Scribd
Upload
79 views

Intro To Gpu &amp Cuda

GPUs are specialized processors used to rapidly manipulate graphics memory and accelerate image building. They have hundreds of cores compared to CPUs' few cores, making them better for parallel processing. The two main GPU vendors are Nvidia and AMD. CUDA is a popular programming model that allows easy GPU programming through C extensions. To start with GPUs, install the CUDA toolkit and SDK then run example programs to learn basic architecture and programming guidelines.

Uploaded by

f3ziii
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
79 views

Intro To Gpu &amp Cuda

GPUs are specialized processors used to rapidly manipulate graphics memory and accelerate image building. They have hundreds of cores compared to CPUs' few cores, making them better for parallel processing. The two main GPU vendors are Nvidia and AMD. CUDA is a popular programming model that allows easy GPU programming through C extensions. To start with GPUs, install the CUDA toolkit and SDK then run example programs to learn basic architecture and programming guidelines.

Uploaded by

f3ziii
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

Hatim Nazir Ahmed Sayed Saad Ali Suleman Khan

What are GPUs Advantages of GPUs Vendors of GPUs Comparison of CPUs & GPUs Platform for Programming CUDA How to start working with GPUs Basic Architecture of GPU Programming guideline Some sample programs

A graphics processing unit or GPU is a specialized electronic circuit designed to rapidly manipulate and alter memory in such a way so as to accelerate the building of images in a frame buffer. GPUs are used in embedded systems, mobile phones, personal computers, workstations, and game consoles. Modern GPUs are very efficient at manipulating computer graphics, and their highly parallel structure makes them more effective than general-purpose CPUs for algorithms where processing of large blocks of data is done in parallel.

Co-processor to accelerate CPUs GPUs can deliver up to a teraflop (1 trillion calculations per second) CPUs have few (two to eight) large, complex cores, while GPUs have up to a few hundred E.g NVIDIAs Tesla GPU is shipping with 240 cores

Nvidia AMD (no longer ATI) Intel Matrox Graphics PowerVR SiS

Number of cores per chip doubles every 2 years, while clock speed decreases (not increases) Need to deal with systems with millions of concurrent threads Future generation will have billions of threads!

Science & Engineering disciplines

Effective Resource Utilization Cooling Redundancy and Failover

CUDA

model Extension to C programming language Allows easy multi-threading - parallel execution on all thread processors on the GPU CUDA works on modern NVidia cards (Quadro, GeForce, Tesla) CUDA programs Compiles through NVCC

is a scalable parallel programming

OpenCL (Open Computing Language) For general-purpose parallel programming

System

with at least 2GB RAM Nvidia CUDA enabled GPU CUDA Toolkit CUDA SDK NVIDIA Parallel Nsight NVIDIA Drivers Microsoft Visual Studio 2008 or 2010

CUDA Toolkit, CUDA SDK & Dev.drivers

http://developer.nvidia.com/cuda-downloads

Nvidia Parallel Nsight

http://developer.nvidia.com/content/introducing-nvidiansight-visual-studio-edition-22

Running of built-in SDK Example & Device Query

Contact Us [email protected] [email protected]

Please provide us your valuable Feedback on above email

15

You might also like