Search

The term “in situ processing” has evolved over the last decade to mean both a specific strategy for visualizing and analyzing data and an umbrella term for a processing paradigm. The resulting confusion makes it difficult for visualization and analysis scientists to communicate with each other and with their stakeholders. To address this problem, a group of over 50 experts convened with the goal of standardizing terminology. This paper summarizes their findings and proposes a new terminology for describing in situ systems. An important finding from this group was that in situ systems are best described via multiple, distinct axes: integration type, proximity, access, division of execution, operation controls, and output type. This paper discusses these axes, evaluates existing systems within the axes, and explores how currently used terms relate to the axes.

With the anticipation of exascale architectures, energy consumption is becoming one of the critical design parameters, especially in light of the energy budget of 20–30 Megawatts set by the U.S. Department of Energy. Understanding an application’s execution pattern and its energy footprint is critical to improving application operation on a diverse heterogeneous architecture. Applying application-specific performance optimization can consequently improve energy consumption. However, this approach is only applicable to current systems. As we enter a new era of exascale architectures that is projected to contain more complex memory hierarchies, increased levels of parallelism, heterogeneity in hardware, and complex programming models and techniques, energy and performance management is getting more cumbersome. We therefore propose techniques that predict the energy consumption beforehand or at runtime to enable proactive tuning. Such energy prediction approaches must be generic and adapt themselves at runtime to changing application and hardware configurations. Most existing energy estimation and prediction approaches are empirical in nature and thus tied to current systems. To overcome this limitation, we propose two energy estimation techniques: ACEE (Algorithmic and Categorical Energy Estimation), which uses a combination of analytical and empirical modeling techniques; and AEEM (Aspen’s Embedded Energy Estimation), a system-level analytical energy estimation technique. Both of these models incorporate the Aspen domain specific language for performance modeling. We present the methodologies of these two models and test their accuracy using five proxy applications. We also describe three use cases.

Computational science is well established as the third pillar of scientific discovery and is on par with experimentation and theory. However, as we move closer toward the ability to execute exascale calculations and process the ensuing extreme-scale amounts of data produced by both experiments and computations alike, the complexity of managing the compute and data analysis tasks has grown beyond the capabilities of domain scientists. Thus, workflow management systems are absolutely necessary to ensure current and future scientific discoveries. A key research question for these workflow management systems concerns the performance optimization of complex calculation and data analysis tasks. The central contribution of this article is a description of the PANORAMA approach for modeling and diagnosing the run-time performance of complex scientific workflows. This approach integrates extreme-scale systems testbed experimentation, structured analytical modeling, and parallel systems simulation into a comprehensive workflow framework called Pegasus for understanding and improving the overall performance of complex scientific workflows.

Performance modeling of extreme-scale applications on accurate representations of potential architectures is critical for designing next generation supercomputing systems because it is impractical to construct prototype systems at scale with new network hardware in order to explore designs and policies. However, these simulations often rely on static application traces that can be difficult to work with because of their size and lack of flexibility to extend or scale up without rerunning the original application. To address this problem, we have created a new technique for generating scalable, flexible workloads from real applications, we have implemented a prototype, called Durango, that combines a proven analytical performance modeling language, Aspen, with the massively parallel HPC network modeling capabilities of the CODES framework. Our models are compact, parameterized and representative of real applications with computation events. They are not resource intensive to create and are portable across simulator environments. We demonstrate the utility of Durango by simulating the LULESH application in the CODES simulation environment on several topologies and show that Durango is practical to use for simulation without loss of fidelity, as quantified by simulation metrics. During our validation of Durango's generated communication model of LULESH, we found that the original LULESH miniapp code had a latent bug where the MPI_Waitall operation was used incorrectly. This finding underscores the potential need for a tool such as Durango, beyond its benefits for flexible workload generation and modeling. Additionally, we demonstrate the efficacy of Durango's direct integration approach, which links Aspen into CODES as part of the running network simulation model. Here, Aspen generates the application-level computation timing events, which in turn drive the start of a network communication phase. Results show that Durango's performance scales well when executing both torus and dragonfly network models on up to 4K Blue Gene/Q nodes using 32K MPI ranks, Durango also avoids the overheads and complexities associated with extreme-scale trace files.

As the visualization research community reorients its software to address up-coming challenges, it must successfully deal with diverse processor architectures, distributed systems, various data sources, massive parallelism, multiple input and output devices, and interactivity.

One of the most critical challenges for high-performance computing (HPC) scientific visualization is execution on massively threaded processors. Of the many fundamental changes we are seeing in HPC systems, one of the most profound is a reliance on new processor types optimized for execution bandwidth over latency hiding. Our current production scientific visualization software is not designed for these new types of architectures. To address this issue, the VTK-m framework serves as a container for algorithms, provides flexible data representation, and simplifies the design of visualization algorithms on new and future computer architecture.

This article considers trends in heterogeneous system design, particularly for GPUs. Using the Keeneland Initial Delivery System, the authors examine the performance implications of increased parallelism and specialized hardware on parallel scientific applications. They examine how nonuniform data-transfer performance across the node-level topology can impact performance. Finally, they help users of GPU-based systems avoid performance problems related to this nonuniformity.

Reconstructing boundaries along material interfaces from volume fractions is a difficult problem, especially because the under-resolved nature of the input data allows for many correct interpretations. Worse, algorithms widely accepted as appropriate for simulation are inappropriate for visualization. In this paper, we describe a new algorithm that is specifically intended for reconstructing material interfaces for visualization and analysis requirements. The algorithm performs well with respect to memory footprint and execution time, has desirable properties in various accuracy metrics, and also produces smooth surfaces with few artifacts, even when faced with more than two materials per cell.

The Scalable HeterOgeneous Computing (SHOC) benchmark suite was released in 2010 as a tool to evaluate the stability and performance of emerging heterogeneous architectures and to compare different programming models for compute devices used in those architectures. Since then, high-performance computing (HPC) system architectures have increasingly incorporated both discrete and fused multi-core and many-core processors. The TOP500 list illustrates this trend: heterogeneous systems grew from a 3.4% to 18.0% share of the list between June 2010 and June 2015. Not only are there more heterogeneous systems on the TOP500 list today, those machines are responsible for a disproportionately large percentage of list's aggregate performance: as of June 2015, the performance share for heterogeneous systems has grown to 33.7%.Part of this shift toward heterogeneous architectures has stemmed from new products in the hardware accelerator market, such as Intel's Xeon Phi coprocessor, and improvements in the approaches for programming such accelerators. Existing approaches such as CUDA and OpenCL have become more powerful and easy to use, and directive-based programming models such as OpenACC, OpenMP 4.0, and Intel's Language Extensions for Offload (LEO) are rapidly gaining user acceptance. The benefits of these hardware and software advances are not limited to HPC; other problem domains such as "big data" are reaping the rewards also.The original SHOC benchmarks had adequate support for CUDA and OpenCL for graphics processing units, but did not support more recent programming models and devices. We extended SHOC to support evaluation of recent heterogeneous architectures and programming models such as OpenACC and LEO, and we added new benchmarks to increase SHOC's application domain coverage. In this paper, we describe our modifications to the stock SHOC distribution and present several examples of using our augmented version of SHOC for evaluation of recent heterogeneous architectures and programming models.

A concise description of an application's communication pattern is often useful, for example, as an efficient way to communicate application behavior to a system vendor. Several existing performance analysis tools can capture aspects of an application's communication behavior such as which processes communicated with which others and the communications operations they used. However, a human with a high degree of expertise is still required to recognize and characterize common communication idioms within the performance data collected by those tools. To simplify this characterization for non-experts, we have developed an approach for automatically characterizing a MPI application's communication behavior. We use the mpiP profiling tool to collect information about an application's communication topology and message volume. We then use a post-mortem search-based analysis to compare the application's observed communication pattern against a library of common communication patterns. By comparing the result of the various search paths, our approach identifies the combination of patterns that best matches the observed behavior. To evaluate our approach, we applied it to a synthetic example communication matrix and communication matrices obtained from two scientific applications. We determined that our automated approach was highly effective in characterizing the communication patterns represented in the matrices.

The XVis project brings together the key elements of research to enable scientific discovery at extreme scale. Scientific computing will no longer be purely about how fast computations can be performed. Energy constraints, processor changes, and I/O limitations necessitate significant changes in both the software applications used in scientific computation and the ways in which scientists use them. Components for modeling, simulation, analysis, and visualization must work together in a computational ecosystem, rather than working independently as they have in the past. This project provides the necessary research and infrastructure for scientific discovery in this new computational ecosystem by addressing four interlocking challenges: emerging processor technology, in situ integration, usability, and proxy analysis.

Characterizing the behavior of a scientific application and its associated proxy application is essential for determining whether the proxy application actually does mimic the full application. To support our ongoing characterization activities, we have developed the Oxbow toolkit and an associated data store infrastructure for collecting, storing, and querying this characterization information. This paper presents recent updates to the Oxbow toolkit and introduces the Oxbow project's Performance Analytics Data Store (PADS). To demonstrate the possible insights when using the toolkit and data store, we compare the characterizations of several full and proxy applications, along with the High Performance Linpack (HPL) and High Performance Conjugate Gradient (HPCG) benchmarks. Using techniques such as cluster visualizations of PADS data across many experiments, we found that the results show unexpected similarities and differences between proxy applications, and a greater similarity of proxy applications to HPCG than to HPL along many dimensions.

Knowledge discovery from large and complex scientific data is a challenging task. With the ability to measure and simulate more processes at increasingly finer spatial and temporal scales, the growing number of data dimensions and data objects presents tremendous challenges for effective data analysis and data exploration methods and tools. The combination and close integration of methods from scientific visualization, information visualization, automated data analysis, and other enabling technologies—such as efficient data management—supports knowledge discovery from multi-dimensional scientific data. This paper surveys two distinct applications in developmental biology and accelerator physics, illustrating the effectiveness of the described approach.

This paper surveys the four software frameworks being developed as part of the visualization pillar of the SDAV (Scalable Data Management, Analysis, and Visualization) Institute, one of the SciDAC (Scientific Discovery through Advanced Computing) Institutes established by the ASCR (Advanced Scientific Computing Research) Program of the U.S. Department of Energy. These frameworks include EAVL (Extreme-scale Analysis and Visualization Library), DAX (Data Analysis at Extreme), DIY (Do It Yourself), and PISTON. The objective of these frameworks is to facilitate the adaptation of visualization and analysis algorithms to take advantage of the available parallelism in emerging multi-core and many-core hardware architectures, in anticipation of the need for such algorithms to be run in-situ with LCF (leadership-class facilities) simulation codes on supercomputers.

We present a novel extraction scheme for crack-free isosurfaces from adaptive mesh refinement (AMR) data that builds on prior work utilizing dual grids and filling resulting gaps with stitch cells. We use a case-table-based approach to simplify the implementation of stitch cell generation. The most significant benefit of our new approach is that it uses ghost data to handle parallel isosurface extraction efficiently. We further present the results of applying this method to large scale data sets and analyze its computation time on parallel high-performance computing (HPC) platforms.

This paper accompanies a poster that is being presented at the SciDAC 2006 meeting in Denver, CO. This project focuses on leveraging scientific visualization and analytics software technology as an enabling technology for increasing scientific productivity and insight. Advances incomputational technology have resulted in an "information big bang," which in turn has createda significant data understanding challenge. This challenge is widely acknowledged to be one of the primary bottlenecks in contemporary science. The vision for our Center is to respond directly to that challenge by adapting, extending, creating when necessary and deploying visualization and data understanding technologies for our science stakeholders. Using an organizational model as a Visualization and Analytics Center for Enabling Technologies (VACET), we are well positioned to be responsive to the needs of a diverse set of scientific stakeholders in a coordinated fashion using a range of visualization, mathematics, statistics, computer and computational science and data management technologies.

Adaptive Mesh Refinement (AMR) is a highly effectivesimulation method for spanning a large range of spatiotemporal scales,such as astrophysical simulations that must accommodate ranges frominterstellar to sub-planetary. Most mainstream visualization tools stilllack support for AMR as a first class data type and AMR code teams usecustom built applications for AMR visualization. The Department ofEnergy's (DOE's) Science Discovery through Advanced Computing (SciDAC)Visualization and Analytics Center for Enabling Technologies (VACET) isextending and deploying VisIt, an open source visualization tool thataccommodates AMR as a first-class data type, for use asproduction-quality, parallel-capable AMR visual data analysisinfrastructure. This effort will help science teams that use AMR-basedsimulations and who develop their own AMR visual data analysis softwareto realize cost and labor savings.

The SciDAC2 Visualization and Analytics Center for Enabling Technologies (VACET) began operation on 10/1/2006. This document, dated 11/27/2006, is the first version of the VACET project management plan. It was requested by and delivered to ASCR/DOE. It outlines the Center's accomplishments in the first six weeks of operation along with broad objectives for the upcoming future (12-24 months).

VisIt is a richly featured visualization tool that is used to visualize some of the largest simulations ever run. The scale of these simulations requires that optimizations are incorporated into every operation VisIt performs. But the set of applicable optimizations that VisIt can perform is dependent on the types of operations being done. Complicating the issue, VisIt has a plugin capability that allows new, unforeseen components to be added, making it even harder to determine which optimizations can be applied. We introduce the concept of a contract to the standard data flow network design. This contract enables each component of the data flow network to modify the set of optimizations used. In addition, the contract allows for new components to be accommodated gracefully within VisIt's data flow network system.

We present techniques for multiresolution approximation and hardware-assisted splat based rendering to achieve interactive volume visualization of large irregular data sets. We examine two methods of generating multiple resolutions of irregular volumetric grids and a data structure supporting the splatting approach for volume rendering. These techniques are implemented in combination with a view-dependent error based resolution selection to maintain accuracy at both low and high zoom levels. In addition, the error tolerance may be adjusted at run time to obtain the desired balance between high frame rates and accurate rendering. Along with an effective way to compute gradients for lighting, we offer an integrated solution for interactive volume rendering of irregular-mesh or meshless data, and we demonstrate our technique on unstructured-grid data sets from aerodynamic flow simulations.

The DCA++ code was one of the early science applications that ran on jaguar at the National Center for Computational Sciences, and the first application code to sustain a petaflop/s under production conditions on a general-purpose supercomputer. The code implements a quantum cluster method with a Quantum Monte Carlo kernel to solve the 2D Hubbard model for high-temperature superconductivity. It is implemented in C++, making heavy use of the generic programming model. In this paper, we discuss how this code was developed, reaching scalability and high efficiency on the world's fastest supercomputer in only a few years. We show how the use of generic concepts combined with systematic refactoring of codes is a better strategy for computational sciences than a comprehensive upfront design.

One of the central challenges facing visualization research is how to effectively enable knowledge discovery. An effective approach will likely combine application architectures that are capable of running on today's largest platforms to address the challenges posed by large data with visual data analysis techniques that help find, represent, and effectively convey scientifically interesting features and phenomena.

As scientific instruments and computer simulations produce more and more data, the task of locating the essential information to gain insight becomes increasingly difficult. FastBit is an efficient software tool to address this challenge. In this article, we present a summary of the key underlying technologies, namely bitmap compression, encoding, and binning. Together these techniques enable FastBit to answer structured (SQL) queries orders of magnitude faster than popular database systems. To illustrate how FastBit is used in applications, we present three examples involving a high-energy physics experiment, a combustion simulation, and an accelerator simulation. In each case, FastBit significantly reduces the response time and enables interactive exploration on terabytes of data.