Visit our partners' booths during exhibit hours to see the latest NVIDIA technology:
Dell - 340
HP - 640
PNY – 853

See the GPU Computing Ecosystem

ISC 2012

At ISC 2012, many of NVIDIA's partners, will be featuring solutions powered by NVIDIA® GPUs. We invite you to visit our partners' exhibits and attend the featured ISC sessions, to learn about the latest NVIDIA Tesla® GPU computing solutions.




VIP Briefing on GPU Accelerator Technology

TUESDAY, JUNE 19, 2012 | 8:00 AM - 9:00 AM | Radisson Blu Hotel

Steve Scott, CTO of Tesla GPU Computing Business, NVIDIA
Ian Buck, GM of GPU Computing, NVIDIA
Dr. Dirk Pleiter, Juelich

Hybrid computing is playing an ever more important role in supercomputing and computational research. At the center this hybrid computing model is the GPU, making faster, more efficient science and discovery possible. Attend this briefing to hear about the latest in NVIDIA GPU architecture and programming technology, and learn about how one of the top supercomputing centers around the world is working to leverage this technology to increase the pace and scope of research. Download Presentation (PDF 3.1 MB) >


Inside the NVIDIA Kepler Architecture

TUESDAY, JUNE 19, 2012 | 9:30 AM - 10:30 AM | Radisson Blu Hotel

Thomas Bradley, Manager of Developer Technology for HPC, NVIDIA

In this talk, we will dive into the features of the compute architecture for "Kepler" – NVIDIA's new 7-billion transistor GPU. From the reorganized processing cores with new instructions and processing capabilities, to an improved memory system with faster atomic processing and low-overhead ECC, we will explore how the Kepler GPU achieves world leading performance and efficiency, and how it enables wholly new types of parallel problems to be solved.
Download Presentation (PDF 1.5 MB) >


CARMA: CUDA on ARM Architecture – A New Era of Power-Efficient Computing

TUESDAY, JUNE 19, 2012 | 1:00 PM - 2:00 PM | Radisson Blu Hotel

Don Becker, Systems Architect, NVIDIA

The world's largest computer systems are increasingly being limited by power and thermal limitations. This previous generation's focus on cost-effective and long-term-viable compute platforms has been expanded with the additional requirement for power-efficient computing. CARMA is the introductory system for developing the software ecosystem for the next generation of power-focused, high performance computing. It joins the power efficient high compute performance of a GPGPU, with a power-efficient ARM host processor. Both elements leverage the commodity market cost-effectiveness and leading edge development. This talk will introduce the CARMA hardware, outline its performance characteristics, describe the initial software system, and demonstrate the operational system.
Download Presentation (PDF 1.3 MB) >


GPU-Accelerated Science on Titan: Tapping into the World's Preeminent GPU Supercomputer to Achieve Better Science

TUESDAY, JUNE 19, 2012 | 3:00 PM - 4:00 PM | Radisson Blu Hotel

Buddy Bland, Project Director, Oak Ridge National Laboratory
Jack Wells, Ph.D., Director of Science, Oak Ridge Leadership Computing Facility, Oak Ridge National Laboratory
Julia White, INCITE Program Manager, Oak Ridge National Laboratory

This year, the leadership-class computing facility at Oak Ridge National Labs is upgrading its largest supercomputer for open science, "Jaguar", to employ high-performance, power- efficient GPUs. Once the transition is complete, the machine will be known as "Titan". This talk will present an overview of the Titan supercomputer, showcase research codes that will run computational science on the GPU at scale, and investigate the progress and anticipated results of GPU-acceleration of these significant codes. In this session, we will also explain how research scientists interested in tapping into the immense capabilities of Titan can do so, through programs such as the INCITE program sponsored by the US Department of Energy. Download Presentation (PDF 2.8 MB) >


GPUs and OpenACC: Enabling the Next Wave of HPC Revolution

TUESDAY, JUNE 19, 2012 | 4:00 PM - 5:00 PM | Radisson Blu Hotel

Duncan Poole, ISV Alliance Manager, NVIDIA
Thomas Bradley, Manager of Developer Technology for HPC, NVIDIA

OpenACC is a directives-based programming standard for parallel computing on accelerators (including GPUs). It is designed to harness the transformative power of heterogeneous computing systems easily and quickly. Adding simple compiler hints to your code to express parallelism, allows the compiler to map computation onto an accelerator. OpenACC directives allow researchers and developers to make simple and portable code changes, enabling an easier migration to accelerated computing. This talk discusses the merits of this model, and provides an overview and guidance of the tools available to the developer from the OpenACC members. This talk discusses why directives like OpenACC are key to wide spread adoption, and provides an overview of the tools available from the OpenACC members. Download Presentation (PDF 1.8 MB) >


TUTORIAL: "Programming Accelerators with OpenACC and CUDA C/Fortran"

Sunday, June 17, 2012 |9:00 AM - 6:00 PM| HAMBURG UNIVERSITY, MAIN BUILDING, Room 222

NVIDIA engineers and The Portland Group present a tutorial on programming GPUs using the newly available OpenACC compilers and CUDA for scientific and engineering tasks. OpenACC directives allow developers to make simple and portable code changes, enabling an easier migration to accelerated computing.


Partner sessions


DELL GPU computing solutions

Theater presentations at the Dell booth:

  • GPU computing with Tesla based solutions from Dell
  • GPU Computing for molecular dynamics
  • Accelerating code with OpenACC directives
  • GPU computing for Matlab
  • GPU computing for CAE
  • GPU computing for Accelerating science

HP GPU computing solutions



At HP-CAST 18 a special focus will be on the following sessions:

Radisson Blu Ball Rooms - Saturday, June 16th

  • 09:00 – 10:00 Tutorial A1b: NVIDIA Tesla GPU Update
    GPU Roadmap and Technology Update (Special registration required)
    Chair: Tom Reed - NVIDIA, Speaker: David Jones - NVIDIA
  • 10:30 – 12:30 Tutorial A2: Accelerators - Software Development
    • Accelerating Scientific Computing with PGI's OpenACC Compilers
      (Speaker: Dave Norton, PGI)
    • Surviving in an Accelerated World: How TotalView Erases Differences in Debugging Multiple Platforms (Speaker: Nikolay Piskun, Rogue Wave)
    • Allinea DDT: Intelligence Within Designing Software for Accelerators
      (Speaker: Patrick Wohlschlegel, Allinea)
  • 13:30 – 14:30 Accelerator SIG Session
    Best Practices and Customer Requirements for GPU-enabled Systems
    Chairs: Jan-Philipp Weiss, KIT & Patrick Demichel, HP
  • 16:00 – 17:00 Tutorial A3a: Accelerators – Ecosystems and Libraries
    • ArrayFire – A Simple, Fast and Free GPU Platform
      (Speaker: James Malcolm, AccelerEyes)
    • Using FMSlib for the Solution of Large Linear Systems on Multiple GPUs (Speaker: Ronald Young, Multipath Corp.)
    • Chair: Dave Korf, HP
  • 17:00 – 18:00 Tutorial A3b: CUDA Class for Programmers and Software Developers
    • CUDA – A Tutorial for Programmers: All You Need to Know to Start Accelerating Your Applications (Speaker: Thomas Reed, NVIDIA)
    • Chair N. N., NVIDIA



TUTORIAL: "Reverse & CUDA Debugging for Computationally Intensive Application Development"

Sunday, June 17, 2012 |9:00 AM - 1:00 PM| HAMBURG UNIVERSITY, MAIN BUILDING, Room 124

A significant challenge in developing, maintaining and porting numerical simulations is avoiding subtle errors that undermine the validity of the results without causing an obvious failure. This tutorial will share experiences, best practices and debugging techniques for identifying and resolving such defects in parallel applications.