Hi all I am a recent user of the OpenSceneGraph library. Some of the image processing algorithms that I have written cannot be ported easily to the GPU. Hence, the code finds its way into a callback function where I can do processing on the CPU.
I now have a 2 stage algorithm: it first processes a texture using the CPU and then this texture is processed on the GPU. However, there appears to be a large latency between the 2 stages that drops the frame rate significantly. I suspect this occurs since data must be transferred between the GPU and CPU and the overhead is large. How can I use the PixelDataBufferObject to allocate memory on the GPU and then process this data using the CPU? I have a feeling that the data can be transferred from the GPU to CPU using DMA. Can you please provide me with sample code? Many thanks. Regards, Asheer Bachoo Image Processing Researcher Signal Processing Research Group Defence, Peace, Safety and Security Building 44, Scientia, CSIR Pretoria Brummeria South Africa Telephone: 012 841 3787 e-mail: [email protected] -- This message is subject to the CSIR's copyright terms and conditions, e-mail legal notice, and implemented Open Document Format (ODF) standard. The full disclaimer details can be found at http://www.csir.co.za/disclaimer.html. This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. MailScanner thanks Transtec Computers for their support. _______________________________________________ osg-users mailing list [email protected] http://lists.openscenegraph.org/listinfo.cgi/osg-users-openscenegraph.org
