Tag Archives: AI

Panasas’ new ActiveStor Ultra targets emerging apps: AI, VR

Panasas has introduced ActiveStor Ultra, the next generation of its high-performance computing storage solution, featuring PanFS 8, a plug-and-play, portable, parallel file system. ActiveStor Ultra offers up to 75GB/s per rack on industry-standard commodity hardware.

ActiveStor Ultra comes as a fully integrated plug-and-play appliance running PanFS 8 on industry-standard hardware. PanFS 8 is the completely re-engineered Panasas parallel file system, which now runs on Linux and features intelligent data placement across three tiers of media — metadata on non-volatile memory express (NVMe), small files on SSDs and large files on HDDs — resulting in optimized performance for all data types.

ActiveStor Ultra is designed to support the complex and varied data sets associated with traditional HPC workloads and emerging applications, such as artificial intelligence (AI), autonomous driving and virtual reality (VR). ActiveStor Ultra’s modular architecture and building-block design enables enterprises to start small and scale linearly. With dock-to-data in one hour, ActiveStor Ultra offers fast data access and virtually eliminates manual intervention to deliver the lowest total cost of ownership (TCO).

ActiveStor Ultra will be available early in the second half of 2019.

Video Coverage: postPerspective Live from SMPTE 2018

The yearly SMPTE Technical Conference and Exhibition was held late last month in Downtown Los Angeles at the Westin Bonaventure Hotel, a new venue for the event.

The conference included presentations that touched on all three of the organization’s “pillars,” which are Standards, Education and Membership.

One of the highlights was a session on autonomous vehicles and how AI and machine learning are making that happen. You might wonder, “What will everyone do with that extra non-driving time?” Well, companies are already thinking of ways to entertain you while you’re on your way to where you need to go. The schedule of sessions and presentations can be found here.

Another highlight at this year’s SMPTE Conference was the Women in Technology lunch, which featured a conversation between Disney’s Kari Grubin and Fem Inc.’s Rachel Payne. Payne is a tech entrepreneur and technology executive who has worked at companies like Google. She was also a Democratic candidate for the 48th Congressional District of California. It was truly inspiring to hear about her path.

Feeling like you might have missed some cool stuff? Well don’t worry, postPerspective’s production crews were capturing interviews with manufacturers in the exhibit hall and with speakers, SMPTE members and so many others throughout the Conference.

A big thank you to AlphaDogs , who shot and posted our videos this year, as well as our other sponsors: Blackmagic Design, The Studio – B&H, LitePanels and Lenovo.

Watch Here!

Quick Chat: AI-based audio mastering

Antoine Rotondo is an audio engineer by trade who has been in the business for the past 17 years. Throughout his career he’s worked in audio across music, film and broadcast, focusing on sound reproduction. After completing college studies in sound design, undergraduate studies in music and music technology, as well as graduate studies in sound recording at McGill University in Montreal, Rotondo went on to work in recording, mixing, producing and mastering.

He is currently an audio engineer at Landr.com, which has released Landr Audio Mastering for Video, which provides professional video editors with AI-based audio mastering capabilities in Adobe Premiere Pro CC.

As an audio engineer how do you feel about AI tools to shortcut the mastering process?
Well first, there’s a myth about how AI and machines can’t possibly make valid decisions in the creative process in a consistent way. There’s actually a huge intersection between artistic intentions and technical solutions where we find many patterns, where people tend to agree and go about things very similarly, often unknowingly. We’ve been building technology around that.

Truth be told there are many tasks in audio mastering that are repetitive and that people don’t necessarily like spending a lot of time on, tasks such as leveling dialogue, music and background elements across multiple segments, or dealing with noise. Everyone’s job gets easier when those tasks become automated.

I see innovation in AI-driven audio mastering as a way to make creators more productive and efficient — not to replace them. It’s now more accessible than ever for amateur and aspiring producers and musicians to learn about mastering and have the resources to professionally polish their work. I think the same will apply to videographers.

What’s the key to making video content sound great?
Great sound quality is effortless and sounds as natural as possible. It’s about creating an experience that keeps the viewer engaged and entertained. It’s also about great communication — delivering a message to your audience and even conveying your artistic vision — all this to impact your audience in the way you intended.

More specifically, audio shouldn’t unintentionally sound muffled, distorted, noisy or erratic. Dialogue and music should shine through. Viewers should never need to change the volume or rewind the content to play something back during the program.

When are the times you’d want to hire an audio mastering engineer and when are the times that projects could solely use an AI-engine for audio mastering?
Mastering engineers are especially important for extremely intricate artistic projects that require direct communication with a producer or artist, including long-form narrative, feature films, television series and also TV commercials. Any project with conceptual sound design will almost always require an engineer to perfect the final master.

Users can truly benefit from AI-driven mastering in short form, non-fiction projects that require clean dialog, reduced background noise and overall leveling. Quick turnaround projects can also use AI mastering to elevate the audio to a more professional level even, when deadlines are tight. AI mastering can now insert itself in the offline creation process, where multiple revisions of a project are sent back and forth, making great sound accessible throughout the entire production cycle.

The other thing to consider is that AI mastering is a great option for video editors who don’t have technical audio expertise themselves, and where lower budgets translate into them having to work on their own. These editors could purchase purpose-built mastering plugins, but they don’t necessarily have the time to learn how to really take advantage of these tools. And even if they did have the time, some would prefer to focus more on all the other aspects of the work that they have to juggle.

IBC 2018: Convergence and deep learning

By David Cox

In the 20 years I’ve been traveling to IBC, I’ve tried to seek out new technology, work practices and trends that could benefit my clients and help them be more competitive. One thing that is perennially exciting about this industry is the rapid pace of change. Certainly, from a post production point of view, there is a mini revolution every three years or so. In the past, those revolutions have increased image quality or the efficiency of making those images. The current revolution is to leverage the power and flexibly of cloud computing. But those revolutions haven’t fundamentally changed what we do. The images might have gotten sharper, brighter and easier to produce, but TV is still TV. This year though, there are some fascinating undercurrents that could herald a fundamental shift in the sort of content we create and how we create it.

Games and Media Collide
There is a new convergence on the horizon in our industry. A few years ago, all the talk was about the merge between telecommunications companies and broadcasters, as well as the joining of creative hardware and software for broadcast and film, as both moved to digital.

The new convergence is between media content creation as we know it and the games industry. It was subtle, but technology from gaming was present in many applications around the halls of IBC 2018.

One of the drivers for this is a giant leap forward in the quality of realtime rendering by the two main game engine providers: Unreal and Unity. I program with Unity for interactive applications, and their new HDSRP rendering allows for incredible realism, even when being rendered fast enough for 60+ frames per second. In order to create such high-quality images, those game engines must start with reasonably detailed models. This is a departure from the past, where less detailed models were used for games than were used for film CGI shots, to protect for realtime performance. So, the first clear advantage created by the new realtime renderers is that a film and its inevitable related game can use the same or similar model data.

NCam

Being able to use the same scene data between final CGI and a realtime game engine allows for some interesting applications. Habib Zargarpour from Digital Monarch Media showed a system based on Unity that allows a camera operator to control a virtual camera in realtime within a complex CGI scene. The resulting camera moves feel significantly more real than if they had been keyframed by an animator. The camera operator chases high-speed action, jumps at surprises and reacts to unfolding scenes. The subtleties that these human reactions deliver via minor deviations in the movement of the camera can convey the mood of a scene as much as the design of the scene itself.

NCam was showing the possibilities of augmenting scenes with digital assets, using their system based on the Unreal game engine. The NCam system provides realtime tracking data to specify the position and angle of a freely moving physical camera. This data was being fed to an Unreal game engine, which was then adding in animated digital objects. They were also using an additional ultra-wide-angle camera to capture realtime lighting information from the scene, which was then being passed back to Unreal to be used as a dynamic reflection and lighting map. This ensured that digitally added objects were lit by the physical lights in the realworld scene.

Even a seemingly unrelated (but very enlightening) chat with StreamGuys president Kiriki Delany about all things related to content streaming still referenced gaming technology. Delany talked about their tests to build applications with Unity to provide streaming services in VR headsets.

Unity itself has further aspirations to move into storytelling rather than just gaming. The latest version of Unity features an editing timeline and color grading. This allows scenes to be built and animated, then played out through various virtual cameras to create a linear story. Since those scenes are being rendered in realtime, tweaks to scenes such as positions of objects, lights and material properties are instantly updated.

Game engines not only offer us new ways to create our content, but they are a pathway to create a new type of hybrid entertainment, which sits between a game and a film.

Deep Learning
Other undercurrents at IBC 2018 were the possibilities offered by machine learning and deep learning software. Essentially, a normal computer program is hard wired to give a particular output for a given input. Machine learning allows an algorithm to compare its output to a set of data and adjust itself if the output is not correct. Deep learning extends that principle by using neural network structures to make a vast number of assessments of input data, then draw conclusions and predications from that data.

Real-world applications are already prevalent and are largely related in our industry to processing viewing metrics. For example, Netflix suggests what we might want to watch next by comparing our viewing habits to others with a similar viewing pattern.

But deep learning offers — indeed threatens — much more. Of course, it is understandable to think that, say, delivery drivers might be redundant in a world where autonomous vehicles rule, but surely creative jobs are safe, right? Think again!

IBM was showing how its Watson Studio has used deep learning to provide automated editing highlights packages for sporting events. The process is relatively simple to comprehend, although considerably more complicated in practice. A DL algorithm is trained to scan a video file and “listen” for a cheering crowd. This finds the highlight moment. Another algorithm rewinds back from that to find the logical beginning of that moment, such as the pass forward, the beginning of the volley etc. Taking the score into account helps decide whether that highlight was pivotal to the outcome of the game. Joining all that up creates a highlight package without the services of an editor. This isn’t future stuff. This has been happening over the last year.

BBC R&D was talking about their trials to have DL systems control cameras at sporting events, as they could be trained to follow the “two thirds” framing rule and to spot moments of excitement that justified close-ups.

In post production, manual tasks such as rotoscoping and color matching in color grading could be automated. Even styles for graphics, color and compositing could be “learned” from other projects.

It’s certainly possible to see that deep learning systems could provide a great deal of assistance in the creation of day-to-day media. Tasks that are based on repetitiveness or formula would be the obvious targets. The truth is, much of our industry is repetitive and formulaic. Investors prefer content that is more likely to be a hit, and this leads to replication over innovation.

So, are we heading for “Skynet” and need Arnold to save us? I thought it was very telling that IBM occupied the central stand position in Hall 7 — traditionally the home of the tech companies that have driven creativity in post. Clearly, IBM and its peers are staking their claim. I have no doubt that DL and ML will make massive changes to this industry in the years ahead. Creativity is probably, but not necessarily, the only defence for mere humans to keep a hand in.

That said, at IBC2018 the most popular place for us mere humans to visit was a bar area called The Beach, where we largely drank Heineken. If the ultimate deep learning system is tasked to emulate media people, surely it would create digital alcohol and spend hours talking nonsense, rather than try and take over the media world? So perhaps we have a few years left yet.


David Cox is a VFX compositor and colorist with 20-plus years of experience. He started his career with MPC and The Mill before forming his own London-based post facility. Cox recently created interactive projects with full body motion sensors and 4D/AR experiences.

Our SIGGRAPH 2018 video coverage

SIGGRAPH is always a great place to wander around and learn about new and future technology. You can get see amazing visual effects reels and learn how the work was created by the artists themselves. You can get demos of new products, and you can immerse yourself in a completely digital environment. In short, SIGGRAPH is educational and fun.

If you weren’t able to make it this year, or attended but couldn’t see it all, we would like to invite you to watch our video coverage from the show.

SIGGRAPH 2018

postPerspective Impact Award winners from SIGGRAPH 2018

postPerspective has announced the winners of our Impact Awards from SIGGRAPH 2018 in Vancouver. Seeking to recognize debut products with real-world applications, the postPerspective Impact Awards are voted on by an anonymous judging body made up of respected industry artists and professionals. It’s working pros who are going to be using new tools — so we let them make the call.

The awards honor innovative products and technologies for the visual effects, post production and production industries that will influence the way people work. They celebrate companies that push the boundaries of technology to produce tools that accelerate artistry and actually make users’ working lives easier.

While SIGGRAPH’s focus is on VFX, animation, VR/AR, AI and the like, the types of gear they have on display vary. Some are suited for graphics and animation, while others have uses that slide into post production, which makes these SIGGRAPH Impact Awards doubly interesting.

The winners are as follows:

postPerspective Impact Award — SIGGRAPH 2018 MVP Winner:

They generated a lot of buzz at the show, as well as a lot of votes from our team of judges, so our MVP Impact Award goes to Nvidia for its Quadro RTX raytracing GPU.

postPerspective Impact Awards — SIGGRAPH 2018 Winners:

  • Maxon for its Cinema 4D R20 3D design and animation software.
  • StarVR for its StarVR One headset with integrated eye tracking.

postPerspective Impact Awards — SIGGRAPH 2018 Horizon Winners:

This year we have started a new Imapct Award category. Our Horizon Award celebrates the next wave of impactful products being previewed at a particular show. At SIGGRAPH, the winners were:

  • Allegorithmic for its Substance Alchemist tool powered by AI.
  • OTOY and Epic Games for their OctaneRender 2019 integration with UnrealEngine 4.

And while these products and companies didn’t win enough votes for an award, our voters believe they do deserve a mention and your attention: Wrnch, Google Lightfields, Microsoft Mixed Reality Capture and Microsoft Cognitive Services integration with PixStor.

 

Dell EMC’s ‘Ready Solutions for AI’ now available

Dell EMC has made available its new Ready Solutions for AI, with specialized designs for Machine Learning with Hadoop and Deep Learning with Nvidia.

Dell EMC Ready Solutions for AI eliminate the need for organizations to individually source and piece together their own solutions. They offer a Dell EMC-designed and validated set of best-of-breed technologies for software — including AI frameworks and libraries — with compute, networking and storage. Dell EMC’s portfolio of services include consulting, deployment, support and education.

Dell EMC’s Data Science Provisioning Portal offers an intuitive GUI that provides self-service access to hardware resources and a comprehensive set of AI libraries and frameworks, such as Caffe and TensorFlow. This reduces the steps it takes to configure a data scientist’s workspace to five clicks. Ready Solutions for AI’s distributed, scalable architecture offers the capacity and throughput of Dell EMC Isilon’s All-Flash scale-out design, which can improve model accuracy with fast access to larger data sets.

Dell EMC Ready Solutions for AI: Deep Learning with Nvidia solutions are built around Dell EMC PowerEdge servers with Nvidia Tesla V100 Tensor Core GPUs. Key features include Dell EMC PowerEdge R740xd and C4140 servers with four Nvidia Tesla V100 SXM2 Tensor Core GPUs; Dell EMC Isilon F800 All-Flash Scale-out NAS storage; and Bright Cluster Manager for Data Science in combination with the Dell EMC Data Science Provisioning Portal.

Dell EMC Ready Solutions for AI: Machine Learning with Hadoop includes an optimized solution stack, along with data science and framework optimization to get up and running quickly, and it allows expansion of existing Hadoop environments for machine learning.

Key features include Dell EMC PowerEdge R640 and R740xd servers; Cloudera Data Science Workbench for self-service data science for the enterprise; the Apache Spark open source unified data analytics engine; and the Dell EMC Data Science Provisioning Engine, which provides preconfigured containers that give data scientists access to the Intel BigDL distributed deep learning library on the Spark framework.

New Dell EMC Consulting services are available to help customers implement and operationalize the Ready Solution technologies and AI libraries, and scale their data engineering and data science capabilities. Dell EMC Education Services offers courses and certifications on data science and advanced analytics and workshops on machine learning in collaboration with Nvidia.

SIGGRAPH conference chair Roy C. Anthony: VR, AR, AI, VFX, more

By Randi Altman

Next month, SIGGRAPH returns to Vancouver after turns in Los Angeles and Anaheim. This gorgeous city, whose convention center offers a water view, is home to many visual effects studios providing work for film, television and spots.

As usual, SIGGRAPH will host many presentations, showcase artists’ work, display technology and offer a glimpse into what’s on the horizon for this segment of the market.

Roy C. Anthony

Leading up to the show — which takes place August 12-16 — we reached out to Roy C. Anthony, this year’s conference chair. For his day job, Anthony recently joined Ventuz Technology as VP, creative development. There, he leads initiatives to bring Ventuz’s realtime rendering technologies to creators of sets, stages and ProAV installations around the world

SIGGRAPH is back in Vancouver this year. Can you talk about why it’s important for the industry?
There are 60-plus world-class VFX and animation studios in Vancouver. There are more than 20,000 film and TV jobs, and more than 8,000 VFX and animation jobs in the city.

So, Vancouver’s rich production-centric communities are leading the way in film and VFX production for television and onscreen films. They are also are also busy with new media content, games work and new workflows, including those for AR/VR/mixed reality.

How many exhibitors this year?
The conference and exhibition will play host to over 150 exhibitors on the show floor, showcasing the latest in computer graphics and interactive technologies, products and services. Due to the increase in the amount of new technology that has debuted in the computer graphics marketplace over this past year, almost one quarter of this year’s 150 exhibitors will be presenting at SIGGRAPH for the first time

In addition to the traditional exhibit floor and conferences, what are some of the can’t-miss offerings this year?
We have increased the presence of virtual, augmented and mixed reality projects and experiences — and we are introducing our new Immersive Pavilion in the east convention center, which will be dedicated to this area. We’ve incorporated immersive tech into our computer animation festival with the inclusion of our VR Theater, back for its second year, as well as inviting a special, curated experience with New York University’s Ken Perlin — he’s a legendary computer graphics professor.

We’ll be kicking off the week in a big VR way with a special session following the opening ceremony featuring Ivan Sutherland, considered by many as “the father of computer graphics.” That 50-year retrospective will present the history and innovations that sparked our industry.

We have also brought Syd Mead, a legendary “visual futurist” (Blade Runner, Tron, Star Trek: The Motion Picture, Aliens, Time Cop, Tomorrowland, Blade Runner 2049), who will display an arrangement of his art in a special collection called Progressions. This will be seen within our Production Gallery experience, which also returns for its second year. Progressions will exhibit more than 50 years of artwork by Syd, from his academic years to his most current work.

We will have an amazing array of guest speakers, including those featured within the Business Symposium, which is making a return to SIGGRAPH after an absence of a few years. Among these speakers are people from the Disney Technology Innovation Group, Unity and Georgia Tech.

On Tuesday, August 14, our SIGGRAPH Next series will present a keynote speaker each morning to kick off the day with an inspirational talk. These speakers are Tony Derose, a senior scientist from Pixar; Daniel Szecket, VP of design for Quantitative Imaging Systems; and Bob Nicoll, dean of Blizzard Academy.

There will be a 25th anniversary showing of the original Jurassic Park movie, being hosted by “Spaz” Williams, a digital artist who worked on that film.

Can you talk about this year’s keynote and why he was chosen?
We’re thrilled to have ILM head and senior VP, ECD Rob Bredow deliver the keynote address this year. Rob is all about innovation — pushing through scary new directions while maintaining the leadership of artists and technologists.

Rob is the ultimate modern-day practitioner, a digital VFX supervisor who has been disrupting ‘the way it’s always been done’ to move to new ways. He truly reflects the spirit of ILM, which was founded in 1975 and is just one year younger than SIGGRAPH.

A large part of SIGGRAPH is its slant toward students and education. Can you discuss how this came about and why this is important?
SIGGRAPH supports education in all sub-disciplines of computer graphics and interactive techniques, and it promotes and improves the use of computer graphics in education. Our Education Committee sponsors a broad range of projects, such as curriculum studies, resources for educators and SIGGRAPH conference-related activities.

SIGGRAPH has always been a welcoming and diverse community, one that encourages mentorship, and acknowledges that art inspires science and science enables advances in the arts. SIGGRAPH was built upon a foundation of research and education.

How are the Computer Animation Festival films selected?
The Computer Animation Festival has two programs, the Electronic Theater and the VR Theater. Because of the large volume of submissions for the Electronic Theater (over 400), there is a triage committee for the first phase. The CAF Chair then takes the high scoring pieces to a jury comprised of industry professionals. The jury selects then become the Electronic Theater show pieces.

The selections for the VR Theater are made by a smaller panel comprised mostly of sub-committee members that watch each film in a VR headset and vote.

Can you talk more about how SIGGRAPH is tackling AR/VR/AI and machine learning?
Since SIGGRAPH 2018 is about the theme of “Generations,” we took a step back to look at how we got where we are today in terms of AR/VR, and where we are going with it. Much of what we know today couldn’t have been possible without the research and creation of Ivan Sutherland’s 1968 head-mounted display. We have a fanatic panel celebrating the 50-year anniversary of his HMD, which is widely considered and the first VR HMD.

AI tools are newer, and we created a panel that focuses on trends and the future of AI tools in VFX, called “Future Artificial Intelligence and Deep Learning Tools for VFX.” This panel gains insight from experts embedded in both the AI and VFX industries and gives attendees a look at how different companies plan to further their technology development.

What is the process for making sure that all aspects of the industry are covered in terms of panels?
Every year new ideas for panels and sessions are submitted by contributors from all over the globe. Those submissions are then reviewed by a jury of industry experts, and it is through this process that panelists and cross-industry coverage is determined.

Each year, the conference chair oversees the program chairs, then each of the program chairs become part of a jury process — this helps to ensure the best program with the most industries represented from across all disciplines.

In the rare case a program committee feels they are missing something key in the industry, they can try to curate a panel in, but we still require that that panel be reviewed by subject matter experts before it would be considered for final acceptance.

 

Dell makes updates to its Precision mobile workstation line

Recently, Dell made updates to its line of Precision mobile workstations targeting the media and entertainment industries. The Dell Precision 7730 and 7530 mobile workstations feature the latest eighth-generation IntelCore and Xeon processors, AMD Radeon WX and Nvidia Quadro professional graphics, 3200MHz SuperSpeed memory and memory capacity up to 128GB.

The Dell Precision 7530 is a 15-inch VR-ready mobile workstation with large PCIe SSD storage capacity, especially for a 15-inch mobile workstation — up to 6TB. Dell says the 7730 enables new uses such as AI and machine learning development and edge inference systems.

Also new is the 15-inch Dell Precision 5530 two-in-one, which targets content creation and editing and features a very thin design. A flexible 360-degree hinge enables multiple modes of interaction, including support for touch and pen. It features the next-generation InfinityEdge 4K Ultra HD display. The Dell Premium pen offers precise pressure sensitivity (4,096 pressure points), tilt functionality and low latency for an experience that is reminiscent of drawing on paper. The new MagLev keyboard design reduces keyboard thickness “without compromising critical keyboard shortcuts in content creation workflows,” and ultra-thin GORE Thermal Insulation keeps the system cool.

This workstation weighs 3.9 pounds and delivers next-generation professional graphics up to Nvidia Quadro P2000. With enhanced 2666MHz memory speeds up to 32GB, users can accelerate their complicated workflows. And with up to 4TB of SSD storage, users can access, transfer and store large 3D, video and multimedia files quickly and easily.

The fully customizable 15-inch Dell Precision 3530 mobile workstation features eighth-generation Intel Core and next-generation Xeon processors, memory speeds up to 2666MHz and Nvidia Quadro P600 professional graphics. It also features a 92WHr battery and wide range of ports, including HDMI 2.0, Thunderbolt and VGA.

GTC embraces machine learning and AI

By Mike McCarthy

I had the opportunity to attend GTC 2018, Nvidia‘s 9th annual technology conference in San Jose this week. GTC stands for GPU Technology Conference, and GPU stands for graphics processing unit, but graphics makes up a relatively small portion of the show at this point. The majority of the sessions and exhibitors are focused on machine learning and artificial intelligence.

And the majority of the graphics developments are centered around analyzing imagery, not generating it. Whether that is classifying photos on Pinterest or giving autonomous vehicles machine vision, it is based on the capability of computers to understand the content of an image. Now DriveSim, Nvidia’s new simulator for virtually testing autonomous drive software, dynamically creates imagery for the other system in the Constellation pair of servers to analyze and respond to, but that is entirely machine-to-machine imagery communication.

The main exception to this non-visual usage trend is Nvidia RTX, which allows raytracing to be rendered in realtime on GPUs. RTX can be used through Nvidia’s OptiX API, as well as Microsoft’s DirectX RayTracing API, and eventually through the open source Vulkan cross-platform graphics solution. It integrates with Nvidia’s AI Denoiser to use predictive rendering to further accelerate performance, and can be used in VR applications as well.

Nvidia RTX was first announced at the Game Developers Conference last week, but the first hardware to run it was just announced here at GTC, in the form of the new Quadro GV100. This $9,000 card replaces the existing Pascal-based GP100 with a Volta-based solution. It retains the same PCIe form factor, the quad DisplayPort 1.4 outputs and the NV-Link bridge to pair two cards at 200GB/s, but it jumps the GPU RAM per card from 16GB to 32GB of HBM2 memory. The GP100 was the first Quadro offering since the K6000 to support double-precision compute processing at full speed, and the increase from 3,584 to 5,120 CUDA cores should provide a 40% increase in performance, before you even look at the benefits of the 640 Tensor Cores.

Hopefully, we will see simpler versions of the Volta chip making their way into a broader array of more budget-conscious GPU options in the near future. The fact that the new Nvidia RTX technology is stated to require Volta architecture CPUs leads me to believe that they must be right on the horizon.

Nvidia also announced a new all-in-one GPU supercomputer — the DGX-2 supports twice as many Tesla V100 GPUs (16) with twice as much RAM each (32GB) compared to the existing DGX-1. This provides 81920 CUDA cores addressing 512GB of HBM2 memory, over a fabric of new NV-Link switches, as well as dual Xeon CPUs, Infiniband or 100GbE connectivity, and 32TB of SSD storage. This $400K supercomputer is marketed as the world’s largest GPU.

Nvidia and their partners had a number of cars and trucks on display throughout the show, showcasing various pieces of technology that are being developed to aid in the pursuit of autonomous vehicles.

Also on display in the category of “actually graphics related” was the new Max-Q version of the mobile Quadro P4000, which is integrated into PNY’s first mobile workstation, the Prevail Pro. Besides supporting professional VR applications, the HDMI and dual DisplayPort outputs allow a total of three external displays up to 4K each. It isn’t the smallest or lightest 15-inch laptop, but it is the only system under 17 inches I am aware of that supports the P4000, which is considered the minimum spec for professional VR implementation.

There are, of course, lots of other vendors exhibiting their products at GTC. I had the opportunity to watch 8K stereo 360 video playing off of a laptop with an external GPU. I also tried out the VRHero 5K Plus enterprise-level HMD, which brings the VR experience to whole other level. Much more affordable is TP-Cast’s $300 wireless upgrade Vive and Rift HMDs, the first of many untethered VR solutions. HTC has also recently announced the Vive Pro, which will be available in April for $800. It increases the resolution by 1/3 in both dimensions to 2880×1600 total, and moves from HDMI to DisplayPort 1.2 and USB-C. Besides VR products, they also had all sorts of robots in various forms on display.

Clearly the world of GPUs has extended far beyond the scope of accelerating computer graphics generation, and Nvidia is leading the way in bringing massive information processing to a variety of new and innovative applications. And if that leads us to hardware that can someday raytrace in realtime at 8K in VR, then I suppose everyone wins.


Mike McCarthy is an online editor/workflow consultant with 10 years of experience on feature films and commercials. He has been involved in pioneering new solutions for tapeless workflows, DSLR filmmaking and multi-screen and surround video experiences. Check out his site.