Nvidia GTC 2018 - March 26th - 29th

Discussion in 'Gaming (Software and Graphics Cards)' started by hmscott, Mar 26, 2018.

  1. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    What’s Happening at GTC 2018
    Published on Mar 27, 2018
    Check out the latest and greatest from this year’s NVIDIA GPU Technology Conference, the world’s premier AI event. All the highlights are featured here: http://www.GPU-tech-conf.com

    I Am AI: GTC 2018 kickoff video
    Published on Mar 27, 2018
    The GPU Technology Conference 2018 keynote kicked off showing the many ways AI is changing our lives.

    NVIDIA Volta in the Cloud at GTC 2018
    Published on Mar 27, 2018
    At GTC 2018, learn how AWS was first to the cloud with NVIDIA Tesla V100. AWS and NVIDIA are partnering to revolutionize industries and companies by enabling developers to build powerful machine learning applications on the most advanced, highest-performing GPU-accelerated cloud infrastructure.
     
  2. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    NVIDIA GTC 2018 supercut
    Published on Mar 28, 2018
    NVIDIA's President and CEO, Jensen Huang, kicks off their GTC technology conference in Silicon Valley today with a keynote. Here it is in under 15 minutes.
     
    Last edited: Mar 28, 2018
  3. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    Gone in 60.121 seconds: Your guide to the pricey new gear Nvidia teased at its annual GPU fest
    Yours if you can afford it... and wait long for the fabs to make the chips
    By Katyanna Quach 28 Mar 2018 at 07:29
    https://www.theregister.co.uk/2018/03/28/nvidia_gtc_roundup/

    "GTC Nvidia CEO Jensen Huang flaunted a bunch of stuff, from bigger boxes of graphics chips to robot simulators, at its 2018 GPU Technology Conference (GTC) in Silicon Valley on Tuesday.

    Here's a quick summary of what went down, minus the fluff.
    • Huang acknowledged in a Q&A session that there is indeed a shortage right now of top-end Nv GPUs, mainly due to people grabbing them for cryptocurrencies and blockchain ledgers. Nvidia simply can't make enough Tesla chips to go around, partly due to demand and partly due to yield, we reckon. Thus far, the chip designer's only solution is: make and ship as many GPUs as possible. The biz wants to concentrate on giving hardware to cloud and supercomputer builders, gamers, graphics artists, scientists, engineers, enterprises... anyone but those annoying crypto-kids.
    • If you've got roughly a million dollars to blow on deep-learning research, Pure Storage and Nvidia have produced a hyperconverged stack of flash memory and flagship Tesla Volta GV100 GPUs, plus some extra bits and pieces, called AIRI. Assuming the GPUs are available, natch.
    • Programmers, engineers, and other techies dreaming of creating robots that sport some sort of machine intelligence can ask nicely to check out Isaac: this is a forthcoming software development kit and simulator, with libraries, drivers and other tools, for designing, testing and building machine-learning-based robotic gizmos.
    • Speaking of programmers, TensorRT 4 – a GPU-accelerated deep-learning inference framework – has landed. Nvidia and Google boffins have integrated TensorRT into TensorFlow 1.7, if you prefer to use that engine for AI coding.
    • Nvidia is stepping into the world of networking with the NVSwitch, a switch for its high-speed NVLink interconnect. Meanwhile, Tesla V100 GPUs – Nvidia's top of the line chips for data centers – are now available with 32GB of HBM2 memory rather than the usual 16. Tying it all together is the new DGX-2 workstation, which has 16 32GB V100s connected via 12 NVSwitches for 2.4TB/s of bisection bandwidth and 512GB total HBM2 memory. The box has 1.5TB of system memory, two Intel Xeon CPUs, 30TB of flash storage, and Infiniband, 100GbE, and 10/25GbE interfaces. Nvidia claims it can hit as high as 2 PTLOPS with mixed-precision floating-point math. Yours for $400,000. This gear builds upon the $150,000 DGX-1 and DGX Station previously launched.
    • Nvidia has jumped aboard Project Trillium, Arm's effort to cram AI inference processing into chips powering wearables, gadgets, and Internet-of-Things devices. This is aimed at silicon designers: Nvidia is offering NVDLA as a free and open architecture for building deep-learning accelerators into hardware.
    • If you're working on self-driving cars – and who isn't – you may or may not be tempted by Nvidia's new Drive Constellation, a stack of boxes for simulating autonomous vehicle control software without crashing robo-rides or killing people (right, Uber?) Don't hold your breath – these GPU-accelerated machines won't arrive until the third quarter of 2018 at the earliest, and that's only for Nv's favorite customers.
    • Scientists, engineers and artists needing some serious fire power for simulations and rendering are offered the new Quadro GV100 with 32GB of HBM2 memory. Each offers up to 7.4 TFLOPS of double-precision floating-point math performance, or 14.8 TFLOPS with single-precision, and can be linked via an NVLink interconnect to form one GPU, doubling the maximum potential performance and HBM2 capacity. These should be available now direct from Nvidia, or from suppliers next month.
    • For those interested in virtualized GPUs in the cloud, there's a bunch of announcements here. And if you're a virtual reality designer or developer, there's stuff to tease you here.
    Of course, this is all subject to GPU availability."

    Comments
     
  4. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    GTC 2018 Keynote with NVIDIA CEO Jensen Huang

    Published on Mar 28, 2018
    Watch a replay of NVIDIA CEO Jensen Huang's keynote address at the GPU Technology Conference 2018 in Silicon Valley, where he unveiled a series of advances to NVIDIA’s deep learning computing platform that deliver a 10x performance boost on deep learning workloads; launched the Quadro GV100 GPU, transforming workstations with 118.5 TFLOPS of deep learning performance; introduced NVIDIA DRIVE Constellation to run self-driving car systems for billions of simulated miles, and much more.

    Jump ahead to:

    2:38 - NVIDIA founder and CEO Jensen Huang takes the stage
    3:53 - Computer graphics and NVIDIA RTX ray-tracing technology
    11:40 - Epic Games' Star Wars themed "Reflections" demo, with real-time ray tracing
    19:06 - Announcing Quadro GV100 with NVIDIA RTX
    27:54 - Rise of GPU computing - science needs supercharged computers
    38:17 - Project Clara medical imaging supercomputer demo
    48:24 - Introducing Tesla V100 GPU with 32GB of HBM2 memory
    54:30 - Introducing the world's largest GPU, NVIDIA DGX-2 with NVSwitch
    1:08:55 - Advancing the software stack for AI inferencing with TensorRT 4, NVIDIA GPU Cloud
    1:23:20 - Kubernetes on NVIDIA GPUs
    1:33:45 - NVIDIA Research conditional GANs demo
    1:37:56 - Future of autonomous vehicles - data is the new source code
    1:49:25 - Self-driving car technology demo, NVIDIA DRIVE roadmap with Orin
    2:00:31 - VR simulated training demo, announcing NVIDIA DRIVE Constellation and DRIVE Sim
    2:11:18 - Robotics boosts every industry, introducing SDK for NVIDIA Isaac robotics platform
    2:14:45 - Remote control of autonomous car in VR using NVIDIA Holodeck
    2:22:17 - The GPU computing revolution continues

    GTC 2018 NVIDIA News Recap
    Published on Mar 28, 2018
    Watch this summary of NVIDIA's key announcements from the keynote at the GPU Technology Conference 2018 in Silicon Valley, featuring updates in computer graphics, AI computing, robotics, VR, and more.
    Read more details: https://nvda.ws/2J1RHQ2


    NVIDIA DRIVE—GTC 2018 Demonstration
    Published on Mar 28, 2018
    At this year’s GPU Technology Conference, NVIDIA illustrated some of its AI building blocks for self-driving cars and an autonomous drive through city streets and onto a highway.


    I am AI Docuseries, Episode 6: Running Wild for Nature Conservation - Wildbook

    Published on Mar 28, 2018
    Wildbook, an AI-powered software developed by researchers, is helping the Kenyan government track zebra movement to save them from extinction.


    NVIDIA Isaac platform for robotics at GTC 2018
    Published on Mar 28, 2018
    The robotics revolution shifted into high gear at this year’s NVIDIA GPU Technology Conference. Watch to learn how to accelerate the development and deployment of robotics with the NVIDIA Isaac platform. The new Isaac software development kit (SDK) is a collection of libraries, drivers, APIs, and other tools that will save manufacturers, researchers, startups, and developers hundreds of hours by making it easy to add AI into next-generation robots for perception, navigation, and manipulation.
    Read the blog here: https://nvda.ws/2J31TaY
     
    Last edited: Mar 28, 2018
  5. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    Discover the World’s Largest GPU: NVIDIA DGX-2
    Published on Mar 28, 2018
    Watch to learn how we’ve created the first 2 petaFLOPS deep learning system, using NVIDIA NVSwitch to combine the power of 16 V100 GPUs for 10X the deep learning performance.


    Visual Tour of GTC 2018
    Published on Mar 28, 2018
    See what's going on at our GPU Technology Conference, the premier AI and deep learning event in Silicon Valley. Read about what we announced during this event: https://nvda.ws/2GzqVjD


    GTC 2018: Inception Awards Winners Recap
    Published on Mar 28, 2018
    In this year’s NVIDIA Inception Program, more than 200 AI startups applied to compete in three categories—healthcare, enterprise, and autonomous systems—for a chance to win part of a $1 million prize pool. The top twelve semi-finalists participated in Inception Pitch Day to earn one of the six finalist spots at our annual GPU Technology Conference. Watch the winning pitches from Subtle Medical, AiFi, and Kinema Systems, delivered to a high-profile panel of judges from Goldman Sachs, Fidelity Investments, and Coatue Management. Read the blog here: https://nvda.ws/2GEKQxs


    VMware powers Virtualization at GPU Technology Conference

    Published on Mar 28, 2018
    In this video from from 2018 GPU Technology Conference, Ziv Kalmanovich from VMware and Fred Devoir from NVIDIA describe how they are working together to bring the benefits of virtualization to GPU workloads.
     
    Last edited: Mar 28, 2018
  6. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    Jensen's Coffee Delivery Bot & AI at GTC
    Published on Mar 28, 2018
    These collaborative working robots were shown at GTC. Veo Robotics works with humans, Kinema packs pallets, and NVIDIA's delivers coffee to Jensen.
    We show a few cool robots at GTC 2018. This was stuff that was just kind of neat -- not necessarily directly related to our audience, but stuff that you all might find interesting or amusing. The AI bots in this video are one half collaborative working (augmenting human abilities) and one half rudimentary -- closing and opening drawers, for instance.
     
  7. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    Try our new driverless car software says Nvidia, as it suspends driverless car trials
    Post crash test hits share price
    By Gareth Corfield 28 Mar 2018 at 18:32
    https://www.theregister.co.uk/2018/03/28/nvidia_halts_driverless_trials_announces_simulator/
    [​IMG]
    "Nvidia chief exec Jen-hsung Huang waving a Drive PX board"

    "Nvidia has declared the creation of a “cloud-based system” for testing driverless cars – just as it, er, suspended testing of driverless cars.

    Hot on the heels of its announcement of its Drive Constellation system, the chipmaker then quietly suspended autonomous vehicle tests that use its technology after a pedestrian was killed by an Uber vehicle operating autonomously in Arizona.

    "Ultimately AVs will be far safer than human drivers, so this important work needs to continue. We are temporarily suspending the testing of our self-driving cars on public roads to learn from the Uber incident," a Nvidia spokesperson told CNN. "Our global fleet of manually driven data collection vehicles continue to operate."

    The announcement saw Nvidia's stock price fall by as much as 10 per cent before recovering slightly.

    The Drive Constellation system is a two-server offering intended for simulated trials of autonomous vehicle software. One server runs Nvidia’s Drive Sim software, which simulates sensors such as cameras, radar and LIDAR, while the other server simulates “the complete autonomous vehicle software stack”, using sensor data generated by the first server.

    “With virtual simulation, we can increase the robustness of our algorithms by testing on billions of miles of custom scenarios and rare corner cases, all in a fraction of the time and cost it would take to do so on physical roads,” Nvidia’s Rob Csongor, a company veep, said in the inevitable canned statement.

    Evidently Nvidia, along with the other firms that have adopted its Drive PX autonomous driving suite for their auto autos, will now have even more time on their hands to road-test the Drive Constellation.

    At the CES consumer tech knees-up in Las Vegas last year, Nvidia chief exec Jen-hsun Huang promised to put Level 4 driverless cars on the roads by 2020, in partnership with Audi. It would appear there is a significant speed bump along that particular road."

    Comments
     
  8. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    HW News - Next-Gen Gaming GPUs, GPP (Cont'd), Meltdown Performance
    Published on Apr 1, 2018
    We talk about hardware news for the past week, including next-generation gaming GPUs (i.e. Turing, Ampere), Meltdown performance, GPP, and more.


    4x Volta Custom EK Water Cooling (& DGX-2 Torn Down)
    Published on Mar 29, 2018
    We got a hands-on with the DGX-2 and DGX1 Station, the latter of which has 4x Volta V100s under a custom EK water cooling loop.


    GDDR6 Price, New GPU Launch Timelines, & Mass Production
    Published on Mar 27, 2018
    SK Hynix's GDDR6 memory is coming soon, and it'll land on the next-generation of nVidia GPUs -- the fabled GTX 1180 (or 2080) sometime... eventually.
     
    Last edited: Apr 1, 2018
  9. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    RAID No More: GPUs Power NSULATE for Extreme HPC Data Protection

    Published on Apr 2, 2018
    "In this video from GTC 2018, Alexander St . John from Nyriad demonstrates how the company's NSULATE software running on Advanced HPC gear provides extreme data protection for HPC data.

    "RAID6 was standardized in 1993 in an era of single-core computing. For exascale computing, RAID is an obstacle to higher performance and resilience. NSULATE revolutionises the role of the storage controller by replacing a fixed-function RAID controller with a powerful general-purpose GPU. Using a GPU as a storage controller enables the calculation of several storage functions on the same high performance controller, enabling more efficient storage processing without sacrificing performance. This enables modern storage appliances to deliver unprecedented speed, scale, security, storage efficiency and intelligence in real-time.

    Extreme Resilience
    NSULATE offers extreme data resilience. It uses a GPU to generate erasure encoded parity calculations to enable automatic data recovery on scales impossible with a RAID card or a CPU.

    While traditional RAID and erasure coding solutions support parity calculations between 2 and 6, NSULATE supports real-time Reed-Solomon erasure coding up to 255 parity. Stable I/O throughput can be maintained even while experiencing dozens of simultaneous device failures and corruption events across an array.

    Continuous Verification
    NSULATE adds support for cryptographic data verification and recovery to all storage applications. NSULATE includes a complete suite of hash functions for corruption detection and recovery, including CRC32C as well as the NIST compatible cryptographic hash functions, SHA2 & SHA3. NSULATE also includes support for blockchain cryptographic hash functions SHA2 Merkle & SHA3 Merkle for blockchain auditable storage solutions."

    Learn more: http://www.nyriad.com/products/nsulate/
    and
    https://www.advancedhpc.com/ "

    Inside the new NVIDIA DGX-2 Supercomputer with NVSwitch

    Published on Apr 2, 2018
    "In this video from the GPU Technology Conference, Marc Hamilton from NVIDIA describes the new DGX-2 supercomputer with the NVSwitch interconnect.

    "The rapid growth in deep learning workloads has driven the need for a faster and more scalable interconnect, as PCIe bandwidth increasingly becomes the bottleneck at the multi-GPU system level.

    NVLink is a great advance to enable eight GPUs in a single server, and accelerate performance beyond PCIe. But taking deep learning performance to the next level will require a GPU fabric that enables more GPUs in a single server, and full-bandwidth connectivity between them.

    NVIDIA NVSwitch is the first on-node switch architecture to support 16 fully-connected GPUs in a single server node and drive simultaneous communication between all eight GPU pairs at an incredible 300 GB/s each. These 16 GPUs can be used as a single large-scale accelerator with 0.5 Terabytes of unified memory space and 2 petaFLOPS of deep learning compute power."

    Learn more: https://www.nvidia.com/en-us/data-cen... "
     
    KY_BULLET likes this.
  10. hmscott

    hmscott Notebook Nobel Laureate

    Reputations:
    4,348
    Messages:
    15,337
    Likes Received:
    18,834
    Trophy Points:
    931
    Disney showed off what Real Time Ray tracing of Star Wars looks like with 8 Nvidia GPUs via SVGN.io

    Published on Apr 1, 2018
    Shaky video of the last minute or so of a session at GTC 2018 where Disney showed off what Real Time Ray tracing of Star Wars looks like with 8 Nvidia GPU's. Only 8 GPUS. This is possible thanks to AI Denoising technology.

    The session was called: S8414 - Walt Disney Imagineering Technology Preview: Real-time Rendering of a Galaxy Far, Far Away
    Walt Disney Imagineering strives to create amazing guest experiences at Disney Parks worldwide. Partnering with Nvidia and Epic Games, Imagineering has developed new technology to drive one of the key attractions at the upcoming Star Wars: Galaxy's Edge opening in Disneyland Resort, CA and Disney's Hollywood Studios, FL. Come learn more about how we took advantage of the newest in Nvidia hardware and the technical modifications that we made for the Unreal Engine which will allow 8 GPUs to render at unprecedented quality and speed.

    Silicon Valley Global News SVGN.io
     
    KY_BULLET likes this.
Loading...

Share This Page