GPU cluster

GPU cluster

A GPU cluster is a computer cluster in which each node is equipped with a Graphics Processing Unit (GPU). By harnessing the computational power of modern GPUs via General-Purpose Computing on Graphics Processing Units (GPGPU), very fast calculations can be performed with a GPU cluster.

Hardware (GPU)

The hardware classification of GPU clusters fall into two categories:Heterogeneous and Homogeneous.

Heterogeneous

Hardware from both of the major IHV's can be used (ATi and nVidia). Even if different models of the same GPU are used (ie 8800GT mixed with 8800GTX) the gpu cluster is considered hetergeneous.

Homogeneous

Every single GPU is of the same hardware class, make, and model. (ie a homogeneous cluster comprising 100 8800GTs, all with the same amount of VRAM)

Classifying a GPU cluster according to the above semantics largely directs software development on the cluster, as diffent GPUs have different capabilities that can be utilized.

Hardware (Other)

Interconnect

In addition to the computer nodes and their respective GPUs, a fast enough interconnect is needed in order to shuttle data amongst the nodes. The type of interconnect largely depends on the number of nodes present. Some examples of interconnects include Gigabit Ethernet and InfiniBand.

Software

The software components that are required to make many GPU-equipped machines act as one include:

1) Operating System
2) GPU driver for the each type of GPU present in each cluster node.
3) Clustering API (such as the Message Passing Interface, MPI).

Algorithm Mapping

Mapping an algorithm to run a GPU cluster is somewhat similar to mapping an algorithm to run on a traditional computer cluster. Example: rather than distributing pieces of an array from RAM, a texture is divided up amongst the nodes of the GPU cluster.

References and external links

*cite book | author=Are Magnus Bruaset, Aslak Tveito | title=Numerical Solution of Partial Differential Equations on Parallel Computers | publisher=Birkhäuser | year=2006 | id=ISBN 3-540-29076-1
* [http://www.ncsa.edu/Projects/GPUcluster/ NCSA's Innovative Systems Laboratory]


Wikimedia Foundation. 2010.

Игры ⚽ Нужно сделать НИР?

Look at other dictionaries:

  • Cluster (computing) — A computer cluster is a group of linked computers, working together closely so that in many respects they form a single computer. The components of a cluster are commonly, but not always, connected to each other through fast local area networks.… …   Wikipedia

  • Molecular modeling on GPU — Ionic liquid simulation on GPU (Ascalaph Designer) Molecular modeling on GPU is the technique of using a graphics processing unit (GPU) for molecular simulations. [1] In 2007, NVIDIA introduced video cards that could be used not only to show… …   Wikipedia

  • Computer cluster — Not to be confused with data cluster. A computer cluster is a group of linked computers, working together closely thus in many respects forming a single computer. The components of a cluster are commonly, but not always, connected to each other… …   Wikipedia

  • DEGIMA (computer cluster) — The DEGIMA (DEstination for Gpu Intensive MAchine) is a high performance computer cluster used for hierarchical N body simulations at the Nagasaki Advanced Computing Center, Nagasaki University. The system consists of a 144 node cluster of PCs… …   Wikipedia

  • Larrabee (GPU) — Blockschaltbild des Larrabee GPU Architektur. Larrabee ist der Codename für eine neue Grafikkartengeneration von Intel, die ursprünglich Ende 2009 oder Anfang 2010 auf den Markt kommen sollte. Im Gegensatz zu heute verwendeten Grafikprozessoren… …   Deutsch Wikipedia

  • Graphics processing unit — GPU redirects here. For other uses, see GPU (disambiguation). GeForce 6600GT (NV43) GPU A graphics processing unit or GPU (also occasionally called visual processing unit or VPU) is a specialized circuit designed to rapidly manipulate and alter… …   Wikipedia

  • Monte Carlo method for photon transport — Modeling photon propagation with Monte Carlo methods is a flexible yet rigorous approach to simulate photon transport. In the method, local rules of photon transport are expressed as probability distributions which describe the step size of… …   Wikipedia

  • GPGPU — General purpose computing on graphics processing units (GPGPU, also referred to as GPGP and to a lesser extent GP²) is the technique of using a GPU, which typically handles computation only for computer graphics, to perform computation in… …   Wikipedia

  • Nvidia-Geforce-400-Serie — Geforce GTX 480 von Point of View im Referenzdesign Die Geforce 400 Serie ist eine Serie von Desktop Grafikchips des Unternehmens Nvidia. Alle Grafikprozessoren dieser Serie unterstützen erstmals das Shadermodell 5.0 (SM 5.0) nach DirectX 11,… …   Deutsch Wikipedia

  • AMD-Radeon-HD-6000-Serie — Die Radeon HD 6000 Serie ist eine Serie von Desktop Grafikchips der Firma AMD, welche im Herbst 2010 als Nachfolger für die Radeon HD 5000 Serie eingeführt wurde. Alle Grafikprozessoren dieser Serie unterstützen das Shadermodell 5.0 nach DirectX… …   Deutsch Wikipedia

Share the article and excerpts

Direct link
Do a right-click on the link above
and select “Copy Link”