Difference between revisions of "VTK Cuda Memory Management Classes"
From NAMIC Wiki
| Line 2: | Line 2: | ||
The Idea is to get a safe object oriented interface for the memory management of CUDA devices in VTK. | The Idea is to get a safe object oriented interface for the memory management of CUDA devices in VTK. | ||
| − | Also take a look at [[Cuda | + | Also take a look at [[VTK Cuda Wrapper Classes]] for more information on VTK CUDA wrappings |
== Cuda Memory == | == Cuda Memory == | ||
Cuda memory comes in different: | Cuda memory comes in different: | ||
Revision as of 20:55, 28 December 2007
Home < VTK Cuda Memory Management ClassesObjective
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. Defined in vtkCudaHostMemory.h
- Linear Memory: Linerely arranged memory on the CUDA device. vtk
- 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)
- Array Memory: Arrays allocated over the CUDA API.
- Texture Memory: Not discussed here.
Class Diagram
