Tesla V100 FHHL and Tesla A100 - video card comparison

Tesla V100 FHHL

Tesla A100

Architecture

Volta (2017−2020)

Ampere (2020−2022)

GPU code name

GV100

GA100

Market segment

Workstation

Workstation

Release date

March 2018

-

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 8-pin

None

Boost clock speed

1290 MHz

-

Core clock speed

937 MHz

1110 MHz

Manufacturing process technology

12 nm

7 nm

Number of transistors

21,100 million

38,000 million

Pipelines / CUDA cores

5120

7936

Power consumption (TDP)

250 Watt

260 Watt

Texture fill rate

412.8

550.6

Memory type

HBM2

HBM2e

Maximum RAM amount

16 GB

32 GB

Memory bus width

4096 Bit

4096 Bit

Memory clock speed

1620 MHz

2400 MHz

Memory bandwidth

829.4 GB/s

1,229 GB/s

Display Connectors

No outputs

No outputs

DirectX

12 (12_1)

12 (12_1)

CUDA

7.0

-

OpenCL

1.2

-

OpenGL

4.6

4.6

Shader Model

6.4

-

Vulkan

1.2.131

-