Loading…
This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
View analytic
Thursday, February 28
 

7:00am

Registration & Networking with continental breakfast

Name badge pickup, continental breakfast & networking


Thursday February 28, 2013 7:00am - 8:15am
Martel Hall Duncan Hall

8:15am

Opening and Welcome: George McLendon, Provost, Rice University

 

Watch the video

 

 


Moderator(s)
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
avatar for George McLendon

George McLendon

Provost, Rice University


Thursday February 28, 2013 8:15am - 8:30am
McMurtry Auditorium Duncan Hall

8:30am

Keynote: "Compute Challenges to meet Future Energy Demand," Dirk Smit, Chief Scientist Geophysics, Shell

 

No Video Available

 

To meet future energy demand a significant increase in production from primary energy sources of a wide variety from renewables to fossil-based in a context in which environmental concerns are growing. However, the role of hydrocarbons for a good part in this century will remain important- in particular the role of natural gas may in fact be crucial for the coming decades. Hence there is growing need for technology innovation for efficient hydrocarbon production with smaller foot prints and with an emphasis on gas. In turn, more accurate geoscience technology and monitoring and management of operations will be needed, enabled by more accurate measurements made possible through ubiquitous large scale sensor networks. Thus, in future subsurface characterization and field management may require the processing and interpretation of PByte scale data sets acquired in a more or less continuous fashion. Furthermore, the need to understand more fundamentally rock and fluid interactions often require techniques very similar to quantum-chemistry technologies used in catalysis used in large scale gas to liquid applications. As a result now, more than ever, the need for high performance computing driven by large scale data processing and interpretation needs of a wide variety is key enabler to meet future energy demand in almost any scenario. In this talk some of the geoscience challenges will be illustrated as well as some in computational chemistry and some views will be presented on how these challenges may be met by innovations in computing.


Moderator(s)
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)
avatar for Dirk Smit

Dirk Smit

Chief Scientist Geophysics, Shell
Dirk Smit  has been with Shell since 1992, and currently Vice President of Exploration Technology in R&D and is Chief Scientist for Shell for Geophysics. He has a PhD in Mathematical Physics (String Theory), and had an Academic live before Shell as faculty (non tenure) at Berkeley in the US was awarded a position at Harvard Univ. He started his career with Shell in R&D and has held numerous positions since then among which chief... Read More →


Thursday February 28, 2013 8:30am - 9:25am
McMurtry Auditorium Duncan Hall

9:30am

Plenary: "Role of Computational Science in Energy and Environmental Subsurface Modeling," Mary Wheeler, Director, Center for Subsurface Modeling, Institute for Computational Engineering and Sciences, The University of Texas at Austin

Moderator(s)
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)
avatar for Mary Wheeler

Mary Wheeler

Director, Center for Subsurface Modeling, Institute for Computational Engineering and Sciences, The University of Texas at Austin


Thursday February 28, 2013 9:30am - 10:10am
McMurtry Auditorium Duncan Hall

10:10am

Networking & coffee break
Coffee & networking break

Thursday February 28, 2013 10:10am - 10:45am
Martel Hall Duncan Hall

10:50am

Plenary: "What have I learned about HPC and will it help me in the next decade of change?," William Kramer, Deputy Project Director, Blue Waters Project Office, NCSA

 

Watch the video

 

Using his perspective from fielding high performance systems and services at NCSA and NERSC, Bill will talk about important things to remember when deploying and supporting high performance systems and facilities.  He will comment on the challenges meaningful performance, achieving consistency, energy and helping science and engineering teams effectively use these complex systems.   He will take this perspective forward into extreme scale to try to provide insights and areas to watch as we embark on what may be a decade of technology transition.


Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →

Speaker(s)
avatar for William Kramer

William Kramer

Deputy Project Director, Blue Waters Project Office, NCSA
William T.C. Kramer is deputy project director at the National Center for Supercomputing Applications; he is responsible for leading the Blue Waters project, a National Science Foundation-funded project, to deploy the first general purpose, open science, sustained-petaflop supercomputer as a powerful resource for the nation’s researchers. Previously Kramer was the General Manager of NERSC at Lawrence Berkeley National Laboratory (LBNL... Read More →


Thursday February 28, 2013 10:50am - 11:30am
McMurtry Auditorium Duncan Hall

11:30am

Networking & lunch break

Boxed lunch provided to all atendees in Martel Hall. Enjoy your lunch will catching up with our sponsors.


Thursday February 28, 2013 11:30am - 12:30pm
Martel Hall Duncan Hall

12:30pm

Facility and Infrastructure: "What do supercomputers, bank vaults and garage lighting have in common?," Donny Cooper, Total

Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
CW

Chap Wong

Chevron
Chap Wong is a Chevron Fellow, he is recognized as Chevron’s thought leader in high-performance computing. He is currently a member of the Strategy, Architecture and Emerging Technology Team in Chevron Energy Technology Company’s Technical Computing Department. Chap is engaged in market evaluation, proof of concept and deployment of the emerging technologies required to maximize the performance of Chevron’s HPC environment. 
He has over... Read More →

Speaker(s)
JW

Jing Wen

Technical Computing Supervisor, TOTAL E&P Research & Technology USA LLC


Thursday February 28, 2013 12:30pm - 12:55pm
McMurtry Auditorium Duncan Hall

12:30pm

Applications and Programming Models: "Parallel Reservoir Simulation Using the Trilinos Software Framework," Serguei Maliassov, ExxonMobil Upstream Research Company

 

No Video Available

 

Numerical simulation of reservoirs is an integral part of geoscientific studies to optimize petroleum recovery. Modern petroleum reservoir simulation requires simulating detailed and computationally expensive geological and physical models. Parallel reservoir simulators have the potential to solve larger, more realistic problems than previously possible.

To make the solution of these large problems feasible, an efficient parallel implementation of the algorithm is necessary. Such a parallelization of the algorithm requires proper data structures and data layout, some parallel direct and iterative solvers, and some parallel preconditioners. For the development of parallel reservoir simulator, we found the Trilinos Project to be an efficient environment to develop such a complex parallel application.


Moderator(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
OL

Olav Lindtjorn

HPC and Innovation Manager, Schlumberger
Coming soon
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
SM

Serguei Maliassov

Associate Staff Mathematician, ExxonMobil Upstream Research Co.


Thursday February 28, 2013 12:30pm - 12:55pm
DH 1064 Duncan Hall

12:30pm

Accelerated Computing: "Fully hybrid and scalable downward extrapolation migration on Xeon Phi cluster," Victor Arslan, CGGVeritas

 

Watch the video

 

The aim of this work is to evaluate the benefits of using dual-socket server accelerated with Intel Xeon Phi Coprocessor in a single node or in a cluster configuration. This heterogeneous architecture (CPUs + coprocessors) raises a load balancing issue which is managed by a fully hybrid (MPI+OMP) implementation.


Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →
avatar for Scott Morton

Scott Morton

Manager and Global Geophysical Advisor, Hess Corporation
Scott Morton has 25 years of experience in computational and theoretical physics distributed between academia, the computer industry and the petroleum industry. Although originally trained as an astrophysicist, he switched to geophysics when he joined Shell in 1991 to do research and development in seismic imaging. Scott spent the next 7 years distributed between Shell, Thinking Machines, Cray Research and SGI, gaining expertise in both... Read More →
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)
avatar for Victor Arslan

Victor Arslan

High Performance Computing Research Engineer, CGG
High Performance Computing Research Engineer. Graduated a Master in Applied Mathematics in 2009 and specialist in software programming on massively parallel architectures. I work at CGG on technology forecasting for computational accelerators, including the Intel MIC architecture (Many integrated Core).


Thursday February 28, 2013 12:30pm - 12:55pm
DH 1070 Duncan Hall

12:55pm

Facility and Infrastructure: "Impact of fresh air cooling in your data center – modern server tolerances," Mehrdad Foroozesh, Dell

Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
CW

Chap Wong

Chevron
Chap Wong is a Chevron Fellow, he is recognized as Chevron’s thought leader in high-performance computing. He is currently a member of the Strategy, Architecture and Emerging Technology Team in Chevron Energy Technology Company’s Technical Computing Department. Chap is engaged in market evaluation, proof of concept and deployment of the emerging technologies required to maximize the performance of Chevron’s HPC environment. 
He has over... Read More →

Speaker(s)

Thursday February 28, 2013 12:55pm - 1:20pm
McMurtry Auditorium Duncan Hall

12:55pm

Applications and Programming Models: "A New Approach to Load Balance for Parallel Compositional Simulation Based on Reservoir Model Over-decomposition," Yuhe Wang, Texas A&M University, Petroleum Engineering

 

Watch the video

 

The quest for efficient and scalable parallel reservoir simulators has been evolving with the advancement of high performance computing architectures. Among the various challenges of efficiency and scalability, load imbalance is a major obstacle that has not been fully addressed and solved. The reasons that cause load imbalance in parallel reservoir simulation are both static and dynamic. Robust graph partitioning algorithms are capable of handling static load imbalance by decomposing the underlying reservoir geometry to distribute a roughly equal load to each processor. However, these loads determined by a static load balancer seldom remain unchanged as the simulation proceeds in time. This so called dynamic imbalance can be further exacerbated in parallel compositional simulations. The flash calculations for equations of state in complex compositional simulations not only can consume over half of the total execution time but also are difficult to balance merely by a static load balancer.


Moderator(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
OL

Olav Lindtjorn

HPC and Innovation Manager, Schlumberger
Coming soon
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
avatar for John Killough

John Killough

Professor, Texas A&M University
HPC applications to petroleum reservoir simulation including uncertainty and implicit modeling of complex phenonena.
YW

Yuhe Wang

Texas A&M University, Petroleum Engineering


Thursday February 28, 2013 12:55pm - 1:20pm
DH 1064 Duncan Hall

12:55pm

Accelerated Computing: "Early Experiences In Porting Depth Imaging Applications on Intel MIC Architecture," Asma Farjallah, University of Versailles Saint-Quentin-en-Yvelines

 

Watch the video

As we are moving towards the Exascale level of performance, challenges on the hardware and the software levels are becoming more acute, imposing constraints on both architects and developers. Rethinking the way we express parallelism and consequently the way we develop applications
considering a relevant architectural context is a first step in the co-design process. Intel Many-Integrated Cores (MIC) architecture represents an interesting opportunity to study the impact of this new architectural tendency on the existing applications in Oil and Gas industry.


Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →
avatar for Scott Morton

Scott Morton

Manager and Global Geophysical Advisor, Hess Corporation
Scott Morton has 25 years of experience in computational and theoretical physics distributed between academia, the computer industry and the petroleum industry. Although originally trained as an astrophysicist, he switched to geophysics when he joined Shell in 1991 to do research and development in seismic imaging. Scott spent the next 7 years distributed between Shell, Thinking Machines, Cray Research and SGI, gaining expertise in both... Read More →
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
AF

Asma Farjallah

University of Versailles Saint-Quentin-en-Yvelines
Asma Farjallah obtained a master's degree in Computer Science from École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB) in France. She is currently a PhD candidate in the Exascale Computing Research Laboratory in Versailles. She is working with Henri Calandra and William Jalby to prepare depth imaging applications for the Exascale.


Thursday February 28, 2013 12:55pm - 1:20pm
DH 1070 Duncan Hall

1:20pm

Facility and Infrastructure: "Open Compute Platform project, what it is, how it might help Oil & Gas HPC," Matt Corddry, Open Compute Platform

 

Watch the video

 

Open Source has transformed the software industry over the past twenty years, especially HPC and scale computing. Come learn about Open Compute, the first open source hardware project for datacenter computing. Open Compute enables collaboration and innovation between the consumers and producers of datacenter hardware, resulting in designs that are more focused on the needs of datacenter computing.


Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
CW

Chap Wong

Chevron
Chap Wong is a Chevron Fellow, he is recognized as Chevron’s thought leader in high-performance computing. He is currently a member of the Strategy, Architecture and Emerging Technology Team in Chevron Energy Technology Company’s Technical Computing Department. Chap is engaged in market evaluation, proof of concept and deployment of the emerging technologies required to maximize the performance of Chevron’s HPC environment. 
He has over... Read More →

Speaker(s)
avatar for Matt Corddry

Matt Corddry

Matt Corddry leads the server hardware design team for Facebook. The Facebook server hardware platform powers Facebook.com and supports hundreds of millions of users worldwide. These designs are open sourced via the OpenCompute foundation, to foster innovation in large scale datacenter computing across the industry. Prior to joining Facebook, Mr. Corddry led the Amazon Web Services hardware and operating system engineering team... Read More →


Thursday February 28, 2013 1:20pm - 1:45pm
McMurtry Auditorium Duncan Hall

1:20pm

Applications and Programming Models: "Integrated Reservoir Modeling and Simulation Optimization Workflow Based on a High-Performance Parallel Computing Cluster," Guoxiang Liu, Energy & Environmental Research Center, University of North Dakota

 

Watch the video

 

Large model size and multiple predictive simulation scenarios are two of the primary challenges in reservoir modeling and simulation. In trying to capture heterogeneity within a reservoir, the cell count can increase drastically by adding horizontal and vertical resolution. In addition, multiple predictive and optimization scenarios designed to investigate strategies for drilling, optimization of production, and net present value analysis and carbon dioxide injection for enhanced oil recovery (EOR) and storage can take considerable time and computational power. These challenges slow down simulation speed and overall computation time, leading to increased project timelines, and can cause project delays. To solve these issues, an integrated model optimization workflow was proposed, as well as the design and construction of a high-performance parallel computer cluster built at the Energy & Environment Research Center (EERC). To obtain the maximum speed-up for this integrated optimization workflow, a scalability test of the cluster for multiple simulation jobs over various cores was performed. This was followed by a grid sensitivity analysis that aims to find the coarsest grid cell size that will capture the necessary heterogeneity of the reservoir. Then numerical tuning was performed with the objective of reducing processing time while minimizing material balance error and solver failure percent. Finally, a sensitivity analysis was performed to identify properties and parameters that most affect the history match or predictive simulations.


Moderator(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
OL

Olav Lindtjorn

HPC and Innovation Manager, Schlumberger
Coming soon
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
GL

Guoxiang Liu

Research Manager, Energy & Environmental Research Center, University of North Dakota


Thursday February 28, 2013 1:20pm - 1:45pm
DH 1064 Duncan Hall

1:20pm

Accelerated Computing: "Experiences with a Performance Comparison of a Simple RTM Kernel on Xeon Phi," James Brodman, Intel

Watch the video recording

 

Accelerators are now a common tool for increasing the computing power of a machine. Xeon Phi is a new accelerator that combines the compute power of a GPGPU accelerator with the programmability of a multicore processor. Expert programmers can wring all the performance that this class of device can offer by meticulously performing low level optimizations. This talk presents experiences obtained from an exercise at the other end of the spectrum. A simple, unoptimized isotropic, 8th-order-in-space 3D RTM kernel that performs wave propagation without boundary conditions was chosen as the test vehicle to examine what performance can be achieved on Xeon Phi applying only three basic high-level optimizations.


Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →
avatar for Scott Morton

Scott Morton

Manager and Global Geophysical Advisor, Hess Corporation
Scott Morton has 25 years of experience in computational and theoretical physics distributed between academia, the computer industry and the petroleum industry. Although originally trained as an astrophysicist, he switched to geophysics when he joined Shell in 1991 to do research and development in seismic imaging. Scott spent the next 7 years distributed between Shell, Thinking Machines, Cray Research and SGI, gaining expertise in both... Read More →
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)
JC

James C. Brodman

Software Engineer, Intel


Thursday February 28, 2013 1:20pm - 1:45pm
DH 1070 Duncan Hall

1:45pm

Facility and Infrastructure: "Dreamworks HPC and how it compares with Oil and Gas Requirements," Derek Chan, Dreamworks

 

Watch the video

 

 


Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
CW

Chap Wong

Chevron
Chap Wong is a Chevron Fellow, he is recognized as Chevron’s thought leader in high-performance computing. He is currently a member of the Strategy, Architecture and Emerging Technology Team in Chevron Energy Technology Company’s Technical Computing Department. Chap is engaged in market evaluation, proof of concept and deployment of the emerging technologies required to maximize the performance of Chevron’s HPC environment. 
He has over... Read More →

Speaker(s)
avatar for Derek Chan

Derek Chan

Head of Technology Global Operations, DreamWorks Animation
Derek Chan is Head of Technology Global Operations for DreamWorks Animation, where he is responsible for providing strategic vision, planning and implementation of the studio’s computing infrastructure, including Systems Engineering, Systems Operations, Technical Resource Management and Hardware Engineering. He also leads the studio’s adoption and leverage of cloud computing, which has been crucial to providing the massive compute... Read More →


Thursday February 28, 2013 1:45pm - 2:10pm
McMurtry Auditorium Duncan Hall

1:45pm

Applications and Programming Models: "Reverse Time Migration using Coarray Fortran," Alan Richardson, Massachusetts Institute of Technology

 

Watch the video

 

Coarray Fortran (CAF) is a new set of language extensions introduced in the Fortran 2008 standard. It permits distributed memory parallel programming without the use of an external library such as MPI. CAF follows the Partitioned Global Address Space (PGAS) model of parallel programming. This partitions an array among processors. Processors are allowed to access any element in the global array, but it is likely that most accesses will be to their local portion. The PGAS model is particularly suited to domain decomposition parallelization strategies, where parallelism is achieved by dividing the problem domain among processors.


Moderator(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
OL

Olav Lindtjorn

HPC and Innovation Manager, Schlumberger
Coming soon
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
TL

Terrence Liao

TOTAL S.A.
avatar for Alan Richardson

Alan Richardson

Massachusetts Institute of Technology
Alan Richardson obtained a bachelor's degree in Theoretical Physics from Trinity College Dublin, followed by an MSc in High Performance Computing from the Edinburgh Parallel Computing Centre (EPCC) at the University of Edinburgh. He is currently a PhD candidate in the Geophysics program at the Massachusetts Institute of Technology's Earth Resources Laboratory, where he works with Professor Alison Malcolm to develop seismic imaging algorithms that... Read More →


Thursday February 28, 2013 1:45pm - 2:10pm
DH 1064 Duncan Hall

1:45pm

Accelerated Computing: "Forward seismic modeling on AMD Accelerated Processing Unit," Henri Calandra, Total

 

Watch the video

 

Seismic modeling is an area of significant research in the Oil and Gas industry. Forward modeling consists in computing theoretical or synthetic seismograms in order to validate a real geological model by comparing the synthetic data with the field data. This corresponds to a basic problem in reflection seismology, which is to determine the wave response of a given model to the excitation of an impulse source by solving the wave equation. The modeling of wave propagation with high accuracy in complex media is useful for data interpretation, for velocity analysis and for understanding imaging problems, with the help of many inversion algorithms such as migrations (Reverse Time Migration, Kirchhoff migration etc.) that highly require communication in order to store data snapshots. Such applications are extremely resource-intensive, in terms of compute power and also of memory bandwidth, and need resources far greater than a single CPU can provide. Thanks to the advent of high performance computing facilities, these applications are seeing significant acceleration using clusters of multi-core CPUs and GPUs (Graphic Processing Units). Although very large gains in performance can be achieved by GPUs, the PCI interconnection between CPU and GPU remains the bottleneck for this kind of calculations due to their high CPU-GPU communication requirements (data snapshots).


Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →
avatar for Scott Morton

Scott Morton

Manager and Global Geophysical Advisor, Hess Corporation
Scott Morton has 25 years of experience in computational and theoretical physics distributed between academia, the computer industry and the petroleum industry. Although originally trained as an astrophysicist, he switched to geophysics when he joined Shell in 1991 to do research and development in seismic imaging. Scott spent the next 7 years distributed between Shell, Thinking Machines, Cray Research and SGI, gaining expertise in both... Read More →
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
avatar for Issam Said

Issam Said

Computational Scientist, TOTAL/LIP6
My current research interests include high performance computing (HPC), numerical methods and applied geophysics. I specialize in adapting scientific applications to hardware accelerators, mainly Graphics Processing Units (GPUs). It implies improving the performance of numerical solvers, surveying cutting edge hardware/architectures and studying the viability of scientific friendly programming models such as OpenACC. My current work involves... Read More →


Thursday February 28, 2013 1:45pm - 2:10pm
DH 1070 Duncan Hall

2:10pm

Facility and Infrastructure: "Tape NAS – The Data Storage Game Changer!," Matt Star, Spectra Logic

 

Watch the video

 

The Oil and Gas industry today faces many challenges. Among the most critical of those challenges is how to manage the onslaught of exponential data growth rates. As users create, gather and
move various data assets though the exploration and production life‐cycle, multiple applications are used to access, process, manipulate and output the data. For the Oil and Gas industry, today’s
storage infrastructures must be configured and tiered appropriately to enable an efficient workflow that allows timely, cost-effective access to data. They must also provide scalability as needed, as
well as performance and transparency for end users. The best technology platforms to accomplish this today are a combination of disk, tape and in some cases, flash with intelligent file system
applications on the front end. Current tape technologies combined with disk technologies, and eventually flash technologies in a strategically organized implementation can address the current and
future challenges and objectives of oil and gas storage administrators, including performance, compliance, security, cost, energy consumption, asset preservation, and data protection


Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
CW

Chap Wong

Chevron
Chap Wong is a Chevron Fellow, he is recognized as Chevron’s thought leader in high-performance computing. He is currently a member of the Strategy, Architecture and Emerging Technology Team in Chevron Energy Technology Company’s Technical Computing Department. Chap is engaged in market evaluation, proof of concept and deployment of the emerging technologies required to maximize the performance of Chevron’s HPC environment. 
He has over... Read More →

Speaker(s)
avatar for Matt Starr

Matt Starr

CTO, Spectra Logic
I love solving problems, high tech, low tech I just love problem solving. I have worked at Spectra Logic for the last 23 years. Spectra Logic specializes in storing massive amounts of data, exabytes. That means we get to build the largest data storage systems in the world, using both disk and tape and flash. I have a BS in Electrical Engineering, specializing in VLSI design. I currently hold 41 US patents and have 65 under file. I have... Read More →


Thursday February 28, 2013 2:10pm - 2:30pm
McMurtry Auditorium Duncan Hall

2:10pm

Applications and Programming Models: "Large GPI-based 3D stencil computation," Mauricio Araya-Polo, Shell

 

Watch the video

 

Stencil operators are the basic building blocks in solving finite difference based
wave propagators, such as the ones that are used for seismic modeling
and migration (RTM). As such, these kernels are part of many contemporary
industry codes. Both, the software side (increasing data sets, physical
model complexity) as well as the hardware side (increasing machine
size, accelerator cards) increase the pressure to produce parallel and
scalable code.


Moderator(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
OL

Olav Lindtjorn

HPC and Innovation Manager, Schlumberger
Coming soon
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
DG

Daniel Grunewald

Competence Center High Performance Computing, Fraunhofer ITWM


Thursday February 28, 2013 2:10pm - 2:35pm
DH 1064 Duncan Hall

2:10pm

Accelerated Computing: "Reverse Time Migration: A Case Study of GPU/CPU Hybrid Computing," Scott Quiring, Acceleware Ltd

 

Watch the video

 

Reverse Time Migration (RTM) is now the dominant imaging technique used in deep marine seismic exploration. This commercial case study highlights the need for the implementation to be continuously re-balanced as hardware performance and software features evolve over time in order to avoid performance bottlenecks and maintain optimum throughput. The basic methodology of RTM and the computational challenges it raises will be shown, and a solution that takes full advantage of the resources available on a GPU / CPU hybrid compute node will be presented.

There are two major computational challenges in RTM: efficient propagation of a 3D seismic wavefield and accessing the wavefield in reverse-time order.


Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →
avatar for Scott Morton

Scott Morton

Manager and Global Geophysical Advisor, Hess Corporation
Scott Morton has 25 years of experience in computational and theoretical physics distributed between academia, the computer industry and the petroleum industry. Although originally trained as an astrophysicist, he switched to geophysics when he joined Shell in 1991 to do research and development in seismic imaging. Scott spent the next 7 years distributed between Shell, Thinking Machines, Cray Research and SGI, gaining expertise in both... Read More →
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)

Thursday February 28, 2013 2:10pm - 2:35pm
DH 1070 Duncan Hall

2:30pm

Facility and Infrastructure: "Managing congestion within multi-tiered, standards based networks," Fred Homewood, Gnodal

 

Watch the video

 

 


Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
CW

Chap Wong

Chevron
Chap Wong is a Chevron Fellow, he is recognized as Chevron’s thought leader in high-performance computing. He is currently a member of the Strategy, Architecture and Emerging Technology Team in Chevron Energy Technology Company’s Technical Computing Department. Chap is engaged in market evaluation, proof of concept and deployment of the emerging technologies required to maximize the performance of Chevron’s HPC environment. 
He has over... Read More →

Speaker(s)

Thursday February 28, 2013 2:30pm - 2:45pm
McMurtry Auditorium Duncan Hall

2:30pm

Applications and Programming Models: "IWAVE to IWAVE++: from modeling to inversion," William Symes, Rice University

 

Watch the video

 

At last year's meeting, the author presented IWAVE, an open source package for synthesizing seismic data. This talk marks the release of IWAVE++, the migration and inversion package based on the IWAVE modeling engine. This first-ever open source inversion package includes a variety of optimization and modeling options and hooks for adding many more. Along with standard time-domain full waveform inversion and least squares migration applications, the first release of IWAVE++ also includes extended modeling and nonlinear differential semblance options. Biondo Biondi and his group recently used a nonlinear differential semblance algorithm to give a satisfactory solution of the Marmousi velocity-model building problem for the first time in its 20+ year history.


Moderator(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
OL

Olav Lindtjorn

HPC and Innovation Manager, Schlumberger
Coming soon
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
avatar for William Symes

William Symes

Rice University


Thursday February 28, 2013 2:30pm - 2:45pm
DH 1064 Duncan Hall

2:35pm

Accelerated Computing: "GPU accelerated discontinuous Galerkin methods for wave propagation," TIm Warburton, Rice University

Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →
avatar for Scott Morton

Scott Morton

Manager and Global Geophysical Advisor, Hess Corporation
Scott Morton has 25 years of experience in computational and theoretical physics distributed between academia, the computer industry and the petroleum industry. Although originally trained as an astrophysicist, he switched to geophysics when he joined Shell in 1991 to do research and development in seismic imaging. Scott spent the next 7 years distributed between Shell, Thinking Machines, Cray Research and SGI, gaining expertise in both... Read More →
avatar for Amik St-Cyr

Amik St-Cyr

Senior researcher, Shell
Amik St-Cyr recently joined the Royal Dutch Shell company as a senior researcher in computation & modeling. Amik came to the industry from the NSF funded National Center for Atmospheric Research (NCAR). His work consisted in the discovery of novel numerical methods for geophysical fluid flows with particular attention to their implementation on supercomputers. He has experience in a plethora of numerical methods for solving time-dependent... Read More →

Speaker(s)

Thursday February 28, 2013 2:35pm - 3:00pm
DH 1070 Duncan Hall

2:45pm

Facility and Infrastructure: "Accelerating Diverse Data Center Communications by Optics," Yiting Xia, Rice University

 

Watch the video

 

Current big data applications have diverse communication patterns [6]. For example, the popular MapReduce computing paradigm shows frequent many-to-one data aggregation and all-to-all data shuffle. Relational join, a typical database operation, requires a "table" to be replicated to all the nodes in a network. Due to massive traffic volumes, these communication patterns lay increasing burden on data center networks. Recent proposals to offload this burden to optical circuit-switched networks [7, 11, 5, 12] provide significant bandwidth increase for stand-alone point-to-point bulk transfers. But they are unable to efficiently support other communication patterns that are crucial to application performance [4]. To address this problem, we propose an unconventional approach that leverages novel physical layer photonics technologies to build customized communication devices for accelerating diverse communication patterns, and integrates such devices into an application-driven, dynamically configurable photonics accelerated data center network. We present preliminary results from a case study to highlight the potential benefits of this approach.


Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
CW

Chap Wong

Chevron
Chap Wong is a Chevron Fellow, he is recognized as Chevron’s thought leader in high-performance computing. He is currently a member of the Strategy, Architecture and Emerging Technology Team in Chevron Energy Technology Company’s Technical Computing Department. Chap is engaged in market evaluation, proof of concept and deployment of the emerging technologies required to maximize the performance of Chevron’s HPC environment. 
He has over... Read More →

Speaker(s)
avatar for Yiting Xia

Yiting Xia

PhD student, Rice University
Yiting Xia is a second-year PhD student in Computer Science Department of Rice University. She received the Bachelor's degree on Telecoms Engineering from Beijing University of Posts and Telecommunications in China. She is now working under the supervision of Prof. T.S. Eugene Ng. Her research mainly focuses on building novel network architectures in cloud data centers that facilitate data-intensive cluster computing applications. She is... Read More →


Thursday February 28, 2013 2:45pm - 3:00pm
McMurtry Auditorium Duncan Hall

2:45pm

Applications and Programming Models: "From Equations to Simulators: FEniCS in Reservoir Simulation," Yaakoub El Khamra, Texas Advanced Computing Center, The University of Texas at Austin

 

Watch the video

There are many applicable adjectives to the process of reservoir simulator development. Quick and easy are not typically among them.

However, with the advent of automated scientific computing tools, namely the FEniCS project, it is possible to rapidly solve the coupled, nonlinear partial differential equations we encounter in reservoir simulation. The FEniCS project is a collaborative project that spans a problem-solving environment, a form compiler, finite element tabulator, a code generation interface, high performance solver/preconditioner packages, visualization packages, mesh generation and partitioning etc... . Using FEniCS it is possible to solve a system of coupled PDE's with only a variational form, a mesh and a boundary specification. We show the efficiency of using FEniCS by demonstrating a black oil reservoir simulator written in Python, using FEniCS, running in parallel on HPC infrastructure in under two hundred lines of code. We discuss lessons learned during development and possible future directions for automated scientific computing.

 


Moderator(s)
HC

Henri Calandra

Total
Henri Calandra obtained his M.Sc. in mathematics in 1984 and a Ph.D. in mathematics in 1987 from the Universite des Pays de l’Adour in Pau, France. He joined Cray Research France in 1987 and worked on seismic applications. In 1989 he joined the applied mathematics department of the French Atomic Agency. In 1990 he started working for Total SA. After 12 years of work in high performance computing and as project leader for Pre-stack Depth... Read More →
OL

Olav Lindtjorn

HPC and Innovation Manager, Schlumberger
Coming soon
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
YE

Yaakoub El Khamra

Research Engineer, Texas Advanced Computing Center, The University of Texas at Austin
Yaakoub is a research engineer at the Texas Advanced Computing Center with a background in petroleum and mechanical engineering. He is part of the performance and architecture high performance computing group.


Thursday February 28, 2013 2:45pm - 3:00pm
DH 1064 Duncan Hall

3:00pm

Networking & coffee break

Coffee & networking break


Thursday February 28, 2013 3:00pm - 3:30pm
Martel Hall Duncan Hall

3:30pm

Keynote: "High Performance Computing: Solving Oil and Gas Problems Today – Poised for the Future," John Kuzan, Manager, Computational Sciences Function, ExxonMobil Upstream Research Company

 

No video available

As energy demand rises globally, oil and gas will continue to supply about half of that demand and energy efficiency will become increasingly important.  The pace of improvement is likely to accelerate, reflecting the development and deployment of new technologies in the oil and gas business, as well as for personal transportation and power generation.  Ensuring access to energy for people around the world has been and will remain a great challenge.  Effective technology solutions to the energy challenges before us will naturally rely on modeling complicated processes and that in turn will lead to a strong need for high-performance computing.  The presentation will include ExxonMobil's global energy outlook through 2040.


Moderator(s)
avatar for Simanti Das

Simanti Das

Manager, High Performance Computing Software Development & Support, ExxonMobil Technical Computing Company
Simanti Das, is currently the manager of High Performance Computing software development and support group in ExxonMobil Upstream IT organization. She is responsible for providing software development, optimization and support for massively parallel seismic imaging technologies for Upstream business use. Upon receiving her M.S in Computer Science from University of Houston in 1988, Simanti started her career at Exxon Production Research... Read More →

Speaker(s)
JD

John D. Kuzan

Manager, Computational Sciences Function, ExxonMobil Upstream Research Company


Thursday February 28, 2013 3:30pm - 4:15pm
McMurtry Auditorium Duncan Hall

4:15pm

Plenary Panel: "HPC Infrastructure: Planning for the Future"

 

No video available


Moderator(s)
avatar for Keith Gray

Keith Gray

Manager, High Performance Computing, BP
Keith Gray is Manager of High Performance Computing for BP. The HPC Team supports the computing requirements for BP’s Advanced Seismic Imaging Research efforts. This team supports one of the largest Linux Clusters dedicated to research in Oil and Gas. Mr. Gray graduated from Virginia Tech with a degree in geophysics, and has worked for BP and Amoco since 1985. He was listed in HPCWire’s People to Watch 2006.
avatar for Bill Menger

Bill Menger

Director, HPC, Global Geophysical
Bill Menger is the Director of HPC at Global Geophysical Services, Inc. Bill started his career as a nuclear engineer for the US Navy prior to joining Conoco in 1982 to work on magnetotellurics and electrical methods. Bill has also worked on multicomponent seismic, data management, and seismic processing systems for Conoco and ConocoPhillips. He left Conoco for three years to join AGS, working on Kirchhoff and demultiple techniques. He returned... Read More →
avatar for Jan Odegard

Jan Odegard

Executive Director, Ken Kennedy Institute for Information Technology, Rice University
Jan E. Odegard joined the Ken Kennedy Institute for Information Technology (formerly Computer and Information Technology Institute) at Rice University as Executive Director in 2002. In this role he led the development and deployment of large scale competing resources in support of research. Today, the computational resources deployed at Rice supports the research of over 100 faculty members and close to 500 users. The majority of users are... Read More →

Speaker(s)
avatar for Scott Denham

Scott Denham

Senior IT Architect, IBM
HPC and advancing computing technology
JJ

Jeff Jackson

High Performance Computing Geophysics Solution Lead, Shell
avatar for Jay Williamson

Jay Williamson

Emerging technologies team, Chevron
Jay Williamson has worked at several companies throughout his career. After getting his B.S. in Engineering Analysis from Clemson University in 1988, he has worked at Clemson University, Chevron, Schlumberger, Collective Technologies Consulting (@Broadband Technologies, @Nynex, @Lucent), and Marconi/Bosch Telecom and back to Chevron. | | Jay’s Chevron career started in 1991-1995 and then again from 2002-present. He has held a variety of... Read More →


Thursday February 28, 2013 4:15pm - 5:00pm
McMurtry Auditorium Duncan Hall

5:00pm

5:00pm

Poster: "A New Approach for Performance Analysis of OpenMP Programs", Xu Liu, Rice University
Speaker(s)

Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm

5:00pm

Poster: "Accelerating Diverse Data Center Communications by Optics", Yiting Xia, Rice University
Speaker(s)
avatar for Yiting Xia

Yiting Xia

PhD student, Rice University
Yiting Xia is a second-year PhD student in Computer Science Department of Rice University. She received the Bachelor's degree on Telecoms Engineering from Beijing University of Posts and Telecommunications in China. She is now working under the supervision of Prof. T.S. Eugene Ng. Her research mainly focuses on building novel network architectures in cloud data centers that facilitate data-intensive cluster computing applications. She is... Read More →


Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm

5:00pm

5:00pm

5:00pm

5:00pm

Poster: "Computational study of damage in hybrid masonry structural systems", Zhenjia Gao
Speaker(s)

Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm

Poster: "DG solution of flow and transport for random media", Kun Liu, Rice University
Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm

5:00pm

5:00pm

5:00pm

Poster: "Locally mass-conservative method for miscible displacement simulations", Jizhou Li, Rice University
Speaker(s)
JL

Jizhou Li

Graduate Student, Rice University
I am PhD student in Computational and Applied Mathematics at Rice University. I am interested in developing efficient and accurate solutions to porous media flow and transport problems, while maintaining a solid theoretical base.


Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm

Poster: "Performance of ISO/TTI kernels on CPU/GPU using OpenMP, PGI, HMPP and OpenACC directives", Sayan Ghosh
Speaker(s)
SG

Sayan Ghosh

GRADUATE RESEARCH ASSISTANT, UNIVERSITY OF HOUSTON
University of Houston


Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm

5:00pm

5:00pm

Poster: "Two-stage method for extended waveform inversion", Yin Huang, Rice University
Speaker(s)

Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm

Poster: Accelerating Medical Imaging Applications Using a Distributed, Heterogeneous Platform, Max Grossman, Rice University
Speaker(s)
MG

Max Grossman

Student, Rice University


Thursday February 28, 2013 5:00pm - 6:30pm
Martel Hall Duncan Hall

5:00pm