General-purpose computing on graphics processing units

General-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the central processing unit (CPU). The use of multiple video cards in one computer, or large numbers of graphics chips, further parallelizes the already parallel nature of graphics processing.

Comment
enGeneral-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the central processing unit (CPU). The use of multiple video cards in one computer, or large numbers of graphics chips, further parallelizes the already parallel nature of graphics processing.
Date
enFebruary 2017
Has abstract
enGeneral-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the central processing unit (CPU). The use of multiple video cards in one computer, or large numbers of graphics chips, further parallelizes the already parallel nature of graphics processing. Essentially, a GPGPU pipeline is a kind of parallel processing between one or more GPUs and CPUs that analyzes data as if it were in image or other graphic form. While GPUs operate at lower frequencies, they typically have many times the number of cores. Thus, GPUs can process far more pictures and graphical data per second than a traditional CPU. Migrating data into graphical form and then using the GPU to scan and analyze it can create a large speedup. GPGPU pipelines were developed at the beginning of the 21st century for graphics processing (e.g. for better shaders). These pipelines were found to fit scientific computing needs well, and have since been developed in this direction.
Hypernym
Use
Infocom
enyes
Is primary topic of
General-purpose computing on graphics processing units
Label
enGeneral-purpose computing on graphics processing units
Link from a Wikipage to another Wikipage
Abalone (molecular mechanics)
Advanced Encryption Standard
Advanced Simulation Library
AI accelerator
Algorithm
Alpha compositing
Altimesh
AMD
Analog signal processing
Android (operating system)
Antivirus software
Apple Inc.
Application programming interface
Array data structure
Astrophysics
ATI Technologies
Audio processing unit
Audio signal processing
Automatic parallelization
Binary search
Bioinformatics
Biomolecule
Bit blit
Bitcoin
Bitcoin network
Blitter
Boolean function
BrookGPU
C (programming language)
C++
C++ AMP
CABAC
Category:Emerging technologies
Category:GPGPU
Category:Graphics cards
Category:Graphics hardware
Category:Instruction processing
Category:Parallel computing
Category:Video game development
CAVLC
Central processing unit
CHARMM
Climate research
Clinical decision support system
Close to Metal
Cloth simulation
Collision detection
Common Intermediate Language
Computational finance
Computational Fluid Dynamics
Computational physics
Computed tomography
Compute kernel
Computer graphics
Computer vision
Constructive solid geometry
Control engineering
Convolution
Conway's Game of Life
CPU cache
CPUs
Cross-platform
Cryptanalysis
Cryptocurrency
Cryptography
C Sharp (programming language)
CUDA
Database
Data Encryption Standard
Data mining
Deep learning processor
Deinterlacing
Digital image processing
Digital signal processing
DirectCompute
DirectX
Discrete cosine transform
Display device
Distributed computing
Duplex (telecommunications)
Edge detection
Einstein@home
Electronic design automation
Elliptic curve cryptography
Euler equations (fluid dynamics)
Fast Fourier transform
Fastra II
Fermi (microarchitecture)
Fixed-function
Floating point
Floating-point
Framebuffer object
F Sharp (programming language)
Functional completeness
Fuzzy logic
Gather (vector addressing)
GeForce 200 series
GeForce 8 series
GeForce FX
Genome mapping
Global illumination
Google
GPU
GPUs
Graphics pipeline
Graphics processing
Graphics processing unit
GROMACS
Hard drive
Havok (software)
High-dynamic-range imaging
High-Level Shading Language
High-performance computing
Huffman coding
Hybrid Monte Carlo
IEEE floating-point standard
Image processing
Incompressible flow
Integer
Intrusion detection
IOS
IQ
Ising model
Jacket (software)
Kepler (microarchitecture)
Kernel (image processing)
Khronos Group
K-nearest neighbor algorithm
LAMMPS
Larrabee (microarchitecture)
Lattice Boltzmann methods
Lattice gauge theory
Level set methods
Lib Sh
Lighting
Loop (computing)
Machine learning
MATLAB
Matrix (mathematics)
Maxwell (microarchitecture)
MD6
Medical imaging
Merge sort
Metal (API)
Microsoft
Mobile operating system
Molecular modeling on GPU
Monoid
Monte Carlo simulation
Motion compensation
Multi-core processor
Multiplier (coefficient)
NAMD
Navier–Stokes equations
Neural network
Newtonian physics
Nvidia
Nvidia Tesla
OpenACC
OpenCL
OpenGL
OpenHMPP
OpenMP
Operations research
Organic chemistry
Palette (computing)
Parallel computing
Pascal (microarchitecture)
Password cracking
Photon mapping
Physics engine
Physics processing unit
PhysX
Pixel
Prefix sum
Processor register
Protein
Quadro GPU
Quantum mechanical
Radeon R300
Radiosity (computer graphics)
Radix sort
Random-access memory
RapidMind
Ray tracing (graphics)
Register file
RenderScript
ROCm
RSA (algorithm)
S3 Graphics
Scatter (vector addressing)
Scientific computing
Segmentation (image processing)
Semigroup
SETI@home
Shader
Signal processing
Single instruction, multiple data
Sobel operator
Software development kit
Sorting networks
Sparse array
Sparse matrix
Speech processing
Speedup
Statistical physics
Stream processing
Subsurface scattering
SYCL
Tone mapping
Union type
University of Toronto
Vector (mathematics and physics)
Vertex (geometry)
Video card
Video game
Video processing
Visual Studio
Weather forecasting
X86
Xcelerit
XGI Technology
Reason
enfalse see CUDA shared memory: Since GPUs process elements independently there is no way to have shared or static data.
SameAs
56yyM
General Purpose Computation on Graphics Processing Unit
General-purpose computing on graphics processing units
General-purpose processing on graphics processing units
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
GPGPU
Grafik işlemci biriminde genel amaçlı hesaplama
m.04ns4d
Q971505
حوسبة للأغراض العامة على وحدات معالجة الرسوميات
محاسبات همه‌منظوره بر روی واحد پردازش گرافیکی
图形处理器通用计算
Subject
Category:Emerging technologies
Category:GPGPU
Category:Graphics cards
Category:Graphics hardware
Category:Instruction processing
Category:Parallel computing
Category:Video game development
Topics
enyes
WasDerivedFrom
General-purpose computing on graphics processing units?oldid=1121749596&ns=0
WikiPageLength
68601
Wikipage page ID
1268939
Wikipage revision ID
1121749596
WikiPageUsesTemplate
Template:Angbr
Template:As of
Template:Citation needed
Template:CPU technologies
Template:Dubious
Template:Emerging technologies
Template:Further
Template:Graphics Processing Unit
Template:Main
Template:More citations needed
Template:No
Template:Original research section
Template:Parallel computing
Template:Reflist
Template:Short description
Template:Snd
Template:Unreferenced section
Template:Use dmy dates
Template:Vague
Template:Visible anchor
Template:Yes