Updates from Joe RSS Toggle Comment Threads | Keyboard Shortcuts

  • Joe 6:14 pm on September 15, 2010 Permalink  

    VDAC – Hardware Solutions For GPU Rendering 



    RenderStream is pleased to announce our GPU based product line ideal for GPU renderers such as V-Ray and Octane. The RenderStream VDAC (Visualization and Data Analysis Cluster) family of products come equipped with 2-8 GPUs in a single workstation. Whether you are a freelancer looking for a GPU based production workstation or a large studio in need of a GPU server farm, look no further than RenderStream.

    Why use GPU rendering?
    The iterative process of evaluating multiple test renders to achieve a final result can be very time consuming. Make a change, render it, see how it looks and repeat the process on and on…It is section of the production pipeline that GPU rendering will have the greatest affect. In the near future we will start to see GPU based rendering for final shots, but we aren’t quite there yet. Nonetheless, the speed advantages a studio gains by using GPU based rendering during the creative process of approaching a final shot, cannot be over looked.

    Why would you want a GPU server farm?
    The short answer is licensing. For example, V-Ray’s RT for GPUs renderer allows up to 10 servers per license regardless of how many GPUs are on that machine. Packing as many GPUs into a single server can allow studios to get the most bang for their buck. In terms of computation density, our 8 GPU workstations (or 7 GPU + QDR Infiniband) are among the highest on the market today and are the perfect solution for a GPU server farm.

    Another reason is to take advantage of distributed GPU rendering. Just like with a traditional renderfarm comprised of CPUs, certian GPU based renderers allow you to access the GPUs power over a network. This eliminates the need to have all the available GPU “horsepower” at your desk, it can be housed in your server room along with your traditional CPU renderfarm.



    We would like to point out that we can deliver systems with up to 16 GPUs today and have plans to roll out systems with 32 GPUs, 64 GPUs and beyond. Additional information on these systems will require an NDA. These systems will be targeted for large scale studios and will ultimately be the fastest render farm solutions on the planet.

    For a more detailed presentation on our GPU based VDAC product line including our high end Maya-based compositors  using a perfect balance of processors / GPU-acceleration / memory / IO please download this pdf: http://www.renderstream.com/VDAC.pdf. System specs can be found on pages 9-12.

    If you are interested in a quote, you can get in touch with us at 512-850-4098 or email us at info@renderstream.com

     
  • Joe 6:39 pm on July 28, 2010 Permalink  

    CGarchitect and RenderStream GPU Review 

    RenderStream recently assisted Jeff Mottle over at http://www.cgarchitect.com on one of the most comprehensive graphics card reviews geared specifically for the CG industry. Jeff reviewed the top graphics cards from NVIDIA and ATI and evaluated their performance in the top apps in our industry as well as how professional series cards stack up against consumer cards.

    3DSMAX2011-RANK

    This graph from the article is showing the ranking for a couple of 3DSMax / MR tests where shorter bars are better.

    “Anyone who has worked in this industry for any length of time has at one point found themselves specifying a video card for their rendering workstation. The seemingly endless lineup of models and often cryptic specifications make selecting the best card a daunting task.  Most rely upon product reviews from the gaming industry and/or whatever their budget will allow.  Neither however provide the insight required to properly choose a card in the visualization field.  The purpose of this review is to evaluate some of the latest cards in the industry in the context of viewport performance for architectural visualization professionals…”

    You can read the full review here: http://www.cgarchitect.com/news/Reviews/Review076_1.asp

    It should be noted that the tests focused on viewport performance. How well each card would perform in a GPU rendering application was not evaluated due to the early state of that technology. Once GPU rendering matures further we plan to do another review and include GPU rendering in the performance evaluations and well as evaluate the recently released GPUs

    Looking ahead:

    After attending this year’s SIGGRAPH event is Los Angeles, it is quite obvious that the next year is going to be very exciting for the CG industry. This is thanks in no small part to the advances we will see in GPU rendering and server side 3D applications that are driven by the GPU.

    realityserver

    NVIDIA just  announced their latest line of quadro GPUs that are up to 5X faster than the previous generation of FX cards.

    “The newest NVIDIA® Quadro® professional solutions are true technological breakthroughs, delivering up to 5x faster performance across a broad range of design, animation and video applications. Built on the innovative NVIDIA Fermi architecture, the latest Quadro offerings are the first professional-class GPUs to integrate high performance computing capabilities with advanced visualization techniques. Featuring new Scalable Geometry Engine™ technology, Quadro can deliver an unheard of 1.3 billion triangles per second, shattering previous 3D graphics limitations. With Quadro solutions, your work flows — you can design, iterate and deliver higher quality projects in less time.” – http://www.nvidia.com/object/quadro-fermi-overview.html

    The Specs for the new Quadro line are as follows:

    Quadro 4000: 2 GB RAM, 256 CUDA Cores

    Quadro 5000: 2.5 GB RAM, 352 CUDA Cores

    Quadro 6000: 6 GB RAM, 448 CUDA Cores

    These are all big memory cards but remember GPU accelerated renderers will need the memory to gain the most benefit. We look forward to getting our hands on these cards and bringing you some more useful perfromance data. Stay tuned!

     
  • Joe 1:51 pm on June 21, 2010 Permalink  

    Artie | A Turnkey Solution for Small to Mid-Size Studios 

    6U enclosure with a single PCoIP workstation, 2X RenderStream Ridiculous Speed 4 render farm and a switch shown above. 4U, 6U, 12U and 24U enclosures available depending on needs.

    6U enclosure with a single PCoIP workstation, 2X RenderStream Ridiculous Speed 4 render farm and a switch shown above. 4U, 6U, 12U and 24U enclosures available depending on needs.

    RenderStream is pleased to announce Artie, a highly scalable and secure turnkey solution targeted for small to mid-size production houses. Modeled after Omnia, Artie is designed to easily scale up as your business grows. Everything you need to succeed is housed in a small easy to manage, highly secure rack. In the simplest configuration , Artie can be configured with a single rack mounded workstation and RenderStream’s Ridiculous Speed render farm. In the most advanced configuration, Artie can come complete with PCoIP workstations, PCoIP compositing workstations, a RenderStream renderfarm, Qube! Supervisor Server, switches and UPS. (More …)

     
  • Joe 1:56 pm on May 27, 2010 Permalink  

    Omnia. Complete Turnkey Animation Studio. 

    The configuration that is shown above does not contain the first tier extreme-speed 2u and 4u solid state drive arrays. Price depends greatly on desired configuration. Contact us for a quote.

    The configuration that is shown above does not contain the first tier extreme-speed 2u and 4u solid state drive arrays. Price depends greatly on desired configuration. Contact us for a quote.

    RenderStream is pleased to announce Omnia, our turnkey rack mounted animation studio. RenderStream Omnia comes complete with PCoIP workstations and compositors. For the render farm, up to 240 Intel 5600-series Xeon cores per 7u using our Ludicrous-Speed-20 chassis managed by our PipelineFX-based Qube! Farm Supervisor with Gigabit, optical fiber and or Infiniband three-tiered storage that is transparently managed to automatically stage files based on the users’ demand.

    (More …)

     
  • Joe 2:49 pm on May 4, 2010 Permalink  

    GPU Revolution Part 2 | MachStudio Pro 

    msplogo


    At RenderStream we have been keeping a close eye on the advances in GPU accelerated rendering. In this second edition of our GPU Revolution series we wanted to find out more about studio|gpu’s MachStudio Pro.

    I’m sure many of you have heard about MSP since it came out. I’ll be the first to admit that when I first looked at MSP several months ago, I thought the image quality it produced wasn’t spectacular. All the examples I saw had an overall flat look to them that reminded me of the pre-global illumination days. My opinion has certainly changed. MSP shines as a previsualization tool but many artists are using the software as their production renderer – with results that are very comparable to the quality produced by V-Ray and Mental Ray. You can render out animation sequences in most of the popular file formats and the best part is you can do this hundreds of times faster than on the CPU.

    (More …)

     
  • Joe 7:29 pm on April 5, 2010 Permalink  

    Announcing our VDAC 8-16 GPU Systems 

    vdac

    RenderStream is pleased to announce our VDAC (Visual and Data Analysis Cluster) which uses the power of up to 16 GPUs to breeze through computational problems like those found in GPU based rendering, oil and gas, medical research, augmented reality and mobile visualization enhancement. (Application allowing)

    (More …)

     
  • Joe 3:30 pm on January 11, 2010 Permalink  

    Are You Ready For The GPU Revolution? Part 1 

    final02

    Update: Click HERE for more information on our cost effective 8 GPU render servers.

    You probably have heard a lot about GPU acceleration in recent months. In this article we’ll take a look at what exactly we can expect from a GPU accelerated 3D animation package. We’ll talk to some industry experts and examine how to tackle this new computational method from a hardware standpoint.

    First let us provide you with a background of our company so you know where we’re coming from. RenderStream spun off from a designer of scientific supercomputers and we have been using GPUs to solve computationally intensive problems in the semiconductor industry for some time. It turns out those problems are similar to the computational problems found in rendering and that’s how RenderStream was born. We’re excited to see the computer graphics industry take advantage of the GPU as we’ve seen first hand it’s advantages in other industries. With that in mind, we are eager to help the CG community apply this new technology to their pipelines. (More …)

     
  • Joe 5:11 pm on September 8, 2009 Permalink  

    Costs associated with high computation render farms. 

    Building a render farm seems rather simple on the surface.  After all, it doesn’t take a rocket scientist to grasp the basic concept that assembling a cluster of computers to render a series of frames will complete the task faster than a single computer, providing you have the proper software for the job. However, to do this efficiently requires an understanding of the cluster’s expectations and the environment in which it will operate. Regardless of what solution you buy, there will be hidden costs associated with it. This article attempts to uncover those hidden costs so you can make the best possible decision for your work flow.

    Note: This article addresses the costs associated with high computation render farms. We plan to do this same cost analysis on a low computation render farm in the coming weeks so stay tuned :)

    farm

    (More …)

     
  • Joe 12:15 pm on August 28, 2009 Permalink  

    RenderStream sponsors CUDA programming contest. 

    High Performance Computing (HPC) with Graphical Processor Units (GPU) are at the very heart of the RenderStream product line of heterogeneous MPU/GPU Personal Super Computers and HPC clusters. Heterogeneous computing strives to let each processor do what it is best at. GPU computing is rapidly being adapted by the scientific community because where it is possible, it potentially speeds computations by orders of magnitude.

    RenderStream Personal Supercomputer

    RenderStream Personal Supercomputer

    The computer graphics industry is also adapting this technology but further development is required in both fields before the true computational benefits of GPU computing will be realized. Several different models of RenderStream’s single and dual Nehalem based PSC family of MPU/GPU heterogeneous computing workstations have been built and delivered using the nVIDIA Tesla C1060. The C1060 is a PCI-e card with a single high performance 933 GFLOP GPU with 4 GB of DDR3 memory that can potentially deliver over 3.6 Tera-FLOP (TFLOP) of computing power in a single workstation. For the single quad core PSC systems we use one to four C1060 Tesla units or for the nonprofessional environment, general processing cards like the GTX200 series including the GTX295 dual GPU card that in a four card system is capable of delivering a very professional speed of over 7 TFLOP in one RenderStream PSC workstation making it potentially ideal for Folding@home.

    (More …)

     
  • Joe 11:02 pm on August 17, 2009 Permalink  

    Making of The Godbox 

    Like the godfather, the Godbox is the head of our RenderStream High End 3D workstation family. When selling such a high-end system, we thought it would be important to share with you the thought process behind the design of our flagship model – The Godbox.

    With formula-one cars, the experience gained at the high end influences the rest of the fleet. It is the same in rendering hardware. At RenderStream we built the Godbox to be our “formula-one car”, a high-performance machine that a professional or advanced avocation-ist can afford. In building any integrated system it is important to consider the targeted region in which the user wants the tool to operate and to make sure that no critical subsystem will be limited by any other subsystem’s functioning. At RenderStream we strive to achieve the balanced performance of the processors, visualization experience, storage, I/O and cooling with the use case and the budget. This is the Zen of our systems and it is at the heart and soul of everything that we do.

    (More …)

     
c
compose new post
j
next post/next comment
k
previous post/previous comment
r
reply
e
edit
o
show/hide comments
t
go to top
l
go to login
h
show/hide help
esc
cancel