Tesla P10 and GeForce RTX 4090 - video card comparison

Tesla P10

GeForce RTX 4090

Architecture

Pascal (2016−2021)

Ada Lovelace

GPU code name

GP102

AD102-300-A1

Market segment

Workstation

Desktop

Release date

September 2016

September 2022

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 8-pin

1x 16-pin

Boost clock speed

1493 MHz

2520 MHz

Core clock speed

-

2235 MHz

Manufacturing process technology

16 nm

5 nm

Number of transistors

11,800 million

76,300 million

Pipelines / CUDA cores

3840

16384

Power consumption (TDP)

250 Watt

450 Watt

Texture fill rate

358.3

1,290

Memory type

GDDR5X

GDDR6X

Maximum RAM amount

24 GB

24 GB

Memory bus width

384 Bit

384 Bit

Memory clock speed

14.5 GB/s

21000 MHz

Memory bandwidth

694.3 GB/s

1,008 GB/s

Shared memory

-

-

Display Connectors

No outputs

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

-

+

DirectX

12 (12_1)

12 Ultimate (12_2)

CUDA

6.1

8.9

OpenCL

1.2

3.0

OpenGL

4.6

4.6

Shader Model

6.4

6.6

Vulkan

1.2

1.3