|
gptkbp:instance_of
|
gptkb:Graphics_Processing_Unit
|
|
gptkbp:bfsLayer
|
6
|
|
gptkbp:bfsParent
|
gptkb:NVIDIA_Tesla_series
|
|
gptkbp:application
|
gptkb:aircraft
gptkb:Company
gptkb:Deep_Learning
Rendering
Scientific Computing
|
|
gptkbp:architectural_style
|
gptkb:Ampere
|
|
gptkbp:engine
|
54 billion
|
|
gptkbp:form_factor
|
PC Ie
SX M4
|
|
gptkbp:gpu
|
gptkb:battle
4.0
|
|
gptkbp:has_ability
|
8.0
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Tesla A100
|
|
gptkbp:intelligence
|
gptkb:Graphics_Processing_Unit
gptkb:Caffe
gptkb:Chainer
gptkb:Py_Torch
MX Net
|
|
gptkbp:is_compatible_with
|
NVIDIANV Link
|
|
gptkbp:manufacturer
|
gptkb:DJ
|
|
gptkbp:market_segment
|
gptkb:High_School
gptkb:Cloud_Computing_Service
Government Agencies
Research Institutions
AI Startups
|
|
gptkbp:network
|
gptkb:battle
|
|
gptkbp:number_of_cores
|
432
6912
|
|
gptkbp:open_glsupport
|
gptkb:battle
|
|
gptkbp:performance
|
19.5 TFLOPS
9.7 TFLOPS
156 TFLOPS (Tensor Float 32)
312 TFLOPS
19.5 TFLOPS (F P32)
|
|
gptkbp:power_consumption
|
250 W
|
|
gptkbp:powers
|
400 W
|
|
gptkbp:ram
|
40 GB
HB M2
1555 GB/s
|
|
gptkbp:release_date
|
gptkb:2020
|
|
gptkbp:size
|
826 mm²
|
|
gptkbp:successor
|
gptkb:Tesla_H100
|
|
gptkbp:target_market
|
Data Centers
|
|
gptkbp:use_case
|
gptkb:software_framework
High-Performance Computing
AI Inference
AI Training
|
|
gptkbp:virtualization_support
|
gptkb:battle
|