AI accelerator
An AI accelerator is a class of specialized hardware accelerator or computer system designed to accelerate artificial intelligence applications, especially artificial neural networks, machine vision and machine learning. Typical applications include algorithms for robotics, internet of things and other data-intensive or sensor-driven tasks. They are often manycore designs and generally focus on low-precision arithmetic, novel dataflow architectures or in-memory computing capability. As of 2018, a typical AI integrated circuit chip contains billions of MOSFET transistors.A number of vendor-specific terms exist for devices in this category, and it is an emerging technology without a dominant design.
product
AI accelerator (computer hardware)AI acceleratorsAI hardware acceleratorDeep Learning AcceleratorEyerissGraphcore IPUHardware accelerated neural networkHardware accelerators for machine learningList of AI acceleratorsNeural Processing UnitNeural net acceleratorNeural network acceleratorNeural processing unit
Wikipage redirect
AI accelerator (computer hardware)AI acceleratorsAI hardware acceleratorARM Cortex-A78Alibaba_GroupApple-designed processorsApple A11Apple A12Apple A12XApple A13Apple A14Apple M1Arm Ltd.Asus Tinker BoardBfloat16 floating-point formatCadence Design SystemsCognitive computerCognitive computingCompute kernelCoprocessorDLADeep Learning AcceleratorDeep learning processorDeep learning super samplingExmorExynosEyerissFace IDField-programmable gate arrayField-programmable object arrayGeneral-purpose computing on graphics processing unitsGlossary of artificial intelligenceGlossary of computer hardware termsGraphcore IPUGraphics processing unitHardware accelerated neural networkHardware accelerationHardware accelerators for machine learningHuawei MatePad Pro
Link from a Wikipage to another Wikipage
primaryTopic
AI accelerator
An AI accelerator is a class of specialized hardware accelerator or computer system designed to accelerate artificial intelligence applications, especially artificial neural networks, machine vision and machine learning. Typical applications include algorithms for robotics, internet of things and other data-intensive or sensor-driven tasks. They are often manycore designs and generally focus on low-precision arithmetic, novel dataflow architectures or in-memory computing capability. As of 2018, a typical AI integrated circuit chip contains billions of MOSFET transistors.A number of vendor-specific terms exist for devices in this category, and it is an emerging technology without a dominant design.
has abstract
An AI accelerator is a class o ...... ogy without a dominant design.
@en
Link from a Wikipage to an external page
Wikipage page ID
50,827,978
page length (characters) of wiki page
Wikipage revision ID
1,023,799,680
Link from a Wikipage to another Wikipage
wikiPageUsesTemplate
subject
comment
An AI accelerator is a class o ...... ogy without a dominant design.
@en
label
AI accelerator
@en