity accuracy; (2) presents and characterizes HTBAC -- a software system that enables the scalable and adaptive execution of binding affinity protocols at scale; and (3) for a widely used free-energy protocol (TIES), shows improvements in the accuracy of simulations for a fixed amount of resource, or reduced resource consumption for a fixed accuracy as a consequence of adaptive execution.

cs.DC↗

arXiv2018

Adaptive ensemble simulations of biomolecules

Recent advances in both theory and computational power have created opportunities to simulate biomolecular processes more efficiently using adaptive ensemble simulations. Ensemble simulations are now widely used to compute a number of individual simulation trajectories and analyze statistics across them. Adaptive ensemble simulations offer a further level of sophistication and flexibility by enabling high-level algorithms to control simulations based on intermediate results. We review some of the adaptive ensemble algorithms and software infrastructure currently in use and outline where the complexities of implementing adaptive simulation have limited algorithmic innovation to date. We describe an adaptive ensemble API to overcome some of these barriers and more flexibly and simply express adaptive simulation algorithms to help realize the power of this type of simulation.

q-bio.QM↗

arXiv2018

Synapse: Synthetic Application Profiler and Emulator

Motivated by the need to emulate workload execution characteristics on high-performance and distributed heterogeneous resources, we introduce Synapse. Synapse is used as a proxy application (or "representative application") for real workloads, with the advantage that it can be tuned in different ways and dimensions, and also at levels of granularity that are not possible with real applications. Synapse has a platform-independent application profiler, and has the ability to emulate profiled workloads on a variety of resources. Experiments show that the automated profiling performed using Synapse captures an application's characteristics with high fidelity. The emulation of an application using Synapse can reproduce the application's execution behavior in the original run-time environment, and can also reproduce those behaviors on different run-time environments.

cs.DC↗

arXiv2018

Using Pilot Systems to Execute Many Task Workloads on Supercomputers

High performance computing systems have historically been designed to support applications comprised of mostly monolithic, single-job workloads. Pilot systems decouple workload specification, resource selection, and task execution via job placeholders and late-binding. Pilot systems help to satisfy the resource requirements of workloads comprised of multiple tasks. RADICAL-Pilot (RP) is a modular and extensible Python-based pilot system. In this paper we describe RP's design, architecture and implementation, and characterize its performance. RP is capable of spawning more than 100 tasks/second and supports the steady-state execution of up to 16K concurrent tasks. RP can be used stand-alone, as well as integrated with other application-level tools as a runtime system.

cs.DC↗

arXiv2018

Task-parallel Analysis of Molecular Dynamics Trajectories

Different parallel frameworks for implementing data analysis applications have been proposed by the HPC and Big Data communities. In this paper, we investigate three task-parallel frameworks: Spark, Dask and RADICAL-Pilot with respect to their ability to support data analytics on HPC resources and compare them with MPI. We investigate the data analysis requirements of Molecular Dynamics (MD) simulations which are significant consumers of supercomputing cycles, producing immense amounts of data. A typical large-scale MD simulation of a physical system of O(100k) atoms over μsecs can produce from O(10) GB to O(1000) GBs of data. We propose and evaluate different approaches for parallelization of a representative set of MD trajectory analysis algorithms, in particular the computation of path similarity and leaflet identification. We evaluate Spark, Dask and RADICAL-Pilot with respect to their abstractions and runtime engine capabilities to support these algorithms. We provide a conceptual basis for comparing and understanding different frameworks that enable users to select the optimal system for each application. We also provide a quantitative performance analysis of the different algorithms across the three frameworks.

cs.DC↗

arXiv2018

Harnessing the Power of Many: Extensible Toolkit for Scalable Ensemble Applications

Many scientific problems require multiple distinct computational tasks to be executed in order to achieve a desired solution. We introduce the Ensemble Toolkit (EnTK) to address the challenges of scale, diversity and reliability they pose. We describe the design and implementation of EnTK, characterize its performance and integrate it with two distinct exemplar use cases: seismic inversion and adaptive analog ensembles. We perform nine experiments, characterizing EnTK overheads, strong and weak scalability, and the performance of two use case implementations, at scale and on production infrastructures. We show how EnTK meets the following general requirements: (i) implementing dedicated abstractions to support the description and execution of ensemble applications; (ii) support for execution on heterogeneous computing infrastructures; (iii) efficient scalability up to O(10^4) tasks; and (iv) fault tolerance. We discuss novel computational capabilities that EnTK enables and the scientific advantages arising thereof. We propose EnTK as an important addition to the suite of tools in support of production scientific computing.

cs.DC↗

arXiv2018

Use Cases of Computational Reproducibility for Scientific Workflows at Exascale

We propose an approach for improved reproducibility that includes capturing and relating provenance characteristics and performance metrics, in a hybrid queriable system, the ProvEn server. The system capabilities are illustrated on two use cases: scientific reproducibility of results in the ACME climate simulations and performance reproducibility in molecular dynamics workflows on HPC computing platforms.

cs.DC↗

arXiv2018

High-throughput Binding Affinity Calculations at Extreme Scales

Resistance to chemotherapy and molecularly targeted therapies is a major factor in limiting the effectiveness of cancer treatment. In many cases, resistance can be linked to genetic changes in target proteins, either pre-existing or evolutionarily selected during treatment. Key to overcoming this challenge is an understanding of the molecular determinants of drug binding. Using multi-stage pipelines of molecular simulations we can gain insights into the binding free energy and the residence time of a ligand, which can inform both stratified and personal treatment regimes and drug development. To support the scalable, adaptive and automated calculation of the binding free energy on high-performance computing resources, we introduce the High- throughput Binding Affinity Calculator (HTBAC). HTBAC uses a building block approach in order to attain both workflow flexibility and performance. We demonstrate close to perfect weak scaling to hundreds of concurrent multi-stage binding affinity calculation pipelines. This permits a rapid time-to-solution that is essentially invariant of the calculation protocol, size of candidate ligands and number of ensemble simulations. As such, HTBAC advances the state of the art of binding affinity calculations and protocols.

cs.DC↗

arXiv2018

Towards General Distributed Resource Selection

The advantages of distributing workloads and utilizing multiple distributed resources are now well established. The type and degree of heterogeneity of distributed resources is increasing, and thus determining how to distribute the workloads becomes increasingly difficult, in particular with respect to the selection of suitable resources. We formulate and investigate the resource selection problem in a way that it is agnostic of specific task and resource properties, and which is generalizable to range of metrics. Specifically, we developed a model to describe the requirements of tasks and to estimate the cost of running that task on an arbitrary resource using baseline measurements from a reference machine. We integrated our cost model with the Condor matchmaking algorithm to enable resource selection. Experimental validation of our model shows that it provides execution time estimates with 157-171% error on XSEDE resources and 18-31% on OSG resources. We use the task execution cost model to select resources for a bag-of-tasks of up to 1024 GROMACS MD simulations across the target resources. Experiments show that using the model's estimates reduces the workload's time-to-completion up to ~85% when compared to the random distribution of workload across the same resources.

cs.DC↗

arXiv2018

Design and Performance Characterization of RADICAL-Pilot on Titan

Many extreme scale scientific applications have workloads comprised of a large number of individual high-performance tasks. The Pilot abstraction decouples workload specification, resource management, and task execution via job placeholders and late-binding. As such, suitable implementations of the Pilot abstraction can support the collective execution of large number of tasks on supercomputers. We introduce RADICAL-Pilot (RP) as a portable, modular and extensible Python-based Pilot system. We describe RP's design, architecture and implementation. We characterize its performance and show its ability to scalably execute workloads comprised of thousands of MPI tasks on Titan--a DOE leadership class facility. Specifically, we investigate RP's weak (strong) scaling properties up to 131K (65K) cores and 4096 (16384) 32 core tasks. RADICAL-Pilot can be used stand-alone, as well as integrated with other tools as a runtime system.

cs.DC↗

arXiv2017

Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks

Smart systems that can accurately diagnose patients with mental disorders and identify effective treatments based on brain functional imaging data are of great applicability and are gaining much attention. Most previous machine learning studies use hand-designed features, such as functional connectivity, which does not maintain the potential useful information in the spatial relationship between brain regions and the temporal profile of the signal in each region. Here we propose a new method based on recurrent-convolutional neural networks to automatically learn useful representations from segments of 4-D fMRI recordings. Our goal is to exploit both spatial and temporal information in the functional MRI movie (at the whole-brain voxel level) for identifying patients with schizophrenia.

cs.CV↗

arXiv2017

High-Throughput Computing on High-Performance Platforms: A Case Study

The computing systems used by LHC experiments has historically consisted of the federation of hundreds to thousands of distributed resources, ranging from small to mid-size resource. In spite of the impressive scale of the existing distributed computing solutions, the federation of small to mid-size resources will be insufficient to meet projected future demands. This paper is a case study of how the ATLAS experiment has embraced Titan---a DOE leadership facility in conjunction with traditional distributed high- throughput computing to reach sustained production scales of approximately 52M core-hours a years. The three main contributions of this paper are: (i) a critical evaluation of design and operational considerations to support the sustained, scalable and production usage of Titan; (ii) a preliminary characterization of a next generation executor for PanDA to support new workloads and advanced execution modes; and (iii) early lessons for how current and future experimental and observational systems can be integrated with production supercomputers and other platforms in a general and extensible manner.

cs.DC↗

arXiv2017

Toward Common Components for Open Workflow Systems

The role of scalable high-performance workflows and flexible workflow management systems that can support multiple simulations will continue to increase in importance. For example, with the end of Dennard scaling, there is a need to substitute a single long running simulation with multiple repeats of shorter simulations, or concurrent replicas. Further, many scientific problems involve ensembles of simulations in order to solve a higher-level problem or produce statistically meaningful results. However most supercomputing software development and performance enhancements have focused on optimizing single- simulation performance. On the other hand, there is a strong inconsistency in the definition and practice of workflows and workflow management systems. This inconsistency often centers around the difference between several different types of workflows, including modeling and simulation, grid, uncertainty quantification, and purely conceptual workflows. This work explores this phenomenon by examining the different types of workflows and workflow management systems, reviewing the perspective of a large supercomputing facility, examining the common features and problems of workflow management systems, and finally presenting a proposed solution based on the concept of common building blocks. The implications of the continuing proliferation of workflow management systems and the lack of interoperability between these systems are discussed from a practical perspective. In doing so, we have begun an investigation of the design and implementation of open workflow systems for supercomputers based upon common components.

cs.SE↗