What’s New: At its inaugural Intel CREATE event today at SIGGRAPH 2019, the company outlined how its vision for exascale computing – driven by its six technology pillars – is foundational to enabling dramatic advancements in filmmaking and content creation. These advancements will be accelerated by a multiyear goal for a 1,000 times advancement in performance, underpinned by deep investments in next-generation hardware architectures and software developer tools.
“We’re relentless in our focus to drive the industry towards a world that unlocks exascale computing for everyone and enables creators to push the boundaries of visually rich and immersive storytelling. I’m deeply passionate about this future opportunity and have challenged my teams to pursue a goal of 1,000 times performance advancement over the coming years to enable this.”
–Raja M. Koduri, Intel chief architect and senior vice president of Architecture, Software and Graphics
What It Looks Like: Two examples of these investments coming to life are Intel’s forthcoming exascale-class GPU and Intel’s comprehensive roadmap for its oneAPI Rendering Toolkit (formerly Intel® Rendering Framework).
Additionally, breakthroughs in memory technology, like those delivered by 2nd Gen Intel® Xeon® Scalable processorscoupled with Intel® Optane™ DC persistent memory, put a higher class of computing performance in closer proximity to content creators. Industry collaboration remains core to Intel’s approach in these areas and spans industry leaders, academic researchers and technology innovators. These relationships allow for the development of workflows that enable the creation of content without compromise today, while preparing for tomorrow’s visual experiences driven by the promise of exascale computing.
Why It’s Important: Exascale computing will unlock new opportunities for fast, high-quality rendering, physical simulations and new artificial intelligence-supported workflows, expanding creation possibilities in studios.
“Only Moore’s Law will deliver compute to meet the dreams of real creators,” said Jim Keller, Intel senior vice president and general manager of Silicon Engineering Group.
Moving, storing and processing data in these complex scenarios requires advancements across the computing spectrum, including architecture (CPU and GPU), memory, I/O and, most important, the software that connects it to the artists.
“The path to exascale computing and content creation have strong interdependencies and opportunities between them. The advancements we make in these areas can be readily shared across both domains to their mutual benefit,” said Jim Jeffers, senior principle engineer and senior director of Intel’s Advanced Rendering and Visualization team. “Our investment in software initiatives, like oneAPI plus advanced algorithm research and development, plays a profound role as we set out to ‘leave no transistor behind’.”
The Intel® oneAPI Rendering Toolkit – used by more than 100 applications developed in-house and by independent software vendors (ISVs) today – is a set of highly optimized software libraries that enable efficient, high-quality rendering for data of virtually any size. Intel shared its roadmap for the Intel oneAPI Rendering Toolkit through the end of 2019, including new and upcoming releases:
Available this week:
- Intel® Embree v3.6 is the latest version of high-performance ray-tracing kernels
- Intel® Open Image Denoise v1.0 uses AI Deep Learning techniques to deliver leadership quality images to speed ray-tracing applications’ rendering time
Available by 2019’s fourth quarter:
- Intel® OSPRay v2.0, the open source, scalable, ray-tracing engine, will incorporate Intel® Open Image Denoise v1.0
- Intel® Open Volume Kernel Library for volumetric rendering
How Intel Collaborates: Industry giants showcased how they are leveraging Intel’s products and technologies to advance content creation possibilities:
- Pixar* highlighted the collaboration with Intel to allow Renderman to enable over 2 times acceleration1 of the Open Shading Language by taking advantage of Intel Xeon Scalable processor SIMD vector instructions like AVX-512. Pixar noted its plans to extend its Renderman xPU research and development to upcoming Intel Xearchitecture GPUs to utilize the oneAPI software concept of “no transistor left behind.”
- HP* discussed how Intel Optane DC persistent memory can be used to eliminate the need for slow and disruptive manual and/or auto-saves in content creation applications. Additionally, HP showed how persistent memory can be leveraged to preserve work history across application and system transitions as demonstrated at the event on Blender, allowing creators to rapidly pick up where they left off.
- CHAOS Research* announced a new collaboration with Intel and Charles University in Prague to form a new Intel® Graphics and Visualization Institute of XeLLENCE to advance research in professional rendering technologies.
- Discovery* announced a new science education digital series, a new collaboration with Intel, coming this fall that will use the Intel oneAPI Rendering Toolkit to deliver stunning, high-fidelity visualizations to better educate viewers.
- Maxon* shared how it is leveraging Intel® Embree and Intel® Open Image Denoise in Cinema4D R21 to deliver even faster rendering times and announced a technical partnership with Intel on future CPU and GPU technology.
- BlueSky Studios* showcased how large persistent memory can change the way creators work by enabling tasks that were simply not possible before, such as multi-TB rendering jobs.
- Otoy* disclosed that it will be supporting the Vulkan API going forward in Octane Render, citing the need for industry standards to take advantage of the best hardware available.
More Context: Exascale Computing will Redefine Content Creation
The Small Print:
1 Testing by Pixar on July 17, 2019, indicating 2x total render time with shading alone measuring 2.4x faster on Intel® Xeon Gold 6152 at 2.10 GHz (22 c).
Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors.
Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit www.intel.com/benchmarks.
Performance results are based on testing as of the date in the configurations and may not reflect all publicly available security updates. See configuration disclosure for details. No product or component can be absolutely secure.
Intel does not control or audit third-party data. You should visit other sources to confirm whether referenced data are accurate.