Radeon Pro Duo Polaris and GeForce RTX 3070 - video card comparison

Radeon Pro Duo Polaris

GeForce RTX 3070

Architecture

GCN 4.0 (2016−2020)

Ampere (2020−2022)

GPU code name

Ellesmere

Ampere GA104

Market segment

Workstation

Desktop

Release date

April 2017

September 2020

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 6-pin + 1x 8-pin

1x 12-pin

Boost clock speed

1725 MHz

Core clock speed

1243 MHz

1500 MHz

Floating-point performance

2x 5,728 gflops

Manufacturing process technology

14 nm

8 nm

Number of transistors

5,700 million

17,400 million

Pipelines / CUDA cores

2304

5888

Power consumption (TDP)

250 Watt

220 Watt

Texture fill rate

179.0

317.4

Memory type

GDDR5

GDDR6

Maximum RAM amount

16 GB

8 GB

Memory bus width

256 Bit

Memory clock speed

7000 MHz

14000 MHz

Memory bandwidth

224.0 GB/s

448.0 GB/s

Shared memory

Display Connectors

1x HDMI, 3x DisplayPort

HDMI

DirectX

12 (12_0)

12 Ultimate (12_2)

CUDA

8.5

OpenCL

2.0

OpenGL

4.6

Shader Model

6.4

6.5

Vulkan

1.2.131

1.2