PG506-232 and Radeon Pro W6600 - video card comparison

PG506-232

Radeon Pro W6600

Architecture

Ampere (2020−2022)

RDNA 2.0 (2020−2022)

GPU code name

GA100

Navi 23

Market segment

Desktop

Workstation

Release date

April 2021

June 2021

Interface

PCIe 4.0 x16

PCIe 4.0 x16

Supplementary power connectors

8-pin EPS

1x 6-pin

Boost clock speed

1440 MHz

2903 MHz

Manufacturing process technology

7 nm

7 nm

Number of transistors

54,200 million

11,060 million

Pipelines / CUDA cores

3584

1792

Power consumption (TDP)

165 Watt

100 Watt

Texture fill rate

322.6

325.1

Memory type

HBM2

GDDR6

Maximum RAM amount

24 GB

8 GB

Memory bus width

3072 Bit

128 Bit

Memory clock speed

2.4 GB/s

14 GB/s

Memory bandwidth

933.1 GB/s

224.0 GB/s

Display Connectors

No outputs

4x DisplayPort

DirectX

N/A

12.0 Ultimate (12_2)

CUDA

8.0

-

OpenCL

3.0

2.1

OpenGL

N/A

4.6

Shader Model

N/A

6.5

Vulkan

N/A

1.2