The graphics pipeline

Second conference, gathering about 20 persons from the laboratory and some guests.
An overview of a standard FFP 3d pipeline for everyone to be up to date on the subject.

How to Scrum

As explained in the previous article (Game Development with Agile Method SCRUM), Scrum is a batch of methods and principles. They should be adapted by each team, depending on the constraints. Here are the basis to begin with.

Game Development with Agile Method Scrum

First conference, gathering about 15 persons from the laboratory and some guests.
Based on the book Agile Game Dev with Scrum by Clinton Keith, we tried to get an overview of the ways Scrum can be used in a game development process.

CUDA : My first parallel program, vector addition

For the first parallel program we will make a vector addition. This operation is the simpliest exemple for parallel programming.

[Read the rest of this entry...]

CUDA : How to get a device from predetermined informations ?

Sample to get a device from predetermined informations.

[Read the rest of this entry...]

CUDA : How to get Devices informations ?

Devices information is very important. You don't know if your program will be launch on a PC with a CUDA compatible GPU.

So you have to get informations !

[Read the rest of this entry...]

CUDA : Memory

In this article we will see how to allocate memory for the GPU, how to use it and how to get a result from a CUDA function.

[Read the rest of this entry...]

CUDA Books

We recommand you 2 books to begin CUDA.

CUDA By Exemple "An Introduction to General-Purpose GPU Programming"

by Jason SANDERS and Edward KANDROT
forward by Jack DONGARRA

http://developer.nvidia.com/object/cuda-by-example.html

This book teach you CUDA by examples. You will begin with a "Hello World!", continue with a swap, etc…

Programming Massively Parallel Processors "A Hands-on Approach"

by David B. Kirk and Wen-mei W. HWU

http://blogs.nvidia.com/ntersect/2010/01/worlds-first-textbook-on-programming-massively-parallel-processors.html

This book teach you to think Parallel. It begin with the History of GPU Computing, it will introduce you the CUDA and OpenCL programming and continue with CUDA threads, etc…

Visual Studio 2008 Intellisense for CUDA 3.2

In Explorer, goto %CUDA_PATH%extras\visual_studio_integration\.

Execute the file gpucomputing_intellisense.reg.

Intellisense works now on .cu/.cuh/.cl.

Visual Studio 2008 Project for CUDA 3.2

How to configure a Visual Studio 2008 Project for CUDA 3.2 ?

Follow those instructions.

/!\ Tested with Visual Studio 2008 Professional Edition SP1 and Visual Studio C++ Express 2008 /!\

Prerequierd :
- Download and install Visual Studio 2008
- Download and install devdriver_3
- Download and install cudatoolkit 3.2
Create a new Empty Project :
- File -> New -> Project…
- Visual C++ -> General -> Empty Project
- Name your project (for exemple MyFirstCUDAProject)
- OK
Add rules :
- Right clic on the project
- Choose the rule "CUDA Runtime Api Build Rule (v3.2)" (if you have more than once, choose the rule
where the Path finish by "NvCudaRuntimeApi.v3.2.rules")
- OK
Add binary, include and library directoties :
- Tools -> Options -> Project and Solutions -> VC++ Directories
- For Platform "Win32 and "Include files" add :
- $(CUDA_PATH)include
- For Platform "Win32 and "Library files" add :
- $(CUDA_PATH)lib\Win32
- For Platform "Win32 and "Binary files" add :
- $(CUDA_PATH)bin
Linker :
- Right clic on the project -> Properties
- Configuration Porperties -> Linker -> Input
- cuda.lib cudart.lib
- Configuration Porperties -> Linker -> General
- In "Additional library directories" add :
- $(CUDA_PATH)lib
Write "Hello World!"
- Right clic on the Project -> Add -> New Item…
- On the "Name" box, write "sample.cu"
- Write this code sample who use the CUDA compiler (on sample.cu).
- Right clic on the Project -> Build
- Press F5

Prerequisites

[Read the rest of this entry...]