Scribd
Upload
146 views

Cpu Vs Gpu

CPUs consist of a few powerful cores optimized for serial processing tasks, while GPUs contain thousands of smaller cores designed for parallel processing. Specifically, GPUs are optimized for graphics applications involving large amounts of data parallelism like 3D games and AI, with hardware containing more arithmetic logic units than CPUs. While CPUs can run a variety of applications and provide fast response times, GPUs are built for graphics processing through programming frameworks like CUDA, OpenCL, and OpenACC that take advantage of their parallel architecture.

Uploaded by

Mouhcine Ben Moussa
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
146 views

Cpu Vs Gpu

CPUs consist of a few powerful cores optimized for serial processing tasks, while GPUs contain thousands of smaller cores designed for parallel processing. Specifically, GPUs are optimized for graphics applications involving large amounts of data parallelism like 3D games and AI, with hardware containing more arithmetic logic units than CPUs. While CPUs can run a variety of applications and provide fast response times, GPUs are built for graphics processing through programming frameworks like CUDA, OpenCL, and OpenACC that take advantage of their parallel architecture.

Uploaded by

Mouhcine Ben Moussa
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

CPU Vs GPU

MENU

#01 DEFINITIONS

#02 CPU vs GPU


#01

Definition
DEFINITIONS

CPU
the electronic
circuitry within
a computer that
executes instructions
 that make up a computer
program
DEFINITIONS

GPU
A programmable logic chip
(processor) specialized for
display functions.
The GPU renders images,
animations and video for
the computer's screen 
#02

Differences
Between
CPU & GPU
ARCHITECTURE
CPU GPU

• CPUs consist of a few cores • GPUs consist of thousands of


optimized for serial processing smaller, more efficient cores.
• Serial portions of the code run on • Parallel portions of the code run
the CPU on the GPU
ARCHITECTURE
CPU GPU

Hardware of GPU has more ALU’s 


Better capability to process parallel arithmetic operations, meaning same
operations are performed on different data sets.
APPLICATIONS

GPUs are builts specifically for


rendering and other graphics
CPUs are designed for a applications that have a large
wide variety of applications degree of data parallelism.
and to provide fast response
times to a single task. • High-end 3d Graphic games
• Artificial Inteligence…
• Creating Spreadsheets
• Watching movies...
CPU Implementation GPU Coding
• High-Level language (C • CUDA (Just in
language)
NVIDIA’s GPUs)
• Dijikstra’s Algorithm is • OpenCL
used to implement the • OpenACC . . .
shortest path.

 
Conclusion
CPU GPU
 Few cores optimized for  Thousnads of cores that are
sequentiel serial processing designed for parallel processing

 Few but powerful cores  Less powerful

 A CPU commonly has 4 to 8  Thousands of relatively simple


flexible cores clocked at 2-3 Ghz cores clocked about 1Ghz
Thank you

You might also like