NVIDIA Tesla A100: specs and benchmarks

NVIDIA Tesla A100

Summary

This is Ampere architecture desktop card based on 7 nm manufacturing process and primarily aimed at designers. 32 GB of HBM2e memory clocked at 2.4 GHz are supplied, and together with 4096 Bit memory interface this creates a bandwidth of 1,229 GB/s.

Compatibility-wise, this is dual-slot card attached via PCIe 4.0 x16 interface. Its manufacturer default version has a length of 267 mm. No additional power connector is required, and power consumption is at 260 Watt.

We have no data on Tesla A100 benchmark results.

General info

Of Tesla A100's architecture, market type and release date.

Place in our rating
not rated
 
Architecture
Ampere
 
GPU code name
GA100
 
Market segment
Workstation
 
Launch date
no data (2021 years ago)
 

Technical specs

Tesla A100's general performance parameters such as number of shaders, GPU core clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of Tesla A100's performance, but for precise assessment you have to consider its benchmark and gaming test results.

Pipelines / CUDA cores
7936
 
of 10752 (GA102)
Core clock speed
1110 MHz
 
Transistor count
38,000 million
 
Manufacturing process technology
7 nm
 
Thermal design power (TDP)
260 Watt
 
of 900 (Tesla S2050)
Texture fill rate
550.6
 

Compatibility, dimensions and requirements

Information on Tesla A100's compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop video cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface
PCIe 4.0 x16
 
Length
267 mm
 
Supplementary power connectors
None
 

Memory

Parameters of memory installed on Tesla A100: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors don't have dedicated memory and use a shared part of system RAM.

Memory type
HBM2e
 
Maximum RAM amount
32 GB
 
Memory bus width
4096 Bit
 
of 6144 (GRID A100A)
Memory clock speed
2400 MHz
 
of 19500 (GeForce RTX 3090)
Memory bandwidth
1,229 GB/s
 
of 1024 (Radeon VII)

Video outputs and ports

Types and number of video connectors present on Tesla A100. As a rule, this section is relevant only for desktop reference video cards, since for notebook ones the availability of certain video outputs depends on the laptop model.

Display Connectors
No outputs
 

API support

APIs supported by Tesla A100, sometimes including their particular versions.

DirectX
12 (12_1)
 
OpenGL
4.6
 

AMD equivalent

We believe that the nearest equivalent to Tesla A100 from AMD is Radeon Pro Vega II.

Similar GPUs

User rating

Here you can see the user rating of the graphics card, as well as rate it yourself.

Advices and comments

Here you can ask a question about Tesla A100, agree or disagree with our judgements, or report an error or mismatch.