I have a simple C++ program that performs simple mathematical calculations over millions of iterations in several loops. In order to speed it up I would like to relay the iterations to the GPU. The job is to modify the given C++ code to use CUDA for doing the iterations on the GPU.
I am using Visual Express 2010, 64 Vista Professional, Nvidia on one machine and Visual Express 2010, 64 Win7, nvidia on other machine.
The job would include to configure my machines to run CUDA using "logmein" in case I fail to do it myself based on your instructions.
Finished job has to debug&bulid, run correctly on my machines.
I would need all parts of the C++ code, except for the functions in CUDA to be available for modifications on my side without interfering with the CUDA part of the program.
Please read the project first and write the word "Understood". Also write your steps and suggestions to complete the project with a short description of what you understood.