Tesla A100 and H100 CNX - video card comparison

Tesla A100

H100 CNX

Architecture

Ampere (2020−2022)

Hopper (2022)

GPU code name

GA100

GH100

Market segment

Workstation

Desktop

Release date

-

March 2023

Interface

PCIe 4.0 x16

PCIe 5.0 x16

Supplementary power connectors

None

8-pin EPS

Boost clock speed

-

1845 MHz

Core clock speed

1110 MHz

-

Manufacturing process technology

7 nm

4 nm

Number of transistors

38,000 million

80,000 million

Pipelines / CUDA cores

7936

14592

Power consumption (TDP)

260 Watt

350 Watt

Texture fill rate

550.6

841.3

Memory type

HBM2e

HBM2e

Maximum RAM amount

32 GB

80 GB

Memory bus width

4096 Bit

5120 Bit

Memory clock speed

2400 MHz

3.2 GB/s

Memory bandwidth

1,229 GB/s

2,039 GB/s

Display Connectors

No outputs

No outputs

DirectX

12 (12_1)

N/A

CUDA

-

9.0

OpenCL

-

3.0

OpenGL

4.6

N/A

Shader Model

-

N/A

Vulkan

-

N/A