Events

Subscribe

Join NVIDIA at Supercomputing 2017!

CONNECT WITH NVIDIA AT SUPERCOMPUTING 2017

 

Join NVIDIA at SC17 to learn how GPU-accelerated computing is changing the very definition of the word possible. Humanity’s moonshots, like understanding the most fundamental laws of physics, breakthroughs in drug development, and sustainable energy are being achieved right now. See how leaders in fields such as HPC, accelerated supercomputing, and deep learning are advancing computational science across domains, get free hands-on training with the newest GPU-accelerated solutions, and connect with NVIDIA experts.

Accelerated computing: success stories

 

The very real applications of accelerated computing—like monitoring the Earth's vitals and analyzing global population distribution—are here today, pioneered by the world's most advanced teams and organizations. Read more about them here in these customer success stories.

 
  • Success Story 1
  • Success Story 2
  • Success Story 3
  • Success Story 4
  • Success Story 5

THEATER SCHEDULE

Date: FIlter By:
Reset
Monday, November 13 | GPU Technology Theater
3:00pm - 4:00pm
Accelerated Computing: The Path Forward - Special Address
Jensen Huang (NVIDIA)
7:30pm - 8:30pm
Accelerated Computing: The Path Forward
Ian Buck (NVIDIA)
Tuesday, November 14 | GPU Technology Theater
10:00am - 10:20am
Deep Learning Everywhere, For Everyone: NVIDIA GPU Cloud
Greg Crider (NVIDIA)
10:30am - 10:50am
AWS & NVIDIA: Fast and Furious Innovation in Computing and Visualization
Brendan Bouffler (Amazon Web Services)
11:00am - 11:20am
Adapting Deep Learning to New Data Using ORNL's Titan Supercomputer
Travis Johnston (Oak Ridge National Lab)
11:30am - 11:50am
NVIDIA Developer Tools: New Capabilities in CUDA 9
Sanjiv Satoor (NVIDIA)
12:00pm - 12:20pm
Deep Learning with MATLAB: From Desktop to Cloud to Embedded GPUs
Jos Martin (Mathworks)
12:30pm - 12:50pm
Application Readiness Projects for the Summit Architecture
Tjerk P. Straatsma (Oak Ridge National Lab)
1:00pm - 1:20pm
Dell EMC Machine Learning & Deep Learning Strategy for Innovation & Discovery
1:30pm - 1:50pm
Sierra: The LLNL IBM CORAL System
Bronis de Supinski (Lawrence National Lab)
2:00pm - 2:20pm
Unstructured-Grid CFD Algorithms on the NVIDIA Pascal and Volta Architectures
2:30pm - 2:50pm
The DOE and NCI Partnership on Precision Oncology and the Cancer Moonshot
Fangfang Xia (Argonne National Lab)
3:00pm - 3:50pm
ADAC: Accelerated Data Analytics and Computing Institute (Panel)
4:00pm - 4:20pm
Large Scale Deep Learning on Sierra Early Access Systems
Brian Van Essen (Lawrence Livermore National Lab)
4:30pm - 4:50pm
Deep Learning for Scientific Discovery
Courtney Corley (Pacific Northwest National Lab)
5:00pm - 5:20pm
Synthesis Models: Combining HPC Simulation with the Power of Machine Learning
Karl Freund (Moor Insights & Strategy)
5:30pm - 5:50pm
Programming GPU-based Extreme-Scale HPC Systems: OpenSHMEM and SharP
Manju Venkata (Oak Ridge National Lab)
Wednesday, November 15 | GPU Technology Theater
10:00am – 10:20am
NVIDIA DLI University Ambassador Program
10:30am – 10:50am
Accelerating HPC Programmer Productivity with OpenACC and CUDA Unified Memory
Doug Miles (NVIDIA)
11:00am - 11:20am
Red + Green = Great HPC
Lee Gates (Oracle)
11:30am - 11:50pm
Converging HPC and BD/AI: Tokyo Tech. TSUBAME3.0 and AIST ABCI
Satoshi Matsuoka (Tokyo Tech)
12:00pm – 12:20pm
HPC Exascale & AI
Steve Oberlin (NVIDIA)
12:30pm – 1:20pm
1:30pm – 1:50pm
Rapid Computation of Permeability from Micro-CT Images on GPGPUs
2:00pm – 2:20pm
Accelerated compute in Azure using GPUs
Tariq Sharif (Microsoft)
2:30pm – 2:50pm
An Agile Approach to Building a GPU-enabled and Performance-portable Global Cloud-resolving Atmospheric Model
Richard Loft (National Center for Atmospheric Research)
3:00pm – 3:20pm
An Approach to Developing MPAS on GPUs
Raghu Raj Prasanna Kumar (National Center for Atmospheric Research(NCAR))
3:30pm – 3:50pm
Alexa: Simulating Shock Hydrodynamics on the GPU using Kokkos - Getting real with multi-material mechanics and adaptivity
4:00pm - 4:20pm
MVAPICH2-GDR Library: Pushing the Frontier of HPC and Deep Learning
DK Panda (Ohio State University)
4:30pm – 4:50pm
Why Google Cloud + NVIDIA: Benefits of using NVIDIA Tesla P100 & K80 GPUs on Google Cloud Platform
Chris Kleban (Google)
5:00pm – 5:20pm
Enabling AI with Innovative HPC System Design
5:30pm – 5:50pm
Moving applications to complex architectures through collaborative hackathons
Fernanda Foertter (Oak Ridge National Lab)
Thursday, November 16 | GPU Technology Theater
10:00am - 10:30am
10:30am - 10:50am
Overview of HPC and Energy Saving on Nvidia's V100 for Some Computations
Jack Dongarra (University of Tennessee)
11:00am - 11:20am
Rapid Computation of Permeability from Micro-CT Images on GPGPUs
11:30am - 11:50am
Visualization on GPU Accelerated Supercomputers
Peter Messmer (NVIDIA)
12:00pm - 12:20pm
NVIDIA Enables Faster HPC Application Deployment
Ryan Olson (NVIDIA)
12:30pm – 12:50pm
Enterprise Ready Deep Learning
1:00pm – 1:20pm
Inside SATURNV – Insights from NVIDIA’s Deep Learning Supercomputer
Phil Rogers (NVIDIA)
1:30pm – 1:50pm
Inside Volta
Stephen Jones (NVIDIA)
2:00pm – 2:20pm
High Performance Inferencing with TensorRT
2:30pm – 2:50pm
CUDA 9: New Features and Technologies
Stephen Jones (NVIDIA)
Load More

Demos

Visit the NVIDIA booth to check out various scientific research demos including the use of AI in astrophysics and material sciences, CFD visualization and VR, HPC visualization, and more.

NVIDIA PARTNERS AT SC17

HANDS-ON DEEP LEARNING LABS

The NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers looking to solve the world’s most challenging problems with deep learning.

Join us for Deep Learning Fundamentals hands-on labs on Tuesday, November 14th from 9 AM – 5 PM in the Curtis Hotel in the Marco Polo room.

Plus, stop by the NVIDIA booth for self-paced labs during exhibit hours on Monday through Thursday.

REGISTER NOW

DEVELOPER ZONE

Looking to make your applications faster and smarter? Stop by the in-booth Developer Zone to speak with an HPC and deep learning expert. Or, you can take a free hands-on lab and learn the latest GPU programming tips and tricks for deep learning, debugging, and more. You'll learn how to:

  • Get started with deep learning on GPUs
  • Accelerate your applications with CUDA C/ C++, Fortran, Python, OpenACC, and drop-in math libraries
  • Increase your programming productivity by applying best practices for debugging and advanced optimization techniques

MEET THE EXPERTS

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.

LEARN MORE

The Student Cluster Competition

NVIDIA is a bronze sponsor of this year’s Student Cluster Competition at SC17.The Student Cluster Competition draws high school and college teams from all over the world and is designed to ignite interest in the field of high-performance computing (HPC).

For more information on the competition, visit the
SC17 Website.

DEEP LEARNING CAREERS AT NVIDIA

NVIDIA is currently hiring deep learning experts to help us accelerate the next wave of AI. Widely viewed as one of the world’s most desirable employers, NVIDIA attracts the best talent in the world. With an environment designed to help you do your life's work, NVIDIA’s culture is dedicated to fostering research that makes a lasting impact on the world.

INTERESTED?
Accelerated Computing: The Path Forward
Monday, November 13 | GPU Technology Theater | 7:30pm - 8:30pm

Ian Buck (NVIDIA)

Ian Buck is vice president of NVIDIA's Accelerated Computing business unit, which includes all hardware and software product lines, third-party enablement, and marketing activities for GPU computing. Buck joined NVIDIA in 2004 and created CUDA, which remains the established leading platform for accelerated-based parallel computing. Before joining NVIDIA, he was the development lead on Brook, which was the forerunner to generalized computing on GPUs. Buck holds a Ph.D. in computer science from Stanford University and Bachelor of Science in computer science from Princeton University.

Dell EMC Machine Learning & Deep Learning Strategy for Innovation & Discovery
Tuesday, November 14 | GPU Technology Theater | 1:00pm - 1:20pm
 
Jay Boisseau (Dell)

Unstructured-Grid CFD Algorithms on the NVIDIA Pascal and Volta Architectures
Tuesday, November 14 | GPU Technology Theater | 2:00pm - 2:20pm

In the field of computational fluid dynamics, the Navier-Stokes equations are often solved using an unstructured-grid approach to accommodate geometric complexity. Furthermore, turbulent flows encountered in aerospace applications generally require highly anisotropic meshes, driving the need for implicit solution methodologies to efficiently solve the discrete equations. To prepare NASA Langley Research Center's FUN3D CFD solver for the future HPC landscape, we port two representative kernels to NVIDIA Pascal and Volta GPUs and present performance comparisons with a common multi-core CPU benchmark.

Eric Nielsen (NASA)

Eric Nielsen is a Research Scientist with the Computational AeroSciences Branch at NASA Langley Research Center in Hampton, Virginia. Dr. Nielsen specializes in the development of computational aerodynamics software for the world's most powerful computer systems. The software has been distributed to thousands of organizations around the country and supports major national research and engineering efforts at NASA, in industry, academia, the Department of Defense, and other government agencies.

Deep Learning with MATLAB: From Desktop to Cloud to Embedded GPUs
Tuesday, November 14 | GPU Technology Theater | 12:00pm - 12:20pm

Learn how to adopt a MATLAB-centric workflow to design, develop, scale and deploy deep learning applications on to GPUs whether on your desktop, a cluster, or on embedded Tegra platforms, including Jetson TK1/TX1 and DRIVE PX boards. The workflow starts with algorithm design in MATLAB, which enjoys universal appeal among engineers and scientists because of its expressive power and ease of use. The algorithm may employ deep learning networks augmented with traditional computer vision techniques and can be tested and verified within MATLAB. Next, those networks are trained using MATLAB's GPU and parallel computing support either on the desktop, a local compute cluster, or in the cloud. Finally, a compiler auto-generates portable and optimized CUDA code from the MATLAB algorithm, which is then cross-compiled and deployed to the Tegra board. We'll use examples of common computer vision algorithms and deep learning networks to describe this workflow, and we'll present their performance benchmarks, including training with multiple GPUs on an Amazon P2 cloud instance.

Jos Martin (Mathworks)

Jos Martin is Senior Engineering Manager at MathWorks with responsibility for the development of all HPC and parallel computing product, MATLAB Drive and MATLAB Connector. He has lead the parallel computing team since its inception in 2003 and in that time has architected much of the toolbox, particularly the core infrastructure and parallel language areas. He received a D.Phil in Atomic and Laser Physics and an MA in Physics from Oxford University, UK. After completing his D.Phil he held a Royal Society Post-Doctoral Fellowship at the University of Otago, New Zealand. His area of research was Experimental Bose-Einstein Condensation (BEC), a branch of low-temperature atomic physics.

CUDA 9: New Features and Technologies
Thursday, November 16 | GPU Technology Theater | 2:30pm - 2:50pm

CUDA is NVIDIA's parallel computing platform and programming model. The latest version, CUDA 9, brings major performance improvements to libraries, new features in the programming model, support for Volta GPUs and new debugging and profiling capabilities. In this session, you will learn about library improvements that speed up deep learning, image and video processing and computer vision applications significantly. You will also see how to use Cooperative Groups, a new CUDA component that allows fine-grained thread management so you can take full advantage of Volta’s execution capabilities. The session will conclude with a preview of upcoming GPU programming technologies.

Stephen Jones (NVIDIA)

Stephen Jones is a principal software engineer in the CUDA group at NVIDIA, working on making the CUDA language and programming model span the needs of parallel programming from high performance computing to artificial intelligence. Previously, Stephen led the simulation and analytics group at SpaceX, where he worked on various projects, including large-scale simulation of combustion processes in rocket engines. His background is in computational fluid mechanics and plasma physics, but he has worked in diverse, industries including networking, CAD/CAM, and scientific computing.

AWS & NVIDIA: Fast and Furious Innovation in Computing and Visualization
Tuesday, November 14 | GPU Technology Theater | 10:30am - 10:50am

On October 26, 2017 AWS launched P3, the first instances to include NVIDIA Tesla V100 GPUs and the most powerful GPU instances available in the cloud. These instances are designed for compute-intensive applications that require massive parallel floating point performance, including machine learning, computational fluid dynamics, computational finance, seismic analysis, molecular modeling, genomics, and autonomous vehicle systems. We'll talk about how these instances help AWS customers innovate and accelerate their workloads, and how NVIDIA and AWS are making new exciting use cases possible in the Cloud, both for High Performance Computing and advanced 3D Visualization.

Brendan Bouffler (Amazon Web Services)

Brendan Bouffler has 25 years of experience in the global tech industry creating very large systems in high performance environments. He has been responsible for designing and building hundreds of HPC systems for commercial enterprises as well as research and defense sectors all around the world and has quite a number of his efforts listed in the top500, including some that have placed in the top 5. Brendan previously lead the HPC Organization in Asia for a hardware maker but joined Amazon in 2014 to accelerate the adoption of cloud computing in the scientific community globally, and is the author of the Research’s Handbook –the missing manual for research workloads on AWS. He holds a degree in Physics and an interest in testing several of its laws as they apply to bicycles. This has frequently resulted in hospitalization.

HPC Opportunities in Deep Learning
Tuesday, November 14 | GPU Technology Theater | 1:00pm - 1:30pm

This year we have seen a single deep learning algorithm, Deep Speech, learn to recognize two vastly different languages, English and Mandarin. At Baidu, we think that this is just the beginning, and high performance computing is poised to help.

Greg Diamos(Baidu)

Greg Diamos is a senior researcher at Baidu’s Silicon Valley AI Lab (SVAIL). Previously he was on the research team at NVIDIA. Greg holds a PhD from the Georgia Institute of Technology, where he contributed to the development of the GPU-Ocelot dynamic compiler, which targeted CPUs and GPUs from the same program representation.

Adapting Deep Learning to New Data Using ORNL's Titan Supercomputer
Tuesday, November 14 | GPU Technology Theater | 11:00am - 11:20am

There has been a surge of success in using deep learning as it has provided a new state of the art for a variety of domains. While these models learn their parameters through data-driven methods, model selection through hyper-parameter choices remains a tedious and highly intuition-driven task. We've developed two approaches to address this problem. Multi-node evolutionary neural networks for deep learning (MENNDL) is an evolutionary approach to performing this search. MENNDL is capable of evolving not only the numeric hyper-parameters, but is also capable of evolving the arrangement of layers within the network. The second approach is implemented using Apache Spark at scale on Titan. The technique we present is an improvement over hyper-parameter sweeps because we don't require assumptions about independence of parameters and is more computationally feasible than grid-search.

Travis Johnston (Oak Ridge National Lab)

Travis Johnston is a research associate with the Computational Data Analytics group at Oak Ridge National Laboratory. Travis earned his Ph.D. in mathematics from the University of South Carolina in 2014. Since then, he as focused on machine learning and high performance computing working in the Global Computing lab at the University of Delaware.

Converging HPC and BD/AI: Tokyo Tech. TSUBAME3.0 and AIST ABCI
Wednesday, November 15 | GPU Technology Theater | 11:30am - 11:50pm

The TSUBAME3 supercomputer at Tokyo Institute of Technology became online in Aug. 2017, and became the greenest supercomputer in the world on the Green 500 at 14.11 GFlops/W; the other aspect of TSUBAME3, is to embody various BYTES-oriented features to allow for HPC to BD/AI convergence at scale, including significant scalable horizontal bandwidth as well as support for deep memory hierarchy and capacity, along with high flops in low precision arithmetic for deep learning.

TSUBAME3's technologies are commoditized to construct one of the world’s largest BD/AI focused open and public computing infrastructure called ABCI (AI-Based Bridging Infrastructure), hosted by AIST-AIRC (AI Research Center), the largest public funded AI research center in Japan, at 550 AI-Petaflops, with acceleration in I/O and other data-centric properties desirable for accelerating BD/AI, to be online 1H2018.

Satoshi Matsuoka (Tokyo Tech)

Satoshi Matsuoka has been a Full Professor at the Global Scientific Information and Computing Center (GSIC), a Japanese national supercomputing center hosted by the Tokyo Institute of Technology, and since 2016 a Fellow at the AI Research Center (AIRC), AIST, the largest national lab in Japan, as well as becoming the head of the joint Lab RWBC-OIL (Open Innovation Lab on Real World Big Data Computing) between the two institutions, in 2017. He is the leader of the TSUBAME series of supercomputers, and has won the 2014 IEEE-CS Sidney Fernbach Memorial Award, the highest prestige in the field of HPC.

Bridges: A Pittsburgh Supercomputing Center Resource - A Converged HPC & Big Data System for Nontraditional and HPC Research
Tuesday, November 14 | GPU Technology Theater | 11:30am - 12:00pm

TBA

Ishtar Nyawira (University of Pittsburgh)

Ishtar Nyawira ’18 is a 4th year computer science major at the University of Pittsburgh. Upon entering her freshman year, she chose to study biology but quickly grew interested in computer science, despite having little background in the field. After changing her major in her 3rd year, she became wholly dedicated to educating herself inside and outside of the classroom in the fields of computer science. After she graduates with a BS degree in computer science and a minor in Korean language, she will pursue a PhD in machine learning or computer science.

Currently, she is working at the Pittsburgh Supercomputing Center on a machine learning project that will harness the power of deep learning to automate the process of high resolution biomedical image annotation. Her current research interests include but are not limited to machine learning and deep learning, natural language processing and computational linguistics, software engineering, biological modeling and simulation, and the pairing of HPC and AI.

NVIDIA Developer Tools: New Capabilities in CUDA 9
Tuesday, November 14 | GPU Technology Theater | 11:30am - 11:50am

NVIDIA provides powerful developer tools for debugging and profiling GPU-accelerated applications. The latest version, CUDA 9, provides new capabilities to help optimize unified memory usage in applications and profile NVLink efficiently. We will briefly introduce new capabilities in CUDA 9 followed by a peek at upcoming technologies.

Sanjiv Satoor (NVIDIA)

Sanjiv Satoor manages the CUDA Profiling Tools team at NVIDIA in India.

Application Readiness Projects for the Summit Architecture
Tuesday, November 14 | GPU Technology Theater | 12:30pm - 12:50pm

The Oak Ridge Leadership Computing Facility (OLCF) in partnership with the IBM/NVIDIA Center of Excellence and scientific application developers is preparing a suite of scientific codes for its user programs. The Center for Accelerated Application Readiness (CAAR) projects are using an Early Access Power8+/Pascal system named SummitDev to prepare for the Power9/Volta system Summit. This presentation highlights achievements on this system, and the experience of the teams that will be a valuable resource for other development teams.

Tjerk P. Straatsma, (Oak Ridge National Lab)

Dr. Tjerk P. Straatsma is an internationally recognized scientist with more than 30 years of experience in the development, efficient implementation and application of advanced modeling and simulation methods as key scientific tools in the study of chemical and biomolecular systems, complementing analytical theories and experimental studies. Dr. Straatsma joined Oak Ridge National Laboratory in 2013, where he manages the Scientific Computing group in the National Center for Computational Sciences. This center is the site for the Oak Ridge Leadership Computing Facility and houses the largest supercomputer for open science in the United States.

ADAC: Accelerated Data Analytics and Computing Institute (Panel)
Tuesday, November 14 | GPU Technology Theater | 3:00pm - 3:50pm

TBA

Moderator: Jack Wells (ORNL)
Panelists: Thomas Schulthess (CSCS), Satoshi Matsuoka (Tokyo Tech), Jeff Nichols (ORNL)

TBA

Sierra: The LLNL IBM CORAL System
Tuesday, November 14 | GPU Technology Theater | 1:30pm - 1:50pm

Lawrence Livermore National Laboratory (LLNL) has a long history of leadership in large-scale computing. Our next platform, Sierra, a heterogeneous system that will be sited as part of a Collaboration between Oak Ridge, Argonne and Lawrence Livermore National Laboratories (CORAL) and delivered through a partnership with IBM, NVIDIA and Mellanox, will continue that tradition. That partnership has reached a key milestone that has begun the siting of Sierra as well as the Summit System at ORNL. This talk will provide a detailed look at the design of Sierra. It will compare and contrast Sierra to Summit, explaining the motivation for the design choices of each system. It will also preview some early uses of Sierra that target its technical opportunities and the challenges that accompany them.

Bronis de Supinski (Lawrence National Lab)

As Chief Technology Officer (CTO) for Livermore Computing (LC) at Lawrence Livermore National Laboratory (LLNL), Bronis R. de Supinski formulates LLNL's large-scale computing strategy and oversees its implementation. His frequently interacts with supercomputing leaders and oversees many collaborations with industry and academia. Previously, Bronis led several research projects in LLNL's Center for Applied Scientific Computing. He earned his Ph.D. in Computer Science from the University of Virginia in 1998 and he joined LLNL in July 1998. In addition to his work with LLNL, Bronis is also a Professor of Exascale Computing at Queen's University of Belfast and an Adjunct Associate Professor in the Department of Computer Science and Engineering at Texas A&M University. Throughout his career, Bronis has won several awards, including the prestigious Gordon Bell Prize in 2005 and 2006, as well as an R&D 100 for his leadership in thedevelopment of a novel scalable debugging tool.

GPUs for Sustained Computational and Analytics Research on the Blue Waters Extreme Scale Systems
Tuesday, November 14 | GPU Technology Theater | 2:00pm - 2:30pm

The "sustained Petascale" Blue Waters Supercomputer is the most powerful and productive supercomputer serving the entire academic and open science communities and the largest system Cray has ever created. Blue Waters is enabling "grand challenge" solutions for problems ranging from HIV and Ebola virus, to earthquake analysis, to severe weather, to the search for gravitational waves to the economics of climate change policy. The talk will discuss the architectural decisions for Blue Waters to include GPUs, cover experiences advanced research teams have using GPUs, highlight some of the efforts underway to expand the use of GPUs and then draw observations for future generation systems.

William Kramer (Blue Waters Director and Principle Investigator; Computer Science Research Professor, National Center for Supercomputing Applications at the University of Illinois at Urbana Champaign)

William T.C. Kramer is the Principal Investigator and Project Director for the Blue Waters Leadership Computing Project at the National Center for Supercomputing Applications. Blue Waters is a National Science Foundation-funded project, to deploy the first general purpose, open science, sustained-petaflops supercomputer as a powerful resource for the nation's researchers.

Overview of HPC and Energy Saving on Nvidia's V100 for Some Computations
Thursday, November 16 | GPU Technology Theater | 10:30am - 10:50am

In this talk we will look at the current state of high performance computing and look to the future toward exascale. In addition, we will examine some issues that can help in reducing the power consumption for linear algebra computations.

Jack Dongarra (University of Tennessee)

TBA

Large Scale Deep Learning on Sierra Early Access Systems
Wednesday, November 15 | GPU Technology Theater | 12:00pm – 12:20pm

TBA

Brian Van Essen (Lawrence Livermore National Lab)

Brian is Computer Scientist at the Center for Applied Scientific Computing at Lawrence Livermore National Laboratory (LLNL). He is actively pursuing research in training deep neural networks on high-performance computing systems. His research interests also include developing new Operating Systems and Runtimes (OS/R) that exploit persistent memory architectures, including distributed and multi-level non-volatile memory hierarchies, for high-performance, data-intensive computing. Additionally, he is interested in opportunities related to mapping these scientific, data-intensive, and machine learning applications to Neuromorphic architectures. Dr. Van Essen joined LLNL in October of 2010 after earning his Ph.D. in Computer Science and Engineering from the University of Washington in Seattle. He also holds a M.S in Computer Science and Engineering from the University of Washington, a M.S in Electrical and Computer Engineering from Carnegie Mellon University, and a B.S. in Electrical and Computer Engineering from Carnegie Mellon University.

Deep Learning for Scientific Discovery
Tuesday, November 14 | GPU Technology Theater | 4:30pm - 4:50pm

Big science has often been accompanied by big data, but scientists have often been stymied by the best way to leverage their data-rich observations. By combining advanced scientific computing with cutting edge deep learning, we have been able to broadly apply deep learning through-out our scientific mission. From high energy physics to computational chemistry to cyber-security, we are enhancing the pace and impact of diverse scientific disciplines by bringing together domain scientists and deep learning researchers across our laboratory. We are seeing in field after field, deep learning is driving transformational innovation, opening the door to a future of data-driven scientific discovery.

Courtney Corley (Pacific Northwest National Lab)

Dr. Courtney D. Corley is a Senior Data Scientist and team lead at the Pacific Northwest National Laboratory (PNNL). He is a leader in the field of data science and biosurveillance for his foundational work in social media analytics, computational epidemiology, and natural language processing. His data science acumen centers on the development of transformational deep learning and narrow AI methods which provide scientific insight into multi-scale unstructured and semi-structured data streams. At PNNL he also leads the Deep Learning for Scientific Discovery Initiative.

Synthesis Models: Combining HPC Simulation with the Power of Machine Learning
Tuesday, November 14 | GPU Technology Theater | 5:00pm - 5:20pm

Researchers have begun putting Machine Learning to work solving problems that do not lend themselves well to traditional numerical analysis, or that require unaffordable computational capacity. This talk with discuss three primary approaches being used today, and will share some case studies that show significant promise of lower latency, improved accuracy, and lower cost.

Karl Freund (Moor Insights & Strategy)

Karl Freund has spent his career leading organizations in the server and semiconductor industries, working at HPE, IBM, CRAY, SGI, Calxeda, and AMD. Most recently, as the General Manager of AMD’s HPC business, he became fascinated by the potential of Deep Learning in Artificial Intelligence to improve our lives and businesses. Now at the analyst firm of Moor Insights & Strategy, he helps clients understand and communicate the potential of Deep Learning and HPC.

Karl holds a bachelors degree from Texas A&M University in Applied Mathematics, and a Masters of Computer Science from the University of North Carolina at Chapel Hill.

"Programming Massively Parallel Processors" Book and GPU Teaching Kit: New 3rd Edition!
Tuesday, November 14 | GPU Technology Theater | 5:00pm - 5:30pm

Introducing the 3rd Edition of "Programming Massively Parallel Processors – a Hands-on Approach". This new edition is the result of a collaboration between GPU computing experts and covers the CUDA computing platform, parallel patterns, case studies and other programming models. Brand new chapters cover Deep Learning, graph search, sparse matrix computation, histogram and merge sort.
The tightly-coupled GPU Teaching Kit contains everything needed to teach university courses and labs with GPUs.

Joe Bungo (GPU Educators Program Manager, NVIDIA)

Joe Bungo is the GPU Educators Program Manager at NVIDIA where he enables the use of GPU technologies in universities, including curriculum and teaching material development, facilitation of academic ecosystems, and hands-on instructor workshops. Previously, he managed university programs at ARM Inc. and worked as an applications engineer. Joe received his degree in Computer Science from the University of Texas at Austin.

Programming GPU-based Extreme-Scale HPC Systems: OpenSHMEM and SharP
Tuesday, November 14 | GPU Technology Theater | 5:30pm - 5:50pm

This talk will introduce two programming models OpenSHMEM and SharP to address the programming challenges of HPC systems with multiple GPUs per node, high-performing network, and huge amount of hierarchical heterogeneous memory. SharP uses distributed data-structure approach to abstract the memory and provide uniform interfaces for data abstractions, locality, sharing and resiliency across these memory systems. OpenSHMEM is a well-established library based PGAS programming model for programming HPC systems. We show how NVSHMEM, an implementation of OpenSHMEM, can enable communication in the CUDA kernels and realize OpenSHMEM model for GPU-based HPC systems. These two complementary programming models provide ability to program emerging architectures for Big-Compute and Big-Data applications. After the introduction, we will present experimental results for a wide-variety of applications and benchmarks.

Manju Venkata (Oak Ridge National Lab)

Manjunath Gorentla Venkata is a research scientist at Oak Ridge National Laboratory's computer science group. His area of expertise is programming models and communication libraries for HPC systems. He has researched, designed and developed a number of novel and high-performing communication middleware for HPC systems, including Cray and InfiniBand systems. At ORNL, he was responsible for the development of the collective communications for extreme-scale systems (CORE-Direct and Cheetah/MPI), OpenSHMEM, UCCS, and SharP projects. Dr. Gorentla Venkata has published over 48 peer-reviewed research articles and contributed to international standards in this area. He serves as an OpenSHMEM specification committee secretary, and chairs OpenSHMEM multithreading working group. Additionally, he is engaged in DOE's CORAL, Design Forward, and Path Forward programs. He is the recipient of 2015 R&D 100 award for his contributions to the CORE-Direct technology.

Moving applications to complex architectures through collaborative hackathons
Wednesday, November 15 | GPU Technology Theater | 5:30pm - 5:50pm

Porting or developing applications for complex architecture such as hybrid GPUs can be difficult to get started. The initial steps or fraught with bugs and lack of familiarity with frameworks and hardware. This talk will discuss how a collaborative sprint can be used to accelerate the initial port to a new architecture. Collaborative hackathons have been successfully used as a training device for porting applications to OLCF‘s supercomputers like Titan and Summit Dev. These events give developers an opportunity to sprint through early porting pains and gain rapid familiarity with new computing tools, increasing the likelihood that the application will be ported successfully after the training event ends.

Fernanda Foertter (Oak Ridge National Lab)

 

The DOE and NCI Partnership on Precision Oncology and the Cancer Moonshot
Tuesday, November 14 | GPU Technology Theater | 2:30pm - 2:50pm

The Cancer Moonshot was established in 2016 with the goal to double the rate of progress in cancer research -- to do in five years what normally would take 10. A major area for the acceleration of progress is the strategy to use modeling, simulation, and machine learning to advance our understanding of cancer biology and to integrate what is known into predictive models that can inform research and guide therapeutic developments. In 2015, the U.S. Department of Energy formed a collaboration with the National Cancer Institute for the joint development of advanced computing solutions for cancer.

Fangfang Xia (Argonne National Lab)

Fangfang Xia received his Ph.D. in Computer Science from the University of Chicago. His research combines genomics, machine learning and high performance computing to design efficient algorithms and systems for biomedical analysis.

Accelerating HPC Programmer Productivity with OpenACC and CUDA Unified Memory
Wednesday, November 15 | GPU Technology Theater | 10:30am - 10:50am

CUDA Unified Memory for NVIDIA Tesla GPUs offers programmers a unified view of memory on GPU-accelerated compute nodes. The CPUs can access GPU high-bandwidth memory directly, the GPUs can access CPU main memory directly, and memory pages migrate automatically between the two when the CUDA Unified Memory manager determines it is performance-profitable. PGI OpenACC compilers now leverage this capability on allocatable data to dramatically simplify parallelization and incremental optimization of HPC applications for GPUs. In the future it will extend to all types of data, and programmer-driven data management will become an optimization rather than a requirement. This talk will summarize the current status and near future of OpenACC programming and optimization for GPU-accelerated compute nodes with CUDA Unified Memory.

Doug Miles(NVIDIA)

Doug Miles runs the PGI compilers & tools team at NVIDIA. He has worked in HPC for over 30 years in math library development, benchmarking, programming model development, technical marketing and software engineering management at Floating Point Systems, Cray Research Superservers, The Portland Group, STMicroelectronics and NVIDIA.

Red + Green = Great HPC
Wednesday, November 15 | GPU Technology Theater | 11:00am - 11:20am

 

Lee Gates (Oracle)

Lee leads performance focused research for Oracle Cloud Infrastructure. He has worked in many engineering and business disciplines at Microsoft, NetApp, and Oracle. The area of current research is focused on studying distributed systems and public cloud, migrations, and application modernization.

TBA
Wednesday, November 15 | GPU Technology Theater | 11:30am – 12:00 pm

TBD

TBD (TBD, TBD)

TBD

HPC Exascale & AI
Wednesday, November 15 | GPU Technology Theater | 12:00 pm – 12:20 pm

HPC is a fundamental pillar of modern science. From predicting weather to discovering drugs to finding new energy sources, researchers use large computing systems to simulate and predict our world. AI extends traditional HPC by letting researchers analyze massive amounts of data faster and more effectively. It’s a transformational new tool for gaining insights where simulation alone cannot fully predict the real world.

Steve Oberlin(NVIDIA)

Steve Oberlin is responsible for NVIDIA's Tesla roadmap and architecture. Tesla GPUs are NVIDIA's flagship processors for high performance computing, delivering extreme parallel processing, unrivaled processing power, and world-leading efficiency. They are playing a critical part in the race to build exascale computers to tackle the world’s most complex computational challenges in science and industry.

HPC Exascale & AI Panel
Wednesday, November 15 | GPU Technology Theater | 12:30pm - 1:20pm

TBA

Moderator: Tom Gibbs(NVIDIA),
Panelists: Ian Foster (Argonne National Lab), Rich Loft (NCAR), Chris Hill (MIT)

TBA

Rapid Computation of Permeability from Micro-CT Images on GPGPUs
Wednesday, November 15 | GPU Technology Theater | 1:30pm – 1:50pm

Digital Rock Physics (DRP) technology is rapidly evolving with many promises, including fast turnaround times for repeatable core analysis and multi-scale multi-physics simulation of rock properties. We develop and validate a rapid and scalable distributed-parallel single-phase pore-scale flow simulator for permeability estimation on real 3D pore-scale micro-CT images using a novel variant of the lattice Boltzmann method (LBM). The LBM code implementation takes maximum advantage of distributed computing on multiple General-Purpose Graphical Processing Units (GPGPUs) to accelerate the simulations on images that contain multiple billions of voxels and exhibits excellent parallel scalability.

F. Omer Alpak (Shell)

F. Omer Alpak is a Senior Research Reservoir Engineer in the Upstream Computational Science Team of Shell and an Adjunct Associate Professor in the Rice University, Computational and Applied Mathematics Department. Omer joined Shell in 2005 and has been developing/applying novel multi-scale multi-physics reservoir simulation, computational fluid dynamics, and inversion techniques to Shell’s business problems. Alpak is the recipient of the SPE A Peer Apart Award in 2016, SPE Journal Outstanding Associate Editor Award in 2008, and the Best Paper Award from the SPWLA Petrophysics Journal in 2003 and 2006. He holds M. Sc. and Ph. D. degrees in Petroleum Engineering from The University of Texas at Austin.

Rapid Computation of Permeability from Micro-CT Images on GPGPUs
Wednesday, November 15 | GPU Technology Theater | 1:30pm – 1:50pm

Digital Rock Physics (DRP) technology is rapidly evolving with many promises, including fast turnaround times for repeatable core analysis and multi-scale multi-physics simulation of rock properties. We develop and validate a rapid and scalable distributed-parallel single-phase pore-scale flow simulator for permeability estimation on real 3D pore-scale micro-CT images using a novel variant of the lattice Boltzmann method (LBM). The LBM code implementation takes maximum advantage of distributed computing on multiple General-Purpose Graphical Processing Units (GPGPUs) to accelerate the simulations on images that contain multiple billions of voxels and exhibits excellent parallel scalability.

Mauricio Araya-Polo (Shell)

Mauricio Araya-Polo is a Senior Research Computer Science in the Upstream Computational Science Team of Shell and an Adjunct Associate Professor in the Rice University, Computational and Applied Mathematics Department.He is currently leading efforts on diverse areas such as: Seismic Imaging/Modeling and Compressive Sensing/Machine Learning. He is also adjunct professor of the Computational and Applied Mathematics department at Rice University. Previously, he worked for Repsol USA researching on near real-time visualization/computing HPC geophysical algorithms. Before that position, he worked at the Barcelona Supercomputing Center for the well-known Kaleidoscope project. He holds M. Sc. and Ph. D. degrees in Computer Science from UNSA-INRIA.

Accelerated compute in Azure using GPUs
Wednesday, November 15 | GPU Technology Theater | 2:00pm - 2:20pm

Azure N-series VMs powered by NVIDIA GPUs enable a range of new accelerated scenarios. Learn how you can take advantage of different GPUs offerings in Microsoft Azure to accelerate your scenarios like ray traced rendering, machine learning, remote visualization, etc…

Tariq Sharif (Microsoft)

Tariq Sharif is a Principal Program Manager at Microsoft and owns the GPU offerings line for Azure. Prior to Azure he worked in Office 365, Active Directory and Internet Explorer teams.

An Agile Approach to Building a GPU-enabled and Performance-portable Global Cloud-resolving Atmospheric Model
Wednesday, November 15 | GPU Technology Theater | 2:30pm - 2:50pm

"The strategy of the National Center for Atmospheric Research (NCAR) for supporting its earth system modelers is through the development of community codes - applications that are not only freely downloadable but also contain components developed by a distributed group of contributing authors. Users of community models expect them to not only work, but to also run well on a variety of platforms, particularly the ones chosen by their home institutions. The divergence of computer architectures that occurred with the introduction of heterogeneous systems with accelerators, such as GPUs) has made the issue of achieving performance portability for community models quite challenging. The time required to optimize code also play well with the neither complexity of the code nor the codes complexity. Thus the objectives of NCAR's exploration of accelerator architectures for high performance computing in recent years has been to 1) speed up the rate of code optimization and porting and 2) understand how to achieve performance portability on codes in the most economical and affordable way.

In this talk I will give a high-level overview of the results of these efforts, and how we built a cross-organizational partnership to achieve them. Ours is a directive-based approach using OMP and OpenACC to achieve portability. We have focused on achieving good performance on three main architectural branches available to us, namely: traditional multi-core processors (e.g. Intel Xeons), many core processors like the Intel Xeon Phi, and of course NVIDIA GPUs. Our focus has been on creating tools for accelerating the optimization process, techniques for effective cross-platform optimization, and methodologies for characterizing and understanding performance. The results are encouraging, suggesting a path forward based on standard directives for responding to the pressures of future architectures. "

Richard Loft (National Center for Atmospheric Research)

TBA

An Approach to Developing MPAS on GPUs
Wednesday, November 15 | GPU Technology Theater | 3:00pm – 3:20pm

MPAS-A is a general circulation (global) model of the Earth’s atmosphere that is designed to work down to so-called non-hydrostatic scales where convective (vertical) cloud processes are resolved. To date MPAS-A has been used primarily for meteorological research applications, although climate applications in the Community Earth System Model (CESM) are being contemplated. At a high level, MPAS-A consists of a dynamics part, a fluid flow solver that integrates the non-hydrostatic time dependent nonlinear partial differential equations of the atmosphere, and a physics part, which computes the forcings of these equations due to radiative transport, cloud physics, and surface and near surface processes. The dynamics is in turn divided into the dry dynamics and moist dynamics parts. Algorithmically, the dynamics uses a Finite Volume (FV) method on an unstructured centroidal Voronoi mesh (grid, or tessellation) with a C-grid staggering of the state variables as the basis for the horizontal discretization.As a part of NCAR's Weather and Climate Alliance (WACA) project, a team consisting of NCAR staff, faculty and students at the University of Wyoming, and group of NVIDIA & NVIDIA PGI developers, developed a portable and multi-GPU implementation of the dry dynamical core using OpenACC. The work began in May 2016 and was completed in May 2017. Benchmarks of the OpenACC version (single source code) of the dry dynamical core (approximately 35,000 lines of code) on the Pascal GPU show that a single P100 is 2.7 times faster than a dual socket node composed of 18-core per socket Intel Xeon E5-2697V4 “Broadwell” processors. Put another way, the ported dry dynamics achieves a P100 performance that is 97 times the performance of a single Intel Xeon v4 core, while simultaneously maintaining good performance of the source on traditional Xeon architectures. The WACA team, along with a new collaboration with Korean Institute of Science and Technology Information (KISTI), is currently porting moist dynamics and physics parts of MPAS-A.

Raghu Raj Prasanna Kumar (National Center for Atmospheric Research(NCAR))

TBA

Alexa: Simulating Shock Hydrodynamics on the GPU using Kokkos - Getting real with multi-material mechanics and adaptivity
Wednesday, November 15 | GPU Technology Theater | 3:30pm - 3:50pm

We present the Alexa shock hydrodynamics code, built using Kokkos, and its performance on hardware including Intel KNL and NVIDIA P100 (which is twice as fast). Alexa performs 3D simulations of multiple materials undergoing large deformation at large energies. Part of the goal of Alexa is to bring complex simulations onto laptops for users.

H. Carter Edwards (Sandia National Lab)

H. Carter Edwards is currently the PI and architect for the Kokkos project (github.com/kokkos/kokkos) at Sandia National Laboratories. Carter has a BS and MS in Aerospace Engineering and PhD in Computational Mathematics. He has over three decades of experience in modeling & simulation software development and over two decades of experience in HPC, parallel processing, and C++ software development. His recent (8 year) HPC focus is on algorithms and programming models for thread-scalable and performance portable parallelism across next generation platform (NGP) node architectures. Carter represents Sandia on the ISO C++ language standard committee.

Alexa: Simulating Shock Hydrodynamics on the GPU using Kokkos - Getting real with multi-material mechanics and adaptivity
Wednesday, November 15 | GPU Technology Theater | 3:30pm - 3:50pm

We present the Alexa shock hydrodynamics code, built using Kokkos, and its performance on hardware including Intel KNL and NVIDIA P100 (which is twice as fast). Alexa performs 3D simulations of multiple materials undergoing large deformation at large energies. Part of the goal of Alexa is to bring complex simulations onto laptops for users.

Dan Ibanez (Sandia National Lab)

Dan Ibanez received his BS and PhD in Computer Science from Rensselear Polytechnic institute, then joined Sandia National Laboratories in 2016. His main research interests are simplex mesh adaptation, performance portability, and multi-physics code design. He is the sole developer of the open-source mesh adaptation library Omega_h (github.com/ibaned/omega_h), a developer of the Alexa application, and a developer of the Kokkos framework.

MVAPICH2-GDR Library: Pushing the Frontier of HPC and Deep Learning
Wednesday, November 15 | GPU Technology Theater | 4:00pm - 4:20pm

The talk will focus on the latest developments in MVAPICH2-GDR MPI library that helps HPC and Deep Learning applications to exploit maximum performance and scalability on GPU clusters. Multiple designs focusing on GPUDirect RDMA (GDR), GPUDirect Async (GDS), Managed and Unified memory support, and datatype processing will be highlighted for HPC applications. We will also present novel designs and enhancements to the MPI library to boost performance and scalability of Deep Learning frameworks on GPU clusters.

DK Panda (Ohio State University)

Dhabaleswar K. (DK) Panda is a Professor and University Distinguished Scholar of Computer Science at the Ohio State University. The MVAPICH2 (High-Performance MPI over InfiniBand, Omni-Path, iWARP and RoCE) libraries, developed by his research group (http://mvapich.cse.ohio-state.edu), are currently being used by more than 2,800 organizations in 85 countries. More than 427,000 downloads of these libraries have taken place from the project's website. He is an IEEE Fellow and a member of ACM.

Why Google Cloud + NVIDIA: Benefits of using NVIDIA Tesla P100 & K80 GPUs on Google Cloud Platform
Wednesday, November 15 | GPU Technology Theater | 4:30pm - 4:50pm

TBA

Chris Kleban (Google)

TBA

Enabling AI with Innovative HPC System Design
Wednesday, November 15 | GPU Technology Theater | 5:00pm - 5:20pm

Artificial intelligence, specifically deep learning, is rapidly becoming an important workload within the High Performance Computing space. This talk will present a couple successful systems design approaches HPE has provided customers to help them enable AI and deep learning within their HPC ecosystem.

Mark Simpkins (HPE)

Mark Simpkins is a product marketing manager with HPE on a team focused on AI and HPC. Prior to joining HPE as part of the Company’s acquisition of SGI, Mark was product manager for Accelerators across the SGI system portfolio.

Deep Learning Everywhere, For Everyone: NVIDIA GPU Cloud
Tuesday, November 14 | GPU Technology Theater | 10:00pm - 10:20pm

NVIDIA GPU Cloud (NGC) is a GPU-accelerated platform that runs everywhere. NGC manages a catalog of fully integrated and optimized deep learning framework containers that are composed, tested, and tuned by NVIDIA to take full advantage of NVIDIA Volta™ powered infrastructure in the cloud or on-premises, providing massive deep learning performance and flexibility for analytics, research, and data science. In this session, you will learn how NGC can make it easier for you to get up and running with AI and deep learning.

Greg Crider (NVIDIA)

Greg Crider is Senior Product Manager for GPU Cloud at NVIDIA. Before joining NVIDIA, he spent over 15 years at Oracle and SAP as a senior contributor to their global cloud infrastructure, integrated systems, and enterprise software product management and product marketing. Before joining SAP, Crider was Vice President of Product Management and Product Marketing at Viador, a pioneer in web-based business intelligence and enterprises portals.

Inside SATURNV – Insights from NVIDIA’s Deep Learning Supercomputer
Thursday, November 16 | GPU Technology Theater | 1:00pm - 1:20pm

Like its namesake, NVIDIA DGX SATURNV is yielding insights that have far-reaching impact, helping us build the best AI architecture for every enterprise. In this talk, we describe the architecture of SATURNV, and how we use it every day at NVIDIA to run our deep learning workloads for both production and research use cases. We explore how the NVIDIA GPU Cloud software is used to manage and schedule work on SATURNV, and how it gives us the agility to rapidly respond to business-critical projects. We also present some of the results of our research in operating this unique GPU-accelerated data center.

Phil Rogers (NVIDIA)

Phil Rogers is the lead architect for Compute Server Software at NVIDIA. Phil has been working in accelerated computing for the past 7 years with a focus on performance, scalability and ease of use.

Rapid Computation of Permeability from Micro-CT Images on GPGPUs
Thursday, November 16 | GPU Technology Theater | 11:00am - 11:20am

Digital Rock Physics (DRP) technology is rapidly evolving with many promises, including fast turnaround times for repeatable core analysis and multi-scale multi-physics simulation of rock properties. We develop and validate a rapid and scalable distributed-parallel single-phase pore-scale flow simulator for permeability estimation on real 3D pore-scale micro-CT images using a novel variant of the lattice Boltzmann method (LBM). The LBM code implementation takes maximum advantage of distributed computing on multiple General-Purpose Graphical Processing Units (GPGPUs) to accelerate the simulations on images that contain multiple billions of voxels and exhibits excellent parallel scalability.

F. Omer Alpak (Shell)

F. Omer Alpak is a Senior Research Reservoir Engineer in the Upstream Computational Science Team of Shell and an Adjunct Associate Professor in the Rice University, Computational and Applied Mathematics Department. Omer joined Shell in 2005 and has been developing/applying novel multi-scale multi-physics reservoir simulation, computational fluid dynamics, and inversion techniques to Shell’s business problems. Alpak is the recipient of the SPE A Peer Apart Award in 2016, SPE Journal Outstanding Associate Editor Award in 2008, and the Best Paper Award from the SPWLA Petrophysics Journal in 2003 and 2006. He holds M. Sc. and Ph. D. degrees in Petroleum Engineering from The University of Texas at Austin.

Rapid Computation of Permeability from Micro-CT Images on GPGPUs
Thursday, November 16 | GPU Technology Theater | 11:00am - 11:20am

Digital Rock Physics (DRP) technology is rapidly evolving with many promises, including fast turnaround times for repeatable core analysis and multi-scale multi-physics simulation of rock properties. We develop and validate a rapid and scalable distributed-parallel single-phase pore-scale flow simulator for permeability estimation on real 3D pore-scale micro-CT images using a novel variant of the lattice Boltzmann method (LBM). The LBM code implementation takes maximum advantage of distributed computing on multiple General-Purpose Graphical Processing Units (GPGPUs) to accelerate the simulations on images that contain multiple billions of voxels and exhibits excellent parallel scalability.

Mauricio Araya-Polo (Shell)

Mauricio Araya-Polo is a Senior Research Computer Science in the Upstream Computational Science Team of Shell and an Adjunct Associate Professor in the Rice University, Computational and Applied Mathematics Department.He is currently leading efforts on diverse areas such as: Seismic Imaging/Modeling and Compressive Sensing/Machine Learning. He is also adjunct professor of the Computational and Applied Mathematics department at Rice University. Previously, he worked for Repsol USA researching on near real-time visualization/computing HPC geophysical algorithms. Before that position, he worked at the Barcelona Supercomputing Center for the well-known Kaleidoscope project. He holds M. Sc. and Ph. D. degrees in Computer Science from UNSA-INRIA.

Inside Volta
Thursday, November 16 | GPU Technology Theater | 1:30pm - 1:50pm

The NVIDIA Volta architecture powers the world’s most advanced data center GPU for AI, HPC, and Graphics. Features like Independent Thread Scheduling and game-changing Tensor Cores enable Volta to simultaneously deliver the fastest and most accessible performance of any comparable processor. Join two lead hardware and software architects for Volta on a tour of the features that will make Volta the platform for your next innovation in AI and HPC supercomputing.

Stephen Jones (NVIDIA)

Stephen Jones is a principal software engineer in the CUDA group at NVIDIA, working on making the CUDA language and programming model span the needs of parallel programming from high performance computing to artificial intelligence. Previously, Stephen led the simulation and analytics group at SpaceX, where he worked on various projects, including large-scale simulation of combustion processes in rocket engines. His background is in computational fluid mechanics and plasma physics, but he has worked in diverse, industries including networking, CAD/CAM, and scientific computing.

Visualization on GPU Accelerated Supercomputers
Thursday, November 16 | GPU Technology Theater | 11:30am - 11:50am

This talk is a summary about the ongoing HPC visualization activities, as well as a description of the technologies behind the developer-zone shown in the booth.

Peter Messmer (NVIDIA)

Peter Messmer is a principal software engineer in NVIDIA's Developer Technology organization, working with clients to accelerate their scientific discovery process with GPUs. One area of his current research is to investigate how to utilize the GPUs in high performance computing systems for data analysis and visualization.

NVIDIA Enables Faster HPC Application Deployment
Thursday, November 16 | GPU Technology Theater | 12:00pm - 12:20pm

 

Ryan Olson (NVIDIA)

TBA

TBA
Thursday, November 16 | GPU Technology Theater | 10:00am - 10:20am

 

Francois romain Corradino (Lenovo)

TBA

Enterprise Ready Deep Learning
Thursday, November 16 | GPU Technology Theater | 12:30pm - 12:50pm

Addressing the top inhibitors delaying the implementation of Deep Learning solutions. A discussion of new software and hardware solutions from IBM that make accelerated deep learning easier, safer and faster; delivering maximum business value.

Adel El-hallak (IBM)

Adel El-Hallak is the Director of Product Management for Deep Learning within IBM’s Cognitive Systems unit. Adel’s mission is to democratize and operationalize deep learning so it can be more easily consumed in order to augment human intelligence. Adel’s previous roles include leadership positions across sales and marketing for high performance computing and advanced analytics. Adel holds a bachelor’s degree in computer science from McGill University in Canada and an M.B.A. from Warwick Business School in the U.K.

High Performance Inferencing with TensorRT
Thursday, November 16 | GPU Technology Theater | 2:00pm - 2:20pm

This talk will introduce the TensorRT Programmable Inference Accelerator which enables high throughput and low latency inference on clusters with NVIDIA V100, P100, P4 or P40 GPUs. TensorRT is both an optimizer and runtime – users provide a trained neural network and can easily creating highly efficient inference engines that can be incorporated into larger applications and services. This talk will cover the capabilities, workflow, and performance of TensorRT 3.0 itself and highlight several ways that it can be used to enable organizations add ground breaking DL powered features or save money as they scale out existing services.

Chris Gottbrath (NVIDIA)

Chris Gottbrath is the product manager for the TensorRT programmable inference accelerator at NVIDIA. TensorRT enables users to easily deploy neural networks in data centers, automobiles, and robots, and delivers high throughput and low latency. Chris has been attending GTC since 2010. He's always ready to talk about GPUs, deep learning, astronomy, HPC, debugging technology, and math libraries.

nvGraph
Thursday, November 16 | GPU Technology Theater | 2:30pm - 3:00pm

TBA

Joe Eaton(NVIDIA)

Joe Eaton leads the sparse linear algebra and graph analytics libraries at NVIDIA. His goals is to bring GPU performance to engineering users without the need to learn CUDA programming.

NVIDIA DLI University Ambassador Program
Wednesday, November 15 | GPU Technology Theater | 10:00pm - 10:20pm

The NVIDIA Deep Learning Institute (DLI) enables engineers, researchers, and scientists to solve problems in applied disciplines with deep learning such as self-driving cars, healthcare, consumer services, and robotics. The DLI instructor-led and online content provides state-of-the-art educational value for university students taking courses in Data Science. Machine Learning, and Artificial Intelligence (AI). The DLI University Ambassador Program is a new initiative where NVIDIA partners with and recognizes select faculty and students as experts in applied Deep Learning using GPUs. The DLI enables these awarded ambassadors to bring this valuable content to their campuses and classrooms themselves through workshops and online labs, complementing the traditional theoretical approaches to teaching in these areas.

Joe Bungo(NVIDIA)

Joe Bungo is the GPU Educators Program Manager at NVIDIA where he enables the use of GPU technologies in universities, including curriculum and teaching material development, facilitation of academic ecosystems, and hands-on instructor workshops. Previously, he managed university programs at ARM Inc. and worked as an applications engineer. Joe received his degree in Computer Science from the University of Texas at Austin.

NVIDIA DLI University Ambassador Program
Wednesday, November 15 | GPU Technology Theater | 10:00pm - 10:20pm

The NVIDIA Deep Learning Institute (DLI) enables engineers, researchers, and scientists to solve problems in applied disciplines with deep learning such as self-driving cars, healthcare, consumer services, and robotics. The DLI instructor-led and online content provides state-of-the-art educational value for university students taking courses in Data Science. Machine Learning, and Artificial Intelligence (AI). The DLI University Ambassador Program is a new initiative where NVIDIA partners with and recognizes select faculty and students as experts in applied Deep Learning using GPUs. The DLI enables these awarded ambassadors to bring this valuable content to their campuses and classrooms themselves through workshops and online labs, complementing the traditional theoretical approaches to teaching in these areas.

Yezhou Yang (Arizona State University)

Yezhou Yang is an Assistant Professor at School of Computing, Informatics, and Decision Systems Engineering, Arizona State University. He is directing the ASU Active Perception Group. He is also ASU Barrett Honors Faculty, ASU Keen Entrepreneurial Mindset Education Professor and NVIDIA Deep Learning Institute (DLI) Certified Instructor and University Ambassador. His primary interests lie in Cognitive Robotics, Computer Vision, and Robot Vision, especially exploring visual primitives in human action understanding from visual input, grounding them by natural language as well as high-level reasoning over the primitives for intelligent robots. His research mainly focused on solutions to visual learning, which significantly reduces the time to program intelligent agents. These solutions involve Computer Vision, Deep Learning, and AI algorithms to interpret peoples’ actions and the scene's geometry.

Accelerated Computing: The Path Forward - Special Address
Monday, November 13 | GPU Technology Theater | 3:00pm - 4:00pm

Jensen Huang (NVIDIA)

Jensen Huang co-founded NVIDIA in 1993 and has served since its inception as president, chief executive officer and a member of the board of directors. Prior to founding NVIDIA, Huang worked at LSI Logic and Advanced Micro Devices. He holds a BSEE degree from Oregon State University and an MSEE degree from Stanford University.