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 Annual Meeting 24 – 27 September 2017
George R. Brown Convention Center Houston.

Society of High Performance Computing Professionals Focus Group and Presentation Theater at Booth #100

Geophysics has been associated with computing technology from its inception. High Performance Computing (HPC) consistently provides challenges and opportunities to enhance hardware, software and infrastructure solutions to match the performance and quality of the industry’s algorithms, data consumption and exploration advances.


The geophysical industry constantly increases the demands placed on HPC suppliers to process more data faster than ever before.

Considering the SEG’s interest in and need for HPC, the SEG and The Society of HPC Professionals (SHPCP) have brought together a group of HPC organizations to exhibit in a common area of the Exhibit Hall and make technical presentations. This theater will showcase two state-of-the-art 84” LCD panel systems provided by Prysm. 


Several SHPCP (www.hpcsociety.org) are regular exhibitors at the SEG Annual Meetings; however, the theater will also include participants that are first-time SEG Exhibitors and will feature new industry technology. Sponsors of this area will deliver presentations in the theater with daily programs. 


The following organizations will be participating in the HPC Focused Group: Acceleware, Altair, Avere Systems, Cray, DDN, HGST, IBM, Intel, Micron, NetApp, PCPC Direct, Penguin Computing, Prysm, Unique Digital, Seagate, VCE, and Verrex. Please refer to the Exhibit Hall Panel layout in the show program guide to find location of the HPC Theater at Booth #TBD.

PRESENTATIONS

SCHEDULE

Monday, September 25th  

9:30 AM

Nvidia

Power and Results: Using NVIDIA  
Jason Knudsen


10:30 AM
HGST
Object and Cloud Storage Basics
Shawn Stephens - Systems Engineer


11:30 AM
Tegile Systems
TBD
Kent Kallmeyer


2:00 PM
Cray
Machine Learning for Scientific Data 
Geert Wenest


3:00 PM
Lenovo/Nvidia
System Design for Artificial Intelligence and HPC. Are they the same?
Matthew Ziegler - HPC Strategy and Architecture, Lenovo DCG


4:00 PM
Prairie View A&M
Deep Learning on a GPU-enabled Cloud for Seismic Interpretation
Lei Hung Ph. D., Assistant Professor


Tuesday, September 26th 

9:30 AM

Barcelona Supercomputing

Reduced order techniques to accelerate HPC computations in geophysic
David Modesto, PhD - Postdoc researcher, BSC


10:30 AM
Cray
Machine Learning for Scientific Data -Geert Wenes
Geert Wenests


11:30 AM

Lenovo/Nvidia
System Design for Artificial Intelligence and HPC. Are they the same?
Matthew Ziegler- HPC Strategy and Architecture, Lenovo DCG


1:00 PM

HGST
Object and Cloud Storage Basics
Shawn Stephens


2:00 PM

Lenovo/Nvidia

NVIDIA Virtual GPU Solutions

Osama Qazi


3:00 PM
Prairie View A&M
Deep Learning on a GPU-enabled Cloud for Seismic Interpretation
Lei Hung Ph. D., Assistant Professor


4:00 PM
Cray
Exploration seismology and the return of the Supercomputer Exploring scalability for speed in development and delivery
Sverre Brandsberg-Dahl

Wednesday, September 27th 

9:30 AM

Cray
Machine Learning for Scientific Data 
Geert Wenes


10:30 AM

Prairie View A&M
Deep Learning on a GPU-enabled Cloud for Seismic Interpretation
Lei Hung Ph. D., Assistant Professor


11:30 AM

Lenovo/Nvidia

NVIDIA Virtual GPU Solutions

Osama Qazi


1:00 PM

Sandbox


ABSTRACTS


Monday, September 25th
9:30 AM

Nvidia

Power and Results: Using NVIDIA  
Jason Knudsen


Abstract: In this overview of NVIDIA’s latest technological advance, the DGX-1, you will understand the underlying architecture, software stack, and tools that allow you to focus on your science, not IT. See examples of resulting AI that could lead to benefit in the oilfield. This combination of technology and optimized software will not only demonstrate amazing performance, but also promises astonishing AI results.


Presenter’s Bio: Jason Knudsen is a career technologist in oil and gas with many roles over the years in business development and partnerships. He brings over 20 years of experience with companies like Intel, IBM, EMC, and Cisco. He has always focused on leading edge solution development in the oil patch. Jason is very excited to be with NVIDIA helping to drive industry change from standard IT and traditional software to Advance IT and Artificial Intelligence.





Monday, September 25th
10:30 AM

HGST
Object and Cloud Storage Basics
Shawn Stephens - Systems Engineer


Abstract: Data is the new natural resource. Storing your company’s data has never been more important. Many enterprises are exploring the cloud to help them with storing data, but many don’t have a complete understanding of its capabilities or costs. We’ll discuss use cases for cloud storage and on-premises cloud solutions. We will also discuss what object storage is and the data-protection schemes it uses in very large deployments. We’ll compare object storage to more traditional filesystems and the limitations and capabilities of each. If you or your company is looking at cloud storage, this presentation will educate you on its use cases and the advantages of various deployment options.


Presenter’s Bio: Shawn Stephens has been with HGST for 3 years in their enterprise sales team. He has supported customers with flash storage, dense storage and object storage solutions. He has worked in the oil & gas industry for over 20 years, mostly focused on storage and computing for seismic processing.





Monday, September 25th
3:00 PM

Lenovo/Nvidia
System Design for Artificial Intelligence and HPC. Are they the same?
Matthew Ziegler - HPC Strategy and Architecture, Lenovo DCG


Abstract: In this session, we will examine how the emergence of artificial intelligence (AI) is driving system design in new directions. Prior to the early 2000’s, system design was relatively straight forward as the HPC community as a whole started adopting 2-socket x86-based servers. Distributed computing and scale-out architectures have dominated since that time frame but with the emergence of AI, the varying deep computational needs is driving adoption of novel computing technologies and techniques. Whereas the market for computing resources has become extremely commoditized over the past decade, specialization is making a comeback. The emergence of accelerators and FPGAs are exploding and becoming mainstream.

Come listen to this session to see how system design can influence the speed and price-performance of a computing resource. Is my HPC resource ideal for my AI workloads? You’ll learn why not all systems are designed equally.


Presenter’s Bio: Matthew received his Bachelor of Arts in Molecular, Cellular and Developmental Biology from the University of Colorado, Boulder and went on to work in and publish leading research in plant genetics. Matthew then switched his energies to learning how to design and architect x86 clustered systems for use in genomics and bioinformatics.. After joining IBM, his work with life science companies continued and soon propelled Matthew onto the North America Advanced Technical Support team where he broadened his scope of HPC designs into other sectors such as Oil and Gas, Digital Media, Weather/Atmospheric Sciences and General Research. In his current role as Director of HPC at Lenovo, he has continued to promote and drive innovation in this field as well as to continue with his roles as an architect and as a mentor to the wider Lenovo community.





Monday, September 25th
4:00 PM

Prairie View A&M
Deep Learning on a GPU-enabled Cloud for Seismic Interpretation
Lei Hung Ph. D., Assistant Professor


Abstract:  The Cloud Computing Research Lab at Prairie View A&M University has been working on developing a scalable deep-learning enabled cloud platform for petroleum data analytics to facilitate a variety of interpretation scenarios. The recognition of 3D complex geological features in noisy seismic datasets is a daunting challenge in pattern recognition. This talk will present our experience of building a deep-learning enabled seismic data analytics platform on top of Apache Hadoop, Spark and Google TensorFlow to support seismic interpretation work. The talk will demonstrate our experimental results of applying the deep learning technology on geological fault detection with real seismic volumes.

Moreover, the talk will also present the components of the deep-learning enabled big data analytics platform that manages/analyzes/visualizes large petroleum datasets that are distributed in the Hadoop and Spark environment. It will cover the deep learning performance on the cloud platform accelerated by Nvidia GPUs. The work is sponsored by National Science Foundation (NSF).


Presenter’s Bio: Dr. Lei Huang is an Associate Professor in the Department of Computer Science, Prairie View A&M University (PVAMU), where he is leading research at the Cloud Computing Research Lab. He also serves as the Associate Director of Research in the Center of Excellence in Research and Education for Big Military Data Intelligence at PVAMU sponsored by Department of Defense (DoD). He currently manages several active research projects sponsored by NSF and DoD in Big Data Analytics, Cloud Computing, and High Performance Computing areas. He joined the university in 2011 with previous research experience at the University of Houston, and working experience in seismic interpretation software development. Huang has earned his Ph.D. from the Computer Science department at the University of Houston in 2006.






Tuesday, September 26th

9:30 AM

Barcelona Supercomputing

Reduced order techniques to accelerate HPC computations in geophysic
David Modesto, PhD - Postdoc researcher, BSC


Abstract: Geophysical problems often rely on large amounts of forward modeling realizations to explore the impact of parameter uncertainty in our data (e.g.\ sensitivity studies) or to solve inverse problems. The standard approach is carrying out one realization per member of the parameter set (i.e.\ per source location, per frequency, per perturbation value). Although contemporary compute resources can partly mitigate the cost of exhaustive parameter exploration, each new parameter results in an additional dimension to be considered and costs grow exponentially.

This talk explores the possibility of using reduced order methods (ROM) to circumvent this issue. Particularly, a posteriori and a priori ROM approaches are reviewed, as well as a study of their HPC capabilities. ROMs are used to obtain a low-order representation of the geophysical model that includes variability in all the parameters of interest. This knowledge allows an immediate evaluation of any desired forward modeling, including the corresponding sensitivities, with no need of solving any new problem. This can potentially accelerate those applications requiring numerous repetitive realizations for different parameter values. Here, the possibilities of this methodology are explored for isotropic 2D acoustics and 3D controlled source electromagnetic models.

Presenter’s Bio: Dr. Modesto is a postdoc researcher at Barcelona Supercomputing Center (BSC), where he is carrying out the principal research line on reduced order models for geophysical applications supported by several Repsol projects. Dr. Modesto holds a PhD on applied mathematics, MS on numerical methods and BS on geological engineering from Polytechnic University of Catalonia (Barcelona). He works on the development, analysis and application of new numerical techniques in the framework of reduced order models and high-order finite element methods.






Tuesday, September 26th
11:30 AM

Lenovo/Nvidia
System Design for Artificial Intelligence and HPC. Are they the same?
Matthew Ziegler - HPC Strategy and Architecture, Lenovo DCG


Abstract: In this session, we will examine how the emergence of artificial intelligence (AI) is driving system design in new directions. Prior to the early 2000’s, system design was relatively straight forward as the HPC community as a whole started adopting 2-socket x86-based servers. Distributed computing and scale-out architectures have dominated since that time frame but with the emergence of AI, the varying deep computational needs is driving adoption of novel computing technologies and techniques. Whereas the market for computing resources has become extremely commoditized over the past decade, specialization is making a comeback. The emergence of accelerators and FPGAs are exploding and becoming mainstream.

Come listen to this session to see how system design can influence the speed and price-performance of a computing resource. Is my HPC resource ideal for my AI workloads? You’ll learn why not all systems are designed equally.


Presenter’s Bio: Matthew received his Bachelor of Arts in Molecular, Cellular and Developmental Biology from the University of Colorado, Boulder and went on to work in and publish leading research in plant genetics. Matthew then switched his energies to learning how to design and architect x86 clustered systems for use in genomics and bioinformatics.. After joining IBM, his work with life science companies continued and soon propelled Matthew onto the North America Advanced Technical Support team where he broadened his scope of HPC designs into other sectors such as Oil and Gas, Digital Media, Weather/Atmospheric Sciences and General Research. In his current role as Director of HPC at Lenovo, he has continued to promote and drive innovation in this field as well as to continue with his roles as an architect and as a mentor to the wider Lenovo community.





Tuesday, September 26th
1:00 PM

HGST
Object and Cloud Storage Basics
Shawn Stephens - Systems Engineer


Abstract: Data is the new natural resource. Storing your company’s data has never been more important. Many enterprises are exploring the cloud to help them with storing data, but many don’t have a complete understanding of its capabilities or costs. We’ll discuss use cases for cloud storage and on-premises cloud solutions. We will also discuss what object storage is and the data-protection schemes it uses in very large deployments. We’ll compare object storage to more traditional filesystems and the limitations and capabilities of each. If you or your company is looking at cloud storage, this presentation will educate you on its use cases and the advantages of various deployment options.


Presenter’s Bio: Shawn Stephens has been with HGST for 3 years in their enterprise sales team. He has supported customers with flash storage, dense storage and object storage solutions. He has worked in the oil & gas industry for over 20 years, mostly focused on storage and computing for seismic processing.




Tuesday, September 26th
2:00 PM

Lenovo/Nvidia
NVIDIA Virtual GPU Solutions
Osama Qazi, Solutions Architect 


Abstract: NVIDIA makes systems that are used by the most demanding users in the world — gamers, designers, and scientists.   Quadro Virtual Data Center Workstation software turns tesla GPU servers into powerful multi-user workstations


Presenter’s Bio: Osama is a solutions architect for NVIDIA supporting the Energy Sector in HPC, AI/Deep learning and Accelerated Graphics. Osama is based out of Houston Texas and has been with NVIDIA for 6 months. Prior to NVIDIA, Osama has worked in the Energy sector for 10+ years as an expert in Data and storage management.



Tuesday, September 26th
3:00 PM

Prairie View A&M
Deep Learning on a GPU-enabled Cloud for Seismic Interpretation
Lei Hung Ph. D., Assistant Professor


Abstract:  The Cloud Computing Research Lab at Prairie View A&M University has been working on developing a scalable deep-learning enabled cloud platform for petroleum data analytics to facilitate a variety of interpretation scenarios. The recognition of 3D complex geological features in noisy seismic datasets is a daunting challenge in pattern recognition. This talk will present our experience of building a deep-learning enabled seismic data analytics platform on top of Apache Hadoop, Spark and Google TensorFlow to support seismic interpretation work. The talk will demonstrate our experimental results of applying the deep learning technology on geological fault detection with real seismic volumes.

Moreover, the talk will also present the components of the deep-learning enabled big data analytics platform that manages/analyzes/visualizes large petroleum datasets that are distributed in the Hadoop and Spark environment. It will cover the deep learning performance on the cloud platform accelerated by Nvidia GPUs. The work is sponsored by National Science Foundation (NSF).


Presenter’s Bio: Dr. Lei Huang is an Associate Professor in the Department of Computer Science, Prairie View A&M University (PVAMU), where he is leading research at the Cloud Computing Research Lab. He also serves as the Associate Director of Research in the Center of Excellence in Research and Education for Big Military Data Intelligence at PVAMU sponsored by Department of Defense (DoD). He currently manages several active research projects sponsored by NSF and DoD in Big Data Analytics, Cloud Computing, and High Performance Computing areas. He joined the university in 2011 with previous research experience at the University of Houston, and working experience in seismic interpretation software development. Huang has earned his Ph.D. from the Computer Science department at the University of Houston in 2006.






Wednesday, September 27th
10:30 AM

Prairie View A&M
Deep Learning on a GPU-enabled Cloud for Seismic Interpretation
Lei Hung Ph. D., Assistant Professor


Abstract:  The Cloud Computing Research Lab at Prairie View A&M University has been working on developing a scalable deep-learning enabled cloud platform for petroleum data analytics to facilitate a variety of interpretation scenarios. The recognition of 3D complex geological features in noisy seismic datasets is a daunting challenge in pattern recognition. This talk will present our experience of building a deep-learning enabled seismic data analytics platform on top of Apache Hadoop, Spark and Google TensorFlow to support seismic interpretation work. The talk will demonstrate our experimental results of applying the deep learning technology on geological fault detection with real seismic volumes.

Moreover, the talk will also present the components of the deep-learning enabled big data analytics platform that manages/analyzes/visualizes large petroleum datasets that are distributed in the Hadoop and Spark environment. It will cover the deep learning performance on the cloud platform accelerated by Nvidia GPUs. The work is sponsored by National Science Foundation (NSF).


Presenter’s Bio: Dr. Lei Huang is an Associate Professor in the Department of Computer Science, Prairie View A&M University (PVAMU), where he is leading research at the Cloud Computing Research Lab. He also serves as the Associate Director of Research in the Center of Excellence in Research and Education for Big Military Data Intelligence at PVAMU sponsored by Department of Defense (DoD). He currently manages several active research projects sponsored by NSF and DoD in Big Data Analytics, Cloud Computing, and High Performance Computing areas. He joined the university in 2011 with previous research experience at the University of Houston, and working experience in seismic interpretation software development. Huang has earned his Ph.D. from the Computer Science department at the University of Houston in 2006.






Wednesday, September 27th
11:30 AM

Lenovo/Nvidia
NVIDIA Virtual GPU Solutions
Osama Qazi, Solutions Architect 


Abstract: NVIDIA makes systems that are used by the most demanding users in the world — gamers, designers, and scientists.   Quadro Virtual Data Center Workstation software turns tesla GPU servers into powerful multi-user workstations


Presenter’s Bio: Osama is a solutions architect for NVIDIA supporting the Energy Sector in HPC, AI/Deep learning and Accelerated Graphics. Osama is based out of Houston Texas and has been with NVIDIA for 6 months. Prior to NVIDIA, Osama has worked in the Energy sector for 10+ years as an expert in Data and storage management.



Wednesday, September 27th
11:30 AM

Lenovo/Nvidia
NVIDIA Virtual GPU Solutions
Osama Qazi, Solutions Architect 


Abstract: NVIDIA makes systems that are used by the most demanding users in the world — gamers, designers, and scientists.   Quadro Virtual Data Center Workstation software turns tesla GPU servers into powerful multi-user workstations


Presenter’s Bio: Osama is a solutions architect for NVIDIA supporting the Energy Sector in HPC, AI/Deep learning and Accelerated Graphics. Osama is based out of Houston Texas and has been with NVIDIA for 6 months. Prior to NVIDIA, Osama has worked in the Energy sector for 10+ years as an expert in Data and storage management.

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