Multi-GPU Programming for Visual Computing
MONDAY, 22 JULY | 9-10 am
Modern workstation applications demand a tightly coupled compute-graphics pipeline where the simulation and the graphics are done interactively and in parallel. The use of multiple GPUs provides an affordable way for such applications to improve their performance and increase their useable data size by partitioning the processing and subsequent visualization among multiple GPUs. This session explains the methodologies of how to program your application for a multi-GPU environment, including:
- How to structure an application to optimize compute-graphics performance and manage synchronization.
- How to manage efficient data transfers across the PCIE bus.
- Debugging and profiling.
- Programming considerations when scaling beyond two GPUs, such as multiple compute GPUs feeding to one or more graphics GPUs.
Throughout this session, OpenGL and CUDA code examples designed for a single GPU will be modified to efficiently work in a multi-GPU environment.
Senior Applied Engineer
Seamless Compute and OpenGL Graphics Development in Nsight Visual Studio
MONDAY, 22 JULY | 10:30-11:30 am
NVIDIA Nsight 3.1 Visual Studio Edition is the latest revision of the most advanced GPU-accelerated application development environment for heterogeneous platforms. Jeff Kiel, Manager for Graphics Tools, presents the new architecture and feature set of the product, which brings CUDA and OpenGL graphics development together within the same development activities. From debugging GLSL Graphics Shaders and CUDA kernels within the same GPU debugging session to optimizing applications making complex use of graphics and compute multi-GPUs to tracing compute and graphics asynchronous memory transfers between the GPU and CPU, Nsight 3.1 unleashes GPU development to a level of integration never seen before. The session includes real-world examples to highlight how the development of such GPU-accelerated applications can be more efficiently developed with these new and future versions.
Senior Manager, Graphics Tools
The Future of Visual Computing - OpenGL 4.3 on ARM
MONDAY, 22 JULY | Noon-1 pm
This session covers the development progress, performance characteristics, and future evolution of OpenGL 4.3 on ARM architecture. Much progress has been made since the preliminary demonstration of Seco's CARMA DevKit at the 2013 GTC. The session reviews the existing software environment, discusses common pitfalls when porting x86 OpenGL applications to ARM, shows performance and power efficiency results, discusses the software evolution, and hints at future hardware platforms.
NVIDIA IndeX – Enabling Interactive and Scalable Visualization for Large Data
MONDAY, 22 JULY | 1:30-2:30 pm
While parallel processing and distributed computing are becoming increasingly popular for analyzing large datasets, it's extremely challenging to interact with such large volumes of data. NVIDIA IndeX solves this by providing applications with a highly scalable, interactive solution for in-situ visualization of large-scale data processing and simulations. Learn how IndeX accommodates custom applications and algorithms to scale linearly across a compute cluster for delivering highly interactive frame rates. Also discussed: commercial use of IndeX by a major energy company to visualize terabytes of seismic data.
Engineering Manager and Chief Architect
nvFX: A Scene and Material Effect Framework for OpenGL and DirectX
MONDAY, 22 JULY | 2:15-2:45 pm
This presentation introduces a GPU-shaders effect approach built on the original concepts of NVIDIA CgFX and expands it to new levels of flexibility and extensibility. Rather than creating a new shading language, developers can supersede existing ones (GLSL, HLSL) to avoid complex parsing and still deploy the effect in a variety of environments. This approach allows composition of graphic shaders with "compute kernels" and allows construction of effects for materials objects and global scene management (post-processing, management of rendering passes). Because nvFX is open-source, developers directly benefit from this engineering approach and can leverage its run time or extend it to service other specific custom requirements.
Developer Technology Relations
GPU Ray Tracing and Advanced Rendering Solutions
MONDAY, 22 JULY | 3-4 pm
Learn how GPU computing is revolutionizing performance and possibilities in both interactive and production rendering. This session explores and demonstrates the latest capabilities of Iray 2013, explains what's possible with the latest OptiX for accelerating custom ray tracing solutions, reviews industry trends, and summarizes guidelines for configuring optimal rendering.
Director, Advanced Rendering Product Management
Building Ray Tracing Applications with OptiX
MONDAY, 22 JULY | 4:30-5:30 pm
OptiX is the foremost platform for GPU ray tracing. It exposes the extreme ray tracing performance of the GPU to typical developers, while hiding most of the complexity usually associated with ray tracing. This session will cover everything developers need to get started with ray tracing in OptiX, including OptiX C and C++ APIs, the execution model, acceleration structures, programmable entry points, and best practices.
High-Performance Graphics for 4K and Ultra-High-Resolution Displays
TUESDAY, 23 JULY | 9-10 am
Large-format, high-resolution displays are being utilized everywhere from corporate conference rooms to supercomputing facilities. NVIDIA Quadro SVS solutions provide many features to make it easier to install and utilize these large-scale displays. In this session, attendees learn how to configure Quadro Graphics for thin bezel panel, edge-blended projectors, and stereoscopic and immersive displays.
Senior Solutions Architect
GPU Programming for Video and Image Processing Applications
TUESDAY, 23 JULY | 10:30-11:30 am
As a high-performance parallel-floating-point processor with high memory bandwidth, the GPU is ideal for video and image processing applications. Such applications require efficient transfer of video or image data to and from the GPU as well as optimal use of the GPU hardware resources. This session demonstrates how to design video and image-processing applications to efficiently leverage the GPU.
Senior Applied Engineer
NVIDIA TEGRA: Attacking Mobile Entertainment with Sword and SHIELD
TUESDAY, 23 JULY | Noon-1 pm
The NVIDIA Tegra processor continues to blaze a path at the cutting edge of mobile processor technology. During this session discover the new CPU, GPU, and multimedia features the latest Tegra processors offer and learn how NVIDIA provides technical support for the development of cutting edge mobile applications and games. The speaker will also introduce NVIDIA SHIELD: a new open gaming device that integrates Tegra 4 into a highly innovative mobile game controller design. Learn some background about SHEILD's creation and also explore new opportunities for the convergence of computer games, TV and movies, that SHIELD and upcoming mobile devices provide to the entertainment industry.
Manager, Tegra Developer Technologies
Developing Next-Generation Human Machine Interfaces (HMI)
TUESDAY, 23 JULY | 1:30-2:30 pm
Developed by NVIDIA, the UI Composer Studio is the ground-breaking HMI design tool used for creating next-generation interfaces, from automotive instrument clusters and infotainment systems to gaming. Today, the UI Composer Studio is used by automakers and Tier 1 automotive suppliers to rapidly develop proof of concepts for evaluation, market research, usability testing and ultimately final production. This session covers Studio's user interface, project structure, animation techniques, scripting and previewing. In addition, the basics of constructing an instrument cluster and in-vehicle infotainment system using Studio's advanced authoring environment will be demonstrated.
Director, Media and Entertainment Tools
CUDA Best Practices
TUESDAY, 23 JULY | 3-4 pm
The future of computing is parallelism, and good parallelism is achieved by knowing how to optimize your code. This session explains common best practices for CUDA that give large amounts of parallelism while being both easy to write and optimize. While established optimization techniques are covered, the session also explores some more esoteric best practices that are now commonly available on newer hardware, including memory transactions and atomic ops that are focused on giving you the tools you need to get the most out of your parallel code.
Applied Research Engineer
State of the Art of Virtualized Graphics
TUESDAY, 23 JULY | 4:30-5:30 pm
As businesses look to move PCs to the cloud, users are more and more demanding of better experience and support for all of their devices. NVIDIA GRID enables state of the art graphics in a virtualized environment. This session will show how NVIDIA GRID enables graphics-intensive applications to run interactively in the cloud and display on any device, ranging from phones to tablets to laptops. It also covers the technology behind GPUs in virtual environments and the graphics architecture seen by applications.
Director GRID Products
Director Applied Engineering