Allura GPU Processor

Allura GPU for SketchUp - Powered by NVIDIA Iray® is a hardware accelerated rendering system, leveraging the power of modern GPU (Graphics Processing) architecture. Primarily coded for NVIDIA GPUs, the software architecture (Iray®) created by NVIDIA enables developers to use the power of the GPU to solve complicated tasks.

We developed Allura to support the largest base of GPU accelerators possible - NVIDIA. For reference purposes, we have included a short list of hardware restrictions imposed by the NVIDIA hardware structure. Future versions or upgrades of Allura may remove some or all of these restrictions with the support of new and specialized hardware designs.

Below is a list of general restrictions for GPU Rendering:

  • Normally all calculations are performed on the GPU graphics card and this means that every bit of information needed to render a scene needs to fit on the card. If the scene is too big to fit onto the card it will not render.
  • Single GPU workstation configurations may appear unresponsive while a GPU-only rendering is performed. This is because the GPU is under full load while rendering. To aid single GPU workstations Allura has a GPU usage option where you can utilize a lower percentage of the GPU power enabling use of the workstation for other GPU based tasks.

What is GPU-ACCELERATED Rendering?

GPU-accelerated rendering is the use of a graphics processing unit (GPU) together with a CPU to accelerate rendering applications.

Pioneered in 2007 by NVIDIA, GPU accelerators now power energy-efficient data centers in government labs, universities, enterprises, and small-and-medium businesses around the world. They play a huge role in accelerating applications in platforms ranging from artificial intelligence to cars, drones, and robots. Now you can add the power of GPUs to your renderings using Allura GPU for SketchUp - Powered by NVIDIA Iray®

HOW GPUs ACCELERATE SOFTWARE APPLICATIONS



GPU-accelerated computing offloads compute-intensive portions of the application to the GPU, while the remainder of the code still runs on the CPU. From a user's perspective, applications simply run much faster.


How-gpu-acceleration-works.png


GPU vs CPU Performance A simple way to understand the difference between a GPU and a CPU is to compare how they process tasks. A CPU consists of a few cores optimized for sequential serial processing while a GPU has a massively parallel architecture consisting of thousands of smaller, more efficient cores designed for handling multiple tasks simultaneously.

GPUs have thousands of cores to process parallel workloads efficiently.


Cpu-and-gpu.jpg

Allura Runtime Requirements

Minimum Requirements

  • Windows® 7 64-bit Professional operating system;
  • 64-bit Intel or AMD multi core processor;
  • 4GB Ram;
  • 2GB free disk space for installation;
  • NVIDIA GPU with the following minimum specifications:
  • CUDA compute capability 2.0 or higher;
  • Driver needs to support CUDA 8.0 or higher. For Windows, this depends upon having NVIDIA Quadro driver version 367 or later;
  • Note: Iray+ Interactive requires these specifications.

NOTE: CPU-only mode

Iray+ will run without a compatible GPU, but for best performance we recommend using GPUs. If your GPU does not meet the minimum requirements then Iray+ will automatically use CPU rendering.

Recommended Requirements

  • Windows® 8 or Windows® 7 64-bit Professional operating system;
  • 64-bit Intel or AMD multi core processor;
  • 8GB Ram;
  • 2GB free disk space for installation;
  • 2x NVIDIA GPUs (one dedicated to Iray+) with the following minimum specifications:
  • CUDA compute capability 2.0 or higher;
Driver needs to support CUDA 8.0 or higher. For Windows, it is recommended to use NVIDIA Quadro driver version 372 or later;

Interactive Mode

Note: Iray+ Interactive requires these specifications.

  • Iray+ Interactive (IRT) Requirements
  • GPUs with CUDA Compute Capability 2.0 or above are supported by Iray+ Interactive, i.e. of the Fermi, Kepler, Maxwell and Pascal generations. The following device configurations are supported:
  • Arbitrary combinations of Compute Capability 2.x devices;
  • Compute Capability 3.0 devices only;
  • Compute Capability 3.5 devices only.

Note: The following device configurations are not supported:

  • Mixing devices between generations;
  • Combining Compute Capability 3.0 and Compute Capability 3.5 devices;
  • Switching between different GPU generations at runtime, for example, switching from a Compute Capability 3.0 to a Compute Capability 2.0 device.

Driver requirements

  • The driver needs to support CUDA 8.0.


NVIDIA CUDA GPU Reference

A list of compatible GPUs can be found here.


See also

Iray® is a registered trademark of NVIDIA Corporation