Tesla P100 DGXS and GeForce RTX 4070 Ti SUPER - video card comparison

Tesla P100 DGXS

GeForce RTX 4070 Ti SUPER

Architecture

Pascal (2016−2021)

Ada Lovelace

GPU code name

GP100

AD103-275

Market segment

Workstation

Desktop

Release date

April 2016

January 2024

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

None

1x 16-pin

Boost clock speed

1480 MHz

2610 MHz

Core clock speed

1328 MHz

2340 MHz

Manufacturing process technology

16 nm

5 nm

Number of transistors

15,300 million

45,900 million

Pipelines / CUDA cores

3584

8448

Power consumption (TDP)

300 Watt

285 Watt

Texture fill rate

331.5

689.0

Memory type

HBM2

GDDR6X

Maximum RAM amount

16 GB

Memory bus width

4096 Bit

256 Bit

Memory clock speed

1430 MHz

21000 MHz

Memory bandwidth

732.2 GB/s

716.8 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

6.0

8.9

OpenCL

1.2

3.0

OpenGL

4.6

Shader Model

6.4

6.7

Vulkan

1.2.131

1.3