Google Cloud TPU V4

E434572

Tensor Processing Unit cloud accelerator machine learning accelerator

Google Cloud TPU v4 is a high-performance, fourth-generation tensor processing unit accelerator offered on Google Cloud, optimized for large-scale machine learning and deep learning workloads.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (2)

Label	Occurrences
TPU v4	2
Google Cloud TPU V4 canonical	1

How this entity was disambiguated

This entity first appeared as the object of triple T4326095 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Google Cloud TPU V4
Context triple: [TPUs (via XLA integrations), compatibleWith, Google Cloud TPU V4]

A. Google Cloud TPU V3
Google Cloud TPU v3 is a high-performance, third-generation tensor processing unit offered on Google Cloud for accelerating large-scale machine learning and deep learning workloads.
B. Google Cloud TPU V2
Google Cloud TPU V2 is a second-generation tensor processing unit offered as a cloud service by Google, designed to accelerate large-scale machine learning workloads such as deep neural network training and inference.
C. Google Compute Engine
Google Compute Engine is Google Cloud’s infrastructure-as-a-service offering that provides scalable, customizable virtual machines for running workloads in the cloud.
D. TPUs (via XLA integrations)
TPUs (via XLA integrations) are Google's specialized tensor processing units that can be used as accelerators for PyTorch models through the XLA compilation framework.
E. Google Tensor
Google Tensor is Google's custom-designed system-on-a-chip (SoC) platform created to power Pixel devices with advanced AI and machine learning capabilities.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Google Cloud TPU V4
Target entity description: Google Cloud TPU v4 is a high-performance, fourth-generation tensor processing unit accelerator offered on Google Cloud, optimized for large-scale machine learning and deep learning workloads.

A. Google Cloud TPU V3
Google Cloud TPU v3 is a high-performance, third-generation tensor processing unit offered on Google Cloud for accelerating large-scale machine learning and deep learning workloads.
B. Google Cloud TPU V2
Google Cloud TPU V2 is a second-generation tensor processing unit offered as a cloud service by Google, designed to accelerate large-scale machine learning workloads such as deep neural network training and inference.
C. Google Compute Engine
Google Compute Engine is Google Cloud’s infrastructure-as-a-service offering that provides scalable, customizable virtual machines for running workloads in the cloud.
D. TPUs (via XLA integrations)
TPUs (via XLA integrations) are Google's specialized tensor processing units that can be used as accelerators for PyTorch models through the XLA compilation framework.
E. Google Tensor
Google Tensor is Google's custom-designed system-on-a-chip (SoC) platform created to power Pixel devices with advanced AI and machine learning capabilities.
F. None of above. chosen

Statements (47)

Predicate	Object
instanceOf	Tensor Processing Unit ⓘ cloud accelerator ⓘ machine learning accelerator ⓘ
architecture	matrix-multiply optimized architecture ⓘ
availableAs	TPU v4 Pod ⓘ linked to: TPU Pods TPU v4 slices ⓘ
category	AI hardware accelerator ⓘ
cloudRegionAvailability	available in selected Google Cloud regions ⓘ
deploymentModel	cloud-based accelerator ⓘ
developedBy	Google ⓘ Google Cloud ⓘ
ecosystem	part of Google Cloud AI infrastructure portfolio ⓘ
feature	high energy efficiency for ML workloads ⓘ high-bandwidth interconnect between TPU chips ⓘ integration with Google Cloud AI Platform services ⓘ support for large-scale distributed training ⓘ support for mixed-precision training ⓘ
generation	fourth-generation TPU ⓘ
integratesWith	Google Cloud Storage ⓘ Google Kubernetes Engine ⓘ Vertex AI ⓘ
marketedAs	high-performance TPU for large-scale AI ⓘ
offeredAs	Google Cloud service ⓘ linked to: Google Cloud
optimizedFor	deep learning workloads ⓘ inference workloads ⓘ large-scale machine learning workloads ⓘ training neural networks ⓘ
predecessor	Google Cloud TPU v3 ⓘ linked to: Google Cloud TPU V3
successor	Google Cloud TPU v5e ⓘ Google Cloud TPU v5p ⓘ linked to: Google Cloud TPU v5e
supports	JAX ⓘ PyTorch (via integration on Google Cloud) ⓘ linked to: PyTorch TensorFlow ⓘ data parallel training ⓘ distributed training across many TPU chips ⓘ model parallel training ⓘ pipeline parallelism ⓘ
targetUser	AI-focused enterprises ⓘ ML researchers ⓘ data scientists ⓘ
useCase	computer vision models ⓘ natural language processing models ⓘ recommendation systems ⓘ speech recognition models ⓘ training large language models ⓘ
usedFor	enterprise AI workloads ⓘ research-scale ML experiments ⓘ

How these facts were elicited

Referenced by (3)

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

TPUs (via XLA integrations) → compatibleWith → Google Cloud TPU V4 ⓘ

Tensor Processing Unit → hasGeneration → TPU v4 ⓘ

linked to: Google Cloud TPU V4

Google TPU → hasVersion → TPU v4 ⓘ