Cerebras WSE-1

GPTKB entity

Statements (54)
Predicate Object
gptkbp:instance_of gptkb:computer
gptkbp:application AI training
gptkbp:architecture gptkb:tachymetric_scale
gptkbp:chip_size 4625 square millimeters
gptkbp:competitors gptkb:Google_TPU
gptkb:Intel
gptkb:AMD
gptkb:NVIDIA
gptkbp:connects high bandwidth
gptkbp:cooling_system liquid cooling
gptkbp:deployment gptkb:2020
gptkbp:designed_by gptkb:Cerebras_Systems
gptkbp:development gptkb:2016
gptkbp:form_factor wafer scale
gptkbp:has_units 400,000
https://www.w3.org/2000/01/rdf-schema#label Cerebras WSE-1
gptkbp:key_feature gptkb:neural_networks
gptkb:machine_learning
advanced algorithms
big data processing
cloud integration
data analytics
energy efficiency
low latency
real-time processing
scalability
AI model training
flexible architecture
high throughput
high reliability
high density
AI acceleration
AI inference
data-intensive workloads
custom silicon
ease of programming
massive parallelism
integrated memory
high performance AI
single chip architecture
gptkbp:manufacturer gptkb:TSMC
gptkbp:market_position high performance computing
gptkbp:notable_feature largest chip ever made
gptkbp:performance 1.2 trillion transistors
gptkbp:power_consumption 20 k W
gptkbp:ram 40 GB
gptkbp:released_in gptkb:2020
gptkbp:successor gptkb:Cerebras_WSE-2
gptkbp:supports gptkb:Tensor_Flow
gptkb:Py_Torch
gptkbp:target_market data centers
gptkbp:uses deep learning
gptkbp:bfsParent gptkb:Cerebras_WSE-2
gptkbp:bfsLayer 8