" Live as if you were to die tomorrow. Learn as if you were to live forever.. "
- Mahatma Gandhi

Avoiding if condition in CUDA

Posted on November 24th, 2015 by Manjunath G

Branching is one of the most time consuming operation in CUDA ( in general as well).   For example, See below CPU code and GPU code …   CPU code: void CPUCode( int* input, int* output, int length) { for ( int i = 0; i < length; ++i ) { output[ i ] = input[ i […]

Tips for speed up your algorithm in the CUDA programming

Posted on November 23rd, 2015 by Abhinav Kumar

There are a couple of things you can do to speed up your algorithm in the CUDA programming : 1.)Try to attain .75(75%) to 1 (100%) occupancy of every kernel execution. This can be ensured by optimizing the number of resisters used by the Kernal and number of threads per block. We need to figure […]

How To Start writing CUDA Program

Posted on November 23rd, 2015 by Kundan Kumar

1. Who can start CUDA programming? – Any one who has some basicknowledge on C programming. No prior knowledge of graphics programming. – CUDA is C with minimal extension and some restrictions.( CUDA is C for GPU) 2. If you have a algo that you want to write in CUDA then follow the below steps. […]

Image Processing with CUDA

Posted on November 23rd, 2015 by Kundan Kumar

CUDA is well suited Image processing in parallel threads. The pixels of a image can be directly mapped to parallel threads. For efficient image processing with CUDA one need to understand the location and scope along with access pattern of pixel data . CUDA has different kinds of memories i.e. shared, constant, texture, local and […]