PROGRAMABLE GRAPHICS PROCESSING UNITS (GPUs) As define by Wikipedia, a graphics Processing Unit or GPU, also called Visual Processing Unit or VPU is the microprocessor of a graphics card (or graphics accelerator) [1]. NVIDIA defines a GPU as "a single chip processor with integrated transform, lighting, triangle setup/clipping, and rendering engines that is capable of processing a minimum of 10 million polygons per second" [2]. Modern GPUs use most of their transistors to accelerate the memory intensive work of texture mapping and rendering polygons, as well as geometry calculations such as vertex mapping. The aim of this lecture is to provide the student with an overview of programmable GPUs. This will include a discussion of

skillfulwolverineSoftware and s/w Development

Dec 2, 2013 (3 years and 8 months ago)

80 views

PROGRAMABLE GRAPHICS PROCESSING UNITS (GPUs)
As define by Wikipedia, a graphics Processing Unit or GPU, also called Visual Processing Unit or
VPU is the microprocessor of a graphics card (or graphics accelerator) [1]. NVIDIA defines a GPU as
"a single chip processor with integrated transform, lighting, triangle setup/clipping, and rendering
engines that is capable of processing a minimum of 10 million polygons per second" [2]. Modern
GPUs use most of their transistors to accelerate the memory intensive work of texture mapping and
rendering polygons, as well as geometry calculations such as vertex mapping. The aim of this lecture
is to provide the student with an overview of programmable GPUs. This will include a discussion of
the history of the GPU, the future trends of GPUs, and general GPU performance tips.

USING THE GPU AS A GENERAL PURPOSE STREAM PROCESSOR
Just as massive data sets have fundamentally changed our understanding of how to design efficient
algorithms, a very different kind of computation has had a similar result at the level of the
programmable graphics processing units (GPUs). What has resulted is a capable coprocessor that is
highly optimized for stream computations. This lecture will discuss how the GPU can be use as a
general purpose stream processor. This will include a comparison between CPU and GPU
programming techniques as well as a discussion on what programming languages are available for
general purpose GPU programming.


[1] Graphics processing unit, From Wikipedia, the free encyclopedia.
http://en.wikipedia.org/wiki/Graphics_processing_unit

[2] Graphics Processing Unit (GPU), http://www.nvidia.com/object/gpu.html.