Difference between revisions of "VTK Cuda Memory Management Classes"

From NAMIC Wiki
Jump to: navigation, search
(Delete of the page)
Line 1: Line 1:
= Objective =
 
The Idea is to get a safe object oriented interface for the memory management of CUDA devices in VTK.
 
 
(Also take a look at [[VTK Cuda Wrapper Classes]] for more information on VTK CUDA wrappings.)
 
 
== Cuda Memory ==
 
Cuda memory comes in different:
 
*'''Host Memory''': Non-Paged Memory on the host side for fast interaction with the CUDA devices. see ''vtkCudaHostMemory.h''
 
*'''Linear Memory''': Linerely arranged memory on the CUDA device. see ''vtkCudaMemory.h''
 
*'''Pitch Memory''': 2D memory arrays that are aligned in the correct fashion for a fast interaction on the cuda devices. (Arranged over the memory banks for quick access). see ''vtkCudaMemoryPitch.h''
 
*'''Array Memory''': Arrays allocated over the CUDA API. see ''vtkCudaMemoryArray.h''
 
*'''Texture Memory''': Not discussed here. see [[VTK Cuda Wrapper Classes]]
 
 
 
= Class Diagram =
 
= Class Diagram =
 
[[Image:vtkCudaMemoryManagementClassDiagram.png]]
 
[[Image:vtkCudaMemoryManagementClassDiagram.png]]

Revision as of 21:17, 28 December 2007

Home < VTK Cuda Memory Management Classes

Class Diagram

VtkCudaMemoryManagementClassDiagram.png