Intel Gaussian and Neural Accelerator 2.0

E653485

Intel Gaussian and Neural Accelerator 2.0 is a low-power AI and machine learning accelerator integrated into Intel processors to efficiently handle tasks like noise suppression, voice processing, and other inference workloads.

Try in SPARQL Jump to: Statements Referenced by

Statements (45)

Predicate Object
instanceOf AI accelerator
low-power inference accelerator
neural processing unit
architecture Gaussian and neural network based processing
benefit enhanced user experience for conferencing
improved battery life
lower system power for voice features
reduced CPU utilization for AI tasks
computingParadigm edge AI
designedFor client computing platforms
laptops
mobile PCs
developer Intel NERFINISHED
feature always-on operation capability
hardware acceleration for neural networks
low power consumption
generation second generation
hardwareType on-die accelerator
integratedInto Intel CPU package NERFINISHED
Intel system-on-chip NERFINISHED
marketedAs GNA 2.0 NERFINISHED
optimizationTarget low-latency inference
real-time audio processing
partOf Intel processor platform
powerDomain separate low-power island
powerEfficiencyGoal run AI tasks at minimal power
precisionSupport low-precision neural network operations
predecessor Intel Gaussian and Neural Accelerator 1.0 NERFINISHED
purpose accelerate AI workloads
accelerate machine learning workloads
offload inference from CPU
roleInSystem specialized coprocessor for AI
softwareEcosystem Intel AI software stack NERFINISHED
Intel drivers and firmware
supportsTask AI inference workloads
audio enhancement
background noise reduction
noise suppression
speech recognition assistance
voice processing
targetWorkloadType inference
useCase context-aware audio features
smart assistant wake word processing
video conferencing noise cancellation
vendor Intel Corporation NERFINISHED

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Tiger Lake microarchitecture supports Intel Gaussian and Neural Accelerator 2.0
subject surface form: Tiger Lake