Tesla K20s and Radeon PRO W7700 - video card comparison

Tesla K20s

Radeon PRO W7700

Architecture

Kepler (2012−2018)

RDNA 3.0 (2022)

GPU code name

GK110

Navi 32

Market segment

Workstation

Workstation

Release date

February 2013

November 2023

Interface

PCIe 2.0 x16

PCIe 4.0 x16

Supplementary power connectors

-

1x 8-pin

Boost clock speed

-

2600 MHz

Core clock speed

575 MHz

-

Floating-point performance

3,524 gflops

-

Manufacturing process technology

28 nm

5 nm

Number of transistors

7,080 million

28,100 million

Pipelines / CUDA cores

2496

3072

Power consumption (TDP)

225 Watt

190 Watt

Texture fill rate

119.6

499.2

Memory type

GDDR5

GDDR6

Maximum RAM amount

5 GB

16 GB

Memory bus width

320 Bit

256 Bit

Memory clock speed

5200 MHz

18 GB/s

Memory bandwidth

208.0 GB/s

576.0 GB/s

Display Connectors

No outputs

4x DisplayPort 2.1

DirectX

12 (11_0)

12 Ultimate (12_2)

CUDA

3.5

-

OpenCL

1.2

2.2

OpenGL

4.6

4.6

Shader Model

5.1

6.7

Vulkan

1.1.126

1.3