Google App Engine,Web 2.0,free office download,Jailbreaking iPhone 3Gs,Apple rumors,free downloads,linux download,ubuntu download,Free Software,unlock iPhone 3G,unlock iPhone 3Gs, jailbreak iphone, ipod touch, apple news, programming tutorials
by on September 12th, 2013

The purpose of CUDA applications is to speed up computation on GPUs.  Coding on CUDA naturally involves timing the application to measure the speedup over CPU counterpart.

To profile a CUDA application, you can either use tools such as NVIDIA NSight and Visual Profiler or you can use timing functions; in this article we will use the later approach. CUDA runtime API calls and kernel launches can be timed accurately using CUDA events available in the toolkit. For stuff other than device code, we use the host timers. The following example demonstrated how CUDA runtime calls can be timed using events.

by on September 12th, 2013

If you are used to the programming GPU applications using CUDA runtime API, and have a clear concept of CUDA architecture, porting the application to OpenCL might be a little bit confusing but not difficult.

To exactly demonstrate the difference between CUDA runtime and OpenCL, a downloadable example of vector addition is attached at the end of the tutorial.

The concept of threads, blocks, and kernels is the same, one of the major differences, however, is how the kernel is launched and the number of API calls required to do so. OpenCL is more or less same as the CUDA driver API, but in this article, we will show how a CUDA runtime equivalent OpenCL program can be written. Following are the terminologies and API calls used in a CUDA runtime application, along with their OpenCL counterparts.

by on September 9th, 2013

Many CUDA beginners learn how to write, test and profile CUDA kernels, but most of the times they use randomly generated input data. When it comes to actual real world problem, they are confused how to acquire the input data and process it on the GPU.

In this tutorial, I will show you how to acquire input images on host using OpenCV, then pass that input to CUDA kernel for processing. For this specific tutorial, I will write a basic CUDA function to convert the input color image to gray image. I assume that user has CUDA Toolkit and OpenCV installed in his system. Here’s a good tutorial on setting up OpenCV on your machine with Visual Studio.

We start by writing a CUDA kernel for converting an input BGR image to a gray scale image. Your CUDA kernel will look something like this:

by on September 4th, 2013

This is a step by step guide on running a test program that performs simple color conversion via OpenCV GPU module using Microsoft Visual Studio. You can download the sample source file at the end of this tutorial.

Create a new Microsoft Visual C++ project. Add the source file (available at the end of the tutorial) and add it to the project. Currently, the code will not compile, because the paths to OpenCV header and library files are unknown to the compiler. Let's first set environment variables for OpenCV folders in our system for ease of use

Setting Environment Variables

To create environment variables, go to System Properties. In the Advanced tab, click on Environment Variables. Click on New in the User Variables section. Set Variable Name to CV_INC. In the Variable Value box, paste the path of the OpenCV header files directory ( in our case it's D:\opencv\opencv_build\include). Similarly create environment variable for lib and bin folders as:

by on September 4th, 2013

This tutorial will guide you through how to build and use gpu module of OpenCV version 2.4.6 with Microsoft Visual Studio. I have attached a sample source file for Microsoft Visual C++ that simply performs color conversion on GPU using OpenCV. You can download the source file at the end of this post.

OpenCV's  GPU module is a set of classes and functions to utilize computational capabilities of NVIDIA's CUDA capable GPUs. To do so we can either use the pre-built binaries shipped with OpenCV, or we can compile it from scratch. In this tutorial, we will use the latter approach. To compile OpenCV with GPU support, we need A C++ compiler (Microsoft Visual C++, MinGW etc), CUDA toolkit and CMake. For today's tutorial we're  using Microsoft Visual Studio 2010, CUDA Toolkit 5.0, and CMake 2.8.11 and Windows 7 as platform.

by on December 27th, 2010

You can convert your whole set of DVDs that have collected over the years into iPod compatible formats without losing any quality at all and without the need for iTunes at all! This simple software is a one-stop solution to all your audio/video conversion needs. Since all these formats work with iPhone and iPad, you’re good to go!

by on October 6th, 2010

Managing Music, Movies and files on your iPhone could be a problem if you are on the move and don’t have the machine on which you have iTunes installed. There are also features you would like iTunes to include but it does not have them. This is where a client software that can be easily installed on a Windows machine comes in: iPhone Magic is the perfect match of file manager for your iPhone as well as a back up tool which makes sure you do not lose a bit of data from your iPhone.