As the world’s visually creative leaders come together at FMX’19 in Stuttgart this week, I would like to share some exciting news regarding Intel and its partners’ efforts to continue delivering leadership solutions for advanced, feature rich, photorealistic and high-performance workflows for studio quality asset creation. As I announced in my SIGGRAPH’18 blog, Intel® Rendering Framework open source software libraries continue to increase in features, performance and ease of use.
Intel® Embree, Intel® OSPRay, Intel® OpenSWR, and the recently released Intel® Open Image Denoise provide open source rendering kernels and middleware mapped to Intel® architecture multi-core parallel processors for maximum flexibility, performance and technical transparency. Intel® Xeon® processors running Embree supported renderers are used to provide state-of-the-art visual effects in animated movies, including Dreamworks* MoonRay* renderer, used to render How to Train Your Dragon: The Hidden World that is in theatres now.
For complex shading methods, Intel has been collaborating with Pixar and Sony Imageworks to increase performance of shading processes that use Open Shading Language (OSL). By tapping the parallelism of Intel® Xeon® processors with Intel® AVX2 and AVX-512 vector instructions, as much as 2x shading performance improvements have been seen on Pixar scenes. Look for Pixar’s Dylan Sisson’s FMX talk for more on this topic.
Intel recently launched the 2nd Generation of Intel Xeon Scalable processors that include Deep Learning Boost® instructions adding new levels of performance for Artificial Intelligence (AI) methods. This capability creates opportunities for increased realism and faster asset turnaround for film creators like Ziva Dynamics, who use AI and Intel® Xeon® processors to deliver realistic character behaviors such as the prehistoric shark in 2018 film, The Meg from Warner Brothers Studios.
USD Hydra OSPRay Plug-in and Intel® Open Volume Kernel Library
As the cornerstone of our professional rendering platform, the Intel® Rendering Framework keeps evolving to accelerate your workflows, today. We recently released the first version of our open source Universal Scene Description* (USD) Hydra OSPRay Plug-in to enable interactive, up to real-time, photorealistic, global illuminated previews in Hydra capable application viewing windows (e.g. AutoDesk* Maya*). This plug-in takes advantage of all the benefits Intel® OSPRay with Intel® Open Image Denoise brings to applications, including the ability to interactively render very large-scale data (100’s of gigabytes to many terabytes) and allows scaling with multiple server nodes to increase frame rate, visual quality, and 3D dataset sizes including multi-frame animations.
We continue to work with industry partners like Disney Animation* and Pixar* to improve the breadth and quality for production uses of USD Hydra. We have been jointly testing a preliminary but still incomplete version (e.g. the ocean portion) of the Moana Island Scene. Our goal is to drive increased functionality into both USD and Intel® OSPRay as these projects continue to strive for highest quality and performance for studio asset exchange.
Preliminary ‘Work in Progress’ USD version of Moana Island Scene: Courtesy Walt Disney Animation Studios
Finally, I am very pleased to announce the fifth open source library being added to Intel® Rendering Framework, The Intel® Open Volume Kernel Library (Intel® OpenVKL). Since Intel® OSPRay rendering infrastructure’s first release in 2015, one of its significant strengths has been its broad support for a variety of structured and unstructured volume formats with interactive to real-time performance on Intel processor platforms. Volume rendering is a critical capability for scientific visualization of simulations of everything from gravitational cosmology, weather, geology, and more. For digital content creation and special effects, it enables delivering a truly realistic world by enabling key visual effects like explosions, clouds, water flow, and more.
Screen Capture of OSPRay Studio application rendering the Moroccan Ocean Shelf with Intel® OSPRay and Intel® OpenVKL. Note the unique use of global illumination (shadows and ambient occlusion). Data courtesy of the Bureau of Economic Geology at The University of Texas at Austin and the Moroccan National Office of Hydrocarbon and Mining.
To bring more flexibility, performance and efficiency to volume-based use cases, we are taking the core Intel® OSPRay volume processing algorithms, extending and packaging them for use in a form similar to the Intel® Embree kernel ray tracing library. This will allow renderers and even simulation codes efficient, direct interfaces to efficiently process volume data in its many forms. Intel® OpenVKL’s first release will be in Q3 2019 and Intel® OSPRay will be reformed to use OpenVKL as the kernel library for volume processing. As a Premier Member of the Academy Software Foundation (ASWF) we are participating in the OpenVDB project and planning OpenVDB support in a subsequent OpenVKL release targeting end of 2019 or early 2020. Look for more info and the release of Intel® OpenVKL at www.openvkl.org
Thinking Exponential with Intel® XE architecture compute and graphics processors
Intel® architecture processors are the flexible, large memory capable, performance engines that drive the end-to-end creative process for visual effects and animated feature films. Today’s available GPUs have architecture challenges like memory size limitations and performance derived from years of honing for less sophisticated, “embarrassingly parallel” rasterized graphics use models. Studios continue to reach for maximum realism with complex physics processing for cloth, fluids, hair and more, plus modeling the physics of light with ray tracing. These algorithms benefit from mixed parallel and scalar computing while requiring ever growing memory footprints. The best solutions will include a holistic platform design where computational tasks are distributed to the most appropriate processing resources.
David Blythe’s recent blog provided initial insights into our exciting new Intel® Xe architecture currently under development. We are designing the Intel® Xe architecture as a cohesive acceleration companion to our continuing roadmap of Intel® Xeon® processors. As David closed his blog he mentioned, “We will look forward to sharing more details on the Intel® Xe architecture in the months ahead.” I’m pleased to share today that the Intel® Xe architecture roadmap for data center optimized rendering includes ray tracing hardware acceleration support for the Intel® Rendering Framework family of API’s and libraries.
Your existing investments in graphics and rendering solutions based on Intel® Rendering Framework open source products will seamlessly map to the exponential performance benefits of these flexible accelerated platforms. Further, ray tracing as a general computational technique for a variety of simulation computation beyond rendering is rapidly growing. To put it succinctly in my own words “Leave no transistor behind” by creating a holistic software and compute environment ready to maximize your workflow for exponential benefits.
Partnership and community: announcing Intel Graphics and Visualization Institutes of XeLLENCE
In order to better ensure advanced graphics and visualization capabilities are broadly available to the professional rendering, scientific visualization and virtual design communities, I am thrilled to announce that Intel is supporting the establishment of Intel® Graphics and Visualization Institutes of XeLLENCE (Intel® GVI). Three world class founding institutions have been selected:
- Scientific Computing and Imaging Institute (SCI) at University of Utah, supported by Dr. Chris Johnson.
- Texas Advanced Computing Center (TACC) at University of Texas, Austin with Kitware, Inc, supported by Dr. Paul Navratil and Dr. Berk Geveci.
- Visualization Institute of the University of Stuttgart (VISUS), supported by Dr. Ing. E. h. Thomas Ertl and Dr. rer. nat. Guido Reina.
These institutions have already made significant open research and open source contributions related to Intel Rendering Framework, large scale graphics and visualization and we look forward to working with them to bring their energy and expertise to enable all creative and scientific communities to better utilize Intel® Xe architecture enabled platforms. I highly recommend you track the output of these institutes for the revolutionary ideas and solutions they have and will continue to deliver individually, collectively and openly for all to use and benefit from.
“The Scientific Computing and Imaging (SCI) Institute, an international leader in visualization, imaging and scientific computing, is thrilled to be selected as a member in this elite founding group of Intel Graphics and Visualization Institutes of Xellence. As future Intel Xe architecture products are deployed to further augment visual computing, we look forward to ongoing research and open source contributions in collaboration with Intel and the Intel GVI centers.“ – Dr. Chris Johnson, Founding Director, Scientific Computing and Imaging Institute, University of Utah
“At VISUS at University of Stuttgart, we constantly look for new ways of harnessing modern hardware to allow for interactive visualization of ever-growing data. With Intel Rendering Framework utilizing software defined visualization, we have been able to bring our approaches to HPC systems and maintain interactive performance while dramatically increasing visual fidelity through OSPRay ray tracing. With our status as an Intel Graphics and Visualization Institute of Xellence, and the ability to utilize the Intel Xe architecture scaled across a variety of compute platforms, we will enable even more comprehensive approaches that reflect our overarching goal most closely: distributing computational loads over different resources that maximize each’s strengths; enabling discovery and user engagement though seamless interactivity and visual quality for the rapidly growing data set sizes of tomorrow. We are very excited and honored to be among the select few foundational Intel® GVI institutions poised to deliver impactful research contributions to graphics and visualization.” – Dr.-Ing E. h.. Thomas Ertl, Head of the Visualization Research Center of the University of Stuttgart (VISUS), Vice Rector for Research and Advanced Graduate Education
“TACC is honored to continue our partnership with Kitware and Intel to provide high-performance, high-fidelity visual analysis tools to scientists to help them better understand and better communicate their findings. Intel’s support for groundbreaking visual analysis work through the Intel Graphics and Visualization Institutes of Xellence will provide researchers more powerful analysis sooner in the discovery workflow. Through use of the Intel Rendering Framework and future Intel Xe architecture products, the Intel GVI centers will demonstrate that powerful interactive analysis can be achieved independent of underlying rendering architecture.” – Dr. Paul Navratil, Director of Visualization, Texas Advanced Computing Center.
"Kitware is excited to be an included partner in the Intel Graphics and Visualization Institute of Xellence, continuing our long collaboration with TACC and Intel for delivering compelling, state of the art, open source solutions for large scale, high fidelity graphics and visualization. Through the joint efforts with the Intel IGVI, we look forward to enhancing our partner’s and user’s experience with applications like ParaView and the Visualization Toolkit (VTK) by including the capabilities of future Intel Xe architecture products.” – Berk Geveci, Sr. Director of Scientific Computing
Through collaboration with Intel® Graphics and Visualization Institutes of XeLLENCE and our industry partners who leverage Intel® Rendering Framework, Intel® Xeon® Scalable processors and, in the future, Intel® Xe architecture; Intel will continue to enable delivery of leadership solutions for high fidelity studio assets creation.
To learn more, visit: