---------------------------------------------------------------------------------
1. How to enable CUDA

The CUDA implementation in the package is not compiled by default.

To enable it for visual stuio 2005, use vc/SiftGPU_CUDA_Enabled.sln
To enable it for other OS, you need to change siftgpu_enable_cuda to 1 in the makefile


---------------------------------------------------------------------------------
2. Change CUDA build parameters.
For windows, you need to change the settings in the custom build command line of 
ProgramCU.cu. For example, add -use_fast_match for using fast match. 

For Other OS, you need to change the makefile. The top part of the makefile is 
the configuration section, which includes: 
	siftgpu_enable_cuda = 0             (Set 1 to enable CUDA-based SiftGPU)
	CUDA_INSTALL_PATH = /usr/local/cuda (Where to find CUDA)
	siftgpu_cuda_options = -arch sm_10  (Additional CUDA Compiling options)

	
------------------------------------------------------------------------------------
3. CUDA runtime parameters for SiftGPU::ParseParam
First, you need to specify "-cuda" to use CUDA-based SiftGPU. More parameters can 
be chagned at runtime in CUDA-based SiftGPU than in OpenGL-based version. Check out
the manual for details. 

NEW. You can choose GPU for CUDA computation by using "-cuda [device_index=0]"

One parameter for CUDA is "-di", which controls whether dynamic indexing is used
in descriptor generations. It is turned off by default. My experiments on 8800 
GTX show that unrolled loop of 8 if-assigns are faster than dynamic indexing, but
it might be different on other GPUs.


--------------------------------------------------------------------------------------
4. Speed of CUDA-based SiftGPU
If the size of the first octave (multiply the original size by 2 if upsample is used)
is less than or around 1024x768, CUDA version will be faster than OpenGL versions, 
otherwise the OpenGL versions are still faster. 

**************************************************************************************
This is observed on nVidia 8800 GTX, it might be different on other GPUs. Recent
experiments on GTX280 show that CUDA version is not as fast as OpenGL version. 

Note: the thread block settings are currently tuned on GPU nVidia GTX 8800, 
       which may not be optimized for other GPUs.
**************************************************************************************