Skip to main content

Filed under:

Kepler in the clouds: Nvidia's 2012 GPU Technology Conference

Nvidia' 2012 GPU Technology Conference (GTC) conference brought the usual array of graphics processors, but the company is trying its hand at something new: putting the power of those processors in the cloud. Nvidia's Kepler-based VGX and GeForce Grid distribute graphics processing. Nvidia wasn't the only company showing off wares at the event, but we've got their news and everybody else's all right here.

  • Sean Hollister

    May 16, 2012

    Sean Hollister

    Ubitus GameCloud: the white-label cloud gaming service seeking a US audience

    Ubitus stock 640
    Ubitus stock 640

    When it comes to streaming games to smartphones, tablets and televisions, OnLive and Gaikai may have some company someday soon. Taiwan-based Ubitus is looking to provide a white-label cloud gaming service to cellular carriers and internet service providers in the US. Like Gaikai, the company's using Nvidia's new GeForce Grid GPU to rapidly capture and stream compressed H.264 video frames over the internet, and even its existing technology already has a presence in Japan: the company says its service, re-branded G-Cloud, has 500,000 active users on NTT Docomo's LTE network.

    We met up with Ubitus at Nvidia's 2012 GPU Technology Conference in San Jose this week, and while we weren't able to properly test the service under show conditions, the technology definitely works at a basic level: we streamed Assassin's Creed: Brotherhood to a Samsung Galaxy Tab 8.9, and Street Fighter IV: Arcade Edition on a Galaxy Nexus. Ubitus tells us that game pricing and the streaming video resolution will be determined by its prospective partners and available bandwidth, but laid out some general ideas: a game like Street Fighter IV could be cost effective at, say, a $1.99 monthly subscription, a company rep suggested.

    Read Article >
  • T.C. Sottek

    May 15, 2012

    T.C. Sottek

    Nvidia flaunts Kepler's GPU power in video demos (update: 1080p)

    Kepler video demos
    Kepler video demos

    Nvidia is flexing its graphics muscle at the 2012 GPU Technology Conference, and the trio of videos below show off Kepler's new visual tricks. The first video demonstrates Kepler's real-time raytracing — a realistic technique for simulating light as it encounters virtual objects — in concert with complex physics simulations. Watching the light realistically interact with real-time object destruction and fluid simulations is quite impressive.

    Update: We've uploaded a new 1080p copy of the raytracing video. Happy viewing!

    Read Article >
  • Evan Rodgers

    May 15, 2012

    Evan Rodgers

    Nvidia announces Tesla K10 and K20 GPUs

    Nvidia has announced two new Kepler-based processing units for professionals that need to leverage high performance computing in their research — the Telsa K10 and K20 graphics cards. The K10, based on the GK104 core currently used in Nvidia's high end desktop cards like the GTX 680 and 690, will be available immediately. The K20, based on a new GK110 core, will be available in Q4 of this year. Both cards are part of Nvidia's CUDA 5, a programming platform for parallelizing intensive data processing tasks that's slated for release to developers in Q3

    These new cards feature improved "streaming multiprocessors" — the micro-cores within the GPU — with better energy efficiency, as well as "dynamic parallelism" which allows for the GPU to route data in the most efficient way possible. The Tesla's Hyper-Q feature allows the cards to work in unison with multiple CPU cores, keeping system bottlenecks to a minimum. Nvidia says both of these cards focus on maximizing performance with smart resource allocation while providing the best energy efficiency possible, which means the technical computing pros using these cards will be able to crunch more numbers with less power.

    Read Article >
  • Sean Hollister

    May 15, 2012

    Sean Hollister

    Nvidia announces GeForce Grid: cloud gaming direct from a GPU, with games by Gaikai

    GeForce Grid Nvidia stock 1024
    GeForce Grid Nvidia stock 1024

    Nvidia just finishing telling us about how it's going to stick a Kepler GPU in the cloud: now, CEO Jen-Hsun Huang is telling us how it will use distributed graphics to stream low-latency video games from the internet to computers that don't have one themselves. Nvidia's partnered with cloud gaming provider Gaikai, and claims that the GeForce Grid GPU has reduced latency of streaming games to just ten milliseconds by capturing and encoding game frames rapidly, and in a single pass, and promises that the enhanced Gaikai service will be available on TVs, tablets and smartphones running Android and iOS.

    David Perry from streaming game company Gaikai is on stage to discuss and demo the technology now; Gaikai also announced that it's working in partnership with Nvidia to produce content for GeForce Grid. Perry showed off an unreleased FPS shooter called Hawken running on an Asus Transformer Prime powered by the new GeForce Grid GPU. Perry played against an opponent who was running the game on an LG Cinema TV without the need for an external console — Huang made a big deal of showing off an ethernet cord hooked up to the TV, saying that the cord was the console. One of the most noteworthy aspects of the GeForce Grid demo is the fact that gamers can play across platforms of varying power, thanks to the Grid doing all the heavy lifting. Also of note in that demo was that the server hosting the gameplay was a good 10 miles away — but the gameplay was lag-free, as you'd expect to see when playing on a local machine.

    Read Article >
  • Nathan Ingraham

    May 15, 2012

    Nathan Ingraham

    Nvidia VGX announced: the world's first GPU developed for cloud computing

    Nvidia Kepler Cloud GPU stock 1024
    Nvidia Kepler Cloud GPU stock 1024

    Nvidia CEO Jen-Hsun Huang is kicking off the 2012 GPU Technology Conference (GTC) conference right now, and he just announced that Nvidia has developed the world's first GPU for cloud computing, based on Nvidia's Kepler GPU. He's calling it the Nvidia VGX, and described it as "a technology that virtualizes the computing environment such that irrespective of your computing device, we can provide access to the corporate technologies and data that you need." Nvidia envisions deploying the VGX in a data center so that employees can access the power of the virtual machine from any device. It's a pretty scalable solution, as well — a single VGX node can serve up to 100 users simultaneously, and Jen-Hsun Huang demonstrated that live on stage.

    In a demo, Nvidia showed off an iPad running Citrix Receiver connected to the VGX virtual GPU and displayed a 3D simulation running in Autodesk on Windows that ran in real time. A second demo showed Grady Cofer (visual effects supervisor at Industrial Light & Magic) using a Macbook Air to remotely access the ILM render farm to make changes to scenes from The Avengers and Battleship in real-time.

    Read Article >