Tesla A100 and RTX A40 - video card comparison

Tesla A100

RTX A40

Architecture

Ampere (2020−2022)

Ampere (2020−2022)

GPU code name

GA100

GA102

Market segment

Workstation

Desktop

Release date

-

October 2020

Interface

PCIe 4.0 x16

PCIe 4.0 x16

Supplementary power connectors

None

8-pin EPS

Boost clock speed

-

1755 MHz

Core clock speed

1110 MHz

-

Manufacturing process technology

7 nm

8 nm

Number of transistors

38,000 million

28,300 million

Pipelines / CUDA cores

7936

10752

Power consumption (TDP)

260 Watt

300 Watt

Texture fill rate

550.6

589.7

Memory type

HBM2e

GDDR6

Maximum RAM amount

32 GB

48 GB

Memory bus width

4096 Bit

384 Bit

Memory clock speed

2400 MHz

14.5 GB/s

Memory bandwidth

1,229 GB/s

695.8 GB/s

Display Connectors

No outputs

3x DisplayPort

DirectX

12 (12_1)

12 Ultimate (12_2)

CUDA

-

8.6

OpenCL

-

2.0

OpenGL

4.6

4.6

Shader Model

-

6.5

Vulkan

-

1.2