GeForce RTX 2070 Super and Radeon Instinct MI100 - video card comparison

GeForce RTX 2070 Super

Radeon Instinct MI100

Architecture

Turing (2018−2021)

CDNA 1.0 (2020)

GPU code name

Turing TU104

Arcturus

Market segment

Desktop

Release date

July 2019

November 2020

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 6-pin + 1x 8-pin

2x 8-pin

Boost clock speed

1770 MHz

1502 MHz

Core clock speed

1605 MHz

Manufacturing process technology

12 nm

7 nm

Number of transistors

13,600 million

50,000 million

Pipelines / CUDA cores

2560

7680

Power consumption (TDP)

215 Watt

300 Watt

Texture fill rate

283.2

721.0

Memory type

GDDR6

HBM2

Maximum RAM amount

8 GB

32 GB

Memory bus width

256 Bit

4096 Bit

Memory clock speed

14000 MHz

2.4 GB/s

Memory bandwidth

448.0 GB/s

1,229 GB/s

Shared memory

Display Connectors

1x HDMI, 3x DisplayPort, 1x USB Type-C

No outputs

HDMI

G-SYNC support

DirectX

12 Ultimate (12_1)

N/A

CUDA

7.5

OpenCL

1.2

2.1

OpenGL

4.6

N/A

Shader Model

6.5

N/A

Vulkan

1.2.131

N/A

VR Ready