JOIN SHPCP   |   EVENTS   |  NEWS  |  LOGIN

As a charitable service-based nonprofit organization (NPO) coordinating individuals, businesses, academia and governments with interests in High Technology, Big Data and Cybersecurity, we bridge the global digital divide by providing supercomputing access, applied research, training, tools and other digital incentives “to empower the underserved and disadvantaged.”
SEG 2014 Presentation Theater


Title:  Computational Trade-Offs of Higher Order in Time RTM 

Presenter:   Scott Quiring, Team Lead Software Developer

This presentation examines the computational trade-offs of higher order in time for RTM. It compares the hardware trade-offs for running RTM with 2nd order accurate temporal derivatives and 4th order accurate temporal derivatives. The exact difference in computational complexity depends on the RTM implementation. The timestep using 4th order accuracy can be much longer for the same level of accuracy theoretically leading to an overall savings in computational resources. This analysis is true for the main propagation, however practical RTM is often limited by hard disk speed, available random access memory (RAM), or data transfers between compute nodes in a distributed system. In this presentation we will discuss these additional elements and how they impact performance.  

<< Back to Agenda


Title:  Accelerate Insights – Speed Hydrocarbon Exploration

Presenter:   Paul Anderson, Director of Professional Services

The Energy industry is renowned for investing in the highest end of computing technology to speed time to hydrocarbon discovery. By matching HPC with sophisticated modeling, simulation, and process tools to manage and analyze unprecedented amounts of diverse data, complexity can mount quickly.  Learn how to reduce the complexity and speed hydrocarbon exploration by processing seismic analysis and recovery simulations more rapidly, accurately and cost-effectively. Adaptive Computing will share their experiences with the world's largest oil companies and show you how to unify data center resources by breaking down siloed environments, optimize the analysis process and guarantee services to the business to accelerate insights!

<< Back to Agenda

       




Title:  Leveraging HPC for Deep-Sea Component Engineering

Presenters:  

Rick Watkins, Altair-Business Development Manager-Oil and Gas

Geert Wenes, Cray-Senior Practice Leader in Custom Engineering

In this session, experts from Cray and Altair will discuss a new solution proven to improve speed and performance for oil and gas component engineering -- specifically, design of subsea drilling risers that transport hydrocarbon products from deep-sea wells to surface-level structures. The complexity of the models required for riser simulation has proven challenging, so technology providers like Altair and Cray have advanced their products for scalable and realistic simulations – even full-scale simulation of a riser is now possible, which means operators and engineers responsible for riser system design and analysis can increase component life, reduce uncertainty and improve the overall safety of their ultra-deep-water systems -- all while still meeting their demanding development schedule. In this session, Cray and Altair experts will describe the solution (including Altair's AcuSolve CFD solver running on Cray® XC30™ supercomputer systems powered by Intel® Xeon® processors), present performance benchmark results, and provide recommended configurations for deploying such a solution in smaller and larger environments.

<< Back to Agenda


 

Title:  Simplifying the Management of HPC Application Environments

Presenter:   Victor Wright, Enterprise Computing Solutions Specialist

High-performance computing (HPC) is vital to staying competitive in the oil and gas industry, especially for upstream exploration and development. Exascale-level computing and data analytics requirements are not only being driven by established areas of study such as Seismic Processing and Reservoir Simulation, but by growing disciplines such as Computational Fluid Dynamics and Geomechanics. To maximize user productivity, Oil and Gas companies need HPC resources operating reliably around the clock -- and these systems need to be easy to use, manage, and scale while still being cost-effective. Attend this session to learn how Altair's PBS Works addresses these challenges with the most comprehensive suite of integrated HPC workload management products available. PBS Works simplifies and streamlines the management of HPC resources with powerful policy-based scheduling,  user-friendly portals for job submission and remote visualization, and deep analytics and reporting capabilities. The presentation will include a case study of an HPC Oil and Gas implementation.



<< Back to Agenda


 

Title:  A Recipe for Getting Started with HPC Clusters

Presenter:   Steve Gombosi, Senior Application Engineer

To be provided



<< Back to Agenda


 

Title: Speed Up Reservoir Processing with End-to-End Workload Management

Presenter:  Rick Watkins, Regional Manager

Reservoir simulation has long been proven as a good-fit problem for high-performance computing (HPC). Parallelization via cluster computing has brought the benefits of HPC to a wider number of operators; however, since the level of complexity of the simulation models still tends to exceed the speed and memory of the hardware, reservoir simulation problems benefit from the application of an HPC workload management system to optimize job placement, accelerate processing and simplify the process of job submission and management. In this session, engineers responsible for reservoir simulation (and the IT managers responsible for the hardware that serves this purpose) will learn how to apply HPC workload management products to the challenge of efficient reservoir simulation. The speaker will provide an overview of necessary tools in an HPC workload management suite, from job scheduling to remote visualization, and will give an overview of the steps needed to employ HPC workload management in a reservoir simulation environment.

<< Back to Agenda


Title: Roofline-based Optimization of Elastic Wave Propagation on Xeon Processors for Large-scale Execution

Presenter:  Mauricio Hanzich, Senior Researcher at Barcelona Supercomputing

Full wave elastic propagation is expensive, both computationally and development-wise. Hence, maximizing the efficiency of your propagation code at the minimum development cost is mandatory. For that, a mechanism to evaluate the current efficiency of your application and the maximum attainable is needed. We will show our experience in enhancing elastic wave propagation on Xeon processors by means of a roofline-directed optimization methodology. This will provides the means to evaluate which kind of optimizations to apply and when to stop the optimization process.

<< Back to Agenda





Title: Taking Exploration Geophysics to a Next Level with Big Data 

Presenter:  Dr. Satyam Priyadarshy, Landmark Chief Data Scientist

Big Data is no longer a buzzword. The emerging landscape consisting of technologies, algorithms, products, and solutions for leveraging wide range of disparate data sets large of small, irrespective of the domain. There is high degree of complexity in creating value from the geophysical, seismic, and related data sets. However, these complexities could be alleviated by leveraging the four foundational legs of Big Data. In this presentation, I will discuss some of the key challenges and an approach to resolve those challenges.

<< Back to Agenda


Title:  Technology Trends in Advanced Visualization & Collaboration and the Benefits of Vertical-Focused Integration in Oil & Gas

Presenter:  Maz Zaeefjou, PMP, Sr. Project Development Manager

To be provided




<< Back to Agenda

Title: Full Range RTM in Support of FWI using Dense GPU and HPC System

Presenter:  Bert Beals, Global Lead-Energy Industries

To be provided




<< Back to Agenda

Title:  Accelerating Geophysical Processing to Get Better Results 

Presenter:  Phil Schwan - Head of Software Development

DownUnder GeoSolutions has taken the radical step of porting and optimizing their industry-leading time migration for Intel® Xeon Phi™ coprocessors to deliver massive performance gains over the latest high performance CPUs.  The Xeon Phi's unique design, packaging and development environment provide a compelling platform capable of optimizing performance. Through the use of highly- tuned hand-optimized code, full-volume high-density (1400km^2@12.5x12.5m) time migrations can be performed in just hours on moderate sized clusters (100 nodes).  This quantum shift in processing power fundamentally changes how time migrations are used in the processing flow and is a genuine move towards interactive processing.

<< Back to Agenda


Title:  Methodology for Application & Modernization Applied to Seismic Imaging

Presenter:  Gregg Skinner – Senior Application Engineer

Intel will present a series of tuning steps for an isotropic 3D finite difference seismic reverse time migration kernel. Including parallelization, cache blocking, vectorization and loop distribution.

<< Back to Agenda


Title:  Reverse Time Migration with Heterogeneous Multicore & Manycore Clusters

Presenter:  Leonardo Borges – Software Application Engineer

In this presentation we will share our experiences and results from an implementation of RTM (Reverse Time Migration) that harness the compute power of CPUs and coprocessors cooperatively. We explore a unified programming model and unified communication layer in a hybrid system composed of CPUs and MIC (Many Integrated Cores) coprocessors.

<< Back to Agenda


Title:  Accelerate Exploration Data Access with HGST Flash Storage

Presenters: 

Monday 10/27, 1:00PM  Brian Morris, Oil and Gas Enterprise Account Manager

Tuesday 10/28, 11:30AM  Ed Hinton, VP of Sales

Wednesday 10/29, 11:30AM  Shawn Stephens, Sales Engineer

The evolution of computing hardware has delivered a new era of enhanced exploration productivity. New workflows are now computationally and economically feasible, and old ones can become much more efficient and deliver better results using more or higher-quality data. Just buying the latest hardware, however, rarely delivers the full potential of the latest technology advances. Many systems are designed and configured for generic workloads. Operating systems and file systems need to be tuned for optimal performance of applications. Furthermore, the rapid evolution in computing technologies including more efficient multi-core processors and the application of GP-GPUs has increased the demands on storage.

This presentation will explore the interfaces, integration and configuration of flash storage, and show how SSD's reliability, performance, and data integrity will help to achieve breakthroughs in storage and application performance.

Application use models will demonstrate how SSDs boost:

Seismic acquisition, processing, and interpretation acceleration

Database acceleration

Virtualized server and VDI environments

Attend this presentation to learn how to get the most out of SSDs for Oil and Gas exploration.

<< Back to Agenda


Title:  The Linux Clusters Institute: Promoting HPC Learning

Presenter:  Rich Knepper, co-chair of the Linux Clusters

Workshop

The Linux Clusters Institute provides training for IT professionals new to High Performance Computing.  LCI workshops cover planning, installation and maintenance of Linux clusters, as

well as information about running parallel analyses, supporting scientific users, and models for managing and funding local resources.  LCI plans to offer two workshops in 2015 in order to provide training and networking opportunities to new system administrators.  Rich Knepper, co-chair of the Linux Clusters Workshop, will discuss the LCI's workshop initiatives and offerings for HPC training.

<< Back to Agenda


Title:  Why the Time is Right for High Performance Computing in the Public Cloud

Presenter:  Leo Reiter, Chief Technology Officer

The public cloud is quickly becoming the fastest and easiest way to increase computational and storage capacity for your most demanding projects.  It's not without challenges, however.  In this presentation, we'll be looking at why it's time to take a serious look at the public cloud for your toughest compute challenges, and how innovation in technology and delivery models are taking quality of service to previously unimagined levels.


We'll also discuss how a new wave of on demand high performance compute services are tackling data movement, data security, and performance issues – all the barriers that previously eliminated public cloud services from consideration.  Finally, we'll discover best practices to get the most out of your public cloud compute experience, as well as what you should be asking of (and expecting from) your vendors and partners in this space.

<< Back to Agenda


Title:  The Best of Both Worlds for Oil & Gas IT Environments: x86 Cloud Economics with Enterprise Capabilities

Presenters: 

Monday 10/27, 2PM   Marty Sanders, VP Americas Sales

Tuesday 10/28,9AM  Dan Pearl, Product Marketing

Wednesday 10/29,10AM  Dan Pearl, Product Marketing

SimpliVity provides the best of both worlds for Oil & Gas IT environments, offering x86 cloud economics and enterprise capabilities for critical applications. SimpliVity will discuss a customer case study for how we provide unique solutions for remote sites, including off-site rigs and FPSOs.



<< Back to Agenda


Title:  High Performance Computing technology trends and directions

Presenter:  Eric Collins, Chief Architect

Over the last year, we have distilled our observations from discussions with customers, manufacturers, consultants and more into a summary of what is the current state of the art in High Performance Computing (HPC) HPC as well as near term trends and directions to watch. If you work with HPC, but not every day, this technical talk will give a solid overview of what is going on in the HPC world, and what trends are shaping it. We will cover:

·         Processors (ARM,

·         Offload processors (Nvidia GPU, Xeon Phi, TI)

·         Memory

·         Disk Technology

·         Interconnects – Infiniband 

·         "Cloud"

<< Back to Agenda


Title:  High Performance Storage Solution for Landmark SeisSpace

Presenter:  Chuck Smith, O&G Solutions Architect

To be provided

<< Back to Agenda


Title:  Introduction to Rescale: Cloud Simulation Platform

Presenter:  Joris Poort, CEO

Rescale's cloud simulation platform overview will be presented including a live demonstration of a reservoir simulator running on the platform.

Rescale provides a secure, cloud-based, high performance computing platform that allows engineers and scientists to run their compute-intensive simulations with improved performance and decreased runtime. The platform allows users to quickly build, compute, and analyze large simulations on demand. Rescale partners with industry-leading software vendors to provide instant access to a variety of simulation packages while simultaneously offering customizable HPC hardware. Headquartered in San Francisco, CA, Rescale's customers include global Fortune 500 companies in the aerospace, automotive, life sciences, and energy sectors.

<< Back to Agenda


Title:  To be provided

Presenter:  To be provided

To be provided

<< Back to Agenda


Title:  To be provided

Presenter:  Laura Shepard, Director of HPC & Life Sciences Marketing

To be provided

<< Back to Agenda


Title:  High Performance Resource Scheduling

Presenter: Melinda McDade

To be provided


<< Back to Agenda


Title:   Fast Data Transfers

Presenter:  Kip Schauer
VP of Sales

To be provided

Contact Us

Society for HPC Professionals
10690 Shadow Wood Dr, Ste 132 Houston, TX 77043-2840

info@hpcsociety.org
Copyright © 2016 Society of HPC Professionals