3. Introduction
A dedicated parallel processor optimized for accelerating
graphical computations.
Like the CPU (Central Processing Unit), it is a single-chip
processor.
4. Need for a GPU
To provide a separate dedicated graphics resources
including a graphics processor and memory.
To relieve some of the burden of the main system
resources.
7. GPU - highly parallel
operation
GPU has many execution
units
GPU has faster memory interfaces as they need to shift
around a large amount of data.
GPUs have much deeper pipelines
GPU vs CPU
CPU executes programs
serially.
CPU has fewer execution
units
10. Components of a GPU
❖ Graphics Processor
Mainly 2 configurations:
○ Graphics coprocessor : Independent of CPU
○ Graphics accelerator: Based on Commands from CPU
12. GPU Pipeline
The GPU receives
geometry information
from the CPU as an
input and provides a
picture as an output.
13. Input assembler stage
This stage is the communication bridge between the CPU
and the GPU.
It receives commands from the CPU and also pulls
geometry information from system memory.
It outputs a stream of vertices in object space with all their
associated information.
14. Vertex Processing
The vertex-shader stage processes vertices, typically
performing operations such as transformations, skinning,
and lighting.
A vertex shader always takes
a single input vertex and
produces a single output vertex.
15. Triangle Setup
In this stage geometry information becomes raster
information (screen space geometry is the input,
pixels are the output)
16.
17.
18. Triangle Setup (Contd…)
Prior to rasterization, triangles that are backfacing or
are located outside the viewing frustum are rejected.
The rasterizer clips primitives, prepares primitives
for the pixel shader, and determines how to invoke
pixel shaders.
A pixel is generated if and only if its center is inside
the triangle
19. Pixel Processing
Each pixel provided by triangle setup is fed into pixel
processing as a set of attributes which are used to
compute the final color for this pixel
The computations taking place here include texture
mapping and math operations
20.
21. Output Merger Stage
The output-merger stage combines various types of
output data (pixel shader values, depth and stencil
information) to generate the final pipeline result.
22.
23.
24. Programmability in GPU Pipeline
In current state of the art GPUs, vertex and pixel processing
are now programmable
The programmer can write programs that are executed for
every vertex as well as for every pixel
This allows fully customizable geometry and shading effects
that go well beyond the generic look and feel of older 3D
applications
25.
26. Looking Forward
Bigger and faster (more cores, more FLOPS) – 2
TFLOPs today, and counting
Addition of (select) CPU-like features – More
traditional caches
Tight integration with CPUs (CPU+GPU hybrids).
Completely programmable hardware.
32. Conclusion
● Graphics Processing Unit is not a wonder that this
piece of hardware is often referred to as an exotic
product as far as computer peripherals are
concerned.
● By observing the current pace at which work is going
on in developing GPUs we can surely come to a
conclusion that we will be able to see better and
faster GPUs in the near future.